From 791b7715b12f3439b1e4686039f53f3c3ef13ede Mon Sep 17 00:00:00 2001
From: Saim Momin <momin@minimus.ie-freiburg.mpg.de>
Date: Mon, 6 Mar 2023 15:32:07 +0100
Subject: [PATCH 01/33] Cleanup

---
 config/README.md        |   2 -
 config/config.yaml      |  13 -----
 config/file_layout.yaml |  10 ----
 config/samples.csv      |   2 -
 envs/kraken2.yaml       |   7 ---
 envs/synapse.yaml       |  65 ----------------------
 envs/umi_tools.yaml     |   6 ---
 test/test_download.sh   |   2 -
 workflow/Snakefile      | 116 ----------------------------------------
 workflow/common.smk     |  40 --------------
 10 files changed, 263 deletions(-)
 delete mode 100644 config/README.md
 delete mode 100644 config/config.yaml
 delete mode 100644 config/file_layout.yaml
 delete mode 100644 config/samples.csv
 delete mode 100755 envs/kraken2.yaml
 delete mode 100644 envs/synapse.yaml
 delete mode 100755 envs/umi_tools.yaml
 delete mode 100644 test/test_download.sh
 delete mode 100644 workflow/Snakefile
 delete mode 100644 workflow/common.smk

diff --git a/config/README.md b/config/README.md
deleted file mode 100644
index 44c6f7e..0000000
--- a/config/README.md
+++ /dev/null
@@ -1,2 +0,0 @@
-Describe how to configure the workflow (using config.yaml and maybe additional files).
-All of them need to be present with example entries inside of the config folder.
diff --git a/config/config.yaml b/config/config.yaml
deleted file mode 100644
index 64d03ef..0000000
--- a/config/config.yaml
+++ /dev/null
@@ -1,13 +0,0 @@
-defaults: 
-  bc_pattern: CCCCCCCCCCCCCCCCNNNNNNNNNN
-  cell_number: 1000
-
-output_dir: "results"
-
-file_layout: "config/file_layout.yaml"
-samples: "config/samples.csv"
-
-kraken:
-  threads: 8
-  db_paths:
-    virus: /data/repository/kraken2_contaminome/virus_db
\ No newline at end of file
diff --git a/config/file_layout.yaml b/config/file_layout.yaml
deleted file mode 100644
index 95fc405..0000000
--- a/config/file_layout.yaml
+++ /dev/null
@@ -1,10 +0,0 @@
-umi_tools_whitelist:
-  whitelist: {sample}_whitelist.txt
-
-umi_tools_extract:
-  read_one: {sample}_extracted_R1.fastq.gz
-  read_two: {sample}_extracted_R2.fastq.gz
-
-kraken:
-  report: {sample}_mapped_to_{db}.k2report
-  output: {sample}_mapped_to_{db}.kraken2
\ No newline at end of file
diff --git a/config/samples.csv b/config/samples.csv
deleted file mode 100644
index cc80bbb..0000000
--- a/config/samples.csv
+++ /dev/null
@@ -1,2 +0,0 @@
-sample,R1_path,R2_path
-GSM4658507,/data/manke/group/koppstein/data/covid_data/GSM4658507/,/data/manke/group/koppstein/data/covid_data/GSM4658507/
\ No newline at end of file
diff --git a/envs/kraken2.yaml b/envs/kraken2.yaml
deleted file mode 100755
index 6668674..0000000
--- a/envs/kraken2.yaml
+++ /dev/null
@@ -1,7 +0,0 @@
-channels:
-  - conda-forge
-  - bioconda
-  - defaults
-dependencies:
-  - kraken2
-
diff --git a/envs/synapse.yaml b/envs/synapse.yaml
deleted file mode 100644
index 88a6939..0000000
--- a/envs/synapse.yaml
+++ /dev/null
@@ -1,65 +0,0 @@
-name: synapse_py
-channels:
-  - conda-forge
-  - bioconda
-  - defaults
-dependencies:
-  - _libgcc_mutex=0.1=conda_forge
-  - _openmp_mutex=4.5=2_gnu
-  - bcrypt=3.2.2=py311hd4cff14_1
-  - bzip2=1.0.8=h7f98852_4
-  - ca-certificates=2022.12.7=ha878542_0
-  - cffi=1.15.1=py311h409f033_3
-  - cryptography=39.0.0=py311h9b4c7bb_0
-  - ld_impl_linux-64=2.39=hcc3a1bd_1
-  - libblas=3.9.0=16_linux64_openblas
-  - libcblas=3.9.0=16_linux64_openblas
-  - libffi=3.4.2=h7f98852_5
-  - libgcc-ng=12.2.0=h65d4601_19
-  - libgfortran-ng=12.2.0=h69a702a_19
-  - libgfortran5=12.2.0=h337968e_19
-  - libgomp=12.2.0=h65d4601_19
-  - liblapack=3.9.0=16_linux64_openblas
-  - libnsl=2.0.0=h7f98852_0
-  - libopenblas=0.3.21=pthreads_h78a6416_3
-  - libsodium=1.0.18=h36c2ea0_1
-  - libsqlite=3.40.0=h753d276_0
-  - libstdcxx-ng=12.2.0=h46fd767_19
-  - libuuid=2.32.1=h7f98852_1000
-  - libzlib=1.2.13=h166bdaf_4
-  - ncurses=6.3=h27087fc_1
-  - numpy=1.24.1=py311hbde0eaa_0
-  - openssl=3.0.7=h0b41bf4_1
-  - pandas=1.5.3=py311h2872171_0
-  - paramiko=2.12.0=pyhd8ed1ab_0
-  - pip=22.3.1=pyhd8ed1ab_0
-  - pycparser=2.21=pyhd8ed1ab_0
-  - pynacl=1.5.0=py311hd4cff14_2
-  - pysftp=0.2.9=py_1
-  - python=3.11.0=he550d4f_1_cpython
-  - python-dateutil=2.8.2=pyhd8ed1ab_0
-  - python_abi=3.11=3_cp311
-  - pytz=2022.7.1=pyhd8ed1ab_0
-  - readline=8.1.2=h0f457ee_0
-  - setuptools=66.1.1=pyhd8ed1ab_0
-  - six=1.16.0=pyh6c4a22f_0
-  - tk=8.6.12=h27826a3_0
-  - tzdata=2022g=h191b570_0
-  - wheel=0.38.4=pyhd8ed1ab_0
-  - xz=5.2.6=h166bdaf_0
-  - pip:
-    - certifi==2022.12.7
-    - charset-normalizer==3.0.1
-    - deprecated==1.2.13
-    - idna==3.4
-    - importlib-metadata==6.0.0
-    - jeepney==0.8.0
-    - keyring==23.4.1
-    - keyrings-alt==3.1
-    - requests==2.28.2
-    - secretstorage==3.3.3
-    - synapseclient==2.7.0
-    - urllib3==1.26.14
-    - wrapt==1.14.1
-    - zipp==3.11.0
-prefix: /localenv/koppstein/anaconda/miniconda3/envs/synapse_py
diff --git a/envs/umi_tools.yaml b/envs/umi_tools.yaml
deleted file mode 100755
index acb24fe..0000000
--- a/envs/umi_tools.yaml
+++ /dev/null
@@ -1,6 +0,0 @@
-channels:
-  - conda-forge
-  - bioconda
-  - defaults
-dependencies:
-  - umi_tools
diff --git a/test/test_download.sh b/test/test_download.sh
deleted file mode 100644
index 9b68903..0000000
--- a/test/test_download.sh
+++ /dev/null
@@ -1,2 +0,0 @@
-# conda activate synapse_py
-synapse -u koppstein get syn26011026 
diff --git a/workflow/Snakefile b/workflow/Snakefile
deleted file mode 100644
index 44d078a..0000000
--- a/workflow/Snakefile
+++ /dev/null
@@ -1,116 +0,0 @@
-# Main entrypoint of the workflow. 
-# Please follow the best practices: 
-# https://snakemake.readthedocs.io/en/stable/snakefiles/best_practices.html,
-# in particular regarding the standardized folder structure mentioned there. 
-
-
-include: "workflow/common.smk"
-
-
-SAMPLES = list(METADATA.index)
-
-get_bc_pattern = _get_default('bc_pattern')
-get_cell_number = _get_default('cell_number')
-
-paths = create_path_accessor()
-
-rule all:
-    input: expand(paths.kraken.output, sample=METADATA, db=['virus'])
-
-def find_path(wc):
-    "Return the R1_path or R2_path the given sample."
-    return METADATA.loc[str(wc.sample), "R{}_path".format(wc.num)]
-
-# symlink read one and two to resources/
-rule symlink_reads:
-    output:
-        "resources/{sample}_R{num}.fastq.gz",
-    params:
-        path=find_path
-    shell:
-        "ln -fs `readlink -f {params.path}` {output}"
-
-rule umi_tools_whitelist:
-    input: 
-        read_one="resources/{sample}_R{num}.fastq.gz",
-    output: 
-        paths.umi_tools_whitelist.whitelist
-    params:
-        bc_pattern=get_bc_pattern,
-        cell_number=get_cell_number,
-    conda:
-        "envs/umi_tools.yaml"
-    log:
-        "results/logs/whitelist/{sample}_whitelist.log"
-    shell:
-        "umi_tools whitelist "
-        "--stdin {input.read_one} "
-        "--bc-pattern={params.bc_pattern} "
-        "--set-cell-number={params.cell_number} "
-        "--log2stderr > {output} 2> {log} "
-
-
-rule umi_tools_extract:
-    input: 
-        read_one="resources/{sample}_R1.fastq.gz",
-        read_two="resources/{sample}_R2.fastq.gz",
-        whitelist=paths.umi_tools_whitelist.whitelist,
-    output: 
-        read_one=paths.umi_tools_extract.read_one,
-        read_two=paths.umi_tools_extract.read_two,
-    params:
-        bc_pattern=get_bc_pattern,
-        cell_number=get_cell_number,
-    conda:
-        "envs/umi_tools.yaml"
-    log:
-        "results/logs/whitelist/{sample}_whitelist.log"
-    shell:
-        "umi_tools extract "
-        "--stdin {input.read_one} "
-        "--bc-pattern={params.bc_pattern} "
-        "--stdout {output.read_one} "
-        "--read2-in {input.read_two} "
-        "--read2-out {output.read_two} "
-        "--whitelist={input.whitelist} "
-
-def krak_db(wc):
-    return config['kraken']['db_paths'][str(wc.db)]
-
-rule kraken:
-    input: 
-        read_one=paths.umi_tools_extract.read_one,
-        read_two=paths.umi_tools_extract.read_two,
-    output: 
-        kraken_report=paths.kraken.report,
-        kraken_output=paths.kraken.output,
-    threads: 
-        config['kraken']['threads']
-    params:
-        db=krak_db
-    conda: 
-        "envs/kraken2.yaml"
-    shell:
-        "kraken2 --db {params.db} "
-        "--threads {threads} "
-        "--report {output.kraken_report} "
-        "{input} "
-        "> {output.kraken_output} "
-
-# TODO: how to deal with clustering/deduping reads if we can't use BAM files? 
-# Do we even care about this? 
-# c.f. https://github.com/CGATOxford/UMI-tools/issues/436
-# also https://pubmed.ncbi.nlm.nih.gov/30351359/
-# Personally I think we want to use the UMIclusterer class, and if the 
-# reads are in the same UMI cluster *and* are mapping to the same kraken
-# db, then we deduplicate them. 
-
-rule get_synapse:
-    output: 
-        "downloads/{sample}_R{num}.fastq.gz"
-    conda:
-        "envs/synapse.yaml"
-    params:
-
-    shell:
-        "synapse -"
\ No newline at end of file
diff --git a/workflow/common.smk b/workflow/common.smk
deleted file mode 100644
index 203deb4..0000000
--- a/workflow/common.smk
+++ /dev/null
@@ -1,40 +0,0 @@
-import pandas as pd
-from box import Box
-from pathlib import Path
-
-OUTDIR = Path(config["output_dir"])
-
-METADATA = pd.read_csv(
-    (Path(workflow.basedir) / config["samples"]), 
-    dtype=str,
-    ).set_index(["sample"], drop=False)
-
-
-def _get_default(param):
-    "Return an input function (taking wildcards) that takes the given "
-    " parameter `param`, for a particular sample, otherwise looks up 
-    "config["defaults"][param] if it is not specified."
-    def inner(wc):
-        val = METADATA.loc[str(wc.sample)][param]
-        if pd.isnan(val):
-            if param in config["defaults"]:
-                return config["defaults"][param]
-            else:
-                raise Exception(
-                    "Error: param {param} not found for sample {sample} in "
-                    "either config.yaml or samples.csv"
-                )
-        return val
-    return inner
-
-
-def create_path_accessor(prefix: Path = OUTDIR) -> Box:
-    """Create a Box to provide '.' access to hierarchy of paths"""
-    data = yaml.load(Path(config["file_layout"]).open(), Loader=yaml.SafeLoader)
-    paths = {}
-    for directory in data.keys():
-        paths[directory] = {}
-        for file_alias, file_name in data[directory].items():
-            p = str(prefix / directory / file_name)
-            paths[directory][file_alias] = str(p)
-    return Box(paths, frozen_box=True)

From a69e97bbfcaae62876051db7e12d5e3882fc5290 Mon Sep 17 00:00:00 2001
From: Saim Momin <momin@minimus.ie-freiburg.mpg.de>
Date: Mon, 6 Mar 2023 15:34:32 +0100
Subject: [PATCH 02/33] Initial Commit

---
 SRA.tsv         |  2 ++
 Snakefile       | 86 +++++++++++++++++++++++++++++++++++++++++++++++++
 config.yaml     |  2 ++
 envs/tools.yaml |  9 ++++++
 4 files changed, 99 insertions(+)
 create mode 100644 SRA.tsv
 create mode 100644 Snakefile
 create mode 100644 config.yaml
 create mode 100644 envs/tools.yaml

diff --git a/SRA.tsv b/SRA.tsv
new file mode 100644
index 0000000..13e050f
--- /dev/null
+++ b/SRA.tsv
@@ -0,0 +1,2 @@
+Samples
+SRR10799852
diff --git a/Snakefile b/Snakefile
new file mode 100644
index 0000000..555f22e
--- /dev/null
+++ b/Snakefile
@@ -0,0 +1,86 @@
+import glob 
+import os
+import pandas as pd
+
+#configfile = "/data/manke/processing/momin/virome-scan/workflow/config.yaml",
+data_dir = "/data/manke/processing/momin/virome-scan/workflow"
+
+accession_list = pd.read_table("SRA.tsv")
+samples = list(accession_list.Samples.unique())
+
+
+rule all:
+    input:
+        expand("data/{sample}_1.fastq.gz", sample=samples),
+        expand("data/{sample}_2.fastq.gz", sample=samples),
+        expand("results/whitelist/{sample}_whitelist.txt", sample=samples),
+        expand("results/umi/{sample}_R1_extracted.fastq.gz",sample=samples),
+        expand("results/umi/{sample}_R2_extracted.fastq.gz",sample=samples)
+
+
+rule download_sample:
+    output: 
+        "data/{sample}_1.fastq.gz",
+        "data/{sample}_2.fastq.gz"
+    params:
+        outdir = "data",
+        threads = 8
+    conda:
+        "envs/tools.yaml"
+    shell:
+        "parallel-fastq-dump --sra-id {wildcards.sample} --split-files --threads {params.threads} --outdir {params.outdir}  --gzip"
+
+
+rule whitelist_generation:
+    input:
+        i1 = "data/{sample}_1.fastq.gz",
+    output:
+        "results/whitelist/{sample}_whitelist.txt"
+    conda:
+        "envs/tools.yaml"
+    log:
+        "results/log/whitelist/{sample}_umi_extract.log"
+    shell:
+        "umi_tools whitelist --stdin {input.i1} --bc-pattern={config[bc_pattern]} --set-cell-number={config[cell_no]} --log2stderr > {output} 2> {log}"
+
+
+rule umi_extract:
+    input:
+        i1 = "data/{sample}_1.fastq.gz",
+        i2 = "data/{sample}_2.fastq.gz"
+    output:
+        o1 = "results/umi/{sample}_R1_extracted.fastq.gz",
+        o2 = "results/umi/{sample}_R2_extracted.fastq.gz"
+    params:
+        p1 = "results/whitelist/{sample}_whitelist.txt"
+    conda:
+        "envs/tools.yaml"
+    log:
+        "results/log/umi/{sample}_umi_extract.log"
+    shell:
+        "umi_tools extract --stdin {input.i1} --bc-pattern=CCCCCCCCCCCCCCCCNNNNNNNNNN --stdout {output.o1} --read2-in {input.i2} --read2-out={output.o2} --whitelist={params.p1}"
+
+
+rule alignment:
+    input:
+        i1 = "results/umi/{sample}_R1_extracted.fastq.gz",
+        i2 = "results/umi/{sample}_R2_extracted.fastq.gz"
+    output:
+        o1 = "results/alignment/{sample}.sam"
+    params:
+        p1 = #TODO Path to Database #Config to the external Bowtie2 index ideally needs to be given by runtime config.
+    conda:
+        "envs/tools.yaml"
+    threads: 16
+    log:
+        "results/log/alignment/{sample}_aln.log"
+    shell:
+        "bowtie2 -x {params.p1} -1 {input.i1} -2 {input.i2} --very-fast-local --no-unal -S {output.o1} -p {threads}"
+
+
+onsuccess:
+    print("Snakemake finished successfully!")
+
+onerror:
+    print("Snakemake has failed!")    
+      
diff --git a/config.yaml b/config.yaml
new file mode 100644
index 0000000..e120fdd
--- /dev/null
+++ b/config.yaml
@@ -0,0 +1,2 @@
+"bc_pattern" : CCCCCCCCCCCCCCCCNNNNNNNNNN
+"cell_no" : 100
\ No newline at end of file
diff --git a/envs/tools.yaml b/envs/tools.yaml
new file mode 100644
index 0000000..842fc5a
--- /dev/null
+++ b/envs/tools.yaml
@@ -0,0 +1,9 @@
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - entrez-direct
+  - parallel-fastq-dump
+  - umi_tools
+  - bowtie2
\ No newline at end of file

From e8805bc2c39f417e9788d3ce1091388c4e93b70b Mon Sep 17 00:00:00 2001
From: Saim Momin <64724322+SaimMomin12@users.noreply.github.com>
Date: Mon, 6 Mar 2023 15:42:56 +0100
Subject: [PATCH 03/33] Update README.md

---
 README.md | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index ec70b54..6b2fdd7 100644
--- a/README.md
+++ b/README.md
@@ -1,14 +1,19 @@
-# Snakemake workflow: `Single-cell Virome Scan`
+# Snakemake workflow: `Single-Cell Virome Scan`
 
 [![Snakemake](https://img.shields.io/badge/snakemake-≥6.3.0-brightgreen.svg)](https://snakemake.github.io)
 [![GitHub actions status](https://github.com/maxplanck-ie/sc-virome-scan/workflows/Tests/badge.svg?branch=main)](https://github.com/maxplanck-ie/sc-virome-scan/actions?query=branch%3Amain+workflow%3ATests)
 
 
-A Snakemake workflow for processing . 
+A Snakemake workflow for processing Single Cell Virome Scan. 
 
+## Note
+This is a developmental and alpha phase of the pipeline, upon completion a Python Wrapper will take care of every runtime parameter handling automatically.
 
 ## Usage
 
+> snakemake --cores 8 --use-conda --configfile config.yaml --latency-wait 60
+
+
 The usage of this workflow is described in the [Snakemake Workflow Catalog](https://snakemake.github.io/snakemake-workflow-catalog/?usage=maxplanck-ie%2Fsc-virome-scan).
 
 If you use this workflow in a paper, don't forget to give credits to the authors by citing the URL of this (original) repository and its DOI (see above).

From f41d9a3e116ed45a07957cdd8f4afc266534f218 Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Thu, 16 Mar 2023 18:34:18 +0100
Subject: [PATCH 04/33] Updated Framework of Pipeline

---
 Snakefile                       | 119 ++++++++++++++------------------
 config.yaml                     |   5 +-
 envs/kraken2.yaml               |   6 ++
 envs/samtools.yaml              |   6 ++
 rules/cellranger.smk            |  18 +++++
 rules/download_samples.smk      |  21 ++++++
 rules/envs/kraken2.yaml         |   6 ++
 rules/envs/samtools.yaml        |   6 ++
 rules/envs/tools.yaml           |   9 +++
 rules/extract_bam.smk           |   9 +++
 rules/extract_tags.smk          |  13 ++++
 rules/kraken2_mapping.smk       |  14 ++++
 rules/kraken2_mapping_local.smk |  13 ++++
 scripts/bam_extract.py          |  58 ++++++++++++++++
 14 files changed, 235 insertions(+), 68 deletions(-)
 create mode 100644 envs/kraken2.yaml
 create mode 100644 envs/samtools.yaml
 create mode 100644 rules/cellranger.smk
 create mode 100644 rules/download_samples.smk
 create mode 100644 rules/envs/kraken2.yaml
 create mode 100644 rules/envs/samtools.yaml
 create mode 100644 rules/envs/tools.yaml
 create mode 100644 rules/extract_bam.smk
 create mode 100644 rules/extract_tags.smk
 create mode 100644 rules/kraken2_mapping.smk
 create mode 100644 rules/kraken2_mapping_local.smk
 create mode 100644 scripts/bam_extract.py

diff --git a/Snakefile b/Snakefile
index 555f22e..a2f3fdd 100644
--- a/Snakefile
+++ b/Snakefile
@@ -3,79 +3,66 @@ import os
 import pandas as pd
 
 #configfile = "/data/manke/processing/momin/virome-scan/workflow/config.yaml",
-data_dir = "/data/manke/processing/momin/virome-scan/workflow"
+data_dir = "/data/manke/processing/momin/virome-scan/sc-virome-scan/data"
+
 
 accession_list = pd.read_table("SRA.tsv")
 samples = list(accession_list.Samples.unique())
 
+"""
+samples, = glob_wildcards("/data/manke/processing/momin/virome-scan/sc-virome-scan/data/{sample}_L001_R1.fastq.gz")
+print(samples)
+"""
+
+#ruleorder: download_samples > cellranger > kraken2_mapping
+
+if config["files"] == "local":
+    include: "rules/kraken2_mapping_local.smk"
+
+else:
+    include: "rules/download_samples.smk" 
+    include: "rules/kraken2_mapping.smk"
+
+def input_files():
+    if config["files"] == "local":
+        l1 = [
+            expand("results/kraken2/{sample}/{sample}.kraken",sample=samples),
+            expand("results/kraken2/{sample}/{sample}.report.txt",sample=samples)]
+        return(l1)
+    else:
+        l1 = [
+            expand("data/{sample}_S1_L001_R1_001.fastq.gz", sample=samples),
+            expand("data/{sample}_S1_L001_R2_001.fastq.gz", sample=samples),
+            expand("data/{sample}_test.txt",sample=samples),
+            expand("results/kraken2/{sample}/{sample}.kraken",sample=samples),
+            expand("results/kraken2/{sample}/{sample}.report.txt",sample=samples)
+        ]
+        return(l1)
+
+include: "rules/cellranger.smk"
+include: "rules/extract_bam.smk"
+include: "rules/extract_tags.smk"    
+    
 
 rule all:
     input:
-        expand("data/{sample}_1.fastq.gz", sample=samples),
-        expand("data/{sample}_2.fastq.gz", sample=samples),
-        expand("results/whitelist/{sample}_whitelist.txt", sample=samples),
-        expand("results/umi/{sample}_R1_extracted.fastq.gz",sample=samples),
-        expand("results/umi/{sample}_R2_extracted.fastq.gz",sample=samples)
-
-
-rule download_sample:
-    output: 
-        "data/{sample}_1.fastq.gz",
-        "data/{sample}_2.fastq.gz"
-    params:
-        outdir = "data",
-        threads = 8
-    conda:
-        "envs/tools.yaml"
-    shell:
-        "parallel-fastq-dump --sra-id {wildcards.sample} --split-files --threads {params.threads} --outdir {params.outdir}  --gzip"
-
-
-rule whitelist_generation:
-    input:
-        i1 = "data/{sample}_1.fastq.gz",
-    output:
-        "results/whitelist/{sample}_whitelist.txt"
-    conda:
-        "envs/tools.yaml"
-    log:
-        "results/log/whitelist/{sample}_umi_extract.log"
-    shell:
-        "umi_tools whitelist --stdin {input.i1} --bc-pattern={config[bc_pattern]} --set-cell-number={config[cell_no]} --log2stderr > {output} 2> {log}"
-
-
-rule umi_extract:
-    input:
-        i1 = "data/{sample}_1.fastq.gz",
-        i2 = "data/{sample}_2.fastq.gz"
-    output:
-        o1 = "results/umi/{sample}_R1_extracted.fastq.gz",
-        o2 = "results/umi/{sample}_R2_extracted.fastq.gz"
-    params:
-        p1 = "results/whitelist/{sample}_whitelist.txt"
-    conda:
-        "envs/tools.yaml"
-    log:
-        "results/log/umi/{sample}_umi_extract.log"
-    shell:
-        "umi_tools extract --stdin {input.i1} --bc-pattern=CCCCCCCCCCCCCCCCNNNNNNNNNN --stdout {output.o1} --read2-in {input.i2} --read2-out={output.o2} --whitelist={params.p1}"
-
-
-rule alignment:
-    input:
-        i1 = "results/umi/{sample}_R1_extracted.fastq.gz",
-        i2 = "results/umi/{sample}_R2_extracted.fastq.gz"
-    output:
-        o1 = "results/alignment/{sample}.sam"
-    params:
-        p1 = #TODO Path to Database #Config to the external Bowtie2 index ideally needs to be given by runtime config.
-    conda:
-        "envs/tools.yaml"
-    threads: 16
-    log:
-        "results/log/alignment/{sample}_aln.log"
-    shell:
-        "bowtie2 -x {params.p1} -1 {input.i1} -2 {input.i2} --very-fast-local --no-unal -S {output.o1} -p {threads}"
+        input_files(),
+        expand("results/cellranger/{sample}/{sample}/outs/possorted_genome_bam.bam",sample=samples),
+        expand("results/cellranger/{sample}/unmapped_reads.sam", sample=samples),
+        expand("results/count_matrix/{sample}/count_matrix.tsv", sample=samples)
+
+
+
+
+
+
+
+
+
+
+
+
+
 
 
 onsuccess:
diff --git a/config.yaml b/config.yaml
index e120fdd..3681f39 100644
--- a/config.yaml
+++ b/config.yaml
@@ -1,2 +1,3 @@
-"bc_pattern" : CCCCCCCCCCCCCCCCNNNNNNNNNN
-"cell_no" : 100
\ No newline at end of file
+"files" : "local"
+"chemistry" : "SC3Pv2"
+"transcriptome" : "/data/repository/misc/cellranger_references/cellranger/refdata-gex-GRCh38-2020-A"
diff --git a/envs/kraken2.yaml b/envs/kraken2.yaml
new file mode 100644
index 0000000..516686a
--- /dev/null
+++ b/envs/kraken2.yaml
@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - kraken2
\ No newline at end of file
diff --git a/envs/samtools.yaml b/envs/samtools.yaml
new file mode 100644
index 0000000..2c1c845
--- /dev/null
+++ b/envs/samtools.yaml
@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - samtools
\ No newline at end of file
diff --git a/rules/cellranger.smk b/rules/cellranger.smk
new file mode 100644
index 0000000..b851101
--- /dev/null
+++ b/rules/cellranger.smk
@@ -0,0 +1,18 @@
+rule cellranger:
+    input:
+        i1 = expand("data/{sample}_test.txt", sample=samples)
+    output:
+        o1 = "results/cellranger/{sample}/{sample}/outs/possorted_genome_bam.bam"
+    priority: 90
+    log:
+        "results/cellranger/{sample}/{sample}_cellranger.log"
+    params: 
+        p1 = config["chemistry"], 
+        p2 = config["transcriptome"],
+        p3 = "/data/manke/processing/momin/virome-scan/sc-virome-scan/data/",
+        p4 = "/data/manke/processing/momin/virome-scan/kraken2/negative_ctrl/data/"
+    shell:
+        """
+        cd results/cellranger/{wildcards.sample}/ 
+        cellranger count --id {wildcards.sample} --fastqs {params.p4} --transcriptome {config[transcriptome]} --chemistry SC3Pv2
+        """
diff --git a/rules/download_samples.smk b/rules/download_samples.smk
new file mode 100644
index 0000000..4e77e03
--- /dev/null
+++ b/rules/download_samples.smk
@@ -0,0 +1,21 @@
+rule download_samples:
+    output: 
+        o1 = "data/{sample}_S1_L001_R1_001.fastq.gz",
+        o2 = "data/{sample}_S1_L001_R2_001.fastq.gz",
+        o3 = temp("data/{sample}_test.txt")
+    params:
+        outdir = "data"
+    threads: 16
+    priority: 100
+    conda:
+        "envs/tools.yaml"
+    shell:
+        """
+        parallel-fastq-dump --sra-id {wildcards.sample} --split-files --threads {threads} --outdir {params.outdir}  --gzip
+        mv data/{wildcards.sample}_1.fastq.gz data/{wildcards.sample}_S1_L001_R1_001.fastq.gz 
+        mv data/{wildcards.sample}_2.fastq.gz data/{wildcards.sample}_S1_L001_R2_001.fastq.gz 
+        touch {output.o3}
+        """
+
+
+       
\ No newline at end of file
diff --git a/rules/envs/kraken2.yaml b/rules/envs/kraken2.yaml
new file mode 100644
index 0000000..516686a
--- /dev/null
+++ b/rules/envs/kraken2.yaml
@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - kraken2
\ No newline at end of file
diff --git a/rules/envs/samtools.yaml b/rules/envs/samtools.yaml
new file mode 100644
index 0000000..2c1c845
--- /dev/null
+++ b/rules/envs/samtools.yaml
@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - samtools
\ No newline at end of file
diff --git a/rules/envs/tools.yaml b/rules/envs/tools.yaml
new file mode 100644
index 0000000..842fc5a
--- /dev/null
+++ b/rules/envs/tools.yaml
@@ -0,0 +1,9 @@
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - entrez-direct
+  - parallel-fastq-dump
+  - umi_tools
+  - bowtie2
\ No newline at end of file
diff --git a/rules/extract_bam.smk b/rules/extract_bam.smk
new file mode 100644
index 0000000..ad0a901
--- /dev/null
+++ b/rules/extract_bam.smk
@@ -0,0 +1,9 @@
+rule extract_bam:
+    input:
+        "results/cellranger/{sample}/{sample}/outs/possorted_genome_bam.bam"
+    output:
+        "results/cellranger/{sample}/unmapped_reads.sam"
+    conda:
+        "envs/samtools.yaml"
+    shell:
+        "samtools view -f 4 {input} > {output}"
\ No newline at end of file
diff --git a/rules/extract_tags.smk b/rules/extract_tags.smk
new file mode 100644
index 0000000..c2ee38d
--- /dev/null
+++ b/rules/extract_tags.smk
@@ -0,0 +1,13 @@
+rule extract_tags:
+    input:
+        i1 = "results/cellranger/{sample}/unmapped_reads.sam",
+        i2 = "results/kraken2/{sample}/{sample}.kraken"
+    output:
+        "results/count_matrix/{sample}/count_matrix.tsv"
+    params:
+        p1 = "results/count_matrix/{sample}/",
+        p2 = "results/cellranger/{sample}/{sample}/outs/filtered_feature_bc_matrix/barcodes.tsv.gz"
+    log:
+        "results/count_matrix/{sample}_bam_extract.log"
+    shell:
+        "python3 scripts/bam_extract.py -i {input.i1} -k {input.i2} -b {params.p2} -o {params.p1} "
\ No newline at end of file
diff --git a/rules/kraken2_mapping.smk b/rules/kraken2_mapping.smk
new file mode 100644
index 0000000..ef4ecd5
--- /dev/null
+++ b/rules/kraken2_mapping.smk
@@ -0,0 +1,14 @@
+rule kraken2_mapping:
+    input:
+        i1 = "data/{sample}_S1_L001_R2_001.fastq.gz"
+    output:
+        o1 = "results/kraken2/{sample}/{sample}.kraken",
+        o2 = "results/kraken2/{sample}/{sample}.report.txt"
+    conda:
+        "envs/kraken2.yaml"
+    params:
+        p1 = "/data/repository/kraken2_contaminome/virus_db"
+    log:
+        "results/logs/kraken2/{sample}_kraken.log"
+    shell:
+        "kraken2 --use-names --threads 4 --db {params.p1} --report {output.o2} {input.i1} > {output.o1} &> {log}"
\ No newline at end of file
diff --git a/rules/kraken2_mapping_local.smk b/rules/kraken2_mapping_local.smk
new file mode 100644
index 0000000..a4fb5f7
--- /dev/null
+++ b/rules/kraken2_mapping_local.smk
@@ -0,0 +1,13 @@
+rule kraken2_mapping_local:
+    output:
+        o1 = "results/kraken2/{sample}/{sample}.kraken",
+        o2 = "results/kraken2/{sample}/{sample}.report.txt"
+    conda:
+        "envs/kraken2.yaml"
+    params:
+        p1 = "/data/repository/kraken2_contaminome/virus_db",
+        p2 = "data/{sample}_S1_L001_R2_001.fastq.gz"
+    log:
+        "results/logs/kraken2/{sample}_kraken_local.log"
+    shell:
+        "kraken2 --use-names --threads 4 --db {params.p1} --report {output.o2} {params.p2} > {output.o1} &> {log}"
\ No newline at end of file
diff --git a/scripts/bam_extract.py b/scripts/bam_extract.py
new file mode 100644
index 0000000..ba6e6ff
--- /dev/null
+++ b/scripts/bam_extract.py
@@ -0,0 +1,58 @@
+import pandas as pd
+import argparse
+
+parser = argparse.ArgumentParser()
+parser.add_argument("-i", "--input_file", metavar="PATH", help="Path to your SAM file")
+parser.add_argument("-k", "--kraken_input_file", metavar="FILE", help="Path of your .kraken file from Kraken output")
+parser.add_argument("-b", "--barcode_file", metavar="FILE", help="Filtered Barcodes tsv file generated from Cell Ranger")
+parser.add_argument("-o", "--output-file", metavar="PATH", help="Path to your output file")
+
+args = parser.parse_args()
+file = args.input_file
+tags_dict = {}  
+
+#TODO: Check if the Kraken file is empty 
+
+#Parsing SAM file and storing ReadName along with its TAGS in dictionary
+with open(file) as f:
+    for line in f:
+        if line.startswith("@"):   #Skipping header
+            continue
+        fields = line.strip().split("\t")  
+        read_name = fields[0]  
+        entries = fields[11:]  
+        
+        for tag in entries:
+            tag_fields = tag.split(":")
+            tag_name = tag_fields[0]
+            tag_value = tag_fields[2]
+            if tag_name in ["CR", "CB", "UR", "UB"]:  
+                if read_name in tags_dict:
+                    tags_dict[read_name][tag_name] = tag_value   #Adding tag to existing existing dictionary for the read name
+                else:
+                    tags_dict[read_name] = {tag_name: tag_value}  #Else creating new dictionary and adding rag to it                
+#Converting them to Pandas Dataframe
+df = pd.DataFrame.from_dict(tags_dict, orient='index')  
+df.index.name = "Read Name"  
+df.reset_index(inplace=True)
+df1 = df.drop_duplicates(subset=['CR','UR'],keep = 'last').reset_index(drop = True)
+print(df1.head())
+
+
+#Reading Kraken Output and merging with the previous Dataframe
+columns_name = ['status', 'Read Name', 'Tax_ID', 'length', 'LCA_mapping']
+df2 = pd.read_csv(args.kraken_input_file,sep='\t',names=columns_name, index_col=None)
+merged = pd.merge(df1,df2,on='Read Name', how='inner')
+merged_subset = merged.loc[:, ['Read Name', 'Tax_ID', 'CR', 'CB','UR', 'UB']]
+print(merged_subset.head())
+
+#Filtering dataframe based on barcodes reported by CellRanger
+barcodes = pd.read_csv(args.barcode_file, compression='gzip',sep='\t', names=['CR'])
+barcodes.CR = [x.strip().replace('-1', '') for x in barcodes.CR]
+merged_barcodes = pd.merge(merged_subset,barcodes,on='CR', how='inner')
+print(merged_barcodes.head())
+
+
+#Creating a count matrix and writing it to a file
+result = merged_barcodes.pivot_table(index='Tax_ID', columns='CR', values='Read Name', aggfunc='count').fillna(0.).astype(int)
+result.to_csv(args.output_file + "count_matrix.tsv", sep='\t')

From 472631ba0bec91ca0264e435625b804baf882785 Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Wed, 5 Apr 2023 14:16:18 +0200
Subject: [PATCH 05/33] Minor changes

---
 Snakefile                          | 58 +++++++-----------------------
 config.yaml                        |  3 +-
 rules/download_samples_or_copy.smk | 22 ++++++++++++
 3 files changed, 36 insertions(+), 47 deletions(-)
 create mode 100644 rules/download_samples_or_copy.smk

diff --git a/Snakefile b/Snakefile
index a2f3fdd..1a42b62 100644
--- a/Snakefile
+++ b/Snakefile
@@ -6,7 +6,7 @@ import pandas as pd
 data_dir = "/data/manke/processing/momin/virome-scan/sc-virome-scan/data"
 
 
-accession_list = pd.read_table("SRA.tsv")
+accession_list = pd.read_table("jiang_analysis.tsv")
 samples = list(accession_list.Samples.unique())
 
 """
@@ -14,56 +14,22 @@ samples, = glob_wildcards("/data/manke/processing/momin/virome-scan/sc-virome-sc
 print(samples)
 """
 
-#ruleorder: download_samples > cellranger > kraken2_mapping
-
-if config["files"] == "local":
-    include: "rules/kraken2_mapping_local.smk"
-
-else:
-    include: "rules/download_samples.smk" 
-    include: "rules/kraken2_mapping.smk"
-
-def input_files():
-    if config["files"] == "local":
-        l1 = [
-            expand("results/kraken2/{sample}/{sample}.kraken",sample=samples),
-            expand("results/kraken2/{sample}/{sample}.report.txt",sample=samples)]
-        return(l1)
-    else:
-        l1 = [
-            expand("data/{sample}_S1_L001_R1_001.fastq.gz", sample=samples),
-            expand("data/{sample}_S1_L001_R2_001.fastq.gz", sample=samples),
-            expand("data/{sample}_test.txt",sample=samples),
-            expand("results/kraken2/{sample}/{sample}.kraken",sample=samples),
-            expand("results/kraken2/{sample}/{sample}.report.txt",sample=samples)
-        ]
-        return(l1)
-
+include: "rules/download_samples_or_copy.smk"
+include: "rules/kraken2_mapping.smk"
 include: "rules/cellranger.smk"
 include: "rules/extract_bam.smk"
-include: "rules/extract_tags.smk"    
-    
+include: "rules/extract_tags.smk"
 
 rule all:
     input:
-        input_files(),
-        expand("results/cellranger/{sample}/{sample}/outs/possorted_genome_bam.bam",sample=samples),
-        expand("results/cellranger/{sample}/unmapped_reads.sam", sample=samples),
-        expand("results/count_matrix/{sample}/count_matrix.tsv", sample=samples)
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+            #expand("data/{sample}_S1_L001_R1_001.fastq.gz", sample=samples),
+            #expand("data/{sample}_S1_L001_R2_001.fastq.gz", sample=samples),
+            #expand("data/{sample}_test.txt",sample=samples),
+            #expand("results/kraken2/{sample}/{sample}.kraken",sample=samples),
+            #expand("results/kraken2/{sample}/{sample}.report.txt",sample=samples),
+            #expand("results/cellranger/{sample}/{sample}/outs/possorted_genome_bam.bam",sample=samples),
+            #expand("results/cellranger/{sample}/unmapped_reads.sam", sample=samples),
+            expand("results/count_matrix/{sample}/count_matrix.tsv", sample=samples)
 
 onsuccess:
     print("Snakemake finished successfully!")
diff --git a/config.yaml b/config.yaml
index 3681f39..e481375 100644
--- a/config.yaml
+++ b/config.yaml
@@ -1,3 +1,4 @@
-"files" : "local"
+"files" : "proxy"
 "chemistry" : "SC3Pv2"
 "transcriptome" : "/data/repository/misc/cellranger_references/cellranger/refdata-gex-GRCh38-2020-A"
+"dir" : "/data/manke/processing/momin/virome-scan/sc-virome-scan/data_old/"
\ No newline at end of file
diff --git a/rules/download_samples_or_copy.smk b/rules/download_samples_or_copy.smk
new file mode 100644
index 0000000..d7ae67b
--- /dev/null
+++ b/rules/download_samples_or_copy.smk
@@ -0,0 +1,22 @@
+rule download_samples_or_copy:
+    output: 
+        o1 = temp("data/{sample}_S1_L001_R1_001.fastq.gz"),
+        o2 = temp("data/{sample}_S1_L001_R2_001.fastq.gz")
+    params:
+        outdir = "data",
+        data_directory = config["dir"]
+    threads: 16
+    priority: 100
+    conda:
+        "envs/tools.yaml"
+    shell:
+        """
+        if [ {config[files]} == 'local' ]; then
+            cp {config[dir]}/*.fastq.gz  data/
+
+        else
+            parallel-fastq-dump --sra-id {wildcards.sample} --split-files --threads {threads} --outdir {params.outdir}  --gzip --tmpdir /data/manke/processing/momin/virome-scan/sc-virome-scan/tmp
+            mv data/{wildcards.sample}_1.fastq.gz data/{wildcards.sample}_S1_L001_R1_001.fastq.gz 
+            mv data/{wildcards.sample}_2.fastq.gz data/{wildcards.sample}_S1_L001_R2_001.fastq.gz 
+        fi
+        """
\ No newline at end of file

From 926f86cbd8caf9c6e74209024290595c1c75de8d Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Wed, 5 Apr 2023 14:18:20 +0200
Subject: [PATCH 06/33] Purged rules

---
 rules/download_samples.smk      | 21 ---------------------
 rules/kraken2_mapping_local.smk | 13 -------------
 2 files changed, 34 deletions(-)
 delete mode 100644 rules/download_samples.smk
 delete mode 100644 rules/kraken2_mapping_local.smk

diff --git a/rules/download_samples.smk b/rules/download_samples.smk
deleted file mode 100644
index 4e77e03..0000000
--- a/rules/download_samples.smk
+++ /dev/null
@@ -1,21 +0,0 @@
-rule download_samples:
-    output: 
-        o1 = "data/{sample}_S1_L001_R1_001.fastq.gz",
-        o2 = "data/{sample}_S1_L001_R2_001.fastq.gz",
-        o3 = temp("data/{sample}_test.txt")
-    params:
-        outdir = "data"
-    threads: 16
-    priority: 100
-    conda:
-        "envs/tools.yaml"
-    shell:
-        """
-        parallel-fastq-dump --sra-id {wildcards.sample} --split-files --threads {threads} --outdir {params.outdir}  --gzip
-        mv data/{wildcards.sample}_1.fastq.gz data/{wildcards.sample}_S1_L001_R1_001.fastq.gz 
-        mv data/{wildcards.sample}_2.fastq.gz data/{wildcards.sample}_S1_L001_R2_001.fastq.gz 
-        touch {output.o3}
-        """
-
-
-       
\ No newline at end of file
diff --git a/rules/kraken2_mapping_local.smk b/rules/kraken2_mapping_local.smk
deleted file mode 100644
index a4fb5f7..0000000
--- a/rules/kraken2_mapping_local.smk
+++ /dev/null
@@ -1,13 +0,0 @@
-rule kraken2_mapping_local:
-    output:
-        o1 = "results/kraken2/{sample}/{sample}.kraken",
-        o2 = "results/kraken2/{sample}/{sample}.report.txt"
-    conda:
-        "envs/kraken2.yaml"
-    params:
-        p1 = "/data/repository/kraken2_contaminome/virus_db",
-        p2 = "data/{sample}_S1_L001_R2_001.fastq.gz"
-    log:
-        "results/logs/kraken2/{sample}_kraken_local.log"
-    shell:
-        "kraken2 --use-names --threads 4 --db {params.p1} --report {output.o2} {params.p2} > {output.o1} &> {log}"
\ No newline at end of file

From 6cad1c3ee342790b52818db698252149ea2a2fd9 Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Thu, 6 Apr 2023 13:25:34 +0200
Subject: [PATCH 07/33] Added script for Kraken2 Plots

---
 scripts/kraken_plot.py | 115 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 115 insertions(+)
 create mode 100644 scripts/kraken_plot.py

diff --git a/scripts/kraken_plot.py b/scripts/kraken_plot.py
new file mode 100644
index 0000000..09a87bc
--- /dev/null
+++ b/scripts/kraken_plot.py
@@ -0,0 +1,115 @@
+"""
+Summarizes and performs plotting of Clustermap for the total reads counts assigned for each family and species by Kraken2.
+
+This script processes all the Kraken2.report.txt files Kraken2 tool and organizes the number of reads(fragments)
+mapped to each family and species level. The output of the scripts are two tab-separated files consisting of reads 
+mapped to Family level and Species level respectively. Depending on the TSV files, a clustermap is plotted to analyze 
+the distribution of taxons in the all report files of the samples. The Clustermap are saved to PNG file in the directory
+specified by the user. 
+
+Usage: 
+    ./kraken_plot.py -i <input_file_directory> -o <output_file_directory> 
+
+Outputs:
+    - familywise_taxonomic_readcounts.tsv
+    - specieswise_taxonomic_readcounts.tsv
+    - clustermap_familywise_log10.png
+    - clustermap_specieswise_log10.png
+
+Returns:
+    None. The script saves all the files to a output directory.
+
+Author:
+    Saim Momin <momin@ie-freiburg.mpg.de>
+
+Last Updated:  
+    06-04-2023
+
+"""
+
+import pandas as pd
+import seaborn as sns
+import numpy as np
+import matplotlib.pyplot as plt
+import scipy
+import glob
+import os
+import argparse
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument("-i", "--input_file_directory", metavar="PATH", help="Path to master directory Kraken2 report files")
+parser.add_argument("-o", "--output_file_directory", metavar="PATH", help="Path to directory for output files")
+args = parser.parse_args()
+
+path = args.input_file_directory
+dirs = [os.path.join(path, d) for d in os.listdir(path) if os.path.isdir(os.path.join(path, d))]
+
+kraken_files = []
+family_data = pd.DataFrame(columns=['Taxon'])
+species_data = pd.DataFrame(columns=['Taxon'])
+
+for directory in dirs:
+    kraken_files.extend(glob.glob(os.path.join(directory, '*.txt')))
+   
+for file in kraken_files:
+    df = pd.read_csv(file, sep='\t', names=["Perc", "Reads_covered", "Reads_Assigned", "Order", "Tax_ID", "Taxon"])
+    df1 = df.loc[df['Order'] == 'F'].sort_values("Reads_covered", ascending=False)          #Fetching Families rows
+    df2 = df.loc[df['Order'] == 'S'].sort_values("Reads_covered", ascending=False)          #Fetching Species rows
+    
+    df1 = df1[['Taxon', 'Reads_covered']]
+    df2 = df2[['Taxon', 'Reads_covered']]
+    
+    df1['Taxon'] = df1['Taxon'].str.replace('\s+', '', regex=True)                  #Removing whitespaces 
+    df2['Taxon'] = df2['Taxon'].str.replace('\s+', '', regex=True)
+    
+    filename = os.path.basename(file).split(".")[0]
+    df1 = df1.rename(columns={'Reads_covered': filename})                           #Changing column name to filename
+    df2 = df2.rename(columns={'Reads_covered': filename})
+    
+    family_data = pd.merge(family_data, df1, on='Taxon', how='outer')               #Merging out all columns
+    species_data = pd.merge(species_data, df2, on='Taxon', how='outer')
+    
+cols = [family_data.columns[0]] + sorted(family_data.columns[1:])                   #Sorting the columns 
+cols2 = [species_data.columns[0]] + sorted(species_data.columns[1:])
+
+family_data = family_data[cols]
+species_data = species_data[cols2]
+
+family_data.to_csv(args.output_file_directory + "familywise_taxonomic_readcounts.tsv", sep='\t', index=False)
+species_data.to_csv(args.output_file_directory + "specieswise_taxonomic_readcounts.tsv", sep='\t', index=False)    
+    
+# --- Plotting Clustermap for Taxon ---
+family_map = family_data.set_index("Taxon")
+family_map_log10 = family_map.apply(lambda x: np.log10(x) if np.issubdtype(x.dtype, np.number) else x)                   #Log10 transformation
+family_map_cleaned = family_map_log10.fillna(0)                                                                          #Filling missing values 
+sns.set(rc={"figure.figsize": (80,60)})
+sns.set(font_scale=0.6)
+g = sns.clustermap(family_map_cleaned, cmap="coolwarm", xticklabels=True, yticklabels=True)
+g.ax_heatmap.yaxis.set_tick_params(labelsize=4)
+plt.title("Family-Wise Clustermap")
+plt.suptitle("Family-Wise Clustermap", ha="center", va="center", fontsize=14, y=1.0)
+plt.ylabel("Read Counts (log10)")
+g.savefig(args.output_file_directory + "clustermap_familywise_log10.png", dpi=1200)
+plt.show()
+
+
+# --- Plotting Clustermap for Top-10 Species ---
+species_data['maximum'] = species_data.max(axis=1,numeric_only=True)                                   #Getting maximum reads
+sorted_species_data = species_data.sort_values(by = 'maximum', ascending = False)
+top_10_species = sorted_species_data.head(10)
+species_map = top_10_species.set_index("Taxon")
+species_map_log10 = species_map.apply(lambda x: np.log10(x) if np.issubdtype(x.dtype, np.number) else x)                   #Log10 transformation
+species_map_cleaned = species_map_log10.fillna(0)                                                                          #Filling missing values 
+species_map_data = species_map_cleaned.loc[:, species_map_cleaned.columns != "maximum"]
+sns.set(rc={"figure.figsize": (80,60)})
+sns.set(font_scale=0.6)
+g = sns.clustermap(species_map_data, cmap="coolwarm", xticklabels=True, yticklabels=True)
+g.ax_heatmap.yaxis.set_tick_params(labelsize=4)
+plt.title("Species-Wise Clustermap")
+plt.suptitle("Species-Wise Clustermap (Top 10 Species)", ha="center", va="center", fontsize=14, y=1.0)
+plt.ylabel("Read Counts (log10)")
+g.savefig(args.output_file_directory + "clustermap_specieswise_log10.png", dpi=1200)
+plt.show()
+
+print("--- Script Completed Successfully ---")
\ No newline at end of file

From 793ab5791359799b9c9a6017f4dcc5c503697c52 Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Wed, 12 Apr 2023 17:32:33 +0200
Subject: [PATCH 08/33] Added Synapse ID fetching script

---
 scripts/synapse_fetch.py | 83 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 83 insertions(+)
 create mode 100644 scripts/synapse_fetch.py

diff --git a/scripts/synapse_fetch.py b/scripts/synapse_fetch.py
new file mode 100644
index 0000000..6446806
--- /dev/null
+++ b/scripts/synapse_fetch.py
@@ -0,0 +1,83 @@
+"""
+
+This script logs into Synapse portal and walks through a parent folder to get a list of all entities present in it. 
+It then preprocesses the list into a Pandas DataFrame along with directory information. 
+
+Usage:
+    ./synapse_fetch.py -i <input_synapse_id>
+
+Requirement: Synapse Account and Configuration file (.synapseConfig)
+        
+This script requires the following modules to be imported:
+    - pandas
+    - synapseutils
+    - synapseclient   
+
+Output:
+    - synapse_ids.tsv
+        A tab seperated file consisting of following columns
+            - Directory: Directory name for a file stored in Synapse portal for a ParentID
+            - ParentID: ParentID of the Directory
+            - Filename: Name of the file 
+            - EntityID: SynapseID for the entities under the parent
+
+Returns:
+    None. The script saves all the files to a output directory.
+
+Author:
+    Saim Momin <momin@ie-freiburg.mpg.de>
+
+Last Updated:  
+    12-04-2023
+    
+"""
+
+import pandas as pd
+import synapseutils
+import synapseclient
+import argparse
+
+parser = argparse.ArgumentParser()
+parser.add_argument("-i", "--input_synapse_id", metavar="ID", help="Synapse ID for Query")
+args = parser.parse_args()
+
+
+with open("/home/momin/.synapseConfig") as f:
+    file = f.read().strip().split("\n")
+    for i in file:
+        if i.startswith("username"):
+            user = i[11::] 
+        elif i.startswith("authtoken"):
+            token = str(i[12::])
+
+syn = synapseclient.Synapse()
+syn.login(email=user, authToken=token)
+
+#Walking throw the Parent-ID and getting all the entities present in them
+file_list = []
+test2 = synapseutils.walk(syn, args.input_synapse_id)
+for dirpath,dirname, filename in test2:
+    for f in filename:
+        file_info = {'dir': dirpath, 'file': f}
+        file_list.append(file_info)
+
+#Preprocessing for the fetched directory and file list from Parent ID
+df = pd.DataFrame(file_list)
+df1 = df.applymap(lambda x: str(x).replace("'", "").replace("(", "").replace(")", ""))
+df1[['Directory', 'ParentID']] =  df1['dir'].str.split(',', expand=True)
+df1[['Filename', 'EntityID']] = df1['file'].str.split(',', expand=True)
+df1.drop(['dir', 'file'],axis=1, inplace=True)
+df1.to_csv("synapse_ids.tsv", sep="\t", index=False)
+
+#TODO: Get the list of Synapse ids only with .fastq.gz command
+
+
+
+
+#TODO: Work on the downloading part and storing it in the directory. Possibly by multithreading approach (Discuss?)
+
+
+
+
+
+

From 480f8d921e7617246e7d04a3066dcd11fa453c35 Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Mon, 17 Apr 2023 12:05:30 +0200
Subject: [PATCH 09/33] Snakemake rules and ReadME updation

---
 README.md                 |  22 ++++-
 Snakefile                 |   2 +-
 dag.png                   | Bin 0 -> 23890 bytes
 rules/cellranger.smk      |   3 +-
 rules/extract_tags.smk    |   8 +-
 rules/kraken2_mapping.smk |   9 +-
 scripts/synapse_id.tsv    | 196 ++++++++++++++++++++++++++++++++++++++
 7 files changed, 227 insertions(+), 13 deletions(-)
 create mode 100644 dag.png
 create mode 100644 scripts/synapse_id.tsv

diff --git a/README.md b/README.md
index 6b2fdd7..15d8dfb 100644
--- a/README.md
+++ b/README.md
@@ -1,19 +1,31 @@
-# Snakemake workflow: `Single-Cell Virome Scan`
+# sc-Virome-Scan: A Snakemake pipeline for detection of viruses in single-cell datasets.
 
 [![Snakemake](https://img.shields.io/badge/snakemake-≥6.3.0-brightgreen.svg)](https://snakemake.github.io)
 [![GitHub actions status](https://github.com/maxplanck-ie/sc-virome-scan/workflows/Tests/badge.svg?branch=main)](https://github.com/maxplanck-ie/sc-virome-scan/actions?query=branch%3Amain+workflow%3ATests)
 
 
-A Snakemake workflow for processing Single Cell Virome Scan. 
+A method wrapped around Snakemake for swift, precise, and accurate detection of viral pathogens in single-cell
+RNA (scRNA) datasets to investigate the possible correlation between viral pathogens and neurodegenerative diseases. 
+
+<br /> 
+
+# DAG for the pipeline
+![Graphviz Diagram](dag.png)
 
-## Note
-This is a developmental and alpha phase of the pipeline, upon completion a Python Wrapper will take care of every runtime parameter handling automatically.
+
+
+<br /> 
 
 ## Usage
 
-> snakemake --cores 8 --use-conda --configfile config.yaml --latency-wait 60
+> ***snakemake --cores 16 --use-conda --configfile config.yaml --latency-wait 60***
+    
+### Note
+This is a developmental and alpha phase of the pipeline, upon completion a Python Wrapper will take care of every runtime parameter handling automatically.
 
+<br /> 
 
+## Contributing
 The usage of this workflow is described in the [Snakemake Workflow Catalog](https://snakemake.github.io/snakemake-workflow-catalog/?usage=maxplanck-ie%2Fsc-virome-scan).
 
 If you use this workflow in a paper, don't forget to give credits to the authors by citing the URL of this (original) repository and its DOI (see above).
diff --git a/Snakefile b/Snakefile
index 1a42b62..d5452fe 100644
--- a/Snakefile
+++ b/Snakefile
@@ -6,7 +6,7 @@ import pandas as pd
 data_dir = "/data/manke/processing/momin/virome-scan/sc-virome-scan/data"
 
 
-accession_list = pd.read_table("jiang_analysis.tsv")
+accession_list = pd.read_table("SRA.tsv")
 samples = list(accession_list.Samples.unique())
 
 """
diff --git a/dag.png b/dag.png
new file mode 100644
index 0000000000000000000000000000000000000000..276925b149664d477af910bd00c25d861bcc5211
GIT binary patch
literal 23890
zcmce;byQW|8!ozN=`KNG(}FY-g0zIBq9CDkhjdCvcXyYBbc1w*w6t_cDk&ZN&iy;*
z-ZSpFzccRr>yGc+%3!TM*PL_B`OfEg-sd$$Raq7n>me2dLAdgA(r+LL2@`^lsUDz%
z-&|%|nuEX44HRUhAvof{?AF3K2%?4Lr6u0FrvF)T`~3E-RqTE?#dF9gtJKICQ;%#M
zi}igroo@`kdb?cML+d&(%O|4a+7&0`H?1o_KXRhkU7dLy8|<U2=R2!;EU}uslt6tp
zkQg2D$Ad?kC*}9)jUi7^%F{S`9*5DC&AZPcC$0=N>8F|UTM1)V>0?))1^XyaVE*9}
zOwLID1m=0swEn0sVG<88UvW?4&ZU=`Rb`56z%~B~aTttSe;JyjiTw3|FkZ4C;MHTl
z_fGsob!c+DI(V%-@BUOv_bb(JR4;j9B`kT%6y80B_HGy^34<7xJ`XFg_{nRqICJNw
z*vieN|Gg~OAgz5Lg<%sM*PX5Cr=0R2K#^*O4wKM#XcE7<23y?}o5BHOG0EhTj6<RA
zk^5Kq{JkFDoamy%8v@e5oE;<SZH4qNb^V`iyvpARdqO=>yL$33Z{++LM=E~Kh&qz4
zg68Ox*GAv5=c`J3*j4plfvDY0<pQ?l`%$;-c6&M`sXt<hGRQkm9uR6AisQ2W(v`jt
zXY|(gTEuM}c4QW`rBi20x0CYyvKE$DIAJ7&1x4H0>m+_=w%<@6OBM(jw!*=wYdzdZ
zi%eRje2z01tQpGovwk>utfLWjtkf^6v*U&hWykN^8UIpe*eAn!Lk)ZLbJ`m(OF#@W
zXaNUGexw^Z6e|#-^KKLE5%cSn3m6RnYZKD!=(P*h10F+03+zg(nGMxJT*wFe#iyLM
zL#ddO&=zi~t}QFsmp9nU7<Trb+5RH+6!D<3g%dmpeQj(Yf9)4-w+xffZD@z~^-2cb
zy_`u#^o8wKGkhraP`dhnr!$mJ`Ug?nsh#G@BM8EGSa;m^ieU>aeJz!{<P}PTL0B;;
zYqMw}5k@Dy2L?+2F%BOxt9mTkd>21J`f{`g_ImzoJLgakOvFw2PA8)gouDlXUjm9$
zR>Y5k_Fyd)hKL84`+988Z^n?JH~)I&rpO+AB!NxPO7LPlxu%1}3-55OMtA20xak<Q
zteID-^b?JBV75a3(n$(ggn?xHnA{2>$%L?pXH%i8f<mALUvg<VKKY3xpN&nZWrL+4
zj}WHs%m+a@Klr|rf$_2!X;H+3EmgCTJ1{NX7aUDtdw~o&{xIqcgE2hZjSqo3qI%M8
zWc>XXcppHj15>`_QgVDJb&Ve~kz&|F!e1+Yx#swtd}}^7Gox-x9W**RD*wr_I+5c;
z=ysO3sKEmHX`Rx${FStnp$pBF%s9>o>LmZ@Y!-$GFp1Z41d_g33Ualzwb`|`Br<t~
z*kn&Ts6Mq2+Io9<2zwp*(R3K`z!(|PT$bIKzc)7{L7!TV(YHpL`I@H<qh6p#Zm6oM
zp+JJpe<%zL4cF|OAc&EX(e+PNf2GAVD@BCNaGC)AVe7?mavj=&02H5?=(`~}V8pYz
zwPkQ~{`V-$z_4YOY?yaU#BXs?XXniQscsuJvq~n8TRUiH?z<CPBBw5%U#AZmHreW2
zmEl~SB{>f-FCi6Gn8#r&`Qs?&RiP-+YZk;^c@x3CVdNVFG4zHrrgd6X#zSOArl#~9
z9C%;9el4n~z%Rbn>+={>c=f8%dV#<6eHAh{H@EBGx>;YFF)Mz<p+xq9k&&05KZ|&s
z#AS7u)C9CtR4vE7@Ho$|<g)c$`1XyJg(TGHLch<j`}XP<{e1hBYHoW(1-IQ&aVUw?
zbOnBYp{cD+)oi<l+`JyjMgh%COmtEh{#jVL=htqqd1Pr}VL;CL(TGi>+-QHM%rKmL
zW@%}}h=;PIqQW$syWVm44ZrCq_4%U17<V7VLYt?scDvV$_KNj&gT#b{-pEJ7eOCNb
zh~M+3C=PENbM;YZR~un2G`n!ZFZFKDx9ywe2IH9L|IF9S-{0Lxd086@dEbkuu_pY9
zQxVm_ySw{SGbU<?|KgwOzzsVGhl!Ao(4R2QHa)VifF-Bd4^Nqx0+$@dUX+%UguPQ&
zub!HEdw#uNfg!>yDw_G|xnuCz*;y5HrmHVygv`wHvgn?Nn!0-5O!<c)3k!?)y1FzT
zN1Yh+xi7<#7yjZk-A{yHWRjDU*MMf6HwOr}?3?<QmaotD=c|o}=5{9wHC0sbJr0_-
z=h8m4QJ%E*xvM-S!{&V$f#~cS4SdxPznaRX5tcu@d+K(ocDrrzJk?%Kr_uHclAg7-
z^{q9{=OZMz#JBQt6X?CQHM=*wSgjDu`QqX*nDbD!a=rGOr9(uw!XhG!5kJqdH!OBh
z7+Up)lKx3C&0NdU*3lVu{`;#Jz6jm}RN2=j)AxQA0~YUzfAMcpr3ROZ-~Zn)-{Rt8
zefQSPcW>XKdM=vXoVAWJXMK)^UybKTg>ML&)M;HUcwKhWRD0jedgHo|(npC9RW4nf
zZl8YHhcEN-@o_<=#l<1sr3-&eWb$G_Gm4E~S*pvY;I-C!-ke9*Yv}5ZL6zUWeUm?A
zoAa=T-(A!wrSXF$Kt(~J7ZMWkCqiKP!POZL|DBY<k07duh=}q1Gp-a4rDvI0S!3QS
z<Ks|(<d^hx>ihcn8q?DYqz>>hgYZQ!p&-0RUGFqL1UT)_taamy`A=K)nr3+h?w2=n
z=w;pC{IqD@F1opq<#<5yqYeMD2x9wm>v8#P2wKfoqk-qZTI==f9UP8>#BPz`C!BC!
zw(>?~mlaQew)<<#`+L2cGkN7UzHFtu3Gu>7iHcc_MgCi-?ccv6F5NDjk+SRS$)M<%
z7^KLJ4m;{id!b<y-o3rOzB2EpIW5~zbV9<jgL){tyd2NI>GRaZiz!bu4;8QL$*lD#
z?_2us-@n@)txB+vU@baMD#51t)f9yoz}DBVnIB(X9$nemSAl#qYfL(S+pn$nDoCkw
z>NIw&V7N-HgOT>!9JWVImuS#Gdq%puyX(4FTo|3491Pxy%D4LC^QD=Yzz8aV_2YgT
zSp@}bk;nMXhsz@u-r*O&`Wz;e1lBTKmODZ4jC@z3zV^$qB4Eje#-&|t?dIraHZ4WS
zUZ(2LA1e^W9G#tg-L&IxlMbbL)bBd|Pj1kmNNj6rWo2c&MH_){B_+(Q6?%t*zG&E$
zMuS8xm+N73HKzDKhK6$9vPylkE=abQ+uYvXNVP2Q9P>Kob#!#hE+{~c5;=L`?fvoN
z<MP&XtwnG6ote40gp?GD*Zpah;oo0%atf!BZo2hWlwd+Xy8R|?o3;h}cTJ%EY9v^_
zM>@RW@c!P*RpfC`U!UaHH)}f+d2_8EE&~<p$rmf$G>CA?q0<NzPGUAJj2wPyxl``V
zeBp64AxqO~P^Gs$nqg*TC9SDBAKY(jY^;BGea6DcDQj%Z_{Ui|l141Dx|&CjIx_nV
zgZRgx2VHe_wW^j@X!BtkmFZaKOR(L}50=6jmfhJlJtHnMZ~qmFAtKk&ZeiAXzu5h;
zzh(MCm%Z~w#}|}Jt+Ii!F<Eo-CkKrik%SjiIOrs#q-!TboU$@9=pVhVjPJebv?7d$
z5+(8`j#@`bG%5n;tuo)pfdPWm{%5WVg-XE2f5NP1rcB%JbVNX9r!L|*BHFI6uU9(%
z)#~Z*H@rAla=km7)#sv+{B>xw1P+b4dTXkmlap26aIcoT^97_J_It#$NJvQZz}#}B
zD9*LG@giQ4dWqkRSmv?U3US@16;Tp0GJ}!SX9Gh+-66!xmG-}XL|;5x_IRVNj-H|z
zn82oS62!I{OQ^O7|9Zj?iOUSXyHx*0_Bxa<PVLPb-=N3t57PLR;O5Ixq(3~?Z3Uw<
zGb2~-&l?*5)-N!%L~XFE<PDxsLaQDQep#atGJMIQ!)D>!x91J*0qP~a7wvG*s-YML
ztPpvys5Zv1aNw+*oaD_d!I&5OWH+8uyN;J5pS=89Jucn^{iYx>ASWoZx3}+Ls;Bkn
z@jRQ>AY74c)OE>U=|5hMn^4Y(6Q|cAYAbFG<ZM-bK$&q^vwrhOQGi}jQi$(M;G`jO
z3x#Cv#Ok=|OChB~4{Aapt(Qbl2hZG7S8ji4`h7iO0E3b<)kGs7guHjcgY-J4QPOHW
zFPHoY#Q05x(RG&H^dt7HVoE~70oM7c``xj=_qr*&mw?FnR*b$NC&0ZRjSv=-tBWeM
zoq^g=eu%<_N)xCspxC=A@nHo6f|?W~NIXLTUh89dl=R%_VFl9ahm(r(3zW_<I);Z+
zXI{{Lwu^bYCihTw{H}C43y;hr#dp!J*qc&nds(~BeIy!Qj^{pzd0w~>Sn~k`39?rX
zXu_oD%uVBv!Nn}2Lvq+?$L_c>`8<6uQn2s1=C4TIo%9zz0zXYpJ9@DbFHbj1B4mg+
zl$oK5)yhK(javx?@@8P5vV{^n5uS8|MiLDn2wbQke)Y1PrMeFXQ>d`(XL!)%Mk&CM
z+21c7bz;#=hko-|kubi{g<NkA6HP==g$jw9z71fxf6)kMC0=>u?L%YZ{_XDN=jr;S
zK&v>)piaNZjEeQQH(?Nj$D@;Z&f8NYGkX1ODLh%lfDd;|<;Zx!;fRYFqLptT=q;du
z$s{~JM#dyeGp?l6ZGhutoKHd!WnoWle3o9KUCKZLCVhT1<Wqj{AUM+!c32u?XTRCI
z<RgT+5};)hZWiMo+_}b|_wA;lXx9@XGiRm-a3RKBe7e`#wDwM2m_iIt$Cg$1;0!zn
zG;wRqqa5<~&LICG8NG4_b_P$1u5n7V+4{-9?t?$l6?y1o^>Jo(nVZ^UP;?P{$NCf;
zx0UB*4{LxxPV|v^U4}RS{FTCapNy>~nO@}u_jlz-Bpd5QDzF8QQO99nLbe{%jb`^0
zXPz{<v#*8ki3j3sZP+)<r6C{f2{fj{!8dg5%5gzf8?THgD}G~;k4nekVS3+{b2y%5
z`OVuA;x$lm;NKwyr7aL)$SQC^;u-4LZi*EHq)K8~DP$H+gfdQKfHUO0V+j5b%izz*
zAh+q{=(swZ!V9%v{|JAkBnn%TAzmYr^v(UhsAH(4F98ur04j`u1q)MBPL+h{{|1`>
z|GW{a3Y(TbWyIv)*%{iRNzMG_Ve|LzTwGiPw%%4&Ps3&MXwPC&0wg7U1tX=Dltz*-
z8tUpI8m*7ldt;u44C^^I!XyCF9k-~1iG3`Yrek7a@+FN)373@2Rb*0=eylJc{aQ{A
z3^fJ|3p3>Bt|J!(&W7ly9v3*&F;xjuidh&Kp2m|Q*U`!4gB#z!diA3*DkqvYMg|7c
zXHCGWs;V+vrXeTCsMBKCduha!8y(%K$Bt(4k^rVECzn2GgxqgOZ?i3kCoeBg_g32E
zA$W=!3yGYZ9EF{Sq$G0utFI40e*z`xu)>|+O9VZXW+5SZP0P(qXy23$*JO%=adW@!
z2^~=E;_geHd#RYPWY|AjUvX6T*HXuEDzAGQsd)h}u*loIW#3(czTKN2%GUBgqUmYn
zw12tQ{l!nYT&kLma(<7RWH(H;l=F+Sj9*Va?Ki31q3HlIr`9hjBeJV{cvV9oMbxr*
zGmaH#P)pj8SdrRnh^BH+vCy+}{*QiX#O+biXmzPQBndF?0rX?%3++qo3td@%sTR7&
z=HK{w1`MHa5jKJ{!M?TXR7oGCLQ`)Pd=Y~r5*Zw_1~hg*_8q%3)Wy85srOk&9~P5U
zu}BMvirZ4y_at-8D+z_uoO4I!f2<^ad)4b=P|@9hqtTV04n%{5gapW^$zeNGM}D(b
zc)@P*TIhb_0!a&l^Da^?zSxyz17=jj^Rm>&B=lRfps`p$VOo~&(niKtdCu958_b5)
z>&s`+BR-;Y%gZ03<(S0DM=0IQTiyoV{i4ZBCXkOzLGM=W$ou?4OlN<RXE3`SdsGiC
zIJV6eI`lL|)0ZaY;EROleL^gQyXKPmZMi3Bq-G=%w3$wQ@%5f$wnvBF-k4YRt$)we
zy~Cx`M#ZX;GSq=<C$Q=~nXy{%Itzu83Z*;i`*H{PKq!9caT_t=vQ^>@s(*f(pbj=n
zEM)w3t#%`)A#h3lVHZ@Kj%<Lw*0FXI(tv0Hf&?5kb`uN753I<Ws#7F>!a6%D3(w%4
z>-Er4J*`b}v&81N;P>EfB+EcAIGASm^fg?mq>Aee<8Jij@X3?Wvn({|={S22)8r#M
z4e1`|=3TsduDt4YqAX2O(x%*9m1@}9k>HU<zZbMT`mI?>ES1odOU{;Oz_wvmHrioX
zf3L#%Pf#~+E5^?drRuEjQ6n@t3)8qzBg}^V=eu3dW<K4Agi#u2$L8<HDyRK)8howt
z{0w*(kB}i2Ax4{5?>X(CNn6Y?e<pu5>QQ`~(}w@D+{8W3NY1h8yXtlk3iOo!Y2a(+
zq1hO5nI^(8++~S(PLa>SMd@<0>sTYX^nJ1Z3$4kW=R9O9E9fZQP4^CT8oZwJJPZ%1
z$*&Gi`L5{HCG($ZWb}Kl?3fW$#qKJ_!X~!A*XBCM`fk}V<SD3syk6LGxIlAbNWqd1
z^oRdmv7l6<RFNr6G`~E2l!-*hma@!1Npvsy$m;_DDu9s$IIYCYF=5ic+i@SdPzuH3
zV-h|3pK8L#KRj}%s&c`bc~PQWxB`nlb93*FjEq(b#qORAo7Bu1EB%_tlRe&`fxrKs
zcNzhf?+SR~#Q3<+#j*!JjrT1#|EJ}r&YJ$=T<lU^HVqriD|Z|=Eypr*R?C{Dul^tG
z9KcJg$PL=K!RWNKu)hlphNZjD0zXY!)EOWc`{<~Qjt=!J1%=muMTxcL=c7iwIHyoA
z(?SDsfZOTT8qgj#4grR~sB%BE0D{C*okoI-MF;%*t1<7uf7giTIqj<>WCwIVB!v1=
zW!PV7Im=;WVnWByPX_wTDUzvhsuy{o1(buMoxCW6tCQbc4<p{UxN=8Q3lW{%b>j>4
zdE6-}DZK|QKU{{M?CE<Sz_ZAx`*Uh)c=IoO9t6vePmZWmMQjUHf{*`gIv{`NKiDcN
z6BEgtdr37aZw{KHnsmy2Zq(G&=40q(k!^q?kTle*oGCJBGL|`Vez-#OlYi*PkGWrU
zmYPaRxcmG2hJfPHYS)?(Iy5icI@DBG1AU}FdBntUq2ZG$Q(TCfNapK(PBu0}0OMip
zGXOH5_mb;!h4pqFeBb9FBPQ+!?ECS|^mH#P8=Izu1*-=D%CaH?bCwZNQKo=98hCno
z{t02u)C0V=uAw2w5gyB^Ft^<5fl^QY=S<gO<k_G41slV^fB%+#|DO86?RNqWw7;|S
zVE4t*@m+?<((ROgrmUnundEwm>|_0=rY1yV6leF~C1R``{)b_6{B<a`=KnuQa{I_%
zXWqPt0ajMl%k6_-bz$x8&CO{@dVq@3pWgtLsM6mb)p@NeAX;}Hs04%X&pYF=K0E3f
zt+HEdvD-EL`S$z$cIC^u>ohTMQG~c4`Q5uVnqvP<<K4T62mao-8#E+DM9<3b1iauk
zD^i7%Yxg&YG-vmvrKLVu|BV4}*wp-Y7JJ!$#o1dpZGi*<T?J{u`+VN?cu4o22%$=x
zoJ!GrNKH>4_O6&P%bwiLp4~^WIbG3Usd&c8`Kf2@K8o`2eyz_Pv1Gtmi-i3ce}z9L
z(wvk?MdTP23mY4;RR8_^7v8wy?Q~FI&u_KZNEjt{FQ}!ZwR-GY>2YDxs8ep&kdl#s
z3%JMVs4~|l%W(Mj-GVg9@(Z#14Y8wrUHC%;`v+<a)77_r@;%G5fGicTZUBRpY7=`)
zNl6Ll7t$U6vuDqUm+=VuYOyeZh;Vmvu~9w5(fuQVZDLvUoH`f`?#NXnI3gn8)z>bt
zwW~ZX4x;N*5)uN=_Gj~2TByMRRk`q2(Cb$4$B!SYw*LG`KkBU)Dow{8f4)8Lf8WSe
zP5eFZTI=G^ydNN*56HsMgk27#4GrnR?UJA)HKt>I2#I1OO&~8X4+V6`bu&h`;NL^}
zO~sOEs3mOoV5ynBM7^x5ZuX<FiGv_BGlsD9pN_r=Dt*3(RbcBbem)(6eLDS}q$?vK
zfdu3z?6^UHM022b7H5~;17+%LUU&Pt8|%Gc$-*ui-UGQ4W__LqM*i1YK$-k#wNQ@>
zG=jNyZ?R>so4-EYsmBLd!6+Db*$oZkS65e!$9+_G`(+Kt&|6lmuL>3nLSOHB*;O`*
ze)B>dB@Vj8O{pn4AnpKNjey_!7hmyB;T{M$!r*8BgM$Oi7l#-L4M<R8pH4tlp>>F~
zId7)qALM~y$JGubpl;}R-<=f|7k2{HB7DK7S?N#p087ErnoMm8AbR*>f!+y8Nnsy8
z&gr-;ISINR(N@>gyat3DC=>d#<sS@^Udl+YV}=Y44pKTynKB@_p4xZsTq0uP<6oAJ
zER?tm^RY)+&sQ4GnPJ^maO-h<>=^n%7j@>z<CTRM&V+2RHzrhCA09urO@pm54o1tp
zWja|Az~>Knj~P?F)oF5n!@#KIK=C9NCxqIG1AcdPe~LJ9N`D@HqSwx#{|K8*XOPMj
z*Y4nKv0rr8*|Z3L>uGaG?c;(}h;033U|LZ(76-FVF~YzT6Uug9MYg~&(-FgbE3E35
z`o#hg5Ah;YN~V?o_dxF-xx9ei-7BYtC!(If(;7K!>Vgv#y<>4hBtO7H|MfyXyyv`v
zCPJ+CFQr){wM4rqZz!P-$t6jWJ*=1IX6|uTa!^OX=E4=@mhPTwjIMF|u+CDsP0Qjj
z5hOl3Xjiz)5yO^x&+v#S<(pz@h&Bqe<8-zzpd`#C9#%R09wig$w!j?2{X;9{^UTgN
zx;XXnGntVAxE-?9{)t~H-T*<Wheh3!?9ESDOtO*2piG<ji0ho`E%F_*)%tvzVC^X!
z*q}mhP|f$U%Z9-Iah^G3XyA?MT28p``12fI>8KJ6;WY2=tlvCOlrGyf7xd$)UY1*#
z1cw5e#&1e>U$ZMV{(KG#3Rde`8{M=A_>0xvm?0J*uJx~x<X2MRZ{M*#9(6^1@`EIX
zElntwi2?c)wqBgbe3fb4vGC_s;wRIlxf$K`ZoWx2dWG`=)p4^Itu-5ty<c#`h{$VF
zB52isqh;obb@{KSz$$Bph>~bIpH7I|FE=^0uidl);|X70ccI{y+OTP%r`ff^MMN9C
zM)Bj3TTHoUddfPj<;8q_^X75=$(&$olRR_b8qYuWY1AK$I*8{Rf3blbD7F#TOlfY2
zB}+?B1^SOYxq0$={N{06wI>?0L+FRm_}_S&205(+W#7osr!&7O*-*jdy9ZLJ9niNV
z|GwU^^!yi46swji-Tq*<x2)jH8zO=;*xJUCplvyvdhe0bj;(XYK~*=(*riH*^6<H)
z+}>Gcolu$s8Qye{%Ef4_ApUoxM<P7<%G;hO4T`^rF9vA+lnbP)dH#d^cd)XzcC>Jc
zllfuXAJPTwkkv~_UwtLg(DgjauLszqgVQ-KDJcl(i2*gzJl(2enf{GSHeRHTd3Gm;
z5Ri*tNghEp0?(d>@R%~Chyq5`W5s_;vs3Kvufrh=&Q7Rf%@*}(q3nOSRPemjR(n)L
zM8?m05O1&QRHz<4EU0DYsR8s!4oGCsVOJkuWNN<>W%48pa$U+*!+MDb#Qhaf1N{Bp
zKP7|26%}!es*B+kw;H#PEtTF%_DR8Dg#2l^97)(6Q`hvjy?uQr?6Dy7<KT=>*BGsX
z4t2Q{A^CGMK(zGqC{PE5lo~O+ia1lGq$FL}y!q~!5syUKIi8}0x%rwlo4<c3`2A;C
z4mh9Q6nE8sh}-~z6kdlgUS3_@GphwAUX%cT)J7eSe-{@h9r0rp;eqHHF~!-@(a?$}
zE-eo%N0lWyc0D8CSWnLfT*1tVj`ooYLM3p09{-$cP#W+)pJ|KV?E(~Zy!)~0CBHE=
zK=NQ>m6eDG3lsCGj=}NyBa+a8krwGPOdd)SB07iX8Mm~Ba&>f{fp&N434~BEpVE%r
zM()|s1Ste}g!iAzFdyo?lza(;@#IK#8Sxx%aHXcDtvM@r%&^jlVqwN$PMGgTfxd*~
zf^SqX=FIM2A*sY9#>8~$8vmM`lk+P<ka)U>)YO~8_yK}bN0g$CKulAp^o-j9vrCtQ
z|Lk@`hnV3lxama69orROz(0R-HyVt&L%8urJ4yn9H@HN^%K#xdg7`}F5+0;l{8p7U
z!S_%MBuVfK&(EE~MH$dbI$gQoiO{2C8lCCI#iv@2q`$K;NdH_}8N)XMO_<q|QsM{r
z%k>;Y9mNb9$tftHtY+L6l$9yfY6bJXmJ99?19OxSoDfc}^D<Zr3{UPWBN7CbEK?k&
z&jnX7x&|SlH^)v|7JLso0}U~Vt!$@PS7|LQEhiQh*c>&bk?91wF)4`+6^TswZ+Fk!
zff|}uScuWu+Inj?zO`jiTUXb)aV%ak9je1f2wwLCpznIWPIxPcd{ocm?(Pmjg~}OS
ztE+k)cglro;nl$dJGN4&Z}y^&?3$M-C@5An=x81j7%s^ah*`)7cQo{&)83~9acbKC
zpI!jmpzbdP1qIRS7rBW&!_qJqGCZ2#RIt6Z^$`%6vE4*5u|iTp@C2k+u`v@~G47>A
zY;GEPrQWHk$_*=mu^k2Y&zWKiMuKeHDIpCF&CiV|3?@uim|vQ7IPSX(Cd{PE`-Gp~
z0K9^2&gg(>OHxwr&2H4uHg@Q-Nxyyb5`Zqq?_TEng5S3VxI(-BsH+(l)kQ^Si#6<1
zsmX3E45(W)L>6^gJ+EZmuqLpuvSPVYNW-{KRplNGd!I8u`6rK4s9y5=?OVPrMNJYS
zUhv8~KEpcgsKw^Prp)TJNXW^fzPoY<^bCXLz_qd#`0DF=khnt3#|l|}{k32_YQ%RU
z8cC8X7zvA|aQl2}GMqop8%Q}dphTEpTxUEMd=aPp)iRNl%yPq>Ht6CCgZ0<ZRbjnd
zCgamG$v}!a>Uld05(aZSx9>>B=xfYmndP9*Jro;o;-DMV?%(>Z7m}RIP2*vB+L!kW
z0yy7}C3LCFqyC~{pyM*P3US?hc>J$f#H>Ncu4ORPQ`be$s~XSvlvp*H?x2o)5-Gsn
z=e8mj$5amVsarwUDSP^%YeIoKOe*ko!21Z~SMzW2tPN}@@?;WANK@Q}68o?k81z}L
zKRkAv&oHYJTr<JJ=}5s79(9~MF2g~w;ZzQkS78qu1RF3Ke*9T*W}d>4_m9wWs0tNF
zS=-llKPp8Qf{it~lQXh=<Evrf4^vZdcK-b7xn8fewdN}Y)A4!9q&r88msQJJ4~i7f
zJbqV#>%z{X|L)*2@716j2@&!Men@dWgFA-KoLfF6`S;dGIn+MJ^D<VfuVhM@c*rA+
zjf~{Z!*Nz|2fn6ozfYy~OU*=Txil7LZAM>p<h{Khw{D!<?#Sq6l51>#A1f%cKZ;!d
z)+0z=0HFXdLm*Mb{ZcMm3h@@6^5JN9xyOk67=ls$O6p_FzrGK_A>6BXd*DYWj76zO
z4GO%5mB!`|(RxwGpQs{TUC1k*+vctO?u=APz4A$pE9&IbFn%o_?z`c$Z`!|B^~toW
z=)Ar>l3%M5{x)bJ;Uzg1CX!N}N>{g!X=MGXLDmJIg?=brl(&a^4<2Vhm@fnSV_j}+
z^n?pf_x;cKqNRU{o4)Nxz+l<M=khHMIT*V2uKg_e{Y6I|KlxaGPubwTEO;G&QK1}U
zP{e!@5cijU6g_6*wcLXNaw6*fi07L^6gAxu0?HobBNHq}uCAKs|5z;~6nk!s*bi8g
z(ILSXI5%w1fuj8!EdPO7X6_WJ2$U7auC0Hgzg79gke=}6+P+cW?uUtWE_geD1*K-~
z9K#k1VlUE_77;OS$TAW+-fRjI^aP!8W(3#zyATgiKhkeTrc1n^_x9!5Q|`Hl6~`pZ
zaATX1A{KDb>g)d`GLyl9=o!navvL>vf~81xwhy&rIN+|&`&x>%V(UgVE`u-X(z~ZM
z`zmLj5tj`dw?*M}gydW#g@cog*5=|Xb{-Q?#C>+!aULsqvZLzce0U{`{IrxPU+$ic
zDO@lra~|v%p804q9{ets1Q$`<WGt$(H-WVjpH`wjEn-qW3h)<aq9XE)R8Tl%oJa`Q
zPbfNV%i2QP{cz902v%H*m7JhXQbA>*RK(Fw))w!36b>yWS_%+`6!{r$E82+na`V3`
zB&}a<XVIK)?{-~y{UnX-1hZ~b4U-6-0}q#kN#v4(r?4={)q<@NJPy<6PeZs9fC++5
zRP?df)u4)Ajavn6omSagwJ|n8_=M!-K|g=KnVOvqYWW)*ON8JkZ0e;5Sn$!~@3a4>
zjbg0mf1`YSvasm-?zFE5xRPEcvdGP!npHu(jEoG}w1}1xg9zvzouk|$;5~wFCk%l9
zSWnH&tb-I>e~wfT1i38QVSvQ6?d6faPKzrc8X6i48(Z4AK}S3M?(i5vGQn|zNMRk#
zXn#7c`2ycn@$ORKZ1qQwailS~tKUh-J;W;6b#<hOrfk~poJHmMt>zHA(OV6Tjk1R2
zt~Spb<V>npBi)vC`dz`az)LW<)*UntJ}FB!_*ZUO&ywc@XUA%AE3!<%&r<Hno}MpI
zIzYE%7H0u+gDMLOnC|&OE)z&EB}GMgz)As<t@SR4AMfwi#1Iw)gy2xN22zkFRQy&C
zTt~}4G+$;lH#bv4GjnqTpr!xe)mVXp#Is*Jdwi-?v3X;msO8p*HV?mr{DU62Sf(P`
zd_(Jha@Ev;6w)7*l$D{aW=th+2-;F(H0j{g%!h-Nb@W9{LIUa0X{R4XmFuwq1r9oJ
z<gjbkXIE8muW|!X2EN>o>+bC>mYSNX$3=m>bvryXlxB+<{2JKV1Y0hjAMgIY1G&3Z
z=jPWRKD=0O`(LSMZn7gMkev=_!H3U||JM|@?l^yDcsS1cGW9k%5(K7_Nv9@0Nh#a}
zEM!6+hW~A{7F$zO^F1(|fVAgpO-;<^rO1u`sJznBr+U4oAv=eMLH!#NAl2}el{E74
zi_oQJm!R8Q;5FFzR#M)zHIg<lG4Ule^`Xeg06kI#^Ww9(aj^cS2LP`Da$-(pC4uEk
zsRYPpE2j&70hv<dBWGH&|B`NHuB-U(d0jIq3_NP_PoFqXPEYMNA_UgKYD2R%KZvlM
zRg{$7w|TG$AcC2-HHhKb^-ni>sb#6yUH59ppbiv`ulnW%wTW|K@rWfmS8GoEy_sIX
zVQNxV`)GcA&$MFcxq!h<h;yxPlDNN(ymT5M{^B{RtHAgo3*?f=UYGjMBc2d~90~ze
z$ZC1>!E<U6SAzNZc@}o|-f!<p5K>{)5M6enza9&NuY#gt{_9wxm+Y8dE+q|ekzf}d
zEkW*4T|WexD$^x}K_&?iHEMq-w9_rnj%1T4w>c@^t{CzVwF)Bw4Z|*nlIE;cPVq{2
z@!+2iPoHS2$S!q)XbfUWOs>WWe0OxRbX0%R#v#|GLzs?FII&L)6(A2gY7CN8N66<_
zCX(Y^(KABe(fg=n+1;Ru|DW(yU@v1hI1aI*uimA$alPYnaHBZt9KR`2A5fKq5t0B*
z!^GQh_CpcH;Mp=^>Y@5s_M~!INbzNM0ePAFC-0u>Qi`3T4IUPE7u0o2c||6Mcpkil
zr*f!};3CdV+X3}9rP0%R2?4y!17xUZllsRNbFfa#KST&*g&{#JgJDw2=?#8=&GOJ>
zIkdXe7Zf|8+lvtA_teX3gDY%u4+K4=Wn^Kn=;A>CaFie9DXZG5pU23{iuN8p&~W4J
z`ts?yUFif>c`-WUtL@ipbR=LgA0IZRTd4wMR8=epvgQD0+}2{Awen?2vMd+x_3Dng
zSFlV!F?QWa#VIm-SsM-JkbxR>W`C>4(8-G$%Kp?5fjHthQ_D6)EVoX$R;Sf6T#rkf
zp=Gl9vBZ4XWD!wQHR7<1whcgq;*%H*H4_PaTpkTEi&^)T6h1ds8q!Z?_q&|#kGNbA
z`h+d{WaDU(O|42WLfK6jHA0qDPEbmcW5X66`!>Iy#qP+FTm<KGp~>d9W;r|}K)%sL
z9cQyTWg(tlc=2+-$p#$fN$tUGGVJ|+8ijeZ@@)1_6G0{gL~`%mkph~71OcY{EdIyQ
zzi%{_wd(<#3s<l{h@kMb-tJSB&^P}ELf^sE%Y5t~(s*A8zu2i2em%L-F-S(G%&)!n
zui2=cRz3`VSN1laVn?yh2+YN1R{*w|g#|LC<23#5b}?dY)z<B3>+13CnT|_GkYPdC
zENf*I7v@k+L~<J;r5jlN(YB9m02Usw9qN+SNi*#6Aa_3=e5oKlL>J33tC_v(qnt!E
zjW-fs|2597a!OC;w+~r_UtIeRE9XbQgeDoCG;4n?i6t8~z>EmsXl_i^>C4i||6W<K
zD)-@s#lBt;_Sri?;!DBMcW_^Ilr0FTvaLj6Z5$sfjxJTq{O24$9B@_cK9E8sq(wgZ
zgm?|}7~Zb_#P2n`ta|Cg)3`dh@t;{vf)mY82;k92y5xLBf}=Mpe4Jhu@cI4?=jP)<
zW{^iK&40gGNo)OTLD*$95Xh=UDZ~O_pM$glRV2?K$!l#z+IzJf*>8+6zUHM-?}}NK
zyIKP;FVU5p1z@o%N$B&I1NcS!R*LQ?J7&&hkiT+a+R1tRE5>$o7DJqO@7}2`Go?HS
zTl~QUGpyD&2o=gNC_o(WkRE^9#Lu5ZiGO1U^P&j`9Bt%nsrxI49^*M|4X;Vn0r7n1
zhJ+HdU0|rtWm1C#@jX=P*iU0EQx5|%7@}}+a-^e1#EynU|Nf264xfuRXSR-7cuBw(
zNYjOI4V9Fz{kfsd$w9PkDGyltsb5#uG|gJnhTw39hdJR2IONO;%O`>XXqqfzBn(j=
zS_6j7n8d9|9&5IOsz8*8xr<&!K&2(%47q<mYY%pdo15FM69-V=`J5$D!LG|m?AZj8
zC9o`^97Sdnm6qb%)NwKhf}XLEB*}C%>vZXSCY5iC9yjAdLZZL~R5c`IdA^IC4BLC~
z1tB^ZpkU+%zEJK91`5NS!wU`}ia~Y%c7$n7|E;#Rf*~_1V2QN4mUO?Q41ln3s6oie
z!1oXr03sw;{8^BtK%3_TLySLM|7wPhne&`IXlQuYzf%u_99>-UYU0SA5FrEXSfHRl
zx2WMA_(Q<COW=zNcr#P&NfSPjlH!xx4E|Q~|B+XKrh^3e`S}%<ln^_@c?l7i6Sj8j
zn(JN)RFt=@?>aQ8asWb;EIU{JG&?ngS~LID6_*zi(f*LRs;=CFrO>08q2I|bJow?f
z5gEZx5okUr8o`V){6c`*79Ah&pP$bFEk{lPYvF`N$^n>OzDJUhrOHDSz<Utnt+Kzj
zcUkgA-W37T#Te3+3xVR9nVgZ>UHq1Hb8{0qIzJtEbcq3Bh!!3lJhLy5PXgKnmb$!&
zW)2G%7lB_33qbq429pvE|LHZc9IMJgqW>YliuJZ%82~KVzd7k||3~BK7#J^0jZS(*
zYq%e_evASr0b0JOD=3iJ3@tzqkt_IiL|<YLkPvhm=0FdAgQ4dgbI45n{OJpl$3Qv-
zsuya$D$Avb9bY{|{tV5U3R9f^Xu8nt7?|PLFZ7gNfg83gm81<7B!7U_gNcbLr+i*6
zYtgU(6gFD>my<wc==gj`G!+{hj(F*&F&rOTC{%e<5NrFTgF=@}NTVXtMil(3%-1)^
z3TQv)LXLp^1IY85b93H7^8AIarUmF4u=Bz|Y7QD-SO}Y$nIVj-TKKzja6tCGwg{}B
zO0yTZd-hG2?qA)D);=99HX$jXT?5MtH}GPv_Jk1Ej+zA{I_mw9FIAH6ArRAc9iM}2
zAMz2pj+4_fcMlJ{+e^Etsi}^Q<8j6<7?Br`4<(0|><1ZbIY`{ung6-4us#?P0ATg?
z^*%Qk7#Q4KT(tA|q{RRQbmTgTC%iw^QVswk;bf*!(ACWnpO)rCjL<U6zk(5n2erWX
zHXUBk-cCbGO4<lu;&}fAtp5_oD|&6_vyk-kFT(p-t4o=PS1}ca)opE}`8Bdru@p3Q
z45$TfiZAgsYyCkOSYvjKxz3T%&>#n<N=eaHtD5<pZxePPJKHhKNyrW(RLV#Mbe84G
zlaz7eKV)HyzN9aKkVJTiCzShDrK^4N%^pfI)M3U4yvpU`IyyRXQH4^GAOuLS(hyB>
z4LR`DF?<HmEi^Qg3*a|98ikA`z-xkOe?8~S`#T(n-){%Za8e-WB6e-hXHp}?+NJdr
z$Tq?Cuao{00wlz&-Xz4v`T|AI$M$^NxfunoST1|#CPD>eVk%ZIJO@mG_&;ik@IKH7
zKsjh?vV8G``hcs%*9;3_&{2WjJRt_3)jN_YHzEFqij2Ny*qAgDV^&<~H}f@>o>z?2
z)6=$m{9ThP_+$k+f2z>XxO6?(lXdW*op0qbzuVy+@9Wu_l#Bfp3;mwcqwL*&-XUlA
zwYmSShlPR|CxMbDk!04q9tXMmiYIyNVGD|>tZdJDp0Eqvj{}>3rJ5)Wosf$nj)?mU
zqu0v<o$1PrH`jWH`+j%Bl>b_;nBoTqgPYgTd&)FXY>2Q$)Z~K2nc^gh-*)XfzVb4E
z4wLFS|DCksy32@zm&PDdFfEx7gY?qssbIUMZWj!s71^7bDyeXy*>xk6S+b1NgfeVX
zMkuH)+>m@~@=zXCwD`7NtjL~ZxJb5}P59T#!(c=aGAM<UPp-Ogbt~Gn$^t(ZnLoC%
zvLz_<IPW;wEd(yDGP1tkLxeR}l(jXcD1;&<v7Hn^5$xpQjY-U+sk(dcV?)CG9qCiq
z$d21FZ!mFDoipluciY}{TYDujU=~&-sS{rPj|YYIA_sLNMfKAUs)gN~^3#FSWbg0G
z)6ooyM%zvgl>W{}E6P{_Yv0diSl{JNBML!2(f5xE0S{&E>6V1>r^iI_S-9jZ4Lo@H
zVi`r`@q5ub62Fm=fy-XbY~cLyRzr?gkXaL(2zjebjDmu48}KGZaLU%%d40X!`m;ET
z5|h#0o`zg2+^ZA0E2~qF;B%H_G!+h4LK3~@jWf6m`Q(-3k<)nKfO-eJEEUjacyzQy
zyEMZMy~y32*>V+1c{vB<V=_u@ba#?8jx*w@)TI)a6jZ8vhxO~~6bS;C`Cc5OiflX;
z7Ds%0GMkr!LF93*$SDrB6mi!M7B=_(asNy67sGrf$rMJwHR~7<0Qq$G$<&J6JSEut
z=?+v`>Fza|{DRVbx9vxBZMQ^F_A3?HUnuzgcco~QRE2NpJonX$g3uG@!L=8MZNghX
z!jvXb3Zi=Tl}GPaYq4$G$d3C4sE|?2lj!TlmwJqrl%*m7-r_F)3)K1X6@4&&4=yOA
zCc)R}l7_DEGpD5J(oOlF<5T;X76rtrs-qjfdNo(C#3Yjv>+4_51NrouNNs;X$rA<g
zh;-YGKZ#V=nr+8lXOsskIe{e&<XhcANUm`4joC8nA?Lx(-W6B+x8|Vw<aDju_UvD{
zE6`qo!8vFv$RLm<!SI}YBnaOR7fq$>qD}UWfT-gMNw9AFW2j@%CRyy>wZ{<bB8J~y
zA##pdS}K{SkgdhDa1Gr@iPo{jVNKT-wo;}GrOe9Vjai^G_pmjpc^1;Ow(B@tyc53y
zM{Keq?|A9YJarGhqhUi33OPr3<IhCIoob!(WsGasm`ysOIVpwxJabb$Sz)t^N&EB#
zgkA(`{Tp{5uE3EO<1Hsw$4FStOU2PH{~><kX{)S%;n7V-W1vz8LY}YF8sVIx{~B!z
zk_*qjt^wux5|<)R3U@c=>e01(V4Ve+)lIRR+IUGiI(qiIv1K{e6meL5e7xRDo2Nk%
z;Q-u)=Z_*)fd9a)lq74RM4nv+E|Cxjai<w;dg1b05Ai0p>cV{xrg+Y_OM|IHDTHht
zXR!U1lfj5bv%_4AhZh7)#UC(OfD|qe+JO*2D=bW9XJ-f4<4Yi8K-o=Aluw>KLF&H{
zyPk*wuHsi9?X>8;U@d63j*75p0Qmr@OUOs(nEx*t5K@r0Ne!iTy_JNG4afS%#&KNM
zEh>MS^{{97HUJy%+dc~+tSOuy!|7!sk1irK6y)VG>ur`oe-9-A)4yJ)FB+nX2h>9Z
z3=b;;>-hSz$04qp@tGYr9V-aNcr>EJh!3!i(>e<c|F%CqOBZrrvRZiNeNHLdu8)HF
z@OqzX4vet@&xz%1xiLuQmsV6ny|`TUvzo|#ISkAleH0$RilYg1EMbQ&9FN_vNx)8s
zWeJi}S>8Y_sv-aA3e!vL?d^T~>{-GiA$$M-m|}D|$c2GCl?I^J0!Y()-~4aNNQAaT
zeV>5BmgD2&KcGD0KMx1`)36y|_4)aEv<2eY|F@!-ARV>J75q8|X^>`MaC-Rm6<e?X
zKmYoe_dRc>_q`jyg<WQR2K|wbiptCTKrssvH2cBj5n?(Iy)K$B=f}JP0b?TtwIdrg
zH>P4Yl;v&LdxUW}KYrUk)vA4vCh(~bxW5IU4p4G&+|Yi9%h_^-jPMOLHVQ5RlR8)*
z8UHMStNy0apcf0+mPBrkx(5aZI<nxm+jf@6SHQg#ImFqHFfAdJwNiC9P{I%a>@nb7
zW2{__y4c#AQQQLT7YvG2?i*J`NBImSqkpDE{Q9K@-03ptf{`fwcF{w>xza`e1m2(l
zWgQneZEcUk$k@Apt|9r$SzTSdV+;fTaSt#~0RKFw;i$Ko_XSWE694ew5vb=l=@xv$
z_i2vL6TuVieW%ys{+H(kS@J{Pg#X_xJdj7c6b-*89t(Z>3KsLf94mduZ8qO`K^O;w
z29#Tb0J-z+yLW2{r+Wu~Uur=5DHZvD6}fPehR~pa!ND&Je`TDU&WaXNhZVQmpnqVl
zB}`1V8ta0;08{B_8kxT2omtyU$u95gr1wDis`R>Zk55X<tF9(;Zhq7sMI)=JN$LIF
z6&Tda%*;B#WP;G;Ns2FW1hrjlQF&3Bo0}IE6+O6y?f(}63}Xu6!uYRc4>%17_shQt
z*~<4%=b9XtA5u}hR#)e@VK+eJPvP)60~-6wYld1a>ke=2s+QZ6Ar=;v4&dw3=Sit_
zJ2e5Flqyr-01FuLZM?@K4**^#Wm8`zZ@)ydX+2ZFce-6CZ|{KLj=@3tF4Aoa_Fqjg
zNKx|*pJ)(vB9oDao4<dr0r302$=-P2hT;J1?Ox#1K~y0iJU@RMR%C$YC|CC&!cdW}
z`__aD$eEl$Oo1aKBaiG_o{~iM`>BXtp@wraFf$u=j{ojn(-U$hVOM#92FZD>BK7!R
z>eF>SIKRnB^hX7mN`Q~APLB;PWC?Z=V-Aq)9Gj<gmb+AyQ&a|P$D7IIQp3%yY3{cY
zRv8*A;qweUz{G&*mxGyEmWO;V0J{#6&t~fU>m25sqmfUxfdq|ukH-!ax(%}2dND6n
zA^}B{2o~UlxdKW=tmia@lCCn8oo)gMW6&E`Lieim3)`N6Cd3$eC^APVHZG__q;TO+
z_R~j3^jAbvQYG3~LVkYYV+IF5<-L@JHQjCDS=K)$I#^6>7d&VWn8*GsFst#ZYGQUQ
zgsP@0B3*#Yy+1%)l52lu$><sA=4p_iRY5Pt{V%_?1cje>wd3<V8I8ol!NDb-B_)eY
z{unJODfyX3nOjman3sxMA<?y6AII~sohHUJI%MAi?&<YW;ofC42ys^sHOT6N@%tWV
z2S;=1xG`>4RY5+PE-L}RJxF&0%W-ga&fQ*eL4r=^-cyvf*dvZz2I*lhOkKH4nsa{y
z&NxoghM?g!@xm#S@XRmIb=}accH%vLmNi6v7i9ycf=f6CIU57ri(u9R;gv7XnK67W
z+>ydoYOST;C(_I62|43H*`tFJe<&OPfshM+&yERqdrBwz^9_?<aSJuY!=Q=prugXJ
zzR@+S@N|j4BL#-8<9n_@E<Dtr@uIh^EJ3Lrl7Z4aV^%nM>@4CZ1xgUK<(O-}tt=SG
z)W8_CT~r}EIht|X)iIdHFQKi<g+M|KeY2?q_ETRe_N{s<w1XO_OOT+0Hc`IYh4#+t
zUUJ_*9!xc!ch4T)kHNoqn6-}0C9n~;+k6<`23-t4l-hG{Moatpsua69c4$anryj@0
z<!*3`IZJxGq$2WtSgc}(sUDP3(H2?&zg2M!l$m*$#O}A-FZTGN$&s|E=Mv7`03hqr
z$PH}FuWtrv4jz1o8;Ws<->DW9=IyUabZkgmtlXoYiorwjBd7?0+mW7wpN_bD(dK<5
zwZt~fJ*1%$bs-ZewO-ahS5^8n-$@fOBt5R9740&0hN};!1W$4~`nv7pTCPlrczMR}
zyRdD~&by{3{bu0ToQ`eRtT+lulDcnE->H+4R8{3==F%r|6%vCP5ajsiUzUqJlP3!x
z_wPfEp59K!*$-UdJZ2VvVG-rc?gJJ{VOV+nA%*-2UXWi_$Gc%61{{S%ag8^=nF1@)
z7rJn)Eyu3ug|KCpWr;)KLq)G{d!gih6r0qMW3JcfI+1hJB{8-7-N7Xy{QxR)^Q7Q_
zO~{|71ndq!*E;|v3u#zH-l&_+y=cAAyV{KNf%_8o3gWd&ZQpOekE1Asq5|kR@VJK(
zVF%ayvO0~VC;VMH#F!|4olx2cIv@^(leTVBo)AQRi1>E_C?~v-pNz_U<x7cfF(;1o
zzLdh5nlZ@!{?JcJ>1fXC*1Y+c3o4tRr;w9_pt+6p=%3>Ro!`EGQDcQo?&tg%@L>|8
zNnKowzJBBjtR}ReAQ<R((6U#^<>h7YUxiRu=Z2u!$w@Y4{jYZ{Kq%5TH%D6i8=cYY
zT=wsyZhW>{HW6RTDNpQY7%T}<*+u`IGY9A+dB!ZXBv@!5Mn0h}00NP(KMv-K+0gC@
z>|0sc@7a;~q2G;vs)q=OiRta%O+<hjz};e^bg{5C$LDL*&-=)mCwZv%_V?|M*Iz=*
zc&kGk%{Wz3Nd<90=!<62wFLg=?!V5mMl`VpQOTgTkICz+UF1fk?V4myZ*Pe96d#aw
zUf%~%$9$i&{O&JpX~~8t&Fi2dINctT?Hbp_<#7TpoKd>ne_X>`MiP`4kKQPiYOAXH
zZ0gs%h${w@!2*-)nvIPfH1gG<C$a&lJtQP<mjj(-CLz7xaM0!4DT`<AqGtJ0l7*9B
z($;;ba?bw!TLneJw>%KYWC805NGtCG??l&UQ)(-I?YY^cf4a(Czwi)J$nl84%2ACu
z5QFG=dDS+*6#yXv^YoFut4L<0iX?GaMj{~ov<Ooo$a^u`zncVT+5ZY38S4Tj%NK|!
zI0aR?mug+WZ#qDk`Zh@#-~s=a)u%t<!!mq0`PK7Q;D}x2v;@}FUeKkN<rXI3z~CxV
z$G#dLR*bO#LMihVFBPz%BJPt7D#*{*TW)cq(|G29s4b~@reF2G>-z^?Ibg;Z=u3X}
z0gD<B17RN~9f^&NWuZl7T588bUVS46VD&$ICB5hG9!CXb8EO2uBg6|r0q!qST}yx#
zw#Kq(oC+=TKr*=J%H?C~$X2D*q)o$V;oGkdiIfY8fll*T98pdPyvMONXNnsCA{Ejn
z%r@KcP311-swRK_w$I7U^{tpR<9j0>9K7rl0{rQ>|D4wLlA=#`RT>r|LPN3I@@Dk7
zvMVd24?7sU@}h&0+obSHrhnkmrDDOO$CYijHswxSMJ~6}K3#H6?VkZRO6VNxHUl3x
z7dyy_)>2JY$cY|C$nd~(C=CTYuld}AO!{Xm>cD+Oj#acg&#^*S2u8gy`zX8<rCEa>
zw)p@}41Kk=v8<>lxV<AHI1CinTn6>Ly<xn*xw(=ed*Z0Y(`S3IDCFqmgmi>1EiWIk
ziQziJ0G<ajU`L)9YS!{{Ws}w4zF`52H`JoGLQYEhT3ik%Ksx@YjtLzd{c<8G4)!&=
z2;7l;-Bwg2_b+t-xHMjOd8<yp#S_X0R_kZa%xrAXS2GZoSyp}d=^laWbUGPHZ6#vw
zSQE?&$$$nr&Q-gasmLUyuMaDWfaxPz0AZ9KukdH=QN}z$$z*j^6(KN?K^#h+Dwc+F
zRG<f|f;K-i{K1KPL|h+iS2VG>7{0e>0VN^(7PKXag1K0?jBVB_msc`nHu07Q8wV)h
zkSj`Vb~XfRs(oj~nSvzgLU9h0^uj^eE6C3h7OG@zMV%rYTKz<Lq@>w>Twx%wNyv3}
z2Z)Z@-VKYS-+ErKx0ocTHV3<upb|A3UgZh&H;~JPT>EKu9KZXh6|ViM{c~^-IJqkg
z>ZF2iKu#FBpe>8n6i>;M#u%L2R<^bTzy%Gg^#FMznLd-DVgvE$>hKPwch@nuqJnd^
zidi|`M~5RwxzO)p1^81+My4;Hqu<8N43Po_T!@E<=W@Zr-Q9L;m{OGX<m3dvIMKDg
z#CC`>E<+q$;3)RLe%yx@QUz8$uoHs+5o>p*RFk-T(xB>y-1tMIEmAl)5IwuB_&5IT
zPTmq6rKhLMTW1AFfq(%lSBp&!$I}|R0k_m}>|7@IP+nkMmyEhFx3a>yZ2JEFA=r>+
zpFVBl2LOK~0QE15{}La+?*Hl!e2L0MZU-x|fLXxCNMmASd5R|@fxfe|vjeKV92|JX
z&O8D80Et}Y7Hh;}AWBL~B0pNA348VRA-9ATOBrV522*Q?lA)pD_-_oS=a0%FxN#AC
zU5BF|yoWwegD*k!N)A+=DDHhzNE!+N3UD?;0Tu*7Z*G>Gu`3sBE%1uv0I|GI9`yH@
z%t`+DJQW~Wq(a^PpEENu5`@257;<|+Yrc`z6xL*g$JdmAATT|9kq%_lem(zOge7P+
z9dqb5UD_3_Mo>i!6A*A2zLB+*zvLtq{Izk{&!;Hu;c?@?RSP1oYRNRXD^&T5Ow7N3
zj<pR9Q4|zt;mfg5OGZ%M2ZF@7INn{Sr-51L)Y$!Ya!N`sot>TKGAg7~ix>%wLH=A|
zFUX@5f6eTU$i3BT3O1Fqv$u!!KIStYbwA?Y-q85y#<(?_p@2mA8}Wr&Ep|jAA1plE
zoA)$56W5HOMxVJg)1*?}pOYGdV)M)&=Kf%_gSwBLygd3<G4~?&kh!@zdEMN<VyGUC
zz-9*s>??~Z8luP4c@AoE>$UY=zwD9kGECRFbp03fzx0!4zH68I)y_kj!M%bah(}E&
zZE<lZ<Cz{bna#ddo|8pEbaRiIP~!RK<_~vipU<yPwj_q*f|dk^aB8fJowc>@!T9JW
zPO4PA*^y&GqQ-=d@~22zFrAYkMsA7obG02&xapkmC^EtSQOuRNL)HH8LyRTcASQ&-
zB*`8cyKF<22$Af{5@KxGvW|U?>|~7)g=F8iUS(ghWJ#2L$eQ){%=>-+ho9?mU1!X>
z<~im(=XvhW{kiX3&@8F{!7^Ks#W!PEoz1!|@nzP4uU280!eHwU9>YXGlDo|1HyWCQ
z@7yxH7<}r=Gb4kP$@a>0mI6HNa&Xg6DsSF7-2Ig3+7ni~lonWK^cmxuNF#cr%hc2m
zcJ-2BMjYAqeyj_R)o{)zw?ZM^r{ax3Huu=S+Sm)9^-K^uSk3;)4-M3xb+SVeTs5AW
zZS-sG)+gpBK8%0o5SpGb@zwC_Puv%a?wmTTQk41=Rb`i<tid9IbUjB@B@aqr(BJ?$
z)#69=bt7XbB3Skfd3R>gU`8ZTH}W~#?ATaHY%C4%l}G<g1?q^}na%jn=W*R2uK=hO
zKKJ&fAH5s@8hp0NYseDY>bspy6bMiB61y+hLYtYHe2_>_8Igmi?{5w)ukv4X(&<@h
z*E6PZT#$yZQ9c&WxKQ|swY;i|K_y?u#ooT2tZZ5G7_&RxNG61rzv=EkBT{}w%4n3%
zX~4^a>TX9E$@;S-7v@8d7B>d`3*lc(G_xEn#0PbQlLxYcMt*Gw>ew;}uT7uRyb(Cu
z<5fa1(pxQ~t7&EQoq*l%uFP=qvk(EV+|T-&W}9~|rpL)fob^{hP?9ji!@0AT_#1YU
zauq}2UvzfIUU=T%)PsFJ+HcX7S4uU$6#UhmJ)~cc972fR&RaUHI<X*!(}r{kX+1hV
zpPS7h!#w=u1)Vp)xR&Mie7KI5lZ@y>6@s3QE00Trrk;q|UN1)*Zr@c=pl~Dk%>$iB
z*B*_}qp=^K+L)NMu|~R^$5%R6q`EUvEfBke-Nea%9;=gF*>pSd+>hJ*NYRrK-}uk;
z%wNBf`(rDOr_C*HMJ-;(UfCBkF}I1xeLFvARx`oApp!~jSW#u{539_SqOS=t7v}#U
zpAzsbb<yvPuT|OEzNcs)eBa5R5^Hy!<DzU8rQ)PCp0$=UL|X4&lX)h1_+8QL_*G~e
zawx27#q%wP(mQv{oR<kIS+cTM)N1&NphFp&2`xwcy1a@Q<Pb)EY=54gqPRw`trWpq
zsda=wXap+zu8W;ta5|Xx_DJ}HpuZzyLY<quceu-iNOYQ&h){W5Fw`dLB@D@vbF8PF
zm4l05R^<Au<4@jXCCpd1qgNI}{PpKA`C*t!jmH?r{krsuC?tH;hY6`>)LC??*qE9q
zK!rKDcC;7@*!;BfqP}ay)>4(EZX@tg-QF(^{T@qg|BCVX&$>S__kPb`pS!jsgbMQA
zZ1p8Ss?|%nncM8vZB}pXGxKd=L+xrD625o<v-TgimEf>KuWSesL4Hm(kx9`eR1xv>
zbWEoERD!3bv^2NwUr-DRe=LmB6LtNi;V|1M@h(=FMNH?hg(}@kzR*q~fI4!4MF;S4
zsu~&~Z{o6mNj(YYhn#2L-jcFFr#84h0I2xQ2E6Q{uPmQQJtM)-G;&XlS}lQK34~H*
zUr3tzpSlwghW=wd!H1yKf`FzTXpMl%Y|x3w6iAu={BZ&7M;kB<?yZhFquFlDboYIC
zI1Y?8GcX7v1T%o`Shq;43(#(4Y6<35lMn=WHvzD((s6La5h$K8T8;<5NOOjes^rMd
zwD;`HHqG9~#;4m^cjT=9Nw~JqM#jN7Ha3=*pRd@sJFK2pTWbie8HuCw*<XiSS3S&>
zbiYfmLvhK-m=H95>~dD!R26n3g?`6;0KEZlY<Yfm+P=28f1LJh?GhM{2}tc0b_V2V
zXIemikbvj0e-_n1&yjo9|NO=F-Z!(kU4+Zxr<TcWJYb0{Kz7j3=qQRn&RX}SUxUJd
zz#9wT0Z_qr0f8Ov%Mv|sYFW<Iy9bx|_`MO?otk*BM{|TNVC%P%RWc|yZrk6O)&buK
zL2vM{xvJWTFrr3=I5oi(31Wi6!#Mm9)YR0#Wk?1P2<-d8MZv}Z3D;l7&s!dpDr2$2
z0AK`XNj)d{Bj1*lb@gXSVF9{iWF#5y^aTF6q|+x)V*Srfyw>MhIKXzSs-|`aI45R(
zcQgqhCm>S6lophaQC&em9S9_jG@dGoKSDTehb{vG5()r1IMoCawS=6pr+{8M=5GTo
z&Ve7pZ`64N1iHbBN>+`hVBp?8_M86X2%4UOpddo2f#?!i{u%?2Q3bRVAh&~eCu%0(
z`!>Lw<|1kF34hd!icU^W1~(cTrF{Ya><NB_!E}9RR85JAW4}^iq~=8xf$Rlrqe^~Y
zpLH-@-rP6fse>TD7LI!|dyK%vMnKR6w(oQwTczK0Ts|^6F%b?zO9;s+AayEi4v$e*
zCT%no3}{`Qm(8YS1~=(P^E3CQE&Cdd<wGDPBkcCoa!}xnlVc-b=Ohrh!DO_SXD5Ga
zf4}ybcblE6zf!;++DWIGDnt~;EZ7a~dD#8+hv+P=6A)Bn2tuH~Z?+Pnfw-|1u=zmj
zl06S@7=cp6E_6l=$^wvv1#u~ZteYwTKA!l=(bLld^`SFxpy}!9?Un+i9~Hr32Z(Hf
zln?kyp$3l)mR;eadJn>L0?JJ(d?N!v#Rm`^FimW)mc9@5YX&@L<NlOA8l+5t3>{xt
zGuv!N<ftP(1&5+t?Z@d2!hGYBlQRS8GYT~PqpnDKkRx#u4bR^L><g}pA$McW^Cz{A
zp&<{z$v8TN_34^>AZUd$OY1stz4GJ8MUDNAR*FtzcYxwA0$?k^Lo3<Y6&p5qINJIk
zaR7rd56GQ2BINuU0p6nr5i!X!p_#0Xa)aCU_V!&s<`gpNz!VY^0!W%!dPoU_33G0k
zSpY0^6Chpb!0rhmXCi<;l=e)*y5r3%`i<Y<WD6fDl-e^B@%7;nuK~j(fej|4g_V_+
zb<7&r%n*&9AJRaauKPx*pye(x<>?+A>Iee823OoX=L5;KO-y0{Vk1>g5zueoyH7ri
z>W&8$!eCOWeanM#V~NF60mBavn52pzB?!zPA^$U9LJ&>wC9RT$v`$0<usOdxbW6+3
zj0XK8o@O&jTIodc1Qb6cfB1seK;d-vVO!~eSl&=qJo#!?Wj`MK)|g^%X>EmaW_%f4
zmcs%zkfxD>JvUSRI{MX8{910@@6n*A=BgxJs9(fT<Ba1LI(?KsRH6P+KQVcx^77AN
zy>e>@upxAj8C1an%1g=g-{HKyGW(XF(MG?FP|xTtCe?3`CyyN9q2VVP!EQ?lcyYia
zOAd0Lo2t9+JGe((?f_%5ykO(|i6^Er{PX^F;W@8?=qImC@sB2lOi)gYTEGpT<laj$
zV2_YZC^}(cF`0MBTUvZ@=q;&VZo6K2<(#pd8NrhxvZtfU()8bnZrv!u>vB}kmKU3?
z<R2tD=6HFnv5_OoU5*&Cq<484FIDS>wtXywDt{?jOy#X>zW=trp2I?_PJbz~J9%^5
z)fRn%4|GCN4;Q{CL7k<QL=2pXp~{FR-+;}#hX^tnSeHKznc+1M6R(vL$Swavn;R0S
zTT~VxT&KNM5{|@P0NCJhpAqXS?7N%WEtWW62s!b@rvS|oxA5oSoY>5{X#n^A*qq-}
zb*Y3LLTBTsj+b88O7F_z<hHW;1@;V7GtQ`}e(@#UjAHk5x@}Z?7BueKppcTq|MNH3
zi*7up9s0plHX#&j{%LXhSZ|G@fg~!1DT0BS%kEFdV7H-Oxqu5r3vHIceuu|`x@W_5
z(7|2R*GD`F7gHefo?_>=cmzpYKAigez^2xyMBzY<MP}iax_K|pooF#yZ>y)a@d%T9
zhtgYhQuCj_wGVkxnYfe9Z#<(tHD=BT|Cm=~VOdoCp(DPQH1<f*R<fRgy~uGs#!eet
z1BF+MO7CdT<w}c4BsS{A^!9qSKL*ohS{wY6vOUHigDRVQD>Q1`Sf?(Xb)<{CUD{88
zeupDK_VtCD_RETvh{kfJS_ggSY5O0p(?1SsM+GP#?YYD#t(HrWki>p??-+@yk&Nh(
zCxUM>Tr)G=(4Ku_lkPHtUT1l<SeHN;K!he3uYuyr*i%%vD%1av#Q*2P%BVm<Xc1ru
zWMpJcH(l$DbEi`T&6+ob)6&ugR}P0q=C=f|wM($Yvcm4X2Z9{Gxt{KB%ag<Ht0qj!
zaKG>2&Y+!iwO$6U$km>v!423yYHy!Vk{RAmB}T+L>l{c~l$G_vmFC)Zfbun%n&P$c
zptcYyFJQ<PH|fCc+yDegI&VYss1>>HQn@7qnigp2Cv-|e^C-Yy3f{cAlYpAcW}qeo
zuYl?t#mzmtWs`sc<>QlAH}h=U;={RaOFaS_4PZFWH>Os;2*w5Kpg<MZQ}y0B7Ev~;
z2%bFPc6;?|6fYa25)5j@B;GvR*7$IdZ?DBb*T+?enK}xEqkGCMJdQqPKUueJ)xlg4
zsGA;IcW+<WkvBgS3^7&ptQ01N!E1-N9WBX9Vm2-C%uqDTm9JBX#ZFY-U~16iLcYh#
znvv@n?aYdnjMbi5hb2pl`(U0hHN&O)PdAt}Ji78QS3gMf!Lmg~1S?3)?;7(aqcqz-
z*6zY3V8wArVM=ctZG+Lk{QENfZy~|@HcEwUBvs<D+xR7Cdp;UD?s2an%b^@`#kx2a
zffi<d_Uo%MSz9JMHm+eeSnm}uAvFgokVBzJ;r8;~iS4lZQ`;@Kkj*bbsUJ8kxUADE
zF^ihlaPlDTtWYD3xOA-K@XW-IHdc~l`}VOio2w{J7PWGX|Fzc5?h~AJSDf0ag=%!p
z&wiCg*J^s27BYzLz1Vz>n(j8MJ&|Z+*6r_xKtv8YYma>_cysF;s53HR=N+D_FE@uo
zByQ;$!3*GLSM1z`P%59#`i)K=b+irI{dL$upSVs@rGCsGDOMvFULb-?GLh_mG;8hY
z!~9_IgXD|7*m`fNUuM(^KnfF=7>l2*CE<TiG+T7{`j7LbQ2RF?U082!9eX9R=4klR
zyP;Qq$hjgL*Pbp-)A(X9Ok4h)Mn-Is-AKMHCzJ#3$==W3A^pi7)md$`u~EDR${k(t
z+VRlV@6hbQ%P05hg|PHY+*<c*-s*_=o42Vybj?X5_BYB%r^(MPvJb%MpsiGSmc#mu
zGCjmDKz^4}La&cR>XoZr(Ty(l6cO8M@WF9pPsbJ;!>P#>6_C$bn6qz_%~Bbu1=|eY
zRXL$lK_9y>C}~7fM_>J0TuRfE6~k+wqzEqI^TEEl?H-J&%S)&NdKem5lo(}AUts=7
zqcwJ%SAQ)x7mT~;)CQAmDrj3MP)I7JpiQ()#QONcp!ru-#b#k5k!(~Hq#r%A-eQ6O
z{;tNu54Ki%<vhM$s}_mLMOWEZ>r0;Ui;9AC^y(aP%m2ByomMhV|E#dbMxJ$jRDY=w
z6i(oIQXs0{j2+yV?Utkzdb<00lx)i8NcJA11cIJ&dCMd0S<y1AWpUQ<<vUvG>mFtY
z(4+fkOI4m6{1zTTZ4+3ZEPR;hb_~`s1;w^_ZA0{4G{HFlu(an09;5D*;zmOssX;}-
zmCzN>$@TDm2jS*`x`{_ou*ASXYklH_#Raqs`HdLOZMXyQ{6kRoK$ule?2n2bc1561
z2HB_OE>9RWJ-OkefE$X8iXt?8*T2{4Zn*ID3Zb|_;@!0N{rkj;{{Z-`ZE6||5=h^I
zW$ALL67H#kLnjF2Bs9lCWzvB^$j{3oHWifOds&H~hXc7n8~)%b5=jJf1_Td=vU14O
z6CFm&jwiU@zP>Jy!cgHbDFUpdgaiaaZXxKsj0wc#Q5B6Ev}Ui;=2Y&8K;~Z-G5Y1)
zCtH6b98PNQD1lE_LPa6}J)m5ca&L~)l>WA2!l5U1*FG@;yh|BAvaDE>b;f?_CdIv`
z(h}BV>Hog)tk=}gDgX`dP|{<26GTvPy(cJ8bInzGI0d<d-HxejaGOQ{{FL``rWwpk
z1q{`{?}1rP+*CkHXE+?|hyAdYQh{o^xTg&&Q65f}{Eppu)_LFOH%l6(!R(MeL~fa2
z!~)I+;L1#)I0bgqOho-@+Q!?+BwQSRs&r_O!Enl{+)JSaW=fb}AsSKY7#-W0FV<|!
zY}1OLt~9ed*h^4ALaIi5YUz0{%A$H;g2}uzVqCrWq3*A$ZPIpy3UnA(sJOgaM+BX}
z(hFylVdjq{oE3A+a4Vxz4GQpZx-CAw!J2q+*r7VBHLmSeF;x@A6SbQE9wLh`x`h@`
zjd`J*?wQ!gqh8@lj1AKR7ML|VC{W9Ktr8!E^jr$#Vo+4DkW>q1zV(}Pgw7Ck@HU@l
zO%NZ_x29KD`En_&mHE@piSN6&0^|+$m_=-?GTZW8o`@P}-m}Dsde?7R&zy%E9Wc08
z7^WFT-`_ze-PD~Od#!b1Gh&hHCQbzHCcsKZ@U6yQNRn<|y#`h=?UeUq{_oC-iZc6h
zj|;osSSsIz|FJ6LeNaf%Fc8!7>4C-b<G+KP0${BceA0I(S6F#zRrLl{1pL<}KVJ)}
zSf}ZMJyxWousB7P#$;_@Y7k%WW$v=vIoo09#XmmgJ7}GaXB`$88Jg!NA=eQ!@;Sd(
z@FJV?^|J+*Nd=;zoji3@BN6w~{ksQZVb$t7nff-Jm9Ok-rxO@{31h&shj;?kmP7ph
z#ly)VC~m9Rr2oTWj}bQe8ts9h3tj$?%-*3$WG;QpTohPC#Wp=eeb}6jWVWt0no;Jf
z&_;>F7%b_9x>6%iSvngDwv0jqTym^N;4(<y{|pmN6nemw7@N;HVrGTh*QA~`LEuMC
MSxc#0!93{y0PaztKmY&$

literal 0
HcmV?d00001

diff --git a/rules/cellranger.smk b/rules/cellranger.smk
index b851101..65a3610 100644
--- a/rules/cellranger.smk
+++ b/rules/cellranger.smk
@@ -2,7 +2,8 @@ rule cellranger:
     input:
         i1 = expand("data/{sample}_test.txt", sample=samples)
     output:
-        o1 = "results/cellranger/{sample}/{sample}/outs/possorted_genome_bam.bam"
+        o1 = "results/cellranger/{sample}/{sample}/outs/possorted_genome_bam.bam",
+        o2 = "results/cellranger/{sample}/{sample}/outs/filtered_feature_bc_matrix/barcodes.tsv.gz"
     priority: 90
     log:
         "results/cellranger/{sample}/{sample}_cellranger.log"
diff --git a/rules/extract_tags.smk b/rules/extract_tags.smk
index c2ee38d..2108a7a 100644
--- a/rules/extract_tags.smk
+++ b/rules/extract_tags.smk
@@ -1,13 +1,13 @@
 rule extract_tags:
     input:
         i1 = "results/cellranger/{sample}/unmapped_reads.sam",
-        i2 = "results/kraken2/{sample}/{sample}.kraken"
+        i2 = "results/kraken2/{sample}/{sample}.kraken",
+        i3 = "results/cellranger/{sample}/{sample}/outs/filtered_feature_bc_matrix/barcodes.tsv.gz"
     output:
         "results/count_matrix/{sample}/count_matrix.tsv"
     params:
-        p1 = "results/count_matrix/{sample}/",
-        p2 = "results/cellranger/{sample}/{sample}/outs/filtered_feature_bc_matrix/barcodes.tsv.gz"
+        p1 = "results/count_matrix/{sample}/"
     log:
         "results/count_matrix/{sample}_bam_extract.log"
     shell:
-        "python3 scripts/bam_extract.py -i {input.i1} -k {input.i2} -b {params.p2} -o {params.p1} "
\ No newline at end of file
+        "python3 scripts/bam_extract.py -i {input.i1} -k {input.i2} -b {input.i3} -o {params.p1}"
\ No newline at end of file
diff --git a/rules/kraken2_mapping.smk b/rules/kraken2_mapping.smk
index ef4ecd5..55eccdd 100644
--- a/rules/kraken2_mapping.smk
+++ b/rules/kraken2_mapping.smk
@@ -3,12 +3,17 @@ rule kraken2_mapping:
         i1 = "data/{sample}_S1_L001_R2_001.fastq.gz"
     output:
         o1 = "results/kraken2/{sample}/{sample}.kraken",
-        o2 = "results/kraken2/{sample}/{sample}.report.txt"
+        o2 = "results/kraken2/{sample}/{sample}.report.txt",
+        o3 = temp("data/{sample}_test.txt")
     conda:
         "envs/kraken2.yaml"
+    priority: 95
     params:
         p1 = "/data/repository/kraken2_contaminome/virus_db"
     log:
         "results/logs/kraken2/{sample}_kraken.log"
     shell:
-        "kraken2 --use-names --threads 4 --db {params.p1} --report {output.o2} {input.i1} > {output.o1} &> {log}"
\ No newline at end of file
+        """
+        kraken2 --use-names --threads 4 --db {params.p1} --report {output.o2} {input.i1} > {output.o1} &> {log}
+        touch {output.o3}
+        """
\ No newline at end of file
diff --git a/scripts/synapse_id.tsv b/scripts/synapse_id.tsv
new file mode 100644
index 0000000..e8e772a
--- /dev/null
+++ b/scripts/synapse_id.tsv
@@ -0,0 +1,196 @@
+Directory	ParentID	Filename	EntityID
+Data/Gene Expression/Gene Expression scRNA seq/counts - CITEseq	 syn26560200	S33.zip	 syn24610356
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S1.zip	 syn24610321
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S10.zip	 syn24610331
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S11.zip	 syn24610333
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S12.zip	 syn24610334
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S13.zip	 syn24610335
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S14.zip	 syn24610337
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S15.zip	 syn24610338
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S16.zip	 syn24610339
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S17.zip	 syn24610340
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S18.zip	 syn24610341
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S19.zip	 syn24610342
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S2.zip	 syn24610322
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S20.zip	 syn24610343
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S21.zip	 syn24610344
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S22.zip	 syn24610345
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S23.zip	 syn24610346
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S24.zip	 syn24610347
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S25.zip	 syn24610348
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S26.zip	 syn24610349
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S27.zip	 syn24610350
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S28.zip	 syn24610351
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S29.zip	 syn24610352
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S3.zip	 syn24610323
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S30.zip	 syn24610353
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S31.zip	 syn24610354
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S32.zip	 syn24610355
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S4.zip	 syn24610324
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S5.zip	 syn24610325
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S6.zip	 syn24610327
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S7.zip	 syn24610328
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S8.zip	 syn24610329
+Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S9.zip	 syn24610330
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-ADT-ATCACGAT_S29_L001_I1_001.fastq.gz	 syn26534563
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-ADT-ATCACGAT_S29_L001_R1_001.fastq.gz	 syn26534582
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-ADT-ATCACGAT_S29_L001_R2_001.fastq.gz	 syn26534579
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-HTO-ATTACTCG_S30_L001_I1_001.fastq.gz	 syn26534567
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-HTO-ATTACTCG_S30_L001_R1_001.fastq.gz	 syn26534585
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-HTO-ATTACTCG_S30_L001_R2_001.fastq.gz	 syn26534584
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-AGCATCCG_S26_L001_I1_001.fastq.gz	 syn26534562
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-AGCATCCG_S26_L001_R1_001.fastq.gz	 syn26534575
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-AGCATCCG_S26_L001_R2_001.fastq.gz	 syn26534574
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-CCTCATTC_S25_L001_I1_001.fastq.gz	 syn26534565
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-CCTCATTC_S25_L001_R1_001.fastq.gz	 syn26534580
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-CCTCATTC_S25_L001_R2_001.fastq.gz	 syn26534576
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-GTGGCAAT_S27_L001_I1_001.fastq.gz	 syn26534564
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-GTGGCAAT_S27_L001_R1_001.fastq.gz	 syn26534578
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-GTGGCAAT_S27_L001_R2_001.fastq.gz	 syn26534577
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-TAATGGGA_S28_L001_I1_001.fastq.gz	 syn26534566
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-TAATGGGA_S28_L001_R1_001.fastq.gz	 syn26534573
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-TAATGGGA_S28_L001_R2_001.fastq.gz	 syn26534572
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	268_1970_positive_S4_L004_I1_001.fastq.gz	 syn26534419
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	268_1970_positive_S4_L004_R1_001.fastq.gz	 syn26534428
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	268_1970_positive_S4_L004_R2_001.fastq.gz	 syn26534444
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	271_1971_CD45positive_S1_L001_I1_001.fastq.gz	 syn26534424
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	271_1971_CD45positive_S1_L001_R1_001.fastq.gz	 syn26534431
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	271_1971_CD45positive_S1_L001_R2_001.fastq.gz	 syn26534446
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	286_1976_cells_positive_S3_L003_I1_001.fastq.gz	 syn26534420
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	286_1976_cells_positive_S3_L003_R1_001.fastq.gz	 syn26534427
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	286_1976_cells_positive_S3_L003_R2_001.fastq.gz	 syn26534441
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	289_005_positive_S4_L004_I1_001.fastq.gz	 syn26534426
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	289_005_positive_S4_L004_R1_001.fastq.gz	 syn26534430
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	289_005_positive_S4_L004_R2_001.fastq.gz	 syn26534445
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	293_008_cells_positive_S5_L005_I1_001.fastq.gz	 syn26534425
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	293_008_cells_positive_S5_L005_R1_001.fastq.gz	 syn26534429
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	293_008_cells_positive_S5_L005_R2_001.fastq.gz	 syn26534447
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	294_009_cells_positive_S1_L001_I1_001.fastq.gz	 syn26534423
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	294_009_cells_positive_S1_L001_R1_001.fastq.gz	 syn26534442
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	294_009_cells_positive_S1_L001_R2_001.fastq.gz	 syn26534458
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	299_166-cells-positive_S2_L002_I1_001.fastq.gz	 syn26534422
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	299_166-cells-positive_S2_L002_R1_001.fastq.gz	 syn26534440
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	299_166-cells-positive_S2_L002_R2_001.fastq.gz	 syn26534457
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	301_014-cells-positive_S3_L003_I1_001.fastq.gz	 syn26534421
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	301_014-cells-positive_S3_L003_R1_001.fastq.gz	 syn26534437
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	301_014-cells-positive_S3_L003_R2_001.fastq.gz	 syn26534456
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	303_1991-cells-positive_S4_L004_I1_001.fastq.gz	 syn26534432
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	303_1991-cells-positive_S4_L004_R1_001.fastq.gz	 syn26534439
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	303_1991-cells-positive_S4_L004_R2_001.fastq.gz	 syn26534453
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	305_015-cells-positive_S5_L005_I1_001.fastq.gz	 syn26534433
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	305_015-cells-positive_S5_L005_R1_001.fastq.gz	 syn26534452
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	305_015-cells-positive_S5_L005_R2_001.fastq.gz	 syn26534462
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	325_2013_CD45_positive_S1_L001_I1_001.fastq.gz	 syn26534434
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	325_2013_CD45_positive_S1_L001_R1_001.fastq.gz	 syn26534450
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	325_2013_CD45_positive_S1_L001_R2_001.fastq.gz	 syn26534459
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	339_23_pos_cells_S3_L003_I1_001.fastq.gz	 syn26534435
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	339_23_pos_cells_S3_L003_R1_001.fastq.gz	 syn26534451
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	339_23_pos_cells_S3_L003_R2_001.fastq.gz	 syn26534465
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	345_2017-CD45_pos_S4_L004_I1_001.fastq.gz	 syn26534436
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	345_2017-CD45_pos_S4_L004_R1_001.fastq.gz	 syn26534460
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	345_2017-CD45_pos_S4_L004_R2_001.fastq.gz	 syn26534464
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	346_2019_CD45_pos_S1_L001_I1_001.fastq.gz	 syn26534438
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	346_2019_CD45_pos_S1_L001_R1_001.fastq.gz	 syn26534448
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	346_2019_CD45_pos_S1_L001_R2_001.fastq.gz	 syn26534463
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	355_2015_CD45_pos_S4_L004_I1_001.fastq.gz	 syn26534454
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	355_2015_CD45_pos_S4_L004_R1_001.fastq.gz	 syn26534449
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	355_2015_CD45_pos_S4_L004_R2_001.fastq.gz	 syn26534455
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	356_CK030_corticol-CD45-pos_S1_L001_I1_001.fastq.gz	 syn26534466
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	356_CK030_corticol-CD45-pos_S1_L001_R1_001.fastq.gz	 syn26534461
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	356_CK030_corticol-CD45-pos_S1_L001_R2_001.fastq.gz	 syn26534485
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	362_CK031_cortex_CD45-pos_S2_L002_I1_001.fastq.gz	 syn26534467
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	362_CK031_cortex_CD45-pos_S2_L002_R1_001.fastq.gz	 syn26534474
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	362_CK031_cortex_CD45-pos_S2_L002_R2_001.fastq.gz	 syn26534484
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	363_VA_2028-pos_S3_L003_I1_001.fastq.gz	 syn26534468
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	363_VA_2028-pos_S3_L003_R1_001.fastq.gz	 syn26534472
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	363_VA_2028-pos_S3_L003_R2_001.fastq.gz	 syn26534483
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	364_2030-CD45-pos_S4_L004_I1_001.fastq.gz	 syn26534469
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	364_2030-CD45-pos_S4_L004_R1_001.fastq.gz	 syn26534471
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	364_2030-CD45-pos_S4_L004_R2_001.fastq.gz	 syn26534481
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	365_CK033_S5_L005_I1_001.fastq.gz	 syn26534475
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	365_CK033_S5_L005_R1_001.fastq.gz	 syn26534470
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	365_CK033_S5_L005_R2_001.fastq.gz	 syn26534487
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	366_1996T_CD45-pos_S6_L006_I1_001.fastq.gz	 syn26534488
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	366_1996T_CD45-pos_S6_L006_R1_001.fastq.gz	 syn26534482
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	366_1996T_CD45-pos_S6_L006_R2_001.fastq.gz	 syn26534486
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	367_2037-CD45-pos_S7_L007_I1_001.fastq.gz	 syn26534489
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	367_2037-CD45-pos_S7_L007_R1_001.fastq.gz	 syn26534497
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	367_2037-CD45-pos_S7_L007_R2_001.fastq.gz	 syn26534507
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	369_182_positive_S8_L008_I1_001.fastq.gz	 syn26534491
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	369_182_positive_S8_L008_R1_001.fastq.gz	 syn26534499
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	369_182_positive_S8_L008_R2_001.fastq.gz	 syn26534508
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	375_VA_2028_pos_S3_L003_I1_001.fastq.gz	 syn26534490
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	375_VA_2028_pos_S3_L003_R1_001.fastq.gz	 syn26534495
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	375_VA_2028_pos_S3_L003_R2_001.fastq.gz	 syn26534506
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	376_2030_CD45_pos_S4_L004_I1_001.fastq.gz	 syn26534570
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	376_2030_CD45_pos_S4_L004_R1_001.fastq.gz	 syn26534581
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	376_2030_CD45_pos_S4_L004_R2_001.fastq.gz	 syn26534586
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	381_BC_155_Tumor_CD45pos_S1_L001_I1_001.fastq.gz	 syn26534571
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	381_BC_155_Tumor_CD45pos_S1_L001_R1_001.fastq.gz	 syn26534583
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	381_BC_155_Tumor_CD45pos_S1_L001_R2_001.fastq.gz	 syn26534587
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	383_sample_cell_line_553_S3_L003_I1_001.fastq.gz	 syn26534494
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	383_sample_cell_line_553_S3_L003_R1_001.fastq.gz	 syn26534502
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	383_sample_cell_line_553_S3_L003_R2_001.fastq.gz	 syn26534509
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-ACAAGGTA_S54_L002_I1_001.fastq.gz	 syn26534518
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-ACAAGGTA_S54_L002_R1_001.fastq.gz	 syn26534540
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-ACAAGGTA_S54_L002_R2_001.fastq.gz	 syn26534537
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-CGTCCCGT_S55_L002_I1_001.fastq.gz	 syn26534519
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-CGTCCCGT_S55_L002_R1_001.fastq.gz	 syn26534538
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-CGTCCCGT_S55_L002_R2_001.fastq.gz	 syn26534536
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-GTGGTACC_S52_L002_I1_001.fastq.gz	 syn26534521
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-GTGGTACC_S52_L002_R1_001.fastq.gz	 syn26534544
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-GTGGTACC_S52_L002_R2_001.fastq.gz	 syn26534542
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-TACTATAG_S53_L002_I1_001.fastq.gz	 syn26534523
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-TACTATAG_S53_L002_R1_001.fastq.gz	 syn26534546
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-TACTATAG_S53_L002_R2_001.fastq.gz	 syn26534545
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L001_I1_001.fastq.gz	 syn26534492
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L001_R1_001.fastq.gz	 syn26534501
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L001_R2_001.fastq.gz	 syn26534504
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L002_I1_001.fastq.gz	 syn26534514
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L002_R1_001.fastq.gz	 syn26534500
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L002_R2_001.fastq.gz	 syn26534512
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L003_I1_001.fastq.gz	 syn26534510
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L003_R1_001.fastq.gz	 syn26534503
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L003_R2_001.fastq.gz	 syn26534505
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L004_I1_001.fastq.gz	 syn26534493
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L004_R1_001.fastq.gz	 syn26534511
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L004_R2_001.fastq.gz	 syn26534530
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-ATCTCTGT_S45_L002_I1_001.fastq.gz	 syn26534516
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-ATCTCTGT_S45_L002_R1_001.fastq.gz	 syn26534534
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-ATCTCTGT_S45_L002_R2_001.fastq.gz	 syn26534529
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-CCTAGACC_S44_L002_I1_001.fastq.gz	 syn26534513
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-CCTAGACC_S44_L002_R1_001.fastq.gz	 syn26534533
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-CCTAGACC_S44_L002_R2_001.fastq.gz	 syn26534531
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-GGAGAGAG_S47_L002_I1_001.fastq.gz	 syn26534515
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-GGAGAGAG_S47_L002_R1_001.fastq.gz	 syn26534522
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-GGAGAGAG_S47_L002_R2_001.fastq.gz	 syn26534520
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-TAGCTCTA_S46_L002_I1_001.fastq.gz	 syn26534517
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-TAGCTCTA_S46_L002_R1_001.fastq.gz	 syn26534535
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-TAGCTCTA_S46_L002_R2_001.fastq.gz	 syn26534532
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-ATCATGCA_S50_L002_I1_001.fastq.gz	 syn26534524
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-ATCATGCA_S50_L002_R1_001.fastq.gz	 syn26534551
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-ATCATGCA_S50_L002_R2_001.fastq.gz	 syn26534548
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-CCGGGTAT_S51_L002_I1_001.fastq.gz	 syn26534525
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-CCGGGTAT_S51_L002_R1_001.fastq.gz	 syn26534549
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-CCGGGTAT_S51_L002_R2_001.fastq.gz	 syn26534547
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-GGTTCCTC_S49_L002_I1_001.fastq.gz	 syn26534527
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-GGTTCCTC_S49_L002_R1_001.fastq.gz	 syn26534556
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-GGTTCCTC_S49_L002_R2_001.fastq.gz	 syn26534555
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-TAACAAGG_S48_L002_I1_001.fastq.gz	 syn26534528
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-TAACAAGG_S48_L002_R1_001.fastq.gz	 syn26534553
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-TAACAAGG_S48_L002_R2_001.fastq.gz	 syn26534550
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-AGGTATTG_S56_L002_I1_001.fastq.gz	 syn26534526
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-AGGTATTG_S56_L002_R1_001.fastq.gz	 syn26534541
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-AGGTATTG_S56_L002_R2_001.fastq.gz	 syn26534539
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-CTCCTAGT_S57_L002_I1_001.fastq.gz	 syn26534543
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-CTCCTAGT_S57_L002_R1_001.fastq.gz	 syn26534552
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-CTCCTAGT_S57_L002_R2_001.fastq.gz	 syn26534558
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-GATGCCAA_S59_L002_I1_001.fastq.gz	 syn26534557
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-GATGCCAA_S59_L002_R1_001.fastq.gz	 syn26534559
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-GATGCCAA_S59_L002_R2_001.fastq.gz	 syn26534561
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-TCAAGGCC_S58_L002_I1_001.fastq.gz	 syn26534560
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-TCAAGGCC_S58_L002_R1_001.fastq.gz	 syn26534569
+Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-TCAAGGCC_S58_L002_R2_001.fastq.gz	 syn26534568
+Data/Metadata	 syn24168324	HBI_scRNAseq_assay_scrnaSeq_metadata.csv	 syn24610436
+Data/Metadata	 syn24168324	HBI_scRNAseq_biospecimen_metadata.csv	 syn24610438
+Data/Metadata	 syn24168324	HBI_scRNAseq_individual_metadata.csv	 syn24610550

From 0746ed40a85b5d5c6be181f25c38ffd9f1984afb Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Mon, 15 May 2023 15:28:26 +0200
Subject: [PATCH 10/33] Added Flake workflow

---
 .github/workflows/flake.yml | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)
 create mode 100644 .github/workflows/flake.yml

diff --git a/.github/workflows/flake.yml b/.github/workflows/flake.yml
new file mode 100644
index 0000000..f490b2f
--- /dev/null
+++ b/.github/workflows/flake.yml
@@ -0,0 +1,25 @@
+name: Flake Check
+
+on:
+  push:
+    branches:
+      - dev
+
+jobs:
+  flake-check:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v2
+
+      - name: Setup Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.x
+
+      - name: Install Snakemake
+        run: pip install snakemake
+
+      - name: Dry run Snakemake
+        run: snakemake -cores 32 --use-conda --configfile config.yaml --dry-run

From 9ccd0a42e14a65bbd5a73f8f66a232948109c86f Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Mon, 15 May 2023 15:34:15 +0200
Subject: [PATCH 11/33] Updated flake.yml

---
 .github/workflows/flake.yml | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/.github/workflows/flake.yml b/.github/workflows/flake.yml
index f490b2f..25a4ca4 100644
--- a/.github/workflows/flake.yml
+++ b/.github/workflows/flake.yml
@@ -13,7 +13,12 @@ jobs:
       - name: Checkout code
         uses: actions/checkout@v2
 
-      - name: Setup Python
+      - name: Setup Node.js
+        uses: actions/setup-node@v2
+        with:
+          node-version: 16
+
+      - name: Set up Python
         uses: actions/setup-python@v2
         with:
           python-version: 3.x

From 67afd96e82eca3fa9b18d05f228d71c658275629 Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Mon, 15 May 2023 15:35:28 +0200
Subject: [PATCH 12/33] Updated flake.yml

---
 .github/workflows/flake.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/flake.yml b/.github/workflows/flake.yml
index 25a4ca4..d5b75f8 100644
--- a/.github/workflows/flake.yml
+++ b/.github/workflows/flake.yml
@@ -27,4 +27,4 @@ jobs:
         run: pip install snakemake
 
       - name: Dry run Snakemake
-        run: snakemake -cores 32 --use-conda --configfile config.yaml --dry-run
+        run: snakemake --cores 32 --use-conda --configfile config.yaml --dry-run

From 37a0d06ad4cc461c3a84bb9d32e38583ea804d20 Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Mon, 15 May 2023 15:37:35 +0200
Subject: [PATCH 13/33] Updated flake.yml

---
 .github/workflows/flake.yml | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/.github/workflows/flake.yml b/.github/workflows/flake.yml
index d5b75f8..a823983 100644
--- a/.github/workflows/flake.yml
+++ b/.github/workflows/flake.yml
@@ -26,5 +26,8 @@ jobs:
       - name: Install Snakemake
         run: pip install snakemake
 
+      - name: Installing Pandas
+        run: pip install pandas
+
       - name: Dry run Snakemake
         run: snakemake --cores 32 --use-conda --configfile config.yaml --dry-run

From 90aa6def6b2039b6461471d5ea38ce9d96d66dbb Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Mon, 15 May 2023 15:41:07 +0200
Subject: [PATCH 14/33] Updated flake.yml

---
 .github/workflows/flake.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/flake.yml b/.github/workflows/flake.yml
index a823983..cbc9ac0 100644
--- a/.github/workflows/flake.yml
+++ b/.github/workflows/flake.yml
@@ -30,4 +30,4 @@ jobs:
         run: pip install pandas
 
       - name: Dry run Snakemake
-        run: snakemake --cores 32 --use-conda --configfile config.yaml --dry-run
+        run: snakemake --cores 32 --use-conda --configfile config.yaml --dry-run --conda-frontend conda

From 50e9391011eecb29826cde46793cc5be1a1b5c68 Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Mon, 15 May 2023 15:47:10 +0200
Subject: [PATCH 15/33] Added linting

---
 .github/workflows/flake.yml | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/.github/workflows/flake.yml b/.github/workflows/flake.yml
index cbc9ac0..d7ac2e8 100644
--- a/.github/workflows/flake.yml
+++ b/.github/workflows/flake.yml
@@ -13,11 +13,6 @@ jobs:
       - name: Checkout code
         uses: actions/checkout@v2
 
-      - name: Setup Node.js
-        uses: actions/setup-node@v2
-        with:
-          node-version: 16
-
       - name: Set up Python
         uses: actions/setup-python@v2
         with:
@@ -31,3 +26,15 @@ jobs:
 
       - name: Dry run Snakemake
         run: snakemake --cores 32 --use-conda --configfile config.yaml --dry-run --conda-frontend conda
+
+
+  Linting:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - name: Lint workflow
+      uses: snakemake/snakemake-github-action@v1.24.0
+      with:
+        directory: .
+        snakefile: Snakefile
+        args: "--lint"
\ No newline at end of file

From 5845a9d179ed8770e2f61367232cec98114a0454 Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Mon, 15 May 2023 18:03:22 +0200
Subject: [PATCH 16/33] Pipeline Cleanup

---
 READMD.md                          | 32 ++++++++++++++++++++++++++++++
 Snakefile                          | 23 +++++++++------------
 config.yaml                        |  5 +++--
 env.yaml                           | 12 +++++++++++
 rules/cellranger.smk               | 15 ++++++++------
 rules/download_samples_or_copy.smk | 22 ++++++++++----------
 rules/extract_bam.smk              | 12 ++++++-----
 rules/extract_tags.smk             | 11 ++++++----
 rules/kraken2_mapping.smk          | 17 ++++++++--------
 scripts/count_matrix_processing.py | 29 +++++++++++++++++++++++++++
 10 files changed, 128 insertions(+), 50 deletions(-)
 create mode 100644 READMD.md
 create mode 100644 env.yaml
 create mode 100644 scripts/count_matrix_processing.py

diff --git a/READMD.md b/READMD.md
new file mode 100644
index 0000000..15d8dfb
--- /dev/null
+++ b/READMD.md
@@ -0,0 +1,32 @@
+# sc-Virome-Scan: A Snakemake pipeline for detection of viruses in single-cell datasets.
+
+[![Snakemake](https://img.shields.io/badge/snakemake-≥6.3.0-brightgreen.svg)](https://snakemake.github.io)
+[![GitHub actions status](https://github.com/maxplanck-ie/sc-virome-scan/workflows/Tests/badge.svg?branch=main)](https://github.com/maxplanck-ie/sc-virome-scan/actions?query=branch%3Amain+workflow%3ATests)
+
+
+A method wrapped around Snakemake for swift, precise, and accurate detection of viral pathogens in single-cell
+RNA (scRNA) datasets to investigate the possible correlation between viral pathogens and neurodegenerative diseases. 
+
+<br /> 
+
+# DAG for the pipeline
+![Graphviz Diagram](dag.png)
+
+
+
+<br /> 
+
+## Usage
+
+> ***snakemake --cores 16 --use-conda --configfile config.yaml --latency-wait 60***
+    
+### Note
+This is a developmental and alpha phase of the pipeline, upon completion a Python Wrapper will take care of every runtime parameter handling automatically.
+
+<br /> 
+
+## Contributing
+The usage of this workflow is described in the [Snakemake Workflow Catalog](https://snakemake.github.io/snakemake-workflow-catalog/?usage=maxplanck-ie%2Fsc-virome-scan).
+
+If you use this workflow in a paper, don't forget to give credits to the authors by citing the URL of this (original) repository and its DOI (see above).
+
diff --git a/Snakefile b/Snakefile
index d5452fe..46da13b 100644
--- a/Snakefile
+++ b/Snakefile
@@ -2,17 +2,11 @@ import glob
 import os
 import pandas as pd
 
-#configfile = "/data/manke/processing/momin/virome-scan/workflow/config.yaml",
-data_dir = "/data/manke/processing/momin/virome-scan/sc-virome-scan/data"
-
+configfile: "config.yaml"
 
 accession_list = pd.read_table("SRA.tsv")
 samples = list(accession_list.Samples.unique())
 
-"""
-samples, = glob_wildcards("/data/manke/processing/momin/virome-scan/sc-virome-scan/data/{sample}_L001_R1.fastq.gz")
-print(samples)
-"""
 
 include: "rules/download_samples_or_copy.smk"
 include: "rules/kraken2_mapping.smk"
@@ -22,13 +16,14 @@ include: "rules/extract_tags.smk"
 
 rule all:
     input:
-            #expand("data/{sample}_S1_L001_R1_001.fastq.gz", sample=samples),
-            #expand("data/{sample}_S1_L001_R2_001.fastq.gz", sample=samples),
-            #expand("data/{sample}_test.txt",sample=samples),
-            #expand("results/kraken2/{sample}/{sample}.kraken",sample=samples),
-            #expand("results/kraken2/{sample}/{sample}.report.txt",sample=samples),
-            #expand("results/cellranger/{sample}/{sample}/outs/possorted_genome_bam.bam",sample=samples),
-            #expand("results/cellranger/{sample}/unmapped_reads.sam", sample=samples),
+            expand("data/{sample}/{sample}_S1_L001_R1_001.fastq.gz", sample=samples),
+            expand("data/{sample}/{sample}_S1_L001_R2_001.fastq.gz", sample=samples),
+            expand("data/{sample}_test.txt",sample=samples),
+            expand("results/kraken2/{sample}/{sample}.kraken",sample=samples),
+            expand("results/kraken2/{sample}/{sample}.report.txt",sample=samples),
+            expand("results/kraken2/{sample}/{sample}_classified_out.fastq",sample=samples),
+            expand("results/cellranger/{sample}/{sample}_finished.txt",sample=samples),
+            expand("results/cellranger/{sample}/unmapped_reads.sam", sample=samples),
             expand("results/count_matrix/{sample}/count_matrix.tsv", sample=samples)
 
 onsuccess:
diff --git a/config.yaml b/config.yaml
index e481375..7b13f6f 100644
--- a/config.yaml
+++ b/config.yaml
@@ -1,4 +1,5 @@
-"files" : "proxy"
+"files" : None
 "chemistry" : "SC3Pv2"
 "transcriptome" : "/data/repository/misc/cellranger_references/cellranger/refdata-gex-GRCh38-2020-A"
-"dir" : "/data/manke/processing/momin/virome-scan/sc-virome-scan/data_old/"
\ No newline at end of file
+"local_files_dir" : "/data/manke/processing/momin/virome-scan/sc-virome-scan/data_pos_control/SRR13114612"
+"kraken_db": "/data/repository/kraken2_contaminome/virus_db2023"
\ No newline at end of file
diff --git a/env.yaml b/env.yaml
new file mode 100644
index 0000000..ba93358
--- /dev/null
+++ b/env.yaml
@@ -0,0 +1,12 @@
+name: sc-viromescan
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - kraken2
+  - samtools
+  - entrez-direct
+  - parallel-fastq-dump
+  - pandas
+  - snakemake
\ No newline at end of file
diff --git a/rules/cellranger.smk b/rules/cellranger.smk
index 65a3610..60223e8 100644
--- a/rules/cellranger.smk
+++ b/rules/cellranger.smk
@@ -2,18 +2,21 @@ rule cellranger:
     input:
         i1 = expand("data/{sample}_test.txt", sample=samples)
     output:
-        o1 = "results/cellranger/{sample}/{sample}/outs/possorted_genome_bam.bam",
-        o2 = "results/cellranger/{sample}/{sample}/outs/filtered_feature_bc_matrix/barcodes.tsv.gz"
+        o1 = temp("results/cellranger/{sample}/{sample}_finished.txt")
     priority: 90
+    resources:
+        mem_mb = 26000
+    threads: 30
     log:
-        "results/cellranger/{sample}/{sample}_cellranger.log"
+        "results/cellranger/{sample}/{sample}.cellranger.log"
     params: 
         p1 = config["chemistry"], 
         p2 = config["transcriptome"],
-        p3 = "/data/manke/processing/momin/virome-scan/sc-virome-scan/data/",
-        p4 = "/data/manke/processing/momin/virome-scan/kraken2/negative_ctrl/data/"
+        p3 = "/data/manke/processing/momin/virome-scan/sc-virome-scan/data/{sample}/"
     shell:
         """
+        module load cellranger
+        touch {output.o1}
         cd results/cellranger/{wildcards.sample}/ 
-        cellranger count --id {wildcards.sample} --fastqs {params.p4} --transcriptome {config[transcriptome]} --chemistry SC3Pv2
+        cellranger count --id {wildcards.sample} --fastqs {params.p3} --transcriptome {config[transcriptome]} --localcores {threads} --chemistry {config[chemistry]}
         """
diff --git a/rules/download_samples_or_copy.smk b/rules/download_samples_or_copy.smk
index d7ae67b..57a0921 100644
--- a/rules/download_samples_or_copy.smk
+++ b/rules/download_samples_or_copy.smk
@@ -1,22 +1,22 @@
 rule download_samples_or_copy:
     output: 
-        o1 = temp("data/{sample}_S1_L001_R1_001.fastq.gz"),
-        o2 = temp("data/{sample}_S1_L001_R2_001.fastq.gz")
+        o1 = "data/{sample}/{sample}_S1_L001_R1_001.fastq.gz",
+        o2 = "data/{sample}/{sample}_S1_L001_R2_001.fastq.gz",
     params:
-        outdir = "data",
-        data_directory = config["dir"]
+        outdir = "data/{sample}/"
     threads: 16
+    log:
+        "results/logs/download_samples_or_copy/{sample}.log"
     priority: 100
-    conda:
-        "envs/tools.yaml"
     shell:
         """
         if [ {config[files]} == 'local' ]; then
-            cp {config[dir]}/*.fastq.gz  data/
-
+            for file in {wildcards.sample}*; do
+                ln -s {config[local_files_dir]}/$file  data/$file
+            done
         else
             parallel-fastq-dump --sra-id {wildcards.sample} --split-files --threads {threads} --outdir {params.outdir}  --gzip --tmpdir /data/manke/processing/momin/virome-scan/sc-virome-scan/tmp
-            mv data/{wildcards.sample}_1.fastq.gz data/{wildcards.sample}_S1_L001_R1_001.fastq.gz 
-            mv data/{wildcards.sample}_2.fastq.gz data/{wildcards.sample}_S1_L001_R2_001.fastq.gz 
+            mv data/{wildcards.sample}/{wildcards.sample}_1.fastq.gz data/{wildcards.sample}/{wildcards.sample}_S1_L001_R1_001.fastq.gz 
+            mv data/{wildcards.sample}/{wildcards.sample}_2.fastq.gz data/{wildcards.sample}/{wildcards.sample}_S1_L001_R2_001.fastq.gz 
         fi
-        """
\ No newline at end of file
+        """
diff --git a/rules/extract_bam.smk b/rules/extract_bam.smk
index ad0a901..b81b174 100644
--- a/rules/extract_bam.smk
+++ b/rules/extract_bam.smk
@@ -1,9 +1,11 @@
 rule extract_bam:
     input:
-        "results/cellranger/{sample}/{sample}/outs/possorted_genome_bam.bam"
+        i1 = "results/cellranger/{sample}/{sample}_finished.txt"
     output:
-        "results/cellranger/{sample}/unmapped_reads.sam"
-    conda:
-        "envs/samtools.yaml"
+        temp("results/cellranger/{sample}/unmapped_reads.sam")
+    log:
+        "results/samtools/{sample}.log"
+    params:
+        "results/cellranger/{sample}/{sample}/outs/possorted_genome_bam.bam"
     shell:
-        "samtools view -f 4 {input} > {output}"
\ No newline at end of file
+        "samtools view -@ 16 -f 4 {params} > {output}"
\ No newline at end of file
diff --git a/rules/extract_tags.smk b/rules/extract_tags.smk
index 2108a7a..514aedf 100644
--- a/rules/extract_tags.smk
+++ b/rules/extract_tags.smk
@@ -1,13 +1,16 @@
 rule extract_tags:
     input:
         i1 = "results/cellranger/{sample}/unmapped_reads.sam",
-        i2 = "results/kraken2/{sample}/{sample}.kraken",
-        i3 = "results/cellranger/{sample}/{sample}/outs/filtered_feature_bc_matrix/barcodes.tsv.gz"
+        i2 = "results/kraken2/{sample}/{sample}.kraken"
     output:
         "results/count_matrix/{sample}/count_matrix.tsv"
+    threads: 16
+    resources:
+        mem_mb = 40000
     params:
-        p1 = "results/count_matrix/{sample}/"
+        p1 = "results/count_matrix/{sample}/",
+        p2 = "results/cellranger/{sample}/{sample}/outs/filtered_feature_bc_matrix/barcodes.tsv.gz"
     log:
         "results/count_matrix/{sample}_bam_extract.log"
     shell:
-        "python3 scripts/bam_extract.py -i {input.i1} -k {input.i2} -b {input.i3} -o {params.p1}"
\ No newline at end of file
+        "python3 scripts/bam_extract.py -i {input.i1} -k {input.i2} -b {params.p2} -o {params.p1}"
\ No newline at end of file
diff --git a/rules/kraken2_mapping.smk b/rules/kraken2_mapping.smk
index 55eccdd..92dd1f2 100644
--- a/rules/kraken2_mapping.smk
+++ b/rules/kraken2_mapping.smk
@@ -1,19 +1,20 @@
 rule kraken2_mapping:
     input:
-        i1 = "data/{sample}_S1_L001_R2_001.fastq.gz"
+        i1 = "data/{sample}/{sample}_S1_L001_R2_001.fastq.gz"
     output:
         o1 = "results/kraken2/{sample}/{sample}.kraken",
         o2 = "results/kraken2/{sample}/{sample}.report.txt",
-        o3 = temp("data/{sample}_test.txt")
-    conda:
-        "envs/kraken2.yaml"
+        o3 = "results/kraken2/{sample}/{sample}_classified_out.fastq",
+        o4 = temp("data/{sample}_test.txt")
     priority: 95
+    threads: 16
     params:
-        p1 = "/data/repository/kraken2_contaminome/virus_db"
+        p1 = config["kraken_db"]
     log:
-        "results/logs/kraken2/{sample}_kraken.log"
+        "results/logs/kraken2/{sample}.kraken.log"
     shell:
         """
-        kraken2 --use-names --threads 4 --db {params.p1} --report {output.o2} {input.i1} > {output.o1} &> {log}
-        touch {output.o3}
+        kraken2 --use-names --threads {threads} --db {params.p1} --report {output.o2} --output {output.o1} --classified-out {output.o3} {input.i1} 2> {log}
+        gzip {output.o3}
+        touch {output.o4}
         """
\ No newline at end of file
diff --git a/scripts/count_matrix_processing.py b/scripts/count_matrix_processing.py
new file mode 100644
index 0000000..20658a0
--- /dev/null
+++ b/scripts/count_matrix_processing.py
@@ -0,0 +1,29 @@
+import os
+
+directory_path = '/data/manke/processing/momin/virome-scan/DGE/EBV/count_matrix' 
+
+tsv_files = []
+for root, dirs, files in os.walk(directory_path):
+    for file in files:
+        if file.endswith('.tsv'):
+            tsv_files.append(os.path.join(root, file))
+
+taxon_df = pd.DataFrame(columns=['Tax_ID'])
+for file in tsv_files:
+    df = pd.read_csv(file, sep='\t')
+    taxon = df['Tax_ID']
+    taxon_df = pd.merge(taxon_df,taxon,on='Tax_ID', how='outer')
+
+
+for file in tsv_files:
+    df2 = pd.read_csv(file, sep='\t')
+    samplename = str(file.split('/')[-2])
+    summed_data = df2.groupby('Tax_ID').sum().iloc[:, :].sum(axis=1).to_frame(samplename)
+    taxon_df = pd.merge(taxon_df, summed_data, on='Tax_ID', how='left')
+
+taxon_df = taxon_df.fillna(0)
+taxon_df['Tax_ID'] = taxon_df['Tax_ID'].str.split('(').str[0].str.strip()
+taxon_df.iloc[:, 1:] = taxon_df.iloc[:, 1:].astype(int)
+taxon_df = taxon_df.rename(columns={'Tax_ID': 'Taxon'})
+taxon_df.to_csv("/home/momin/count_matrix_summarized.tsv", sep='\t', index=False)
+taxon_df
\ No newline at end of file

From 97a5ca41c83f6bf4aa15ef26541b4b61e3437d9e Mon Sep 17 00:00:00 2001
From: Saim Momin <64724322+SaimMomin12@users.noreply.github.com>
Date: Mon, 15 May 2023 18:11:43 +0200
Subject: [PATCH 17/33] Update flake.yml

---
 .github/workflows/flake.yml | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/.github/workflows/flake.yml b/.github/workflows/flake.yml
index d7ac2e8..945f777 100644
--- a/.github/workflows/flake.yml
+++ b/.github/workflows/flake.yml
@@ -26,15 +26,3 @@ jobs:
 
       - name: Dry run Snakemake
         run: snakemake --cores 32 --use-conda --configfile config.yaml --dry-run --conda-frontend conda
-
-
-  Linting:
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v2
-    - name: Lint workflow
-      uses: snakemake/snakemake-github-action@v1.24.0
-      with:
-        directory: .
-        snakefile: Snakefile
-        args: "--lint"
\ No newline at end of file

From 8c9be2c52de9729896a42039478316a5d99d1416 Mon Sep 17 00:00:00 2001
From: Saim Momin <64724322+SaimMomin12@users.noreply.github.com>
Date: Mon, 15 May 2023 21:28:00 +0200
Subject: [PATCH 18/33] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 15d8dfb..d77a4c7 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,7 @@
 # sc-Virome-Scan: A Snakemake pipeline for detection of viruses in single-cell datasets.
 
 [![Snakemake](https://img.shields.io/badge/snakemake-≥6.3.0-brightgreen.svg)](https://snakemake.github.io)
-[![GitHub actions status](https://github.com/maxplanck-ie/sc-virome-scan/workflows/Tests/badge.svg?branch=main)](https://github.com/maxplanck-ie/sc-virome-scan/actions?query=branch%3Amain+workflow%3ATests)
+[![GitHub actions status](https://github.com/maxplanck-ie/sc-virome-scan/workflows/Flake Check/badge.svg?branch=dev)](https://github.com/maxplanck-ie/sc-virome-scan/actions?query=branch%3Amain+workflow%3ATests)
 
 
 A method wrapped around Snakemake for swift, precise, and accurate detection of viral pathogens in single-cell

From 884e85160f35ec9cb856205b873af471ff1f90b0 Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Thu, 25 May 2023 17:15:38 +0200
Subject: [PATCH 19/33] Code Cleanup

---
 config.yaml              | 1 -
 rules/cellranger.smk     | 2 +-
 rules/envs/kraken2.yaml  | 6 ------
 rules/envs/samtools.yaml | 6 ------
 rules/envs/tools.yaml    | 9 ---------
 5 files changed, 1 insertion(+), 23 deletions(-)
 delete mode 100644 rules/envs/kraken2.yaml
 delete mode 100644 rules/envs/samtools.yaml
 delete mode 100644 rules/envs/tools.yaml

diff --git a/config.yaml b/config.yaml
index 7b13f6f..239b286 100644
--- a/config.yaml
+++ b/config.yaml
@@ -1,5 +1,4 @@
 "files" : None
-"chemistry" : "SC3Pv2"
 "transcriptome" : "/data/repository/misc/cellranger_references/cellranger/refdata-gex-GRCh38-2020-A"
 "local_files_dir" : "/data/manke/processing/momin/virome-scan/sc-virome-scan/data_pos_control/SRR13114612"
 "kraken_db": "/data/repository/kraken2_contaminome/virus_db2023"
\ No newline at end of file
diff --git a/rules/cellranger.smk b/rules/cellranger.smk
index 60223e8..0a79baf 100644
--- a/rules/cellranger.smk
+++ b/rules/cellranger.smk
@@ -18,5 +18,5 @@ rule cellranger:
         module load cellranger
         touch {output.o1}
         cd results/cellranger/{wildcards.sample}/ 
-        cellranger count --id {wildcards.sample} --fastqs {params.p3} --transcriptome {config[transcriptome]} --localcores {threads} --chemistry {config[chemistry]}
+        cellranger count --id {wildcards.sample} --fastqs {params.p3} --transcriptome {config[transcriptome]} --localcores {threads}
         """
diff --git a/rules/envs/kraken2.yaml b/rules/envs/kraken2.yaml
deleted file mode 100644
index 516686a..0000000
--- a/rules/envs/kraken2.yaml
+++ /dev/null
@@ -1,6 +0,0 @@
-channels:
-  - conda-forge
-  - bioconda
-  - defaults
-dependencies:
-  - kraken2
\ No newline at end of file
diff --git a/rules/envs/samtools.yaml b/rules/envs/samtools.yaml
deleted file mode 100644
index 2c1c845..0000000
--- a/rules/envs/samtools.yaml
+++ /dev/null
@@ -1,6 +0,0 @@
-channels:
-  - conda-forge
-  - bioconda
-  - defaults
-dependencies:
-  - samtools
\ No newline at end of file
diff --git a/rules/envs/tools.yaml b/rules/envs/tools.yaml
deleted file mode 100644
index 842fc5a..0000000
--- a/rules/envs/tools.yaml
+++ /dev/null
@@ -1,9 +0,0 @@
-channels:
-  - conda-forge
-  - bioconda
-  - defaults
-dependencies:
-  - entrez-direct
-  - parallel-fastq-dump
-  - umi_tools
-  - bowtie2
\ No newline at end of file

From 5eb03599d09e2f7fb9e99d598f5ff4f9e509fafe Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Thu, 25 May 2023 17:22:23 +0200
Subject: [PATCH 20/33] Code Cleanup

---
 LICENSE            | 21 ---------------------
 READMD.md          | 32 --------------------------------
 envs/kraken2.yaml  |  6 ------
 envs/samtools.yaml |  6 ------
 envs/tools.yaml    |  9 ---------
 5 files changed, 74 deletions(-)
 delete mode 100644 LICENSE
 delete mode 100644 READMD.md
 delete mode 100644 envs/kraken2.yaml
 delete mode 100644 envs/samtools.yaml
 delete mode 100644 envs/tools.yaml

diff --git a/LICENSE b/LICENSE
deleted file mode 100644
index e9b75a4..0000000
--- a/LICENSE
+++ /dev/null
@@ -1,21 +0,0 @@
-MIT License
-
-Copyright (c) 2021, AUTHORS
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
diff --git a/READMD.md b/READMD.md
deleted file mode 100644
index 15d8dfb..0000000
--- a/READMD.md
+++ /dev/null
@@ -1,32 +0,0 @@
-# sc-Virome-Scan: A Snakemake pipeline for detection of viruses in single-cell datasets.
-
-[![Snakemake](https://img.shields.io/badge/snakemake-≥6.3.0-brightgreen.svg)](https://snakemake.github.io)
-[![GitHub actions status](https://github.com/maxplanck-ie/sc-virome-scan/workflows/Tests/badge.svg?branch=main)](https://github.com/maxplanck-ie/sc-virome-scan/actions?query=branch%3Amain+workflow%3ATests)
-
-
-A method wrapped around Snakemake for swift, precise, and accurate detection of viral pathogens in single-cell
-RNA (scRNA) datasets to investigate the possible correlation between viral pathogens and neurodegenerative diseases. 
-
-<br /> 
-
-# DAG for the pipeline
-![Graphviz Diagram](dag.png)
-
-
-
-<br /> 
-
-## Usage
-
-> ***snakemake --cores 16 --use-conda --configfile config.yaml --latency-wait 60***
-    
-### Note
-This is a developmental and alpha phase of the pipeline, upon completion a Python Wrapper will take care of every runtime parameter handling automatically.
-
-<br /> 
-
-## Contributing
-The usage of this workflow is described in the [Snakemake Workflow Catalog](https://snakemake.github.io/snakemake-workflow-catalog/?usage=maxplanck-ie%2Fsc-virome-scan).
-
-If you use this workflow in a paper, don't forget to give credits to the authors by citing the URL of this (original) repository and its DOI (see above).
-
diff --git a/envs/kraken2.yaml b/envs/kraken2.yaml
deleted file mode 100644
index 516686a..0000000
--- a/envs/kraken2.yaml
+++ /dev/null
@@ -1,6 +0,0 @@
-channels:
-  - conda-forge
-  - bioconda
-  - defaults
-dependencies:
-  - kraken2
\ No newline at end of file
diff --git a/envs/samtools.yaml b/envs/samtools.yaml
deleted file mode 100644
index 2c1c845..0000000
--- a/envs/samtools.yaml
+++ /dev/null
@@ -1,6 +0,0 @@
-channels:
-  - conda-forge
-  - bioconda
-  - defaults
-dependencies:
-  - samtools
\ No newline at end of file
diff --git a/envs/tools.yaml b/envs/tools.yaml
deleted file mode 100644
index 842fc5a..0000000
--- a/envs/tools.yaml
+++ /dev/null
@@ -1,9 +0,0 @@
-channels:
-  - conda-forge
-  - bioconda
-  - defaults
-dependencies:
-  - entrez-direct
-  - parallel-fastq-dump
-  - umi_tools
-  - bowtie2
\ No newline at end of file

From 965aef8c93b200cefa83d1f8a5bee543de8ac086 Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Thu, 25 May 2023 17:25:23 +0200
Subject: [PATCH 21/33] Updated Cellranger rule

---
 rules/cellranger.smk | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/rules/cellranger.smk b/rules/cellranger.smk
index 0a79baf..1f6cefa 100644
--- a/rules/cellranger.smk
+++ b/rules/cellranger.smk
@@ -9,9 +9,7 @@ rule cellranger:
     threads: 30
     log:
         "results/cellranger/{sample}/{sample}.cellranger.log"
-    params: 
-        p1 = config["chemistry"], 
-        p2 = config["transcriptome"],
+    params:  
         p3 = "/data/manke/processing/momin/virome-scan/sc-virome-scan/data/{sample}/"
     shell:
         """

From 299eaf39185f65ce8443b56a5c623a90cb618fd2 Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Mon, 10 Jul 2023 16:53:48 +0200
Subject: [PATCH 22/33] Minor Changes to Script

---
 scripts/bam_extract.py   |  78 ++++++++++++---------
 scripts/kraken_build.py  |  94 +++++++++++++++++++++++++
 scripts/kraken_plot.py   | 144 ++++++++++++++++++++++++---------------
 scripts/synapse_fetch.py |  78 ++++++++++++---------
 4 files changed, 276 insertions(+), 118 deletions(-)
 create mode 100644 scripts/kraken_build.py

diff --git a/scripts/bam_extract.py b/scripts/bam_extract.py
index ba6e6ff..f3b8dde 100644
--- a/scripts/bam_extract.py
+++ b/scripts/bam_extract.py
@@ -2,57 +2,71 @@
 import argparse
 
 parser = argparse.ArgumentParser()
-parser.add_argument("-i", "--input_file", metavar="PATH", help="Path to your SAM file")
-parser.add_argument("-k", "--kraken_input_file", metavar="FILE", help="Path of your .kraken file from Kraken output")
-parser.add_argument("-b", "--barcode_file", metavar="FILE", help="Filtered Barcodes tsv file generated from Cell Ranger")
-parser.add_argument("-o", "--output-file", metavar="PATH", help="Path to your output file")
+parser.add_argument("-i", "--input_file",
+                    metavar="PATH",
+                    help="Path to your SAM file")
+parser.add_argument("-k", "--kraken_input_file",
+                    metavar="FILE",
+                    help="Path of your .kraken file from Kraken output")
+parser.add_argument("-b", "--barcode_file",
+                    metavar="FILE",
+                    help="Filtered Barcodes TSV file from CellRanger")
+parser.add_argument("-o", "--output-file",
+                    metavar="PATH",
+                    help="Path to your output file")
 
 args = parser.parse_args()
 file = args.input_file
-tags_dict = {}  
+tags_dict = {}
 
-#TODO: Check if the Kraken file is empty 
+# TODO: Check if the Kraken file is empty
 
-#Parsing SAM file and storing ReadName along with its TAGS in dictionary
+# Parsing SAM file and storing ReadName along with its TAGS in dictionary
 with open(file) as f:
     for line in f:
-        if line.startswith("@"):   #Skipping header
+        if line.startswith("@"):
             continue
-        fields = line.strip().split("\t")  
-        read_name = fields[0]  
-        entries = fields[11:]  
-        
+        fields = line.strip().split("\t")
+        read_name = fields[0]
+        entries = fields[11:]
+
         for tag in entries:
             tag_fields = tag.split(":")
             tag_name = tag_fields[0]
             tag_value = tag_fields[2]
-            if tag_name in ["CR", "CB", "UR", "UB"]:  
+            if tag_name in ["CR", "CB", "UR", "UB"]:
                 if read_name in tags_dict:
-                    tags_dict[read_name][tag_name] = tag_value   #Adding tag to existing existing dictionary for the read name
+                    # Adding tag to existing dictionary for the read name
+                    tags_dict[read_name][tag_name] = tag_value
                 else:
-                    tags_dict[read_name] = {tag_name: tag_value}  #Else creating new dictionary and adding rag to it                
-#Converting them to Pandas Dataframe
-df = pd.DataFrame.from_dict(tags_dict, orient='index')  
-df.index.name = "Read Name"  
+                    # Else creating new dictionary and adding tag to it
+                    tags_dict[read_name] = {tag_name: tag_value}
+
+# Converting them to Pandas Dataframe
+df = pd.DataFrame.from_dict(tags_dict, orient='index')
+df.index.name = "Read Name"
 df.reset_index(inplace=True)
-df1 = df.drop_duplicates(subset=['CR','UR'],keep = 'last').reset_index(drop = True)
-print(df1.head())
+df1 = df.drop_duplicates(subset=['CR', 'UR'],
+                         keep='last').reset_index(drop=True)
 
 
-#Reading Kraken Output and merging with the previous Dataframe
+# Reading Kraken Output and merging with the previous Dataframe
 columns_name = ['status', 'Read Name', 'Tax_ID', 'length', 'LCA_mapping']
-df2 = pd.read_csv(args.kraken_input_file,sep='\t',names=columns_name, index_col=None)
-merged = pd.merge(df1,df2,on='Read Name', how='inner')
-merged_subset = merged.loc[:, ['Read Name', 'Tax_ID', 'CR', 'CB','UR', 'UB']]
-print(merged_subset.head())
+df2 = pd.read_csv(args.kraken_input_file, sep='\t',
+                  names=columns_name, index_col=None)
+merged = pd.merge(df1, df2, on='Read Name', how='inner')
+merged_subset = merged.loc[:, ['Read Name', 'Tax_ID', 'CR', 'CB', 'UR', 'UB']]
 
-#Filtering dataframe based on barcodes reported by CellRanger
-barcodes = pd.read_csv(args.barcode_file, compression='gzip',sep='\t', names=['CR'])
-barcodes.CR = [x.strip().replace('-1', '') for x in barcodes.CR]
-merged_barcodes = pd.merge(merged_subset,barcodes,on='CR', how='inner')
-print(merged_barcodes.head())
 
+# Filtering dataframe based on barcodes reported by CellRanger
+barcodes = pd.read_csv(args.barcode_file,
+                       compression='gzip', sep='\t', names=['CR'])
+barcodes.CR = [x.strip().replace('-1', '') for x in barcodes.CR]
+merged_barcodes = pd.merge(merged_subset, barcodes,
+                           on='CR', how='inner')
 
-#Creating a count matrix and writing it to a file
-result = merged_barcodes.pivot_table(index='Tax_ID', columns='CR', values='Read Name', aggfunc='count').fillna(0.).astype(int)
+# Creating a count matrix and writing it to a file
+result = merged_barcodes.pivot_table(index='Tax_ID', columns='CR',
+                                     values='Read Name',
+                                     aggfunc='count').fillna(0.).astype(int)
 result.to_csv(args.output_file + "count_matrix.tsv", sep='\t')
diff --git a/scripts/kraken_build.py b/scripts/kraken_build.py
new file mode 100644
index 0000000..5975628
--- /dev/null
+++ b/scripts/kraken_build.py
@@ -0,0 +1,94 @@
+import pandas as pd
+import argparse
+
+parser = argparse.ArgumentParser()
+parser.add_argument("-i", "--input_families_list",
+                    metavar="PATH",
+                    help="Path to input txt file consisting of Families Names")
+
+parser.add_argument("-names", "--input_names_dmp",
+                    metavar="PATH",
+                    help="Path to input names.dmp file")
+
+parser.add_argument("-acc", "--input_refseq_acc",
+                    metavar="PATH",
+                    help="Path to input RefSeq AccesionID file")
+
+parser.add_argument("-ngb", "--input_nucl_gb",
+                    metavar="PATH",
+                    help="Path to input nucl_gb.accession2taxid file")
+
+parser.add_argument("-nodes", "--input_nodes_dmp",
+                    metavar="PATH",
+                    help="Path to input nodes.dmp file")
+
+parser.add_argument("-out", "--output_acc_path",
+                    metavar="PATH",
+                    help="Path to save filtered accession list")
+
+args = parser.parse_args()
+
+# Step 1: Reading the Families text file and extracting corresponding TaxIDs from names.dmp file
+with open(args.input_families_list, 'r') as f:
+    families = list(f.read().splitlines())
+
+fam2taxid = {}
+with open(args.input_names_dmp, "r") as file:
+    for line in file:
+        data = line.split("|")
+        taxid = data[0].strip()
+        taxname = data[1].strip()
+        if taxname in families:
+            fam2taxid[taxname] = int(taxid)
+fam_list = [i for i in fam2taxid.values()]
+
+# Step 2: Retreiving the NCBI Accession IDs for each TaxID from nucl_gb.accession2taxid file
+virus_accession = pd.read_csv(args.input_refseq_acc, names=['accession.version'])
+accession2taxid = pd.read_csv(args.input_nucl_gb, sep="\t")
+result = virus_accession.merge(accession2taxid, on='accession.version', how='left')
+result = result[['accession.version', 'taxid']]
+result2 = result.dropna(subset=['taxid'])
+result2.taxid = result2.taxid.astype(int)
+taxid_to_trace = sorted(set(result2["taxid"]))
+
+# Function to backtrace until Family TaxID for a given TaxID
+
+
+def taxatrace(tax_id, df):
+    path = [tax_id]
+    for i in range(len(df)):
+        row = df[df['TaxID'] == tax_id]
+        if len(row) == 0:
+            break
+        parent_id = row['ParentID'].values[0]
+        if tax_id != parent_id:
+            level = row['Level'].values[0]
+            if level == 'family':
+                path.append(parent_id)
+                break
+            else:
+                path.append(parent_id)
+                tax_id = parent_id
+        else:
+            break
+    return path
+
+
+# Step 3: Backtracing the TaxIDs(2) until Family Level
+nodes = pd.read_csv(args.input_nodes_dmp,
+                    sep="|", usecols=[0, 1, 2],
+                    names=['TaxID', 'ParentID', 'Level'])
+nodes = nodes.replace('\t', '', regex=True)
+path_trace = []
+for i in taxid_to_trace:
+    path = taxatrace(i, nodes)
+    path_trace.append(path)
+
+# Step 4: Filtering from Backtracing Step to only keep results of Families of Interest
+filtered_list = [x for x in path_trace if any(y in x for y in fam_list)]
+filtered_taxid = [element[0] for element in filtered_list]
+
+# Step 5: NCBI Accession List Filtering
+filtered_accessions = result2[result2['taxid'].isin(filtered_taxid)]
+filtered_accessions.to_csv(args.output_acc_path + "viral_families.tsv",
+                           sep='\t', index=False)
diff --git a/scripts/kraken_plot.py b/scripts/kraken_plot.py
index 09a87bc..c973471 100644
--- a/scripts/kraken_plot.py
+++ b/scripts/kraken_plot.py
@@ -1,20 +1,23 @@
 """
-Summarizes and performs plotting of Clustermap for the total reads counts assigned for each family and species by Kraken2.
+Summarizes Kraken2 reports and plots Clustermap for
+the total reads counts assigned to each family/species by Kraken2.
 
-This script processes all the Kraken2.report.txt files Kraken2 tool and organizes the number of reads(fragments)
-mapped to each family and species level. The output of the scripts are two tab-separated files consisting of reads 
-mapped to Family level and Species level respectively. Depending on the TSV files, a clustermap is plotted to analyze 
-the distribution of taxons in the all report files of the samples. The Clustermap are saved to PNG file in the directory
-specified by the user. 
+This script processes all the Kraken2.report.txt files Kraken2 tool and
+organizes the number of reads(fragments) mapped to each family and species
+level. The output of the scripts are two tab-separated files consisting of
+reads mapped to Family level and Species level respectively. Depending on
+the TSV files, a clustermap is plotted to analyze the distribution of taxons
+in the all report files of the samples. The Clustermap are saved to PNG file
+in the directory specified by the user.
 
-Usage: 
-    ./kraken_plot.py -i <input_file_directory> -o <output_file_directory> 
+Usage:
+    ./kraken_plot.py -i <input_file_directory> -o <output_file_directory>
 
 Outputs:
-    - familywise_taxonomic_readcounts.tsv
-    - specieswise_taxonomic_readcounts.tsv
-    - clustermap_familywise_log10.png
-    - clustermap_specieswise_log10.png
+    - Familywise_tax_readcounts.tsv
+    - Specieswise_tax_readcounts.tsv
+    - Clustermap_Familywise_log10.png
+    - Clustermap_Specieswise_log10.png
 
 Returns:
     None. The script saves all the files to a output directory.
@@ -22,8 +25,8 @@
 Author:
     Saim Momin <momin@ie-freiburg.mpg.de>
 
-Last Updated:  
-    06-04-2023
+Last Updated:
+    07-07-2023
 
 """
 
@@ -31,85 +34,118 @@
 import seaborn as sns
 import numpy as np
 import matplotlib.pyplot as plt
-import scipy
-import glob
 import os
 import argparse
 
 
 parser = argparse.ArgumentParser()
-parser.add_argument("-i", "--input_file_directory", metavar="PATH", help="Path to master directory Kraken2 report files")
-parser.add_argument("-o", "--output_file_directory", metavar="PATH", help="Path to directory for output files")
+parser.add_argument("-i", "--input_file_directory",
+                    metavar="PATH",
+                    help="Path to master directory Kraken2 report files")
+
+parser.add_argument("-o", "--output_file_directory",
+                    metavar="PATH",
+                    help="Path to directory for output files")
+
 args = parser.parse_args()
 
-path = args.input_file_directory
-dirs = [os.path.join(path, d) for d in os.listdir(path) if os.path.isdir(os.path.join(path, d))]
 
-kraken_files = []
+path = args.input_file_directory
 family_data = pd.DataFrame(columns=['Taxon'])
 species_data = pd.DataFrame(columns=['Taxon'])
+kraken_files = []
+
+for root, dirs, files in os.walk(path):
+    for file in files:
+        if file.endswith(".report.txt"):
+            file_path = os.path.join(root, file)
+            kraken_files.append(file_path)
+
+print("\n --- Kraken2 Reports Summarization Script ---\n")
+print("\n Specified Input directory: ", args.input_file_directory)
+print("\n Specified Output directory: ", args.output_file_directory)
+print("\n Total Kraken2 Reports Detected: ", len(kraken_files))
 
-for directory in dirs:
-    kraken_files.extend(glob.glob(os.path.join(directory, '*.txt')))
-   
 for file in kraken_files:
-    df = pd.read_csv(file, sep='\t', names=["Perc", "Reads_covered", "Reads_Assigned", "Order", "Tax_ID", "Taxon"])
-    df1 = df.loc[df['Order'] == 'F'].sort_values("Reads_covered", ascending=False)          #Fetching Families rows
-    df2 = df.loc[df['Order'] == 'S'].sort_values("Reads_covered", ascending=False)          #Fetching Species rows
-    
+    df = pd.read_csv(file, sep='\t',
+                     names=["Perc", "Reads_covered", "Reads_Assigned", "Order",
+                            "Tax_ID", "Taxon"])
+    # Fetching Families and Species rows
+    df1 = df.loc[df['Order'] == 'F'].sort_values("Reads_covered",
+                                                 ascending=False)
+    df2 = df.loc[df['Order'] == 'S'].sort_values("Reads_covered",
+                                                 ascending=False)
+
     df1 = df1[['Taxon', 'Reads_covered']]
     df2 = df2[['Taxon', 'Reads_covered']]
-    
-    df1['Taxon'] = df1['Taxon'].str.replace('\s+', '', regex=True)                  #Removing whitespaces 
+
+    # Removing whitespaces
+    df1['Taxon'] = df1['Taxon'].str.replace('\s+', '', regex=True)
     df2['Taxon'] = df2['Taxon'].str.replace('\s+', '', regex=True)
-    
+
+    # Changing column name to filename
     filename = os.path.basename(file).split(".")[0]
-    df1 = df1.rename(columns={'Reads_covered': filename})                           #Changing column name to filename
+    df1 = df1.rename(columns={'Reads_covered': filename})
     df2 = df2.rename(columns={'Reads_covered': filename})
-    
-    family_data = pd.merge(family_data, df1, on='Taxon', how='outer')               #Merging out all columns
+
+    # Merging out all columns
+    family_data = pd.merge(family_data, df1, on='Taxon', how='outer')
     species_data = pd.merge(species_data, df2, on='Taxon', how='outer')
-    
-cols = [family_data.columns[0]] + sorted(family_data.columns[1:])                   #Sorting the columns 
+
+# Sorting the columns
+cols = [family_data.columns[0]] + sorted(family_data.columns[1:])
 cols2 = [species_data.columns[0]] + sorted(species_data.columns[1:])
 
 family_data = family_data[cols]
 species_data = species_data[cols2]
+family_data.to_csv(args.output_file_directory +
+                   "Familywise_tax_readcounts.tsv", sep='\t',
+                   index=False)
+species_data.to_csv(args.output_file_directory +
+                    "Specieswise_tax_readcounts.tsv", sep='\t',
+                    index=False)
+
+print("\n Processing Completed! Now Plotting Clustermaps")
 
-family_data.to_csv(args.output_file_directory + "familywise_taxonomic_readcounts.tsv", sep='\t', index=False)
-species_data.to_csv(args.output_file_directory + "specieswise_taxonomic_readcounts.tsv", sep='\t', index=False)    
-    
 # --- Plotting Clustermap for Taxon ---
 family_map = family_data.set_index("Taxon")
-family_map_log10 = family_map.apply(lambda x: np.log10(x) if np.issubdtype(x.dtype, np.number) else x)                   #Log10 transformation
-family_map_cleaned = family_map_log10.fillna(0)                                                                          #Filling missing values 
-sns.set(rc={"figure.figsize": (80,60)})
+family_map_log10 = family_map.apply(lambda x: np.log10(x) if np.issubdtype(x.dtype, np.number) else x)
+family_map_cleaned = family_map_log10.fillna(0)
+sns.set(rc={"figure.figsize": (80, 60)})
 sns.set(font_scale=0.6)
-g = sns.clustermap(family_map_cleaned, cmap="coolwarm", xticklabels=True, yticklabels=True)
+g = sns.clustermap(family_map_cleaned,
+                   cmap="coolwarm",
+                   xticklabels=True,
+                   yticklabels=True)
 g.ax_heatmap.yaxis.set_tick_params(labelsize=4)
 plt.title("Family-Wise Clustermap")
-plt.suptitle("Family-Wise Clustermap", ha="center", va="center", fontsize=14, y=1.0)
+plt.suptitle("Family-Wise Clustermap",
+             ha="center", va="center", fontsize=14, y=1.0)
 plt.ylabel("Read Counts (log10)")
-g.savefig(args.output_file_directory + "clustermap_familywise_log10.png", dpi=1200)
+g.savefig(args.output_file_directory +
+          "Clustermap_Familywise_log10.png", dpi=1200)
 plt.show()
 
 
 # --- Plotting Clustermap for Top-10 Species ---
-species_data['maximum'] = species_data.max(axis=1,numeric_only=True)                                   #Getting maximum reads
-sorted_species_data = species_data.sort_values(by = 'maximum', ascending = False)
+species_data['maximum'] = species_data.max(axis=1, numeric_only=True)
+sorted_species_data = species_data.sort_values(by='maximum', ascending=False)
 top_10_species = sorted_species_data.head(10)
 species_map = top_10_species.set_index("Taxon")
-species_map_log10 = species_map.apply(lambda x: np.log10(x) if np.issubdtype(x.dtype, np.number) else x)                   #Log10 transformation
-species_map_cleaned = species_map_log10.fillna(0)                                                                          #Filling missing values 
+species_map_log10 = species_map.apply(lambda x: np.log10(x) if np.issubdtype(x.dtype, np.number) else x)
+species_map_cleaned = species_map_log10.fillna(0)
 species_map_data = species_map_cleaned.loc[:, species_map_cleaned.columns != "maximum"]
-sns.set(rc={"figure.figsize": (80,60)})
+sns.set(rc={"figure.figsize": (80, 60)})
 sns.set(font_scale=0.6)
-g = sns.clustermap(species_map_data, cmap="coolwarm", xticklabels=True, yticklabels=True)
+g = sns.clustermap(species_map_data, cmap="coolwarm",
+                   xticklabels=True, yticklabels=True)
 g.ax_heatmap.yaxis.set_tick_params(labelsize=4)
 plt.title("Species-Wise Clustermap")
-plt.suptitle("Species-Wise Clustermap (Top 10 Species)", ha="center", va="center", fontsize=14, y=1.0)
+plt.suptitle("Species-Wise Clustermap (Top 10 Species)",
+             ha="center", va="center", fontsize=14, y=1.0)
 plt.ylabel("Read Counts (log10)")
-g.savefig(args.output_file_directory + "clustermap_specieswise_log10.png", dpi=1200)
+g.savefig(args.output_file_directory +
+          "Clustermap_Specieswise_log10.png", dpi=1200)
 plt.show()
 
-print("--- Script Completed Successfully ---")
\ No newline at end of file
+print("\n--- Script Completed Successfully! ---\n")
diff --git a/scripts/synapse_fetch.py b/scripts/synapse_fetch.py
index 6446806..fde04b1 100644
--- a/scripts/synapse_fetch.py
+++ b/scripts/synapse_fetch.py
@@ -1,7 +1,8 @@
 """
 
-This script logs into Synapse portal and walks through a parent folder to get a list of all entities present in it. 
-It then preprocesses the list into a Pandas DataFrame along with directory information. 
+This script logs into Synapse portal and walks through a parent folder
+to get a list of all entities present in it. It then preprocesses the
+list into a Pandas DataFrame along with directory information.
 
 Usage:
     ./synapse_fetch.py -i <input_synapse_id>
@@ -11,14 +12,14 @@
 This script requires the following modules to be imported:
     - pandas
     - synapseutils
-    - synapseclient   
+    - synapseclient
 
 Output:
     - synapse_ids.tsv
         A tab seperated file consisting of following columns
-            - Directory: Directory name for a file stored in Synapse portal for a ParentID
+            - Directory: Directory name for file stored in Synapse portal
             - ParentID: ParentID of the Directory
-            - Filename: Name of the file 
+            - Filename: Name of the file
             - EntityID: SynapseID for the entities under the parent
 
 Returns:
@@ -27,22 +28,33 @@
 Author:
     Saim Momin <momin@ie-freiburg.mpg.de>
 
-Last Updated:  
-    12-04-2023
-    
-"""
+Last Updated:
+    07-07-2023
 
+"""
+import os
+import sys
 import pandas as pd
 import synapseutils
 import synapseclient
 import argparse
+import warnings
 
 parser = argparse.ArgumentParser()
-parser.add_argument("-i", "--input_synapse_id", metavar="ID", help="Synapse ID for Query")
+parser.add_argument("-i", "--input_synapse_id",
+                    metavar="ID",
+                    help="Synapse ID for Query")
+parser.add_argument("-o", "--output_file_dir",
+                    metavar="PATH",
+                    help="Path to output the Fetched Data")
 args = parser.parse_args()
 
 
-with open("/home/momin/.synapseConfig") as f:
+if not os.path.exists(os.path.expanduser("~/.synapseConfig")):
+    raise FileNotFoundError("The Synapse Configuration file not found. Exiting!")
+    sys.exit(0)
+
+with open(os.path.expanduser("~/.synapseConfig")) as f:
     file = f.read().strip().split("\n")
     for i in file:
         if i.startswith("username"):
@@ -51,9 +63,16 @@
             token = str(i[12::])
 
 syn = synapseclient.Synapse()
-syn.login(email=user, authToken=token)
-
-#Walking throw the Parent-ID and getting all the entities present in them
+try:
+    syn.login(email=user, authToken=token)
+    print("Connection Established Successfully!")
+except Exception as e:
+    print("\nConnection failed:", str(e))
+    warnings.simplefilter("ignore", UserWarning)
+    print('\nPlease Check your Login Credentials. Exiting!!')
+
+# Walking throw the Parent-ID and getting all the entities present in them
+print("Retrieving the Requested Data...")
 file_list = []
 test2 = synapseutils.walk(syn, args.input_synapse_id)
 for dirpath,dirname, filename in test2:
@@ -61,23 +80,18 @@
         file_info = {'dir': dirpath, 'file': f}
         file_list.append(file_info)
 
-#Preprocessing for the fetched directory and file list from Parent ID
+# Preprocessing for the fetched directory and file list from Parent ID
 df = pd.DataFrame(file_list)
 df1 = df.applymap(lambda x: str(x).replace("'", "").replace("(", "").replace(")", ""))
-df1[['Directory', 'ParentID']] =  df1['dir'].str.split(',', expand=True)
-df1[['Filename', 'EntityID']] = df1['file'].str.split(',', expand=True)
-df1.drop(['dir', 'file'],axis=1, inplace=True)
-df1.to_csv("synapse_ids.tsv", sep="\t", index=False)
-
-#TODO: Get the list of Synapse ids only with .fastq.gz command
-
-
-
-
-#TODO: Work on the downloading part and storing it in the directory. Possibly by multithreading approach (Discuss?)
-
-
-
-
-
-
+df1[['Directory', 'ParentID']] = df1['dir'].str.split(',', expand=True)
+df1[['Samplename', 'SynapseID']] = df1['file'].str.split(',', expand=True)
+df1.drop(['dir', 'file'], axis=1, inplace=True)
+df1.to_csv(args.output_file_dir + "synapse_ids_all.tsv", sep="\t", index=False)
+
+# Writing Sample and corresponding Synapse IDs
+filtered_df = df1[df1['Samplename'].str.contains('R1|R2')]
+filtered_df = filtered_df[['Samplename', 'SynapseID']]
+filtered_df.to_csv(args.output_file_dir + "synapse_fastqs_ids.tsv",
+                   sep="\t", index=False)
+
+print("\nRetrieving Data Successfull...")

From 0337b71809e475f03cb82477a4168779b6be5529 Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Mon, 10 Jul 2023 16:58:39 +0200
Subject: [PATCH 23/33] Minor Changes

---
 scripts/count_matrix_processing.py |  29 -----
 scripts/synapse_id.tsv             | 196 -----------------------------
 2 files changed, 225 deletions(-)
 delete mode 100644 scripts/count_matrix_processing.py
 delete mode 100644 scripts/synapse_id.tsv

diff --git a/scripts/count_matrix_processing.py b/scripts/count_matrix_processing.py
deleted file mode 100644
index 20658a0..0000000
--- a/scripts/count_matrix_processing.py
+++ /dev/null
@@ -1,29 +0,0 @@
-import os
-
-directory_path = '/data/manke/processing/momin/virome-scan/DGE/EBV/count_matrix' 
-
-tsv_files = []
-for root, dirs, files in os.walk(directory_path):
-    for file in files:
-        if file.endswith('.tsv'):
-            tsv_files.append(os.path.join(root, file))
-
-taxon_df = pd.DataFrame(columns=['Tax_ID'])
-for file in tsv_files:
-    df = pd.read_csv(file, sep='\t')
-    taxon = df['Tax_ID']
-    taxon_df = pd.merge(taxon_df,taxon,on='Tax_ID', how='outer')
-
-
-for file in tsv_files:
-    df2 = pd.read_csv(file, sep='\t')
-    samplename = str(file.split('/')[-2])
-    summed_data = df2.groupby('Tax_ID').sum().iloc[:, :].sum(axis=1).to_frame(samplename)
-    taxon_df = pd.merge(taxon_df, summed_data, on='Tax_ID', how='left')
-
-taxon_df = taxon_df.fillna(0)
-taxon_df['Tax_ID'] = taxon_df['Tax_ID'].str.split('(').str[0].str.strip()
-taxon_df.iloc[:, 1:] = taxon_df.iloc[:, 1:].astype(int)
-taxon_df = taxon_df.rename(columns={'Tax_ID': 'Taxon'})
-taxon_df.to_csv("/home/momin/count_matrix_summarized.tsv", sep='\t', index=False)
-taxon_df
\ No newline at end of file
diff --git a/scripts/synapse_id.tsv b/scripts/synapse_id.tsv
deleted file mode 100644
index e8e772a..0000000
--- a/scripts/synapse_id.tsv
+++ /dev/null
@@ -1,196 +0,0 @@
-Directory	ParentID	Filename	EntityID
-Data/Gene Expression/Gene Expression scRNA seq/counts - CITEseq	 syn26560200	S33.zip	 syn24610356
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S1.zip	 syn24610321
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S10.zip	 syn24610331
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S11.zip	 syn24610333
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S12.zip	 syn24610334
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S13.zip	 syn24610335
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S14.zip	 syn24610337
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S15.zip	 syn24610338
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S16.zip	 syn24610339
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S17.zip	 syn24610340
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S18.zip	 syn24610341
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S19.zip	 syn24610342
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S2.zip	 syn24610322
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S20.zip	 syn24610343
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S21.zip	 syn24610344
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S22.zip	 syn24610345
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S23.zip	 syn24610346
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S24.zip	 syn24610347
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S25.zip	 syn24610348
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S26.zip	 syn24610349
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S27.zip	 syn24610350
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S28.zip	 syn24610351
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S29.zip	 syn24610352
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S3.zip	 syn24610323
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S30.zip	 syn24610353
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S31.zip	 syn24610354
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S32.zip	 syn24610355
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S4.zip	 syn24610324
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S5.zip	 syn24610325
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S6.zip	 syn24610327
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S7.zip	 syn24610328
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S8.zip	 syn24610329
-Data/Gene Expression/Gene Expression scRNA seq/counts - scRNAseq	 syn24171157	S9.zip	 syn24610330
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-ADT-ATCACGAT_S29_L001_I1_001.fastq.gz	 syn26534563
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-ADT-ATCACGAT_S29_L001_R1_001.fastq.gz	 syn26534582
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-ADT-ATCACGAT_S29_L001_R2_001.fastq.gz	 syn26534579
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-HTO-ATTACTCG_S30_L001_I1_001.fastq.gz	 syn26534567
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-HTO-ATTACTCG_S30_L001_R1_001.fastq.gz	 syn26534585
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-HTO-ATTACTCG_S30_L001_R2_001.fastq.gz	 syn26534584
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-AGCATCCG_S26_L001_I1_001.fastq.gz	 syn26534562
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-AGCATCCG_S26_L001_R1_001.fastq.gz	 syn26534575
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-AGCATCCG_S26_L001_R2_001.fastq.gz	 syn26534574
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-CCTCATTC_S25_L001_I1_001.fastq.gz	 syn26534565
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-CCTCATTC_S25_L001_R1_001.fastq.gz	 syn26534580
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-CCTCATTC_S25_L001_R2_001.fastq.gz	 syn26534576
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-GTGGCAAT_S27_L001_I1_001.fastq.gz	 syn26534564
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-GTGGCAAT_S27_L001_R1_001.fastq.gz	 syn26534578
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-GTGGCAAT_S27_L001_R2_001.fastq.gz	 syn26534577
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-TAATGGGA_S28_L001_I1_001.fastq.gz	 syn26534566
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-TAATGGGA_S28_L001_R1_001.fastq.gz	 syn26534573
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - CITEseq	 syn26560199	20190110-cDNA-TAATGGGA_S28_L001_R2_001.fastq.gz	 syn26534572
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	268_1970_positive_S4_L004_I1_001.fastq.gz	 syn26534419
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	268_1970_positive_S4_L004_R1_001.fastq.gz	 syn26534428
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	268_1970_positive_S4_L004_R2_001.fastq.gz	 syn26534444
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	271_1971_CD45positive_S1_L001_I1_001.fastq.gz	 syn26534424
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	271_1971_CD45positive_S1_L001_R1_001.fastq.gz	 syn26534431
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	271_1971_CD45positive_S1_L001_R2_001.fastq.gz	 syn26534446
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	286_1976_cells_positive_S3_L003_I1_001.fastq.gz	 syn26534420
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	286_1976_cells_positive_S3_L003_R1_001.fastq.gz	 syn26534427
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	286_1976_cells_positive_S3_L003_R2_001.fastq.gz	 syn26534441
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	289_005_positive_S4_L004_I1_001.fastq.gz	 syn26534426
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	289_005_positive_S4_L004_R1_001.fastq.gz	 syn26534430
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	289_005_positive_S4_L004_R2_001.fastq.gz	 syn26534445
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	293_008_cells_positive_S5_L005_I1_001.fastq.gz	 syn26534425
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	293_008_cells_positive_S5_L005_R1_001.fastq.gz	 syn26534429
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	293_008_cells_positive_S5_L005_R2_001.fastq.gz	 syn26534447
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	294_009_cells_positive_S1_L001_I1_001.fastq.gz	 syn26534423
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	294_009_cells_positive_S1_L001_R1_001.fastq.gz	 syn26534442
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	294_009_cells_positive_S1_L001_R2_001.fastq.gz	 syn26534458
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	299_166-cells-positive_S2_L002_I1_001.fastq.gz	 syn26534422
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	299_166-cells-positive_S2_L002_R1_001.fastq.gz	 syn26534440
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	299_166-cells-positive_S2_L002_R2_001.fastq.gz	 syn26534457
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	301_014-cells-positive_S3_L003_I1_001.fastq.gz	 syn26534421
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	301_014-cells-positive_S3_L003_R1_001.fastq.gz	 syn26534437
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	301_014-cells-positive_S3_L003_R2_001.fastq.gz	 syn26534456
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	303_1991-cells-positive_S4_L004_I1_001.fastq.gz	 syn26534432
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	303_1991-cells-positive_S4_L004_R1_001.fastq.gz	 syn26534439
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	303_1991-cells-positive_S4_L004_R2_001.fastq.gz	 syn26534453
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	305_015-cells-positive_S5_L005_I1_001.fastq.gz	 syn26534433
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	305_015-cells-positive_S5_L005_R1_001.fastq.gz	 syn26534452
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	305_015-cells-positive_S5_L005_R2_001.fastq.gz	 syn26534462
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	325_2013_CD45_positive_S1_L001_I1_001.fastq.gz	 syn26534434
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	325_2013_CD45_positive_S1_L001_R1_001.fastq.gz	 syn26534450
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	325_2013_CD45_positive_S1_L001_R2_001.fastq.gz	 syn26534459
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	339_23_pos_cells_S3_L003_I1_001.fastq.gz	 syn26534435
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	339_23_pos_cells_S3_L003_R1_001.fastq.gz	 syn26534451
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	339_23_pos_cells_S3_L003_R2_001.fastq.gz	 syn26534465
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	345_2017-CD45_pos_S4_L004_I1_001.fastq.gz	 syn26534436
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	345_2017-CD45_pos_S4_L004_R1_001.fastq.gz	 syn26534460
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	345_2017-CD45_pos_S4_L004_R2_001.fastq.gz	 syn26534464
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	346_2019_CD45_pos_S1_L001_I1_001.fastq.gz	 syn26534438
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	346_2019_CD45_pos_S1_L001_R1_001.fastq.gz	 syn26534448
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	346_2019_CD45_pos_S1_L001_R2_001.fastq.gz	 syn26534463
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	355_2015_CD45_pos_S4_L004_I1_001.fastq.gz	 syn26534454
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	355_2015_CD45_pos_S4_L004_R1_001.fastq.gz	 syn26534449
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	355_2015_CD45_pos_S4_L004_R2_001.fastq.gz	 syn26534455
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	356_CK030_corticol-CD45-pos_S1_L001_I1_001.fastq.gz	 syn26534466
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	356_CK030_corticol-CD45-pos_S1_L001_R1_001.fastq.gz	 syn26534461
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	356_CK030_corticol-CD45-pos_S1_L001_R2_001.fastq.gz	 syn26534485
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	362_CK031_cortex_CD45-pos_S2_L002_I1_001.fastq.gz	 syn26534467
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	362_CK031_cortex_CD45-pos_S2_L002_R1_001.fastq.gz	 syn26534474
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	362_CK031_cortex_CD45-pos_S2_L002_R2_001.fastq.gz	 syn26534484
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	363_VA_2028-pos_S3_L003_I1_001.fastq.gz	 syn26534468
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	363_VA_2028-pos_S3_L003_R1_001.fastq.gz	 syn26534472
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	363_VA_2028-pos_S3_L003_R2_001.fastq.gz	 syn26534483
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	364_2030-CD45-pos_S4_L004_I1_001.fastq.gz	 syn26534469
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	364_2030-CD45-pos_S4_L004_R1_001.fastq.gz	 syn26534471
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	364_2030-CD45-pos_S4_L004_R2_001.fastq.gz	 syn26534481
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	365_CK033_S5_L005_I1_001.fastq.gz	 syn26534475
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	365_CK033_S5_L005_R1_001.fastq.gz	 syn26534470
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	365_CK033_S5_L005_R2_001.fastq.gz	 syn26534487
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	366_1996T_CD45-pos_S6_L006_I1_001.fastq.gz	 syn26534488
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	366_1996T_CD45-pos_S6_L006_R1_001.fastq.gz	 syn26534482
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	366_1996T_CD45-pos_S6_L006_R2_001.fastq.gz	 syn26534486
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	367_2037-CD45-pos_S7_L007_I1_001.fastq.gz	 syn26534489
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	367_2037-CD45-pos_S7_L007_R1_001.fastq.gz	 syn26534497
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	367_2037-CD45-pos_S7_L007_R2_001.fastq.gz	 syn26534507
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	369_182_positive_S8_L008_I1_001.fastq.gz	 syn26534491
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	369_182_positive_S8_L008_R1_001.fastq.gz	 syn26534499
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	369_182_positive_S8_L008_R2_001.fastq.gz	 syn26534508
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	375_VA_2028_pos_S3_L003_I1_001.fastq.gz	 syn26534490
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	375_VA_2028_pos_S3_L003_R1_001.fastq.gz	 syn26534495
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	375_VA_2028_pos_S3_L003_R2_001.fastq.gz	 syn26534506
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	376_2030_CD45_pos_S4_L004_I1_001.fastq.gz	 syn26534570
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	376_2030_CD45_pos_S4_L004_R1_001.fastq.gz	 syn26534581
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	376_2030_CD45_pos_S4_L004_R2_001.fastq.gz	 syn26534586
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	381_BC_155_Tumor_CD45pos_S1_L001_I1_001.fastq.gz	 syn26534571
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	381_BC_155_Tumor_CD45pos_S1_L001_R1_001.fastq.gz	 syn26534583
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	381_BC_155_Tumor_CD45pos_S1_L001_R2_001.fastq.gz	 syn26534587
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	383_sample_cell_line_553_S3_L003_I1_001.fastq.gz	 syn26534494
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	383_sample_cell_line_553_S3_L003_R1_001.fastq.gz	 syn26534502
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	383_sample_cell_line_553_S3_L003_R2_001.fastq.gz	 syn26534509
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-ACAAGGTA_S54_L002_I1_001.fastq.gz	 syn26534518
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-ACAAGGTA_S54_L002_R1_001.fastq.gz	 syn26534540
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-ACAAGGTA_S54_L002_R2_001.fastq.gz	 syn26534537
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-CGTCCCGT_S55_L002_I1_001.fastq.gz	 syn26534519
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-CGTCCCGT_S55_L002_R1_001.fastq.gz	 syn26534538
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-CGTCCCGT_S55_L002_R2_001.fastq.gz	 syn26534536
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-GTGGTACC_S52_L002_I1_001.fastq.gz	 syn26534521
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-GTGGTACC_S52_L002_R1_001.fastq.gz	 syn26534544
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-GTGGTACC_S52_L002_R2_001.fastq.gz	 syn26534542
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-TACTATAG_S53_L002_I1_001.fastq.gz	 syn26534523
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-TACTATAG_S53_L002_R1_001.fastq.gz	 syn26534546
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CK-045-CD45-scRNAseq-3-TACTATAG_S53_L002_R2_001.fastq.gz	 syn26534545
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L001_I1_001.fastq.gz	 syn26534492
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L001_R1_001.fastq.gz	 syn26534501
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L001_R2_001.fastq.gz	 syn26534504
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L002_I1_001.fastq.gz	 syn26534514
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L002_R1_001.fastq.gz	 syn26534500
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L002_R2_001.fastq.gz	 syn26534512
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L003_I1_001.fastq.gz	 syn26534510
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L003_R1_001.fastq.gz	 syn26534503
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L003_R2_001.fastq.gz	 syn26534505
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L004_I1_001.fastq.gz	 syn26534493
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L004_R1_001.fastq.gz	 syn26534511
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	CL402JF_S1_L004_R2_001.fastq.gz	 syn26534530
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-ATCTCTGT_S45_L002_I1_001.fastq.gz	 syn26534516
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-ATCTCTGT_S45_L002_R1_001.fastq.gz	 syn26534534
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-ATCTCTGT_S45_L002_R2_001.fastq.gz	 syn26534529
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-CCTAGACC_S44_L002_I1_001.fastq.gz	 syn26534513
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-CCTAGACC_S44_L002_R1_001.fastq.gz	 syn26534533
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-CCTAGACC_S44_L002_R2_001.fastq.gz	 syn26534531
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-GGAGAGAG_S47_L002_I1_001.fastq.gz	 syn26534515
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-GGAGAGAG_S47_L002_R1_001.fastq.gz	 syn26534522
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-GGAGAGAG_S47_L002_R2_001.fastq.gz	 syn26534520
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-TAGCTCTA_S46_L002_I1_001.fastq.gz	 syn26534517
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-TAGCTCTA_S46_L002_R1_001.fastq.gz	 syn26534535
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2058-CD45-10x-3-TAGCTCTA_S46_L002_R2_001.fastq.gz	 syn26534532
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-ATCATGCA_S50_L002_I1_001.fastq.gz	 syn26534524
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-ATCATGCA_S50_L002_R1_001.fastq.gz	 syn26534551
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-ATCATGCA_S50_L002_R2_001.fastq.gz	 syn26534548
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-CCGGGTAT_S51_L002_I1_001.fastq.gz	 syn26534525
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-CCGGGTAT_S51_L002_R1_001.fastq.gz	 syn26534549
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-CCGGGTAT_S51_L002_R2_001.fastq.gz	 syn26534547
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-GGTTCCTC_S49_L002_I1_001.fastq.gz	 syn26534527
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-GGTTCCTC_S49_L002_R1_001.fastq.gz	 syn26534556
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-GGTTCCTC_S49_L002_R2_001.fastq.gz	 syn26534555
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-TAACAAGG_S48_L002_I1_001.fastq.gz	 syn26534528
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-TAACAAGG_S48_L002_R1_001.fastq.gz	 syn26534553
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2064-CD45-10x-3-TAACAAGG_S48_L002_R2_001.fastq.gz	 syn26534550
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-AGGTATTG_S56_L002_I1_001.fastq.gz	 syn26534526
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-AGGTATTG_S56_L002_R1_001.fastq.gz	 syn26534541
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-AGGTATTG_S56_L002_R2_001.fastq.gz	 syn26534539
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-CTCCTAGT_S57_L002_I1_001.fastq.gz	 syn26534543
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-CTCCTAGT_S57_L002_R1_001.fastq.gz	 syn26534552
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-CTCCTAGT_S57_L002_R2_001.fastq.gz	 syn26534558
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-GATGCCAA_S59_L002_I1_001.fastq.gz	 syn26534557
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-GATGCCAA_S59_L002_R1_001.fastq.gz	 syn26534559
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-GATGCCAA_S59_L002_R2_001.fastq.gz	 syn26534561
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-TCAAGGCC_S58_L002_I1_001.fastq.gz	 syn26534560
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-TCAAGGCC_S58_L002_R1_001.fastq.gz	 syn26534569
-Data/Gene Expression/Gene Expression scRNA seq/fastqs - scRNAseq	 syn26560198	VA-2065-CD45-10x-3-TCAAGGCC_S58_L002_R2_001.fastq.gz	 syn26534568
-Data/Metadata	 syn24168324	HBI_scRNAseq_assay_scrnaSeq_metadata.csv	 syn24610436
-Data/Metadata	 syn24168324	HBI_scRNAseq_biospecimen_metadata.csv	 syn24610438
-Data/Metadata	 syn24168324	HBI_scRNAseq_individual_metadata.csv	 syn24610550

From e302a81dce7de007cb1952c353f09f0b9afe7db3 Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Mon, 10 Jul 2023 17:12:28 +0200
Subject: [PATCH 24/33] Code Cleanup

---
 .snakemake-workflow-catalog.yml        | 11 -----------
 .template/config/config.yaml.tmpl.tmpl |  1 -
 .template/workflow/Snakefile.tmpl.tmpl | 10 ----------
 3 files changed, 22 deletions(-)
 delete mode 100644 .snakemake-workflow-catalog.yml
 delete mode 100644 .template/config/config.yaml.tmpl.tmpl
 delete mode 100644 .template/workflow/Snakefile.tmpl.tmpl

diff --git a/.snakemake-workflow-catalog.yml b/.snakemake-workflow-catalog.yml
deleted file mode 100644
index 3436e32..0000000
--- a/.snakemake-workflow-catalog.yml
+++ /dev/null
@@ -1,11 +0,0 @@
-# configuration of display in snakemake workflow catalog: https://snakemake.github.io/snakemake-workflow-catalog
-
-usage:
-  mandatory-flags: # optional definition of additional flags
-    desc: # describe your flags here in a few sentences (they will be inserted below the example commands)
-    flags: # put your flags here
-  software-stack-deployment: # definition of software deployment method (at least one of conda, singularity, or singularity+conda)
-    conda: true # whether pipeline works with --use-conda
-    singularity: false # whether pipeline works with --use-singularity
-    singularity+conda: false # whether pipeline works with --use-singularity --use-conda
-  report: true # add this to confirm that the workflow allows to use 'snakemake --report report.zip' to generate a report containing all results and explanations
\ No newline at end of file
diff --git a/.template/config/config.yaml.tmpl.tmpl b/.template/config/config.yaml.tmpl.tmpl
deleted file mode 100644
index 0850e6f..0000000
--- a/.template/config/config.yaml.tmpl.tmpl
+++ /dev/null
@@ -1 +0,0 @@
-# add template configuration file (may use variables from copier.yml)
\ No newline at end of file
diff --git a/.template/workflow/Snakefile.tmpl.tmpl b/.template/workflow/Snakefile.tmpl.tmpl
deleted file mode 100644
index 65613a9..0000000
--- a/.template/workflow/Snakefile.tmpl.tmpl
+++ /dev/null
@@ -1,10 +0,0 @@
-configfile: "config/config.yaml"
-
-module [[ module_name ]]:
-    snakefile:
-        # TODO replace <release> with desired release
-        "https://github.com/[[ owner ]]/[[ repo ]]/raw/<release>/Snakefile"
-    config:
-        config
-
-use rule * from [[ module_name ]]
\ No newline at end of file

From be49978748730bec32707d1708445b7352de70c0 Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Fri, 28 Jul 2023 12:21:21 +0200
Subject: [PATCH 25/33] Added Synpase Integration with pipeline

---
 Snakefile                          |  4 ++--
 config.yaml                        |  4 ++--
 metadata.tsv                       | 13 +++++++++++++
 rules/cellranger.smk               |  2 +-
 rules/download_samples_or_copy.smk | 26 ++++++++++++++++++++------
 rules/extract_tags.smk             |  2 +-
 rules/kraken2_mapping.smk          |  7 ++++---
 scripts/synapse_fetch.py           | 15 ++++++++++++++-
 8 files changed, 57 insertions(+), 16 deletions(-)
 create mode 100644 metadata.tsv

diff --git a/Snakefile b/Snakefile
index 46da13b..6bf420d 100644
--- a/Snakefile
+++ b/Snakefile
@@ -4,7 +4,7 @@ import pandas as pd
 
 configfile: "config.yaml"
 
-accession_list = pd.read_table("SRA.tsv")
+accession_list = pd.read_table("metadata.tsv")
 samples = list(accession_list.Samples.unique())
 
 
@@ -21,7 +21,7 @@ rule all:
             expand("data/{sample}_test.txt",sample=samples),
             expand("results/kraken2/{sample}/{sample}.kraken",sample=samples),
             expand("results/kraken2/{sample}/{sample}.report.txt",sample=samples),
-            expand("results/kraken2/{sample}/{sample}_classified_out.fastq",sample=samples),
+            #expand("results/kraken2/{sample}/{sample}_classified_out.fastq",sample=samples),
             expand("results/cellranger/{sample}/{sample}_finished.txt",sample=samples),
             expand("results/cellranger/{sample}/unmapped_reads.sam", sample=samples),
             expand("results/count_matrix/{sample}/count_matrix.tsv", sample=samples)
diff --git a/config.yaml b/config.yaml
index 239b286..ba72732 100644
--- a/config.yaml
+++ b/config.yaml
@@ -1,4 +1,4 @@
-"files" : None
+"files" : "synapse"
 "transcriptome" : "/data/repository/misc/cellranger_references/cellranger/refdata-gex-GRCh38-2020-A"
 "local_files_dir" : "/data/manke/processing/momin/virome-scan/sc-virome-scan/data_pos_control/SRR13114612"
-"kraken_db": "/data/repository/kraken2_contaminome/virus_db2023"
\ No newline at end of file
+"kraken_db": "/data/manke/processing/momin/virome-scan/sc-virome-scan/db/t2tDB/t2tDB/"
\ No newline at end of file
diff --git a/metadata.tsv b/metadata.tsv
new file mode 100644
index 0000000..31ad192
--- /dev/null
+++ b/metadata.tsv
@@ -0,0 +1,13 @@
+Samples	R1	R2
+D17-8765_S1L1	 syn18641014	 syn18641249
+D17-8765_S1L2	 syn18641325	 syn18641475
+D17-8765_S1L3	 syn18641515	 syn18641599
+D17-8765_S1L4	 syn18641650	 syn18641733
+D17-8766_S2L1	 syn18641776	 syn18641855
+D17-8766_S2L2	 syn18641922	 syn18641969
+D17-8766_S2L3	 syn18642006	 syn18642053
+D17-8766_S2L4	 syn18642092	 syn18642140
+D17-8767_S3L1	 syn18641871	 syn18641934
+D17-8767_S3L2	 syn18641881	 syn18641929
+D17-8767_S3L3	 syn18641880	 syn18641930
+D17-8767_S3L4	 syn18641872	 syn18641927
\ No newline at end of file
diff --git a/rules/cellranger.smk b/rules/cellranger.smk
index 1f6cefa..ec2159e 100644
--- a/rules/cellranger.smk
+++ b/rules/cellranger.smk
@@ -2,7 +2,7 @@ rule cellranger:
     input:
         i1 = expand("data/{sample}_test.txt", sample=samples)
     output:
-        o1 = temp("results/cellranger/{sample}/{sample}_finished.txt")
+        o1 = "results/cellranger/{sample}/{sample}_finished.txt"
     priority: 90
     resources:
         mem_mb = 26000
diff --git a/rules/download_samples_or_copy.smk b/rules/download_samples_or_copy.smk
index 57a0921..7ba9146 100644
--- a/rules/download_samples_or_copy.smk
+++ b/rules/download_samples_or_copy.smk
@@ -1,22 +1,36 @@
 rule download_samples_or_copy:
     output: 
         o1 = "data/{sample}/{sample}_S1_L001_R1_001.fastq.gz",
-        o2 = "data/{sample}/{sample}_S1_L001_R2_001.fastq.gz",
+        o2 = "data/{sample}/{sample}_S1_L001_R2_001.fastq.gz"
     params:
-        outdir = "data/{sample}/"
+        outdir = "data/{sample}/",
+        filetype = config["files"]
     threads: 16
+    resources:
+        mem_mb = 20000
     log:
         "results/logs/download_samples_or_copy/{sample}.log"
     priority: 100
     shell:
         """
-        if [ {config[files]} == 'local' ]; then
+        filetype="{params.filetype}"
+        if [ $filetype == "local" ]; then
             for file in {wildcards.sample}*; do
                 ln -s {config[local_files_dir]}/$file  data/$file
             done
+        
+        elif [ $filetype == "synapse" ]; then
+            result=$(grep "{wildcards.sample}" "metadata.tsv")
+            R1=$(echo "$result" | awk '{{print $2}}')
+            R2=$(echo "$result" | awk '{{print $3}}')
+            synapse get $R1 --multiThreaded --downloadLocation {params.outdir} 
+            synapse get $R2 --multiThreaded --downloadLocation {params.outdir}
+            mv data/{wildcards.sample}/*_R1_* data/{wildcards.sample}/{wildcards.sample}_S1_L001_R1_001.fastq.gz
+            mv data/{wildcards.sample}/*_R2_* data/{wildcards.sample}/{wildcards.sample}_S1_L001_R2_001.fastq.gz
+        
         else
             parallel-fastq-dump --sra-id {wildcards.sample} --split-files --threads {threads} --outdir {params.outdir}  --gzip --tmpdir /data/manke/processing/momin/virome-scan/sc-virome-scan/tmp
-            mv data/{wildcards.sample}/{wildcards.sample}_1.fastq.gz data/{wildcards.sample}/{wildcards.sample}_S1_L001_R1_001.fastq.gz 
-            mv data/{wildcards.sample}/{wildcards.sample}_2.fastq.gz data/{wildcards.sample}/{wildcards.sample}_S1_L001_R2_001.fastq.gz 
-        fi
+            mv data/{wildcards.sample}/{wildcards.sample}_2.fastq.gz data/{wildcards.sample}/{wildcards.sample}_S1_L001_R1_001.fastq.gz 
+            mv data/{wildcards.sample}/{wildcards.sample}_3.fastq.gz data/{wildcards.sample}/{wildcards.sample}_S1_L001_R2_001.fastq.gz 
+        fi     
         """
diff --git a/rules/extract_tags.smk b/rules/extract_tags.smk
index 514aedf..47763ee 100644
--- a/rules/extract_tags.smk
+++ b/rules/extract_tags.smk
@@ -11,6 +11,6 @@ rule extract_tags:
         p1 = "results/count_matrix/{sample}/",
         p2 = "results/cellranger/{sample}/{sample}/outs/filtered_feature_bc_matrix/barcodes.tsv.gz"
     log:
-        "results/count_matrix/{sample}_bam_extract.log"
+        "results/logs/count_matrix/{sample}_bam_extract.log"
     shell:
         "python3 scripts/bam_extract.py -i {input.i1} -k {input.i2} -b {params.p2} -o {params.p1}"
\ No newline at end of file
diff --git a/rules/kraken2_mapping.smk b/rules/kraken2_mapping.smk
index 92dd1f2..e3c48b2 100644
--- a/rules/kraken2_mapping.smk
+++ b/rules/kraken2_mapping.smk
@@ -4,9 +4,11 @@ rule kraken2_mapping:
     output:
         o1 = "results/kraken2/{sample}/{sample}.kraken",
         o2 = "results/kraken2/{sample}/{sample}.report.txt",
-        o3 = "results/kraken2/{sample}/{sample}_classified_out.fastq",
+        #o3 = "results/kraken2/{sample}/{sample}_classified_out.fastq",
         o4 = temp("data/{sample}_test.txt")
     priority: 95
+    resources:
+        mem_mb = 20000
     threads: 16
     params:
         p1 = config["kraken_db"]
@@ -14,7 +16,6 @@ rule kraken2_mapping:
         "results/logs/kraken2/{sample}.kraken.log"
     shell:
         """
-        kraken2 --use-names --threads {threads} --db {params.p1} --report {output.o2} --output {output.o1} --classified-out {output.o3} {input.i1} 2> {log}
-        gzip {output.o3}
+        kraken2 --use-names --threads {threads} --db {params.p1} --report {output.o2} --output {output.o1} {input.i1} 2> {log}
         touch {output.o4}
         """
\ No newline at end of file
diff --git a/scripts/synapse_fetch.py b/scripts/synapse_fetch.py
index fde04b1..e1463d7 100644
--- a/scripts/synapse_fetch.py
+++ b/scripts/synapse_fetch.py
@@ -91,7 +91,20 @@
 # Writing Sample and corresponding Synapse IDs
 filtered_df = df1[df1['Samplename'].str.contains('R1|R2')]
 filtered_df = filtered_df[['Samplename', 'SynapseID']]
-filtered_df.to_csv(args.output_file_dir + "synapse_fastqs_ids.tsv",
+filtered_df['Samples'] = filtered_df['Samplename'].str.replace(r'_R[12].*', '', regex=True)
+filtered_df2 = filtered_df[["Samples", "SynapseID"]]
+filtered_df2['count'] = filtered_df2.groupby('Samples').cumcount() + 1
+df2_pivoted = filtered_df2.pivot(index='Samples', columns='count',
+                                 values='SynapseID')
+df2_pivoted.columns = [f"R{i}" for i in df2_pivoted.columns]
+df2_pivoted = df2_pivoted.reset_index()
+df2_pivoted['Samples'] = df2_pivoted['Samples'].str.replace(r'_L(\d+)', r'L\1',
+                                                            regex=True)
+df2_pivoted['Samples'] = df2_pivoted['Samples'].str.replace(r'S1_', 'S1',
+                                                            regex=True)
+df2_pivoted['Samples'] = df2_pivoted['Samples'].str.replace(r'L0*(\d+)', r'L\1',
+                                                            regex=True)
+df2_pivoted.to_csv(args.output_file_dir + "metadata.tsv",
                    sep="\t", index=False)
 
 print("\nRetrieving Data Successfull...")

From 3230f7154e58cfb5d42971a7dd37d7e63e529751 Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Fri, 28 Jul 2023 12:29:50 +0200
Subject: [PATCH 26/33] Added Synapse requirement in env.yaml

---
 env.yaml | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/env.yaml b/env.yaml
index ba93358..1eb9404 100644
--- a/env.yaml
+++ b/env.yaml
@@ -9,4 +9,6 @@ dependencies:
   - entrez-direct
   - parallel-fastq-dump
   - pandas
-  - snakemake
\ No newline at end of file
+  - snakemake
+  - pip:
+    - synapseclient
\ No newline at end of file

From 8b3d139562dc45d84d91ce57747ed354e4f6b499 Mon Sep 17 00:00:00 2001
From: Saim Momin <64724322+SaimMomin12@users.noreply.github.com>
Date: Fri, 28 Jul 2023 12:46:28 +0200
Subject: [PATCH 27/33] Update README.md

---
 README.md | 28 +++++++++++++++++++++++-----
 1 file changed, 23 insertions(+), 5 deletions(-)

diff --git a/README.md b/README.md
index d77a4c7..e3ef86d 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,7 @@
 # sc-Virome-Scan: A Snakemake pipeline for detection of viruses in single-cell datasets.
 
 [![Snakemake](https://img.shields.io/badge/snakemake-≥6.3.0-brightgreen.svg)](https://snakemake.github.io)
-[![GitHub actions status](https://github.com/maxplanck-ie/sc-virome-scan/workflows/Flake Check/badge.svg?branch=dev)](https://github.com/maxplanck-ie/sc-virome-scan/actions?query=branch%3Amain+workflow%3ATests)
+
 
 
 A method wrapped around Snakemake for swift, precise, and accurate detection of viral pathogens in single-cell
@@ -9,6 +9,28 @@ RNA (scRNA) datasets to investigate the possible correlation between viral patho
 
 <br /> 
 
+# Installation
+
+`git clone https://github.com/maxplanck-ie/sc-virome-scan.git`
+
+`cd sc-virome-scan`
+
+`mamba create -f env.yaml`
+
+## Usage
+
+> ***snakemake --cores 16 --configfile config.yaml --latency-wait 60 --profile mpislurm***
+
+## Handling Multiple Input modes to pipeline
+Currently, the pipeline supports Sequence Read Archive (SRA) and Synapse AD Portal input files for analysis. 
+
+<br /> 
+
+## Important Note For Synapse Data Analysis
+In order to download and analyse data from Synapse Portal, make sure you have the `synpaseConfig` file located in `~/.synapseConfig` directory. This file has individual Username and Access Token in order to login in to Synapse programmatically (Automatically taken care by the pipeline) and download the data based on the user input. 
+
+Additionally, the user needs to provide a ***metadata.tsv*** file (present in the base directory of the repository) which consists of Sample names along with its Read 1 and Read 2 Synapse IDs. The pipeline will use this metadata.tsv file for downloading and analysis steps downstream.
+
 # DAG for the pipeline
 ![Graphviz Diagram](dag.png)
 
@@ -16,10 +38,6 @@ RNA (scRNA) datasets to investigate the possible correlation between viral patho
 
 <br /> 
 
-## Usage
-
-> ***snakemake --cores 16 --use-conda --configfile config.yaml --latency-wait 60***
-    
 ### Note
 This is a developmental and alpha phase of the pipeline, upon completion a Python Wrapper will take care of every runtime parameter handling automatically.
 

From 31d46ffa3260e3a18a183319537bbe234d696a38 Mon Sep 17 00:00:00 2001
From: Saim Momin <64724322+SaimMomin12@users.noreply.github.com>
Date: Fri, 28 Jul 2023 12:54:09 +0200
Subject: [PATCH 28/33] Update README.md

---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index e3ef86d..fd7ee1d 100644
--- a/README.md
+++ b/README.md
@@ -11,11 +11,11 @@ RNA (scRNA) datasets to investigate the possible correlation between viral patho
 
 # Installation
 
-`git clone https://github.com/maxplanck-ie/sc-virome-scan.git`
+`git clone -b dev https://github.com/maxplanck-ie/sc-virome-scan.git`
 
 `cd sc-virome-scan`
 
-`mamba create -f env.yaml`
+`mamba create -f env.yaml -n sc-virome-scan`
 
 ## Usage
 

From 89ac587ce6e4d8b08fac6a00d9d7649547d17695 Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Wed, 9 Aug 2023 15:08:27 +0200
Subject: [PATCH 29/33] Updated Repo with minor Changes

---
 README.md                          | 187 ++++++++++++++++++++++++++---
 Snakefile                          |  25 ++--
 config.yaml                        |  11 +-
 dag.png                            | Bin 23890 -> 24447 bytes
 env.yaml                           |   1 +
 rules/cellranger.smk               |  19 +--
 rules/download_samples_or_copy.smk |   9 +-
 rules/extract_bam.smk              |   6 +-
 rules/extract_tags.smk             |   8 +-
 rules/kraken2_mapping.smk          |   9 +-
 rules/report.smk                   |  20 +++
 scripts/synapse_fetch.py           |   2 +-
 12 files changed, 236 insertions(+), 61 deletions(-)
 create mode 100644 rules/report.smk

diff --git a/README.md b/README.md
index fd7ee1d..365c601 100644
--- a/README.md
+++ b/README.md
@@ -1,35 +1,151 @@
-# sc-Virome-Scan: A Snakemake pipeline for detection of viruses in single-cell datasets.
+# scVirusScan: A method for swift and accurate detection of viral pathogens in single-cell RNA datasets.
+
 
 [![Snakemake](https://img.shields.io/badge/snakemake-≥6.3.0-brightgreen.svg)](https://snakemake.github.io)
 
 
+A method wrapped around Snakemake enabling accurate, sensitive and scalable detection of viral pathogens in single-cell
+RNA datasets. The pipeline integrates the strengths of two standard approaches, a standard mapping based approach and a **Kraken2** k-mer based approach which provides rapid taxonomic classification.The output of the scVirusScan pipeline can be
+integrated easily into existing single cell analysis frameworks (Seurat and Scanpy) which can provide
+standardized and reliable way to scrutinize virus infections at the single cell level resolution. 
+
 
-A method wrapped around Snakemake for swift, precise, and accurate detection of viral pathogens in single-cell
-RNA (scRNA) datasets to investigate the possible correlation between viral pathogens and neurodegenerative diseases. 
 
 <br /> 
 
-# Installation
+# Installation and Setup
+1. Clone the Git Repository using: `git clone https://github.com/maxplanck-ie/sc-virome-scan.git`
+
+2. Once cloned, change the directory to sc-virus-scan: `cd sc-virus-scan`
 
-`git clone -b dev https://github.com/maxplanck-ie/sc-virome-scan.git`
+3. To install the dependencies of the pipeline a `env.yaml` file has been provided. The environment and dependencies can be installed using conda/mamba.  
 
-`cd sc-virome-scan`
+     `mamba env create -f env.yaml -n sc-virome-scan`
 
-`mamba create -f env.yaml -n sc-virome-scan`
+4. Additionally, this pipeline needs `CellRanger` tool. To install CellRanger please refer to  https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/installation  
 
-## Usage
 
-> ***snakemake --cores 16 --configfile config.yaml --latency-wait 60 --profile mpislurm***
+5. After installation of CellRanger, the path to CellRanger executable needs to be specified in `config.yaml` file.
+
+6. Finally, the `config.yaml` needs to be modified as per your system environment variables. More information about `config.yaml` along with its description can be found in the section below.
+
+<br /> 
+
+### **A. Contents of `config.yaml` file**
+```
+samplesheet : # Path to your samplesheet file. More details about Samplesheet schema can be found below
+
+mode : # Pipeline mode to execute. (synapse | sra | local)
+
+local_data_dir : # If you choose local as pipeline mode, specify here the directory path of the files.
+
+kraken_db: # Path to Custom KrakenDB. More details can be found below
+
+cellranger: # Path of CellRanger Executable.
+
+transcriptome : # Path to your human transcriptome required from CellRanger count
+
+scripts_dir: # Path to scripts directory present in base directory of the workflow
+```
+<br /> 
+
+### **B. Description about `config.yaml` file**
+1. `samplesheet`: The pipeline requires a `samplesheet.tsv` file to carry out the analysis. The samplesheet is a Tab seperated file (TSV) that provides a blueprint for analysis. As the pipeline supports two modes for analysis, there are two different formats for samplesheet discussed below. This file is further used to download the files from SRA database and perform analysis on it. 
+   
+    **i. SRA mode:**
+    For running the pipeline in SRA mode, the user needs to provide a list of SRA Ids as shown in the example below. This file is further used to download the files from SRA database and perform analysis on it.  
+    ```
+    Samples
+    SRR13419001
+    SRR13419002
+    SRR13419003
+    SRR13419004
+    SRR13419005
+    ```
+    <br /> 
+
+    **ii. Synapse mode:**
+    For running the pipeline in synapse mode, user needs to generate the samplesheet with the help of `synapse_fetch.py` script present in the `scripts` directory of the pipeline. This scripts takes a Parent SynapseID as input and programmatically queries in the Synapse Server to retreive all the associate FASTQ files under the provided SynapseID and finally returns a Tab-Sepated file consisting of SampleName, Read1 SynapseID, Read2 SynapseID as shown below. This file is further used to download the files from Synapse and perform analysis on it. 
+    ```
+    Samples	R1	R2
+    D17-8765_S1L1	 syn18641014	 syn18641249
+    D17-8765_S1L2	 syn18641325	 syn18641475
+    D17-8765_S1L3	 syn18641515	 syn18641599
+    D17-8765_S1L4	 syn18641650	 syn18641733
+    D17-8766_S2L1	 syn18641776	 syn18641855
+    ```
+
+    **iii. Local mode:**
+    For running the pipeline in local mode (ie.Files are already downloaded prior to analysis), the user needs to specify the Sample names in `samplesheet.tsv` file. Along with this, the user has to provide the path to the directory where the files are present in the `config.yaml` file under `local_data_dir` key.
+
+    <br /> 
+2. `mode` **(SRA | synapse):** 
+    At present, the pipeline caters to two distinct modes depending on the input data type: Sequence Read Archive (`SRA`) and Synapse AD Portal (`synapse`) input files for analysis. Depending on the input data type, the mode can be modified in the `config.yaml` file.
+    
+    <br /> 
+
+3. `kraken_db:` As this pipeline relies on Kraken2 for  rapid taxonomic classification and requires a KrakenDB in backend, we have pre-built KrakenDB with curated list of Virus families. The custom VirusDB can be found in the link below. Once downloaded, please specify the path to KrakenDB in `config.yaml` file.
+    
+    <br /> 
+4. `cellranger:` Specify the path of CellRanger executable. 
+    
+    <br /> 
+
+5. `transcriptome:` The CellRanger count requires a Human reference transcriptome for scRNA-seq analysis. This reference        
+   transcriptome can be either be built using `Cellranger count` or can be downloaded pre-built from our Zenodo data repository. Link can be found below. To build the CellRanger reference transcriptome manually, please refer to https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/advanced/references
+
+    Once the transcriptome is downloaded/built, please specify its path in the `config.yaml` file corresponding to `transcriptome` key.
+    
+    <br /> 
+
+6. `scripts_dir:` This path refers to the scripts directory present in the base directory of the workflow. 
+
+
+    <br /> 
+
+## **Important Note For Synapse Data Analysis mode**
+In order to download and analyse data from Synapse Portal, user needs a `synpaseConfig` file located in `~/.synapseConfig` directory. This file has individual Username and Access Token in order to login in to Synapse programmatically (Automatically taken care by the pipeline) and download the relevant data based on the user input. More information on setting up the `synapseConfig` file can be found here https://python-docs.synapse.org/build/html/Credentials.html#use-synapseconfig
+
+Step to setup `synapseConfig` file  
+1. Check in the home directory if `.synapseConfig` exists.
+2. If not, you can download the template from https://raw.githubusercontent.com/Sage-Bionetworks/synapsePythonClient/develop/synapseclient/.synapseConfig
+3. Once downloaded, the user needs to update the fields of username and authtoken. An example is given below:
+   
+   ```
+   ###########################
+    # Login Credentials       #
+    ###########################
+
+    ## Used for logging in to Synapse
+    ## Alternatively, you can use rememberMe=True in synapseclient.login or login subcommand of the commandline client.
+    [authentication]
+    username = YOUR_SYNAPSE_USERNAME
+    authtoken = YOUR_SYNAPSE_AUTHENTICATION_TOKEN
+   ```
+
+4. Authentication Token can be generated from your Synapse User Account
+5. After the changes mentioned above, the `.synapseConfig` file is ready to be used. 
+
+<br />
+
+# Pipeline Execution
+
+Once all the configuration dependencies are met and paramaters are set in the `config.yaml`, follow the instructions below to execute the pipeline
+
+1. Activate the conda environment: `conda activate sc-virus-scan`
+
+2. Once conda environment is activated, trigger the pipeline using following command:
+
+    > ***snakemake --cores 16 --configfile config.yaml --latency-wait 60--profile <Slurm_Profile_Name>***
+
+    --cores: Cores to be specified for the pipeline (Min: 16)  
+    --configfile: Path to the `config.yaml` file  
+    --profile: If slurm profile available, specify the slurm profile name    
 
-## Handling Multiple Input modes to pipeline
-Currently, the pipeline supports Sequence Read Archive (SRA) and Synapse AD Portal input files for analysis. 
 
 <br /> 
 
-## Important Note For Synapse Data Analysis
-In order to download and analyse data from Synapse Portal, make sure you have the `synpaseConfig` file located in `~/.synapseConfig` directory. This file has individual Username and Access Token in order to login in to Synapse programmatically (Automatically taken care by the pipeline) and download the data based on the user input. 
 
-Additionally, the user needs to provide a ***metadata.tsv*** file (present in the base directory of the repository) which consists of Sample names along with its Read 1 and Read 2 Synapse IDs. The pipeline will use this metadata.tsv file for downloading and analysis steps downstream.
 
 # DAG for the pipeline
 ![Graphviz Diagram](dag.png)
@@ -38,13 +154,44 @@ Additionally, the user needs to provide a ***metadata.tsv*** file (present in th
 
 <br /> 
 
-### Note
-This is a developmental and alpha phase of the pipeline, upon completion a Python Wrapper will take care of every runtime parameter handling automatically.
-
+# Pipeline Output
+```
+├── results
+│    ├── kraken2                                   #Kraken Classification Reports
+│    │    ├── Sample1.kraken  
+│    │    └── Sample1.report.txt 
+│    │
+│    ├── cellranger                                #CellRanger scRNAseq Analysis Intermediate Files
+│    │  └── Sample1
+│    │     ├── filtered_feature_bc_matrix
+│    │     ├── raw_feature_bc_matrix 
+│    │     ├── possorted_genome_bam
+│    │     ├── possorted_genome_bam.bai
+│    │     ├── filtered_feature_bc_matrix.h5
+│    │     └── raw_feature_bc_matrix.h5
+│    │
+│    ├── count_matrix                               #Final Count matrix result
+│    │  └── Sample1/
+│    │     └── count_matrix.tsv
+│    │
+│    └── kraken_reports                             #QC Reports and Plots based on Kraken2 Reports
+│       ├── Familywise_tax_readcounts.tsv
+│       ├── Specieswise_tax_readcounts.tsv
+│       ├── Clustermap_Familywise_log10.png
+│       └── Clustermap_Specieswise_log10.png
+└── logs
+
+```
 <br /> 
 
-## Contributing
-The usage of this workflow is described in the [Snakemake Workflow Catalog](https://snakemake.github.io/snakemake-workflow-catalog/?usage=maxplanck-ie%2Fsc-virome-scan).
+# Results
+The user can use the `count_matrix` file from the results directory to integrate the downstream analysis using Seurat and ScanPy
+Intermediate, Cellranger barcodes can also be found in the sample wise directories under cellranger directory. 
+<br />
 
-If you use this workflow in a paper, don't forget to give credits to the authors by citing the URL of this (original) repository and its DOI (see above).
+# Note
+sc-VirusScan pipeline is under active development. Please use issues to the GitHub repository for feature requests or bug reports. 
+<br /> 
 
+# Credits
+sc-VirusScan was developed at Max Planck Institute of Immunobiology and Epigenetics, Freiburg. 
\ No newline at end of file
diff --git a/Snakefile b/Snakefile
index 6bf420d..e15be4e 100644
--- a/Snakefile
+++ b/Snakefile
@@ -4,8 +4,8 @@ import pandas as pd
 
 configfile: "config.yaml"
 
-accession_list = pd.read_table("metadata.tsv")
-samples = list(accession_list.Samples.unique())
+list_of_samples = pd.read_table(config["samplesheet"])
+samples = list(list_of_samples.Samples.unique())
 
 
 include: "rules/download_samples_or_copy.smk"
@@ -13,22 +13,25 @@ include: "rules/kraken2_mapping.smk"
 include: "rules/cellranger.smk"
 include: "rules/extract_bam.smk"
 include: "rules/extract_tags.smk"
+include: "rules/report.smk"
 
 rule all:
     input:
             expand("data/{sample}/{sample}_S1_L001_R1_001.fastq.gz", sample=samples),
             expand("data/{sample}/{sample}_S1_L001_R2_001.fastq.gz", sample=samples),
-            expand("data/{sample}_test.txt",sample=samples),
-            expand("results/kraken2/{sample}/{sample}.kraken",sample=samples),
-            expand("results/kraken2/{sample}/{sample}.report.txt",sample=samples),
-            #expand("results/kraken2/{sample}/{sample}_classified_out.fastq",sample=samples),
-            expand("results/cellranger/{sample}/{sample}_finished.txt",sample=samples),
+            expand("results/kraken2/{sample}.kraken",sample=samples),
+            expand("results/kraken2/{sample}.report.txt",sample=samples),
+            directory(expand("results/cellranger/{sample}/{sample}/",sample=samples)),
+            expand("results/cellranger/{sample}/possorted_genome_bam.bam", sample=samples),
             expand("results/cellranger/{sample}/unmapped_reads.sam", sample=samples),
-            expand("results/count_matrix/{sample}/count_matrix.tsv", sample=samples)
+            expand("results/count_matrix/{sample}/count_matrix.tsv", sample=samples),
+            "results/kraken_plots/Familywise_tax_readcounts.tsv",
+            "results/kraken_plots/Specieswise_tax_readcounts.tsv",
+            "results/kraken_plots/Clustermap_Familywise_log10.png",
+            "results/kraken_plots/Clustermap_Specieswise_log10.png"
 
 onsuccess:
-    print("Snakemake finished successfully!")
+    print("sc-VirusScan Pipeline finished successfully!")
 
 onerror:
-    print("Snakemake has failed!")    
-      
+    print("sc-VirusScan Pipeline has failed!")
\ No newline at end of file
diff --git a/config.yaml b/config.yaml
index ba72732..89116d8 100644
--- a/config.yaml
+++ b/config.yaml
@@ -1,4 +1,7 @@
-"files" : "synapse"
-"transcriptome" : "/data/repository/misc/cellranger_references/cellranger/refdata-gex-GRCh38-2020-A"
-"local_files_dir" : "/data/manke/processing/momin/virome-scan/sc-virome-scan/data_pos_control/SRR13114612"
-"kraken_db": "/data/manke/processing/momin/virome-scan/sc-virome-scan/db/t2tDB/t2tDB/"
\ No newline at end of file
+"samplesheet" : 
+"mode" : "synapse"
+"local_files_dir" : 
+"kraken_db": 
+"cellranger": 
+"transcriptome" : 
+"scripts_dir": 
\ No newline at end of file
diff --git a/dag.png b/dag.png
index 276925b149664d477af910bd00c25d861bcc5211..0b129992c2e72ad7a5a71700e17902e495a48b4e 100644
GIT binary patch
literal 24447
zcmceeWl&sEx2DlRaCdiif;$9v2o50x57xN5TjK-|?(QxjG!O_*f(M%5?mma_-a9pa
zW_}J;DN@~icJH(8toK>(B3eUD9vy`Q1qKENT~R?+3;5ju0|V!a{08`69}d?T@C(*e
zOI{kLc9Lul28IeoQC3RF%k(H0F_lyRcZBh$3Za#i)t6Z=UcMYo+sv;O<~H@g?|%M7
z=LLR-!vFT(WOUX3I?G+W4)GJXFg06l^57$R^5B~}R-%4<d|boQ#QS89iJ*#k8}Shm
zYV`|LRZZ~`LL5PL0vjO;@#Gc&Q|k@&uhzitJ*A*Z;KdUOz|(X5F?)Ra^VRb5@emZb
zkMpvUPxE73@`Tc?plkV!FdHtbt9wjtNyP2M?ETDw5zQr$ZvKq;oVT|Wd*brV-Zs0B
zhlh}yTB^}4yGpU3T_<w^4_Zf$b#J$?(yw1^WyohU+Rb>we8CCSjG%3X);=LvpX#6d
z2&az7GPQz74?CWh&|704e~XM;?RKJ3CWAlNn|)@cOA5W7iO(DB&fF=QD>>-H>n^L=
z2VLaXQY*&j;o`F8j3fU9*>L$SH4jv;ptofAmz(L!SIkARnpez6+V835(cMb?PX+uw
zat4t-M{t^8MUYLxq1|{UGRV5famkjJi;g0ifi&60f(kCK*EF$>{Z7c6D&KFILrgCD
zXikelwVwvaS(V-Gb=)<{2^R<870mMT4c=pKTGme*Ipc<*kt(V>kd0z9AD<Aj=isx;
zX>yZQy5*4|xe}9$!t|efA(j1WK}Vba*e6sKOs#iriwaGTW{6#(s5kMK&KH6e^OELZ
z_&l<sF-T(~Xg5C5By%to=-G-<d}6j1yY8UpNM?*BO5NAe(3Sb+6DT?wt&DL^zEf;h
zpAPw>nAok9<HHmKsL(jI-bU}_z`Rx8tKVZ9W<1u50{f6wh=ENngC9EpnV5m5q*^q(
zs6AtyODQ0s?AO~^VHJr`J-Rl3NYE&XI$uwYGtJqTt=N;<{=A4coDipKN7|f0&6S70
z9^ViLkU+&OUVA%FTNf|2b*-QQbz>bXO#QqB3fgsFd1m9w;svDlFH2;8R2dy9zu)~5
zE9ic*d9Y%VIqons2$iMKU?|YXP&3)$G#U?4rz3Q_?&+pCJ=R<!OD#|QjfW}r@c~cA
zJ74^_9B8?OVOv)R^Jy$Y848QQU7aUI1j?@SrrW1oYOyCw<21|j^Y^#p8MiQcgGMAd
zl0aT`b+G7L%}Rw>qMT7mR#B)u^ca99ByK+R{quSgA0G&+&<WZ`3CE<&<M|AcJX&fg
zBH?Gt&;LrDCmpaq$2^uN*2N|E83M-Rx6@I|e#fp`W2oDVe#9q31cL9WEoL1#jwp)o
zCzt_K%OGQKY>gzkUG8e$KR=1IIIXWq#y;wm;6tZyIZZ`<p6>a{h25gw$CJp3i;Fk=
z-Z;kKDb7DEX5IHQK~V8oWc}|iT|WDse)VDjC+Y`eJNCv%ig+HQ)$>~a%2UN<P{B$P
z|4^;3(`2PeBJ9Q#j!LLzoWiQdan?2zi8))Un$6^W4(0PaHpZ697I0F_;4mpP3%Cpa
z_w%caW}*JI!ytcqMFN?SG^2VRUJ`*jm0Yl32$^ssI_dj1r}a{u3a#n>V0gLD9&}1{
zeZDsw^h&7^Lxh)nW^IQ3rIsrEkns#o?d*3BHtW6qgS~IiNv2N!4l%p!PBnwJmG);!
zP*>YsWOg(8?Fsnp7vfr-*42O(3V!8FXgAwT?*dJKf=YI==vK-ys^t`ri+Dtle%bsU
zty8JP?9w9!RT$xFtTt?k>Giv#dE~Pk!*ijPcDA_QpI5$R(ka)_X|~b)#witou<0ow
zAu)|%9J(&zwoA1%0LG2hvp-vf=G*_8t={&veR+OLrIAC4?Eje~l!C*kreZr&Of5N6
zsmoev)K=@<3wM|+;%PHgAf;3PQR?jEV&|83j-ZPyl57Im*Zuh_`FK)+(q8`u!#Y@F
z(sy49Xyjt18ZE~Wj2CN7io)LFKEnt(=0%{B&dgP4Gs`ECZAJ{DBY;6WlTV?muu=&j
zs@d;Knyi1tkRC3#InjtI=Zp6cO&qUw$;XrM<2W2H)=`RipUVct^bK(|o3D1d&$T)j
z?XUOsof`dVwA>qxC4}RV3^-U|cX7qzFwV64nJLxdd&6+cC>@3@A-Ptpi2Ds*JR;w)
z&5>P;xf!+5Vfmdo{AIxXrK0i6^^wt1qh;(ZIV|$Wt#uptFKg{CwC;ARnM?DmG-Dg{
zMx<}WlZ<Wo$UgM=xG#0Ovs(Vl)O15D-1;T)a){;i=rSCGPm@e*$PBg~PgixrLx8ay
zO%DH1XUbkk0=-!eBqWbOE;kO1ikZ|z(5&=2+bpC#q7^zEjK5lTdhx%5o1%*Pa*aa-
zwfGVD4V(5ovKJR@wQd!`YF}V}p?o68Tmd<7zqlLH;PIhSVfXzgYy<(?8S-XCY|2*0
zweCMl94os-X;caiFeiCpz6j;5NsseYdUzrpUtsBJ1fjs(&}8;MR~s}vPu1@H%8#`N
z2bf=mPNLwmM3G{g|C=Cn;ca!$PhiZuUXwwP8w<gZ(UGGgl?do&iYWinWUc=9HiOeF
zrf*<cJ>O8=Eusk95`Xvfrrl*LhMJ-R6?)S5QtGnxWBMzvb@d`l)?}`Tk?O$JuRO6L
zxmbcH81FbDZe)$$${nC>vRWO4H+Q?!MZ>bBVE9`^R04e`{oN6!Fw)brt&u|Vs7Hkf
zE)?p0S_he~jo7g?R_$OoMA_yKe!(`0QPs#ZC3~}Fu~AN_cfhB^Pw+mbofE+VTarzy
zKN6EN#_eqq`8AbTaE^$l8UlT>9<b@!N@Z@@oz}W9wU41_LKF!859fK(;nBB4i))Zv
z?$1LNQI1h)Q3bn#{qf~yT^<gsZo5p-3U;GbJaQO~Y0cI<E}C~6(mPCC9})JZiz4wO
z2-ppy6rjlGT;_vQ$@I!_KL?KfVxobHk?Z02P`((pJDV4PSzBrG`@3PLDTAo-2UH`l
zQH#Jc97bjvPC<T4&9<L<%~6HYagyv1-*^Md2JtsCmSQp;HZA-N1$3844E8RI-~Rif
zBzBxncoV~C2)r**m`y@6Y!Z<-6-Z14oH~z;cBLSZ3fbp??)t$LA`7D@O>1_B2y->S
z>)X-QM>E14t@U(8_1ewg$AJ{6xz4H3hg#ad{l$&*Ifd_c#Xs+#Nt-QGkL~1w9sW!x
zfQwLM2OJ#L;N`?Zv%UcQlo>02WiBWRRQsKHA=t$=>Mur$vPu>>i^_+pMN)on8rb$_
zz)=*19Hoo>xT+0-#bod$`hm^va$(#TU?MC2kVA$m1f9&B`!oq0a!5(0=BWeq6dH7T
z=~&#-A4}kDV~%hNo1)7K2{)*Eq#WZf5tuQwnnk_Oqtfu@4xMiMX@mk~Si<J9g5sz`
zbSaA8kA25Y0jV@63Dby4FHbYjC%;@Rntcig>l<*obwY@CWUt}{x?4v1zF6+TEczR%
z?HkZke!zY78%zqef=C!Hwhr?SG#LgOk`Jn);bi1*PQlOL6DiHy=pwA6is)sbdF{*`
zrrk{GM=*E=BYp58WPzC2G+~*=z(a5H?-128y{rljY+Ykm`R;Ihm@a-Xf%#Abeigl9
z3Il$?K>QX5H1l@L8^JG*UKW8A`0!6muqpMG%zo7MCUq{HPzd&i4)Dd0hsx#O{1saZ
zZm3mX*Cx|ug`!M*oG|7`cp5)e7|nNTPd8&5O<@plRVY1j`X@;IzD@%4z4v{jPY5RT
zcP|WOcSJN<q{PQ}@d8gQ1YIcW^@l89+W6&8gN-F_8m)*$Pj@%)e4aR=1K0kb657+2
z-bhA5$W+;v&|IY3ajLE@HMl=oaevRWFqw>A5DzfFI<(pRix2Nkg~I&&u^T7mPKD9>
zj4CeFaYW$qJ933l;-m{lN5iv`*YGr$jNHfGLg4=Lymi+|%^(D2GreZh)NGwz{If@W
zpXF)DiU*-i!ape_5F`6rQ}7V+SU{BDY1)lU?UyG)5!b7J4@QgtFe_&Gr&8AO<#)b9
zJAzYaPthh#&UOkgJAQ8@AV&}QoY(E%$dwtio2&npOY_v!(B7_rS-UtY1dT_#qLDu>
zEK@4)LBIUkKozorw!L#}qNqif+WPmUpE(XH5GJ<4lIM+J2AR&dj$}3eJ#;Tr#(AFX
zh}wbDKMmeM?||!kO4{;@jhD)RcdIVw?(UAJ`9AUS2)8>feD<p@MdT2;h&8Q*NmQlY
z#PEAD-ZVvjmsegFS(sM^{_iH7I=MhEKdI_GNjRa^2?JJQkP#-V-SD^Do2S(x$jw><
zWsc1Q4)`c3`Wi7!PyE}>aceM!$k26x?shZ6LrCk@pI(O@TYuO+o=$(8$jz#tFM~qr
zqhs-IJLp;wq6J(ZA8M69PK~16#f)B5TkR;?|5?QP<f}c3+;Qalw_d<Ft{9Kj#Gs`j
zy66}<3`h@PgbPncGTOegpj~U>B_!Uh+v0D=rXHkoY8}e`IW!}44fv8U#G|QA(BeT=
z;7Zqe#q29ATy?T299b>*!>#wrlhg7&+>E8$!^fOW)^2u`z{tcTm0N>Q&llqJeyW>)
z>vrj;U-$#}{w=Mo;Hf)UL&UBMsuvT<>N66^J2`(^K%M~glVpkOkWRG)8?myKMm8FX
zHt&IM4k11-7;9}YK@*ap_(FwA`VMcx%ziD{3`a0)7XPiV6d`V^!X)^ji?tJmAyg|O
zXBMAWaBluhL=N>LJ{NH+FBGi<jcnfzUS<+}fRc$eMhuEDeuLrO5=?CkaYs~nvkf%N
z0Uz19)DPx`cET})f`Cgif@Mq`0O18PflZMT0xliz|5p2s3uvo0XtW>)xYTk(LywdQ
zXiKmEv&JNFDUWk`6*|yXE$c@fCTrl*|93aMl~Mk0{peca0XkyUeEw%vZR&`$?orqG
z`6uqdi}g>O8>E!`L^kv0uU7LTA~s*Qz1a^|>-Tvk?k<Y$(mE~}i))`yt2j=!5s5*Z
zCz9sRvm+<v?nCaC*)x@{rYs+LI`+>^O~KSR=NQdd5_TJ=!ah@tdjTJDxV4C~M9bjh
zV#pQ@rVGwRWGHleK#L36e3n1W%O;o&d4yVya~5qosC0s;F<El&CU1E8YkOyGT|2K?
zWjj#mK!zO1_<&;7uug7DMXVS*#Gen*N||pCr`Fq|cVgaRvwRy-fzp{keM1m5zx1bk
z3B~8-ICf}LpVYJ2s`f)$M!E&0r+EvG&-XlYsM+^mf-)cxR{%#f&xpF5Ur*JS2*huC
zUdkhnxl*JVdj0ef^k>YrTyvakZ4R&IizTGxyjaDDtb~o0F{AJ^vjyaHsb(t|aLz43
zd=9nKKju`PexFr1jjKlGv_?N{9Wu0xzyFH-f}s6Zp;mW9eeDIDuy!@Clsn=h&L*K8
z(3>Bghdj@#jjTwq6^TinT&k<S=kj2z(GTw0sFsX{I~NmJvniRh5DOSN!8Y+x!lQ)?
zXUd+m@Hb?R!lvevsZHaJU$8*+Zbe9nt9_2V7Z>%G&-j;997eCDv6AyvrEO<x@x*O!
z6zLO0^#tVxy*}J8V3iM#K?nIJ&DPEG;LU+ee>n~wW8R&B$xGld7nJ0x%GU047@7UQ
z#_qUbaCStg2mUy6heyqYF)kq2FjW`(!ANU}XdQb|K8`TJYV}o1f|9&0PLQmaKq9bO
z#mW>wuZxpIs4y>k1X!(k+H@VSdnAKQ^Vft0uv&jHCmX-+5#@yPoqycGLf^qttbN@h
z^zw7A7eHGpt}%3rRPfN=-d;R<CA?0rGnx`*#$S;*yTSpUa-g93%pDXcptZ_?2iSCr
z{bF^cUahgB`@up<G%lmo#lMMpojV!g9%>2yd%k!wp=6JfHC0ZtUOWLUK)h6dw#U?t
zEFrm_3eRwPlD#(5G<GZP+^YHFxg>lx8}$wO5`m@l=J4x|22Kzc*F0hO7?uy!3TK<c
zML>W)3q=05Kr5+0dy*p2)EW8aWdxn5cZYwPDlEs-U-eg|K~rf<o^c0A^EIgd-C)t|
zd1AT`#Qywtb5VvZcJu{457+Fk(e;l6a(l#|6rjhzyYp>k5ERn<X&42Cn5Q_ZyBu|~
zC_&=+Hk8MDl5KzZMXypPS}jLVO2p$3i^}3Nvu>qM(9y3{W?bD0t#BYr_z4y%`96-?
z4(|;}l?s_ij4%a92`GGfm0sP<Oo?*E=h5WL=O<sEv(50J7TIVVJZ3FA7jmkefG1(O
zc#^a))aqa=*feJCA0#f^C~hZfxgN(Wia;z+{U~ldNe0Ao1SXwsiqP}&i-j7au(=B7
zzk_@hKhXA9y98D{Tq9{@qc-Xzlj#(tZRD3*9e^Xj`gg@$t@K)rk-+`=HY#<pz?a{r
zNKY^vzSoCv&HV_PUb|D@Xu>t9B%C*30Ii&-RjeTO8kbFdlbP-EJYfQ)uG=|OQ3;Sx
zy7aY_TpwX{t3IeongY5li_1LZ_UYl~<P+ZSChNr82~%+8<=(8kirdzYr?XS`<@20c
zK{;S{Yo*2Q=9rXHnUbQWx;&0>V3tq{D$V+Oqb_6o9<Ei3NuxGyj#rE7%=%*TxuP9b
zJ6rHUvU@o~u7F^ydexnUXdv4az669;x4jv;ptufLH)c3eZavBU&#bTV5MU0m<%vl@
zzH&h)MWKj&T_{5Rvc2(hKmaD_bGf^a4%coqkrnM{f(>0yVN@r;?L{NziAqJp74MJ8
zmWqbH%0)os#Oi|Mh<RhiZ%)?L!%^@H0ez$WGn1R#XHGNsKk+tAo8D(&RqGVJN9R_e
ziqxY;>mcD&H2pyiX$ZSL{KLy)+T9N0aj;NBBM>17hrtC%>`W|gYD$TK;@h(=Z9o)1
zNhMsG4}>7ntp6zHw;W6TG>XZLI8)?vwcmj*^yRzkMP1+Xxqzm}f*4u{FQ)gv$+2`o
zsaU{cW()y43zcjtpnnQwAPs|XkXL2@cQCw2EmwFtm026%vNg%rn<%W0y3m6E4K}g2
zuogLV#rxtP{uPH&Yn)-Tjg;+dsk?re1D(91X{VcQ(&X<oCL&@kSacO45NFWuuhDsu
z7^}do6BYn6C<j<wj9RD<Zrc;t0&{@i#m>dPgC%(;W#vtvy1BT(#Y~40f{|O3`0|?z
z`!A)amn6VaKH&}6DIflB$dz6zlE)<B{`4KQw*NaZErQH(91iEpDn6vAyTbA7ucQ_B
zwo!L%849mJE-2`1Kb;>qrj7{&*W9pQ4>H_3$3J7hdF2?qrAqjEEC~P~srmo@ktBAg
z=Agl~@R{)4buN>R!s^d}hdt8aD6A~t;ZR{jj)C_Oae8s#D<hlkkEOqI9mEcGWPQ6K
z-G_S<-TR;!^;2B-ue5zl-tL6_dDmIU?f@x@=7)9md}7d1*DtR4pvODk@q`bCV;KVZ
zyJKb}qbJ#v;j!4kS^}frN_@T@OdlIv9{%<}TUTT$Eh?{gI{8=P9{!}nuwZEU@m?^Q
zbkD(aKa1xd*U^%Xw((M<1qF*HOSp&~T+hG5(GkA(9W_k`vv1$$D%7PW4!AU_WgH7H
zaz8w6tQqb9_M<g_No^NTve{hUW|ob@Qmb<<>n}JK*<0Bg*_^ROWzqbppWxZxF5fn~
z$OUEalq{G}B<@bcIO$^?b2~HvpA#-PWtw$8;!NawE6vT{wvp+SYLR?3*@|&M>tJ2u
zX*|4Q<t(@EVlNz{8!epOwJmY4d466Mm@C_Q=d<(hRjVvkPG&@8z2bvjXtVYt*nUUZ
zfuCCbeJ$FaSTm93#9omDB1W?+Q2_Y*q?0{>nCIA9DMh^X*quZJR>m<X#iVv~=B{k6
z?!v>xq%+RNW-2q^c;W9P;)BOpsl<CSyo?X!c?kgy=@aDqjV43j@des?BwLgje8@@Q
zqcroZ;F`Lz{jx;h^ZQjp2L=@{iysM+xG%Mm=7YO8&I<Mq@KYmTQmD=RJeiPl;(N>`
z#<88T3~(npQ}w+eJIZ8kK=MLeH=9n&Nm4!vfpTTIA+I|Z)XHbQ*O3kX(<oLFo^tq>
zRcZ-Bbeunt|K20-{-Sp_7rWVCU^3bk>%IbEqg1c&fohiMzk03;=jhLKtwtNx7W<YD
zL5?E3gI^h?pTZ2bnF6FOocQ9Ghr#xT8g29b5BIrCe1_`3@_Whv#5o1+z-Rh!80C0y
z0UcDeubo=gR!7En&;DF8#{VM1K8f4IU@{KQhTc+EwjfsN+|A83tE$ba48=z@?`=ia
zNtsXNPz%J<WyeVPKPvS-b*B5R2b6M|%S@*V;WHV=ot9=rl*qC%OGl`)$T4dTbIns=
zvH%f<bDmX3t+87$!7m}&OWoSEy#05Rm0uk_@sIul#4^MS({a?z3Zm*(qz#zpTA7W2
zvsd9y*8RVIKwrRlCV!1LdD;qZ+y0#YyJECk^b+d{d<o~VidKG-H=HEBk~W7-95*92
zsm*3t5|+eeZbgt6g!&#MFaJ>ERE|!T<zF^Ap8Eyv+TyRN^?o|1ZLw=l==FPM069Z9
zA)}T_xkipta}DxgLg+@H%Rss_W1q5EJ-DE?UdjiJybKgYHKes~Tl7^2Dq~d6&+m}z
z7C(ytq&L2CJ4U@H0xxY;v;~MC?ZislI~Wt!-Ujss-ryem)h8UeZ~wyMb1E*}_(Bnm
zOdP`StZVAm{nv63oIP*eTGz5U%8=(g#<cv-q-+m20cAF;Z9<NIyd-)0XaAQ^kcr&}
zkv3D!jPz`|c`pIPlk(jwgY2>+-)m?OkxOsDlbSaQLm`Jhs(0ng?g25VNG#$0{pGsM
z2&M#<?iRaDw*ymC91)<GC_B~v4n`8Je|;}-CzTf4`w3#=mN_!)AYnh`yXj?S>~Uwk
zs++}s*Ur`Cp3$vyxdUy?{$ful<LKseb<&v2k>|@&c_h*;XgNvn%LdoD_T)^)EUEGK
z4jZ2(FLlZN*GVG=F6T!`yxa31?L=E=%<*T2J>KDO!A0?R)vB@YFb<ls)yRDnrY#}}
z)h%Trud_HKh(PQx8dXEpzn12f2=zO3V>zb^|D@m8$KBT(qIN|`Q7=N0)aJ=V-16UJ
z{AL~7{t4_M(no`AZTMWg`lt3zr6V+*GED+?T@rUO8OPMJvw(Nk?}Fp946~9M5*>Bs
zv*tq+h4VzuOPYy4&2BVE*q7>A%b|5lVi4>%WW1$#mPEl*l_vKg;3_nnIH+IEn2v2t
zwt(<64yaL60MxfLxL!JV<oec%$Mg~6qgNICY+~d%liHB(q+#SfsXVOYGpt1;Q%jFt
zLt0&w)n`>$_%654|HA#=wR^k4>r9Jzw=KcDxq3#!q|VI0_+N`&tZ?jOYTS|=|Bj43
zA?XCTYquUIHecc*?2X4VH6UF$aptS@6|0$9DH$VC$def+IGmP7Mh#nVALvaxZsR@;
zM=NOW=*}tC<oOVRYPx+d`^8AEPD&+X)bbHDcc(+!HUk@!**s#eJPdel*lP5>O!+LJ
zsWYi;;g`5J5yq^$=@Sz2w<Ad#+f|ePC^3XN-6mMW*b~%O*_K5y^H*X4a`1uNP!d7S
zaw2|bPI56Dp=3I$Q4=a`e!C=-V%{}2;G8IIa}w7~CljBu*603{JqWg+mx1p*E<m+r
z?@|-OtyY>V&mXlnZ(FVX1c>&@Ec@#dw2lvA8cmm<<|{Y9$IF^L5CUSW$CVS;uQ5{n
zhH8l6QMzJ=r0Jm64(Wjt0`A%q49xiJ7V%?VuTm?GPtJ{ms}TWEm>+b#iBU~DZgcM4
zR#;T*mxLM9DybIRDm=t3AT2=<k2@|de<@h!X3U4o#kzJCKKzsPEppfBaO%ZE*LT&O
zDz49>#O0L*aP2b?jEQ$q?4=EasMnv9^no=f%virIgMFmLKv>1HmQ(oqVbo*mTSrx;
z_ARn-4qlDi&S_Qak{5S<8a~WgXVctJhml&ne_!`Y)MhGoRkN9(3!P_G<PpdIk{$1A
z@7X?*t`xpA-z9V!>C$&ytZ?Eg>vM_H`LQ|hl!EOj+Loyf-O4Xu;mivxNWWT$`nS!V
zsxLa7rb7f$7x}kvl`&UyCGkAxHEmx`!QW?4qZ_vBWHACvJk;OdKpuj$)}w$a5qMdC
zHn6wJskc76eCAoBns8Z#89q)pQDuU~Aghp-Ie1602ONBbO^lS$t!idE1`AL6WHJGN
zd$uQp2zDq=moJlTE|fL7WLE`cy?gGln5Prk%?B$&{MO>Mn;nPgUC`gb50@6;DD{Ko
zQSl@E1|w3YtU6SDx}mT=;-|^UZi-TWapl3|f`m19|90dT#e22UJC4MoCzhavW@E}7
z>Yp~i>gs8$asr5bn_drCxGGNmn8U3jKI`HqIM5w6u~Mm*W7<$X$Fu#KutBiz60<sG
z-^Ehf+oR=U7O0KyLBv5ANwgj?IqKAyN{c`+zGT{Uh|@6QbFRZ}^SxM$r!$l~qe1Uy
z<0ud~;|>fxI1RI+26EQfrSApLkAug5vs(RuVnBg0C<ev=HD#x+M#`LC_+r;gf(L2^
zOK;J0EGh1|8z9`ic%CCUgC0o)A~xq8XYi!Te;(0XYCY@Z^8VS(lPdVt4ReqP)D)E5
zVCqR_cDiV5*fa;iU~Vn^kv^CFR))hMGSe<W1Pt#Sgt52O$F)7lxjM~-)={CO_@P4t
zOsgw324_3Z%!&UX*ZG7^3>p>WohS388Y#w235*-)`5!NUx<crSW!brIiAc*=YJoJC
zQ5H`m5F6zuVr;D*)AyBk_Ew{Y+Z)AiyX|7zu+BmV`nqV00{83_MZjjgr*ZcljbBJ3
z>q1Y{z@G<`j2khyU%#Wz<qGl2rc3U(Nv)Eh-EZm6jC&%Gc13bE2zbx+fZyG=L$Mj5
zZfP^kXjIk=;(4?rw>_T0Xl7<MeGCi#W~#wr#OCS#D)~;z(KQC2mErMsi85g#TFVKh
zujR31!p(=%XB62PnKy8e-Fmx3a6f@G#T1a^U^Zy{tW#?&w7*b8Ivh{BSTPie3VqGF
zHQUb4s7pN2`IWTTAl?Bu+vf51jL%_-FOs1X{;rAfq(V2eMcV8y&S<%Vz@Az@GW4QN
z<i^%F_g|{0HwZ{vvX-djX61=`OQRC76#!a%7WkKYT~Y-Oe17~o7?I|bC~55h<cJd~
z#C&AO)7gt$cP2Fl!<NLcrcprF<o__Bb!Gv@|J>Q+tD&qpnZj4;$5l^3)a&cT?88r|
z;janRZ!!<-<a>7)J9w-g*rw|{Tz6*b&4+fckCszebXiCQovCzd?7X*Uh@n9Gs1Qge
z#^70<to0!1qY!ea^!QvA0@6^cT;p50&2%B3%ciUnm@0TGTBppQ$%+q<uiRrF!v=QG
zck%<ZzDHrpeI?{H)d14Hwtyhq6kY+h*v%I@EVpWYlMa_9Zmt5lU+73lN%@L2u8voY
z<|^ibTOXevP6`ti>&!$xfB*F>QL9vi+3~qTyG-jx9C3y3&GAB`-C;O6fC@^HFex-<
ziWP^i>gBPGAiyge@28oyOZ5ZS`vUuj<eZD70v?V8xC{LrZ<AgXdkTXpPC)ZXBCqwN
z29O-y{T_{5m{?S*s3^pMR`mVMPse{Ny7P;G$V3_^wR_5mpVkOCzdJBv0gp))m5{9f
zNCYAf!Mt-=l0^q#Yi>5JJch8}Ef>GjT8_uzZz*6XKOo)#3fXpVrbMUlv!c(-vlx&>
zSBN8OhZXm~r;`kLxUS(xhv5To$hTKD?xXnzi_d0CGENW-XxnK3*w_LI@XeRy7JGT%
z-ilYdJW(OvDEANxYK=P@gHSzQP6A(WH;OPGd$dZF`0N+hU?riD1obbWYPTEzCbAI%
zshoP9|At6Fa{q{Uoqn7SSozX^=Zq_(HxQCuZi6cHMaCbKQoK3AC+HqXGk&7moB9S1
zYZ`=}4df149Z}?;lGu&jz3TJ!Hvxy;j>O?C;Bk70gTTwrtXcV-1-7q(5q>8FGR-|7
za9tv;e^Hz!V--3AnNm5ZMlmq0n-bXm^Rl4bd~S>PK>-8h!I#KMz@jLJ>j!pMj9NVL
zY$NA2kfVA<Qkw$6$?UQjl|&7!?M+V@(*jA@GXcr9HYc-Jj|00w<9EXo;Ii-Nh)e}#
z(&4X|N35&@={?$SfluF&Uop)vkW`AJYFDJ5JanIPzU5NM<XT9bA~**Ki58Hpm!lh*
z2-QJxpUe|8`W@G2E<3DX&3XL<q<hh_Bm#Sh-clbIvl5Nkr8V4gTco$o1%7@zN`$##
z4u%ubdb4r_`!?rte?D=!Xux*Ym>&$RM>AO*IjnD3=-ect0BhKgMFyD^!%fA0djyiC
z3-(wIW$O7Hg;X<%uc@_fhNCCgB>-rW1P~H7m{zIIz~ax-=m#K2Pxm221L+Vn_ip)|
zQrr(~n(#;`1onL>FfOx{fsf|lqFlb3$OW)UDj&JCq`>J^JTix_pxd1v@uaWj1pvw6
zx7bWe$Gs<V;eykt`VbE=Hx&Sqd?VqvL++D0d?*Thd8Uzke7yMe>R0I0<RTS|BQw2P
zypQ4BPc>2k#{Px_GGEFX^)4zx3FDXz^qZ5KX35;f@lRvPm6oh+keK6&pi(m3TmP45
z6PU^sXQhNHXns2u*kTwah*Hca^)-Rb1XVzvDN}bsoL+O3cNgrOCgd<?(xQc)#q@i`
zaRp&KyI7q7Ipg7Y0jD+5q(<3Tf_Q*2N$J0p$~#6r2hdsUB^E5~v&`pw0FTYTxqTzR
z9kkx=Ql!uk@N~6ENi~8v)#7nvsQEk>exc)c#-^0UQL~>zCLB=HoCEBoeG~9j!*lNs
z2d3wp6PjPGN3wiMU%lXF`e)GjlU67|vhUquc)|*w{qD{yB8*i#LloN0hu&}t|87G+
z(nj?LHmIE4N8gl9pZ=I^451!gh$hC-@I(bNjdQ#6U$`)`ZLkF`{{WN-SDjw0v5%Nr
zUC95wIdfLfh*2HPk30NafsF4kJ4g?48GFM}V47A71L`xnu`$ZEN@Y+b;U*r!p_xIF
z<*cs$I1D#L|A8GapwJZxMVtV3ju_EafU;H2;QK;i@tA1}@fKWR*)9uR=iY<dcnVo*
zsA)uLs(8+1J3~fSYK+>L>=&vRkl6Io1|H$};LhFo!L%_nA)gArU=qzB6>Fa+@<Ni*
zVLt>#?O<hw(drIXYD*@OIpm0X^SB@W)?E4AifeL-cqkR~I%nKpf1n3njuL>N=k0%{
z1Ir0rQ$e~_8rK72%<_L`IHVG^vs?_D7Nrshn|;FK7-+(ehNwinhn!<Z2|feJm+vzK
zt061+8v(`#vLiLRk<&i_@#+N3H*$#-CcDz6dnizS=`aix7?&XcV{5sUvV((AFk7$?
zu_uyxo1NB8s~IYS$%Od&gLAJ#e6WXIXvqYfC5!Q3OZ3_a1PB}ziUl&+EdJnD@dryK
zy!$j48aPE6Q@{z{vQQ+%b-yHpd!Ndr`6!j}mMsMKaL5jKU&XWvW!Tnuc{}H^?cRRx
zuIXm&t+$3ZDz>s+rX+1A%fUke=!?@mDUDME8u9mX0Ia@?+~{oTgv)Pn=+2{%xU_`C
zBOp(|RZf5*9S_n^hF^gU^_XA<b63b!2B*qIUmG@$n?OX~tt;G|^qNCjb`e^Hxj1d+
zE7OS18)kyHxvLkbp3Xcp(-nZ6yDoydQ45YI^~wFRRj2<2zD%vId_BdJ=mrN=Y}xVK
zfu0!`^xhraeqjtApp~4Vr{Q3|+FFFP=&}!32<~FX(&F{Y7=yt*Xx<u(bjZ!WOdvwZ
zNWqhs9IDQQ=cY$(GcDu4fL91Lx;t`@rPq3{B-}3Ul_OTNMI_pPA9FwfVPDwQX37g4
zK*V!$Eb9V$+O!5!toV+DeO-5u2$xsGyB&(IE^o0V7BD$-yxc`r!ynts7H2NX9z)Xg
zJOiA$*GwQUde;0sK6@o~OXouc8zF5auV2;tPs!)u2dYHY2D(Hj;YOb1TKzuC{pmBR
zx@agR&)VWAPg?J%m~mty?NbZ?lY@(o)(u_YMdr4!UjGXVNGLhC>F<v~JeWY;GR8(w
zGm*0zdH;M&pN-0#eHw{MJcHU5qk8=vUcJ{3v`6|2IJ>o1&z0rUgf8fdkJlPi$*3?F
zK-=)sv30WM(pcMW-D1WX*Xk==e{}+DUiM}M?pu;Aaf=`2k~Kz55kI@eZ#is=2fT1(
ze~Vah?HZxKzduI}S0+fpxtcq^;E^HyYi`-c*mBspt+LklA{}2@i!~hcoReedIeKu2
z1Du@Lpdxl~L$BJ)vck=A_qVX<qM3GLOG`dYlI*qKJ6S*-;#{Y)WyEB)U4^7D6rbfq
zM_eA)r`4MJsBwRiE07@6;hDy{tNM|mCVCd;HStyIyh}F_HS&5*t}Ica@Dy8mc13so
zs%|RQzQ0uZw=uF-$%i+Uvx2c-YW}(nYbI`->XHqj7&KN8gd<~1w<e_g$YV@g*USdQ
zf*3#P=hA)m`R(&J?}Dg3p@+6x2~!Dyj#2qmb>;7|X~Vhe)w`=$mO~r%1;*dwSCysI
zz@l{&QGDfnqI1yqHhAQ7H<gRQ9|5VLjwe#|Baq{|E2Ml7s&E^gYwU=o_MD>~|Cdku
z2v2-rO{|o|m-U65F<$Jq5UPlcl%dB@8G5A>@Q>C&Ani<k1-Vblusyy^*({^p3Ml2<
zV;8w?eB2EtT{P87eD@MX37``7@EFFl3DwsQ{OP?DeiB-1WDYp_CdX_)dE4lo!*~6$
z0$;fn3_u;typW~C`YLmHVvzjg_c4?Y`c&k;gvF2Hxc0jj1tt44ch&&Jd^cTgDifpC
zYCMC85V3*{0!Fj=TaRaKKHUUwNryH^j<+;?=MmO58j(Q=&u5nat+s(5ywC))fbC7*
z{n=@pT#{!_k+iC;g^hr-ynQvY0Lh_;6YMvb<YviQWldzC*pj%Q3Bp^)M~ibE!whHI
zKpynF1Y3fb^T!)<l9vbAvn|MI36sGXQDaBU>sb9Zg<WQo9Me-(Mt>$e4en{YDxbbS
z{OuQ78ZSXpIXwQwt3s6r7%O+kgQr=!Cja<BkwluBBD*j&y?PzWZN0TW&gYwD+2KBu
zgMueuO6MKdq(2B2*~eZkYNmg}k|Y6t;1E`i-O0hfRx#86S~!Bn8Sn5yG6+VRqeZV`
zE5oGhjiKjei*FFT?jP(^o82!V98Lt(p;8h}WZHx-nzy9bOye4f&)Fk<$plvRo5UxB
z|E#9IQnIoM`#Kcgf3I?J=-CsYi|#!S6xLmK<i(-*!E;Sx^YgR~pbL{PGyJSnh+Q*1
z9D111j2bK6Dc*kIk)gnPH?}C%u=T!}*_CxnK7)=Rp1d(1<ETs7d@!sS@xV^$Q<?-X
z(Rq-Mr9z#F+rRI$NftDVpIr`v&HX)QD=aXFMQ*%qOaY7uzn{u2b3Oal-*Z?`>Q*>v
zxB=<jeN8Q6Qli9WdT2IoIL*=xSB65P?sot=pOY#&3ZYu(+cZ2$cl(~NjwXR}IA!j@
zT^0lHhH+k>ZHoho+6JJNVm=$nZ*k<lo$-#3?$Q8;57UMxVTGBIc`cZdFa7y^-fkrP
zEzNlE{tyoUW665(!MM<yS1mf9-oHx?rGP}oK#fwuuSCbzV!Hk<eMx;Zwca1}WdV~i
z2}b>1jD6l}BFoXgMdxE1y46;;;|Z;Mydwbr3rKD_BO8U^$6wY{5V>Ji@J2mbl)CO6
z{PFNRh%#Bs({Eo$e{7Kw7#1oC?@QRHwZ(Jpekbw^4VSxKX#p|2``#xNRl90D4?L!<
zFyYHoM|q>nA7CU|l!btXH)yuMX}W&zBo6l>ojPK!odqjAD!oobd+S5=De$!JxxD?x
z2|UqEAEVR}&MFE3+EApub{9|@UsZQ|K$(M|=*dI%TWXv!;InYxzvvc~|F#I=Tvxa-
z49Mpi8H(dpn{wjLKkAPCLLdeqzV&+>#u+lFv=|W1<O#cXO{8hx%dlN*<}D?*?10@F
z;E)&3qLboCDLXmp;OleUj4L5~(XXK2+0n{S;MJ5IyOXE&!jbMh{<5@Pnm?}O&4MHk
zLToGp&as2QHY$%drpJ$OE9_qeCu0!r)*B*4u0fH_|49?1IK~PlK(FyIb~{5ka-KL(
zFru_f9U8p;?G8Nf0j7+z^;IN-Z#mw$5HAZ?y0)XVBBbN#a;b+Lk2xrS<P-eN0J>mw
z0Qcaz{_X9{aR<*wows9PgU;0^!DNyB%LVj>=~>1TI4HGk%r2i@Oe!ah?L@t{e^={D
zF|!3`EQppNtq@vKysRGuZ1LDuCraV_+zgDDi?Q^pMVo)c7MqxXkGctdII=E27MU7B
zv-rMcBH2OLlm^l{)W4)ZcO^c=$)zzHqU~K9|5c#CDo+_9D_wmF2zE4jzj;EW+OhM2
zqf-*t)7b9Hk5_o|AbGcq(SQAcZM3aV!1p})+W%cIv%N}=#pC&mY}l>2bn=n-JV?5r
z=&eoFq<4k>D6~{om6%mdJfYk8{6Y<QZ(|@r=(pg=2d}-UzP4u~7x48_H~U4#eNGAz
z0r}YsL0%BcNz>`f-^4YN=|D_!iAPCMUP&0RPIEN0*UW78vJ0Nhq3FTNBtIoNkD@W>
z@t^i4Hhq=LvcILNvt=1{%eWEeq-NtOO;)jR=J%eZN#{cU;F6U1<^2m<^KxdT_-f+&
zoA>EhY4kQ-88pQ{Rw}~`b2uW^nC@!g10`8qtxGCxPThrg6&5q6(S7Z1HNoL6fY;3!
z2mWZWuhP|G7JRZAmFkqUJ^oa{lqkMR?MWps9Jzz?Ur@c|G0LDThioqfXY^u(Nfm$V
z9R?5EN4OYI!;pQWNL;6z0whYOPDJmmeb!+lM!_Atom?fBCHeD$H$uV~V5E6WI?>>6
zk3aO6PhFJT%;2cbOIAAOEfRkSSt@NuwOCo22@r^(hu1e?A;`yXL0lBWX*-I^Eiw&`
zrH@aPpLm!n<a}*0F)bkIMT#>qE8&l8xdL;0fuwR(bb-7n)ETK_Lq9=;=d6VJ+W84a
z;kjw{C1suQO(a%LvH09j4q-M3z9%6lXE1nHkgA2$s<hIbXKbG|!gwK%dyK=AS^~5|
z5&wLnJy2TXs#Sqf5zq5y9$?;jVgz$zU8r|!<ZU*a5Sc;pBOhp)G$^0~^MVMtwVJ9U
z7s7KOOEVo8ovyy_oXLrC^$J!MMSgHKt%R?{VlaRFpAP%og}64mtqD!D<lu+#hSK3j
z7|$ed|77!|&X+jgt1<D={4M0Fh#y13o@4&5OCMY2xNs=M*adi-|4#6!>A3QAq!7IY
za28-S-bYYpv{=VA0`V|oqPR*|+iEcopUmdy&d2jC<^tXJ>?TO91$x#Xa~=D%{2!Y8
zPdD`sJzB@l9t(S;hEK!gfEJqr_?oJ!2jTgDKMY1ud;RAr&$Y|cG_Ma|$eXYMpT}4x
zH!V6bPnc5rW#Dm9em*6=a(diax3>%?g=hgX_G5ksnV65;Yk@+ppvz$XBv4PF4ftta
zEf|-FU$@lfek4+=1D5?qSg=wW%QWD{&JDS^I?zMGWkAan^-czm*1zWNE=0IW>)X@6
zg=;e<Evu2!CXfe@rS}<}qPShr=6c-G!-D_8g@BKS7QlsBJeDZzrrnv2>%FQjo8KGm
zt$|{Vxo<K^nzewbN2g4UJg^rYs#z%eD#E7#XjjwMVmlkLP;DRsNPJ{GkZ}_rW&?!*
zfA;&)6p?jhIdmw%s2Cq{h23o09*kAR99cb`zx^j@PXdB=8KDb?;$!%dwW?J?2tePI
zqj3xpD7`Otu>t0he|`8zCLHx;rvRwV&;$(5h|pIQsG7~TGtC4CF#=2s09PvkNSP+U
z>2?8NnMx%EXSdYMJdq>Bs{vtD&5{LZr7HviAcYD5Jke+ky-@(H90<*TO$4hI=-9fC
z1AzK$fVMYFWqNQK)rx^uV&C~cT*m{Sr*|9pQ79K1vu<8SBcDi70uUhV_tbIv3i7}l
z{H@Oe;381!GmAeLp6v_JhQSCx{$dr1IdUQ3JfbfGMGFbFraejkMExe@`cESUkNL4>
z-2{@oU@Ygf?w9-&`nGxA3j$=GRe&;*f`L$^S-@Q(7X#~kbDRr9xu*)4O%SmF977n`
z6iz02b+oMKMiJpCdm0Rnq*bPt`<)3(zZ0<bmlpv@((QOfXbFIUFmQLA&y=l#G4&`a
z3Vj~{{}sRq@dU{Geb1q9x5v_A0j3}e{|2o9s4kgFXHUOyr;rGEEysA}bf_9hr4DP|
z29lH-bZy~e0-AuFWCF6HG)F_|i7?YZxdz~u%Et%IC4NleGMC0i$dd@<aMU+)Ap~vH
z{Y$pg*1YiOXeKjmUa%yC{v9-+Ab>fK!lsRJLrhXk0?a4aRI;B#b*lA~fT7rQDhyY^
zfYcdxNCU>2GQhAOwQB^ph?1@aLsvA_60&R5^Ti9*ej>h7AIL1M&<u<07ln^t+D|Oo
zWLH=lG2|kxnd-8DNy_KuSd~bKs|^`@@a4Xd1OkkhI)GnsXi@#(g3X*$y1mW@QG^`3
zU#;cqnB>B;5-*QUw-eeB>;ddiYW&KwBD3s00r}}5uPrJ)5C}RE#ZdG<z7QS>BTA78
zfm{Os;0I8^SQY;1R?PKBqdkjku&8>T=w>G>AxD%=1m0)BS*1qpnVMozEa_8>Ok?+z
z$MU;sgr;;-KUG_PoVedD;Q7n6pt7UYlHp?McU+OpMEc0{h0~6TlGiG(eZVD!DI{B5
zyHur6909wSRmq<To)W<0hH;s<CfJ@dLLe6?6bz&!OZTse{WHiINRT=l)Dp5_S)QdX
ze>i9JRcvd}FGC{C|9H^L1(Qv80YxA*HvpJujEadWouuh#aznhL#lL^LS(lTQ070Yl
zHG_dt34p;en{>V;+zg?^)hB7uD<;cAuOMA%*|2@I0>HsFT_lei62uE}IMSk$UqZ<D
zh7<arTi*$H7IKmDGn_1G2e2mLVEfKj>b~OHz+m(g0cc0i@VjJqka46aZf?9T5jzzU
zAFxFTS-Bui2a9!_=l;kA!^IdIJ3qf_KdO$79#P+%onbo+KoB(31@R&9%6eq;@Z_yR
z9ZPO<oRCEFZgtuhF{~=fNKu`_=9ke!%%PNyKrRf>gBv0?ZVC-dtRh}I+7YE2n_;tp
ztTi+b=I6U)+L%7SyW~&bqo_Y{%}E|JnG8(DD^mSK3A)KJ3!pBB*QXy476%zv=29}h
z`QZ7niU&%|ULQ&38cikyic&x)t@==-WYY)NarC_j;JlwMrL*QbT&;sc{l%iXk5xpk
zLi~0l1Z?)(X$KcD#85SY3$;$NtjM5a6J+9kUfeou_KRvTp(T99?E3$JLpiO_mjYKx
zg{h%ALa~w^dOaY84ozUlgLwc>PQdGR_0e748#(+O$WIgY0VQAQ=^Q3344w)-Ts}<7
zQP*Hvi68Mnpn7khFzS=T`a4f~w-MF&YxqyaX6<{_*H?l@(%-KDLjP#~R+AHQc1^t|
z9d=1(oZ7gPejWOjd*i?TNEAJ2KeJK4ict7!b&25q3J=UJomXbB`-4I8z*{o$@z0%}
zmN|s}hzNMdBZ2&`BYv$@;l6OFpKZPfB=P@rz5<@{`~LWR%0Oo4b{%snc-1pZ=3i~C
z+TWqB7m`p|Q%eZCbK{(DJAB9a8=8$b&}38@4sWDA$2<}6&3_RCjv2gS*8k&W&o8}6
z$Ls#I3^|!zN*rh%Q1ap~?_<g5KH;jp`SHZmvX3<TGkQz@qxkFG&`xbSZ^UCs)4ENb
z`|~@}CoK+qetXs{(x_8$z|0!jnZ3gT6+CayY{4I_CAs2_4x}TDFh0kaSryfz?(+q5
zV~)0WnI(!<IXaz%&7}UI&O#9}Q?1}CaK7k0IN+qqsJYfZ5l*K*bMB<ZxpR{qaEg~!
zft^;p;;kOd|LivXs{fQqADLKtZCe01%h7Xo=UI%y{mu?~n?YxY)Bmtjlr_&&xj#Ee
z$Z+^#?m6UFfz?UeqprX7(f=HLB_9ePV02HYRwsZ0nc!8AsXJcvFq4agxdP|E(tD0T
z<qsE>LU`(c(-R-GEv1oa^VenpXIy^fe-9Tccq__<j2}ZWgBb&z<SFI&+7|FV)du7C
z7>2Wg%>XaKy<4+i|6|Gu(%jN@^fmY)EG1xduIk&|(5-y_vBqJ&_?*yPnB@G)3MjNR
zp~Y|c&qm;%3P0U(HH+lfYq0X#N12}w_cSy;YuO=%1l@|}pZa)<)zn!v;qSVM%aE-R
zrMfqk)rRSTc=+iUM*WG5t~St904JB+$~&LdG>I{_ds4N|R<8`2ULygQJRs&d{U;^y
z`!DSsy<+`_5;O6ziY3Wo{vI3fH?KDM6R$7~z)#IyPIuug%;8-OB*iZQ|4$4KKiP!g
zK0YfeT8FaOp|rW*OVkM!b(&pqnU89Tn5U_Gm8s~9B>RCu>%@2}JH-{Lsqs|{10htQ
zRvzgiVf8!o#aTe{F!_Z|@%fuuo;f+Cr^r)Io%r8GF?<}1jxNgpYL)fm9oF4)pL3jb
z%IjvC0Ao_FR9z+7beG*3q9NaM<DFf0?Oi!UeH5)iFI0&L1WdKY@M7Ki@M!`Wfwl3b
zSYo|-Ngx76fyfVZ5lN&Q{nl?p{4IR+s*ZnnmQcf}7n@QR*!yHJtnzSly+)DVz;+hN
zG@)Mt9=isotz^}fOSkNWPGV4vm|Yc6;pjA1cuX?5bxPDgGnLwbZz(><FR52Re#L5d
zZTr2d#cOyW7HG1oDgCFIGAltI;e7LPa$?N$A%92pJii`?c$qkPTg(gRwKB+Vp1E$#
zaaK!0rnW?Yd`}uro==`HE}sh}KHnhWP)%cc86ok?VqNAi5ZQK)2Pv&4=Z8h^8y3Lc
z<9rPm#imO6^<;GcD@W<d9WIGxjg|X`KYn)`95LY4u!P{~@vgpM`UGroo*uvFU_*X=
z<@Me>&6qiE+uQGEapfPHgqH+XB{5I>N?wg<oAIXndtsPFpa})%LYpzb$!}k^EtdXF
ztEBOxdJP-htoN2`h8<bl@W;rwDFa%ECV7NHl%*gULI!^s<`u<0c|F;mK)_|U#<-$W
zr}&{#hqp(QW44k4FubT&PV@Rqi3@`^@|c9J3;}e<mX$TG!p`e?uV~nJ-dJxAY0qa?
z^{G%#bB3};tSE#y8v9F$Eg7m=PU;DAyYHJ!LH1WGtMndf+>Xv&W3af<CJYQF*vT2p
zzJp0uVMBcni<`<QVi_a1tkdzwV;aYn7xT+)*~dr6y;0~2Ii8Bw2hwRf(70d$e*m*4
z3u4P*ru>^GvL)xuQ+SfK_49w<2>p+(*3DX+3t?a=sbBvt06_xO3M&FAhfprpp#EMI
zAbOsm3Ap8ySqTmD7JO{QF=mNDyc@#ZFBI{2p2LO4^UZS_GoDRpzg9nekCP1KsQw&L
z)m)xJy*L<KyWh`4laAX^9ku8Lt5FOwH_<J!_db+aD_kSFzdU2z<^<B<J_B?@Fp*r)
z&Sab@kSNh0JWW(w_Md#=Yq0ZJcE-+DPHiTl;Qlaefav}RZJ?}+tm{|tN_{RsBN<o;
zxqI)nC#MSgv+=HOE3T4_ik;<^Edpa0Zlx|lZP|P{?}%#Bbv|g6z>QYT3b;9>uAn{!
z5|#bNu$-1sF=;AlHNw904_ntJfC&Vyf?#no6va;;b|6b=VRC|?n;>p6)Ut6DJ|8&l
z1l3cN10Tx^tG!6<N;ksUx-$_6{wZ+Nn~dn~(MA}T6uGfmb&XK1Sr7QKTcNaC|Cq>N
zabP2P_pSJAsg0(9Ol>%!*nF@9YrQ{WYeRo_w3o~@TZh{-^VLDOiH=#Xp|IVQXtqJA
zjV>opiNPo~f3b60)C`!pzWw;AJzpRGrgbLB>u;H3LT51b4W3#}?MOQ4w;_hn&#xVe
z1&s!_x2NB1kN5Wt`G2VZzU!}RZFRmYQ%`QrCnjgsen>GVQq+*dhSGq8d*w6gW&$`9
z!bx#_O5KrYLdEjO=hZ~J3=^7X5$iRCIscE??3Fx5NHUHdn7<dCe2WFv)*S)H6+~JG
z1LM{&=&gpRs`BHlqu?ldGMgpZSSCHka2$EkzX?I+=Y>KUiu;P@yYa6ieCgDS{n1&K
zL`%Mex#Et0cGr^FR*j8P?!Qob7Efi1w|Z=1MHu6L;?oMj`!v07y$fxKgtdG0_10Bg
z(|3C#gw`*@uV4)#RDins4*wPeQ!hrTC(gmNZ(sZ}zzjxLF?dO$m$my_Q69X~nt=9o
zYbHpOUbJQ*4samyb~_sFln49n0br_ff(!mUDrqokTNZk3%7oVOCpQAmQnHOaED>)G
znW1RA(kr03fHjGX)8?-nJ0~E*BNAK@-D<?^HBh~$lSeD~`@)&v8P=Ra4X0YdYOVH$
zgM~Q&Kt-dPbTlhU=$lR35sNX~(oQnfk^}SRO-IJg-`1z^-~*)^(y`oNM?9!$UL;@x
zueaW%pOjqO57v-OG9FKbXp9Ke#?f{l<Zeub^-C_|o>L`9y3%FffAQ^tGlU&@U>#G|
z&1)VOPe%GCnnQhqfL2u3vYIbfVN``AeGRs6dE?Zam@_xB7t<5!cyq{XK#5K6i=C3b
z@_drg9>MIWS!z=!*4lJ1TK$2XxTvS}J+q^CwYECq*>YQ1y|{SohXL@i@8SFGcbD6H
z+Ir*_zIQ44DN|#ZLULlmLnehdf7wZ2{#P?+8cx-}_VG<*EViMP$R@KUGfC!c9=3T5
zQ6kgMoKl8uW}9c3r$WhGD5W+^=5eF4l_6C4D;b`9pVPVi=f(59J?DA1uC>->Ez4Sd
z-}}Bl-){i#m6`M+^I1O327ay5m&C=U7~Wc5lRv!J-Ow$lYfrf7U4X5o49slK@1QD;
zxY#J4&=IZE%Uxb}|H@41{VSFUh%L3U*<LjnMYUo-Eq$X<uQdgu(&dKB`3lJGW7v4&
zLnUrSQxR=>p9&4D2IH_3y9@VjWe1}q3ziS}*zyz#taZAKsqAOxpSDzaZ(id>Xz+RT
z6<=I!VK@9K{`sK?XLJt9PWIs4w6;20pHX1BvQJlQ<7^^p90<N%RWu^UuuQo}`%4*H
z4(o3!@vE-h12+&?Zh07-LsO1DHTI&CyTS>0U~cq(YWLRLO4<DHVE0aisD<}zySJoN
zYoa-KMIT2hTy78cfqn<VEnD7Kq~XQ{MnXr#yhazs%fFOi@IF@oE*$-3AQ_loNSy#q
z`jz^Jg4B)fQyM_Dl$+Pu{W2b^FycE7))r{Uyk*@SbvuUDBXY=+;8>~un%I5Z?)v*n
z!?l+$h4hmx9gbZwrCI!U6(EkHh}&8#^Bk%xn)S`~i>^HTJHI3%4sniF);y=DqG~~F
zbJ@JbyR8`U(u>(zJ_|UH!rb2ZX*3+X(2s)d%~5jG2KWzk@V5WMF%?Qh_i9bHyBdNf
zHh?pVnT0}Ahm6a>Nl1I2Q+E}B#*w`FSvRu7e|a=s`o_4@o5YjlWWEB*EvWl-hihyv
z#31<&0=Yw+^=;NVYul>!E?cS?ItYW{t=A{Jug2cxU(6BE%~S%j7E;C)4qpck5Ck2_
zK1hJ7yq^qBL2rOf#>2*Sq>6o{!YB;74=c6#$0V*s$$uSUAD;w!hY`9+ExN*Uw!JeF
z58PI)8?<cri!ObIN1yx6oJ>d^!x5bb$aesJ@&0%ZwS9B~*>B}OQKxQ!OF+}S&yt7)
z#EB1K)q>^sU7MM9Cm0z3$5nA-qK+~F8Y{Gjt(7T34Fo#r#JP{3D@`g{;8tT*A`j~&
z@u82%uxRj(`)#e-Qg{KT(-qG!QGY$9*#j<2*$%kMAmDJ7kR-rHZfxvqZ!V`Q-VX9E
zR$T)etP;9CpJvr#*pPU0aBaDc)#z#d?r(%YYqYfQ%48a9?4D=gV49|f=S#pj)Y&vr
z<Bm&J-9;KP<uL{V`Gi_oAhz5rz+dR;2HTRT27<OI06aYaa_RH3+?V(5Ic|9%^w}S<
z$0$Up4%}qkeEG88Ds0MJz*3a~KC<r>eVp*rXHkXb@CoL9Axy`e+ev%XRt?%pc8?v^
zgZ}z@tSj!iT%R|**q?A+o+r9}i-_z5Xt`-F5TFIv53W1)Aj%i7&Vo0L*Q!WDCw*rv
zc$<=%K1%3>Me8RaL39waaPs^!Jz5P~H7GvcV4$y89l}J5eeQfo>s9!186FRo5_)E0
zNz^zVfVXHP+5w{7uu=jigWpRHbpeBX-Jf4NBN!;1;^?745jNnwy|L&+A|P=#g0F33
zNKq;XPSKN)Hc+@W+hH6|i&RU<2g0fe#Uv((erj|L+KcM1UiS2rXr<(;BoMa-iuV)r
zUy)dicAIAJ6ob2np}EOpS_DHgfAt&Nk00~Bu_i+22rDa;Bw*@_ue?b(PZC#Jotxvs
z+K?VFt7(YIiQuQoMafuE3g+5k48S2p_7<0$y-;A5!%2G(HTktI^sjPCy5KF!?V3FD
zM$~(#-XFp0Y9yWgy}fOPrj29F%oM@Xq}PB&5M9rCliB+5yY2(p=J-Yjk57a%IGeL|
z?i;PiHTFNK@JUY`n`^BaL?DNzm%c^(JH$ZLM7gNq7?F9gCdK}1Gl#8N`&oF+q`kuI
zle47U%sRE11}PS(IN-}I6*4M{+Mr~$*S+(2GSud%%)Q&MsB)XNpy_p1AVl-AcE*|0
z1?D_&e1E!=2uYMKZ{^650cL3EHL7=~2$qvcnh~zyc++Fn1W#hKG7vqitd`E7qD^_G
zq6N{|0|kw>o$LfibTQD&mPCrOLgVJB5gV%>e==V+qQ8fQSDwSro&%kF^AyEJMwJbk
z8y01{NxTtvkNtpNu}c2^i?{rYm;`*uz#<vLvv<#6cIT6;={gi?%2;wnvuSC#lJ7Hp
zW6K2(LopQPICPhc04aR6#7yP>^3cJbd8bj1rUymk`V$pSbS4q0o*R|sCvHL$hIce3
z=_apAo$MB(Hs!)rQZIi!_*WMKI6{MuxjiQYBHNhR-OaUaq{TUGpW~PNC#+NxXwDHb
zUWU{0aUb9P{^q1(=bNIw1B@;5ms(7;bqKaqnG6>;5UMo?IR0%VqHIk?{k;IG)`YG5
z7<S{AKS0WXyzIz<G{zR1zB$eR_-<p?Zq;!5Qq@Bb2ThrRn}aQFl7l;`=$Gf_mgd|4
z74&6Z%UCs^rn$PZ@^tGou7NIE#quwc?|u#hsU>Bl)ve738k290ht|!`yUlk9PC4hJ
zj*sRBJVzvuj&Bbwn~sRJjZflAbKGv-zNO%TC>I4?y`+OaJg)QR@bpn>aZ+xI&Y=fS
zU!NzLy$7uQDDOlq+2%WOY;#-@e7{>9yc6s~cxXGtz=$06v?XW~L{R>Wl(CFzUlLJw
zkFhcb%)f^y-o1rl82A5tM^gz*gZ|fB4KTMR-@Ifk*;u~u_4|d8p!fF!9e4NREI;iT
zUdw>lFNX9edy2PEWky-2Q{Q`{#CiQaa?eOq%UG@4$XNTq>D85a4y@;z^7#J7_Y1Dm
zUU^Gp^-H-KQ1jHZKFc`j1V+XK)t~*{8?roR14^sp08cn>gJJ&}hB8-=ILbEp$DePk
zbMuRVCREyff4uVA*Q)d^LoKU1lN2ftHT9}`JuGiA>^OxA<#so4go%Ily8DhET=S~j
z!#pA2lsj&I`I!BaKZbjH*LQxS+<o17frP0$C;xanCi~5JHRx5Jn47FOes*zy`X}P3
z^B~f&2UG8ab)A;0)h#>j%s}?n#8(Lxr1EE$iR7kmQs)nBey~lSw)V7oaOgE$&qFd;
zW5l0qNs)57-_Tl@He^_wE*Dp2*BB&gJ5Yq~o8>BrIIic*=$R3tc$-$(r*XkQCzvH<
z(4?chC;3&4o)K@!ca!*Rs34^5ux6jXjU0sGqz&`#6COcZ+2rt|*TDvQzxU@J(&6^=
zg}d!>M6cRghJ}=Y3x-At{Y5LK=I>t>jto7)^f~%hsBMZ)ifk!Ojd^-@jlk!uFFA*y
z{=t!iHEdOzes}JLLtcDUbpZvRj$vKu`I1MAAA93{mb*{jY+`1-252o&Z?ao-*Wx8e
zXF~any)980-RMUVsElf~&7(+^`4=&qP2T+yu`c|B<s<*)P4-lt*}vn`q_#lQw&=tg
zb8!5_RG+|gf&L0v9!9h97l9xf`tTx57)apP#}*69V5-v(Qo?0(X=L;=S>-(ngqc?M
z)N8!kDrSyNJ}j8n?7ab*QvERZS%8InxXxLJLXk&8wLN5C|L3*mcPTC@)s#cIn?EyR
z*(C9=+1V4Tf%@ylt=@A7SBNdfJ1a098wPMW`-1<Ow%fnc!LzR(vh$tBxi8mpX9i}T
zt%2(TpnfA^MMskj`-i#Y4PmTTEe}3(rHeru1)}CPQ3I6QFg-kV2fc)Z7=diLn*w^d
zvPowyx9h@US5~MRxxM}twD{so+pWDp_Hj%lhF{+M6V=N2<FHR%v4TFp@Am|)z+g^o
z8gyhSu+x|-lS&Y+s`U`P6#@lOp7OA9n-v6#?9eVM0p3qVYu$JQc@<=(E#lJEw;aIo
zQ@jJg34khp52e0R0vk*WkdPrDNDeh%7d4A3)6G&L*8?D=jX~;E!b)z^<Y7D6ew!R2
zXSefIGl|!XAaV7rCj3Sv;JA+AbR*zVm(;M3QiPvv_0_R4hsdVv^H*@qEvv*9RV1$(
zv-GE{C!}0c5y2oN$n`@{iXf9}ji8Ulvfn{D3@d5w?uqLv@Ke;eZ3<PWVXnmmF;21i
z`3k~Hrc@tz@+!=#v+oAOKHlv}m`bxP&URdaNTwVF{~hq_-~EYB0%glE4Ks{76~&Of
z;41Ul{D!#VTq2SLO1^}SRUm5FJ_KaOb->^qU%k-t-`fdHN)QeeN*sm~df?QO#eE3^
zC_^1i8IO|0lb6VWYF**RS>t&Sw@`QO{c69w8X6H7f_LOGHKOWog3&LxVz7`$I-JM4
zWaRXN)Eypjj>d41ou~;Z3pbDbfXS;dIN+<tP+ZxHx8>7LTbq?g!@P1cV;i9JSP=M~
z_+>)w$ErMKkDL@f7D{@x0U*Bz_I7_)8WyT-?EJbJb4;R4b&5jHOj+7<=IdD|4K`{L
z;xvdIeH1!7<&3R-2Fi2vVOFM?C?&x=rO2+tuG#y>`YrgMLIwOGJHg?QK&Gb5xq+8z
z5+1~6$y<Nj2&oLO9=RI~vvwb-80a}ivCqY@s}Nm9lU?&HWZ#Z7sC}v_G8o1#<k-Lv
zzVKon{&NI5+kyLMg<ZYaf52O31fdEppvJ>Z5YHVWC<7r0EN~HoeEp3Hao2$&>QcQN
zvl7vey<g=~I~HBCcXpba53>%#YaeC9g*=Wl$qHz68(WQxF26`><_^3h@Eq*%%zSiM
z_o+x_!qWp`#5<p&Q|U!7xV(W+X?K&Uwnp>bgIgNS^m48gv^wcxNKt+~q(w!ur$Ir8
zPfTQDKWk_6u<=y_m$g!Y5EK`Vj~S!1#5@=uItmqup?Lk#awV$GNFEAxtgf#2oIPc%
zIK^qy!Gm%eXKk7diNWwfu&y5{k$7|kd_s&Zw=}!`(`FJkDda|L!Pz2qd5+7%q`}qH
zyI5FMTpO7{vKzRa5YM=ZztYzJC${3TWDLKt*fqy$q8Z2q1tlf|clYDJ64LI25hF^D
zN}yiT`fCITinj3sOS;zxBfqqIFhS*_80pDF#T;0fT!CI-C|dLF|9J#9JskeaoAjgs
zzTKwjuvDD3{qO_-@^JR7WX3Wf<RFJbk|*t@OC2(5Y+X^4p{`u?B=Lr|uDShI$*a$r
z#Is)Gb;dYF80E1ebzcf}#arF4KajH(*lW5RD<)lLFdWO*B9`~D+HY8FcNYC#M`rA=
z(W@>FGUcLH0Y(~Jd^BH6uSBjg3~^xlx}BYdujFuGA27%z-_lJfp(iK0U?dwPV&OqH
z6l-Dh=t=Mv6#a5@({wFGUG;8tjLOlg2uFR<^q};6ZPpFB39nhMsklR2!vFIf)|hku
z$E`klaGHGc+omlbih{O(=5^46_x0NDK1};|4O@yk7OxdnW(U%oHlD6EntxKBR{%U<
z#b~-D_)VqeJM^|qFE8Xl9MalXnSHa_*1hD`hCQ^e@$p82{(M!5sqIWJgE+}<=APO5
zAC3z%lG}Y##4tA?$t3L%Wdz3$p8n_}I!-g&GP#g^pUGU9lVHa7BJ$E1RHy+}8qCTJ
zX!L0AyMEK^A5LNc|G%S<vQy{R=1qk`U@BKm^i2Zzx{jCGUHub=l!)3Ah{~JT{%4kw
z_;be>=S&?4dCGI~9f`-AGZMJ#Pq@2?0`XipAzBr9B}Jhji?5}eJ9Q;UVK-O&^Eale
z?5DE;>FyKFY0(&eiRb+2%(qM{<h(dp%RGMuPtY`Ws*FWtlnU0@zf^Rl17-JxWEIMv
za^`m`KS#L;ba3t4fA1wFw6$p(bhNXT<%Wb9OQf7>h}E1`3}@a>_Wh-qG<au7&A-m;
zyD+BW8{2s&sva&mt}Z%ORn|6nk&iy==r0E=g0_}Ze1^9uxi;G>tT*p4upqgj_1V@L
zA{Ig{n}QIx2VCSTT<X8F2|EQ$FMU@!Pi`REv~P6&&XN4mt<k!<SlBz(8vJ6Sf+QnB
zXEgAIt*B~mlj0lByO(a9pA|=pI;?CZzSXTUxw#$Qv6PHkFLWHhG8Z`ve)}$!82-2T
zn=E5%w!9x4D6CO*#jhASImqu|n>EORv+*QQ{4BWeWJi6?CTYmHxY^m4hT<~K;x0Aw
zWYhO93ah=~$dR<DrQKvnc9~i#Sdb>@G<7s)FT+!@5J>m#R4X@A91&7|Rj_r0XHs^4
zKwBj>60vd6yEi7O$H{@PxrF#ln=o7wl6*D0{8Z4yTFs1bq8YQmXiS{u=;YU^KK#?E
ztiGD%J8pGS>dHZbB6k{in3_MO#Ghq~qHAOsplFTOiHCp}i|Jpt`%(_of1g+OzU~$M
z;jcS&@e71^6s=ld&0Yy0l^j^>V{zrfF&d;`{OF{S#F>oZ)w7Rk+D#HoLtS5;DQtK;
zvT%hk640F{j<CrJ-ZUUeYU+!RY#&%pmL5Y7{a!oS6|Xpu%bAZdpK@^RahML+*rhHK
zGBZR3dL5nGIl&b3sMYDwIg*t;QJN_)wdhG!%IVWN^N(w!Wi*C{&ep0)?u+`KOx$d#
z04{&P;ocEXtS_xY)N7}kPIb~&Re!nKHnMuNrnAA2bK!BGmvo$Ude3X2f;89Kv9L%-
z3rs}jISPpC;w4CLF|M-eqZO-tCz8uD&zXbgBs6&93D@YBj4nrVgDcJ>DD@e{x4rAy
z7H!P)Iiqz!ZJ)mF;X&u?>;{VGg=Gw7lilWTOl^AOcF?ui3ny_3vPyOjEzXNvZddSy
zOdv@a$T1<W-4OJdVfN0yDiY<t#QTdOb39r<?<M~CuQpVXkp9IkYRXN7Dz_|;z;@&i
zd-bX<>xCqF|5e?8vs{vWn8VH9SKNkVlW(3H3%@CWf_R&AX=0Yi!NI``ge1P<hn5nc
zwOQH4EDY=8$qO7e_V+<hqUoLCbgIz0awY^WU)B40MEh+Vi5#V5RIEWx$6A1>q|SWk
z`wju9M=r2`qb}Xqk!2S#i2{eCASNB!a7N&NU4Wb@UV|?_5i%dg;;>J6e}Vbd1%Nxp
zY3n3$=N?1wadBW{RRet0MSI?b27`JtDb;3|hm0*UPY6VbHuPi5;TqzQonsbYy^%>R
zx3oIdbQT~vV_j*uBLg~?Qw2FPo^V27|2><j^o8PguXvs>#+cc<ItsduP}y!~!ZWsc
zkT3O^wZS#CCP;S!bgSw6$<_0nwUc`brqtN4>g!F9PfAFTtRUIinK`6#zt}v@eH{`a
ztD_{86Hk+N;=d$vJ)aH8MwE`4PI`!K<QSM9YZM!8jrLf6+1Tgq5r-Vhh)=qltLaeS
z)moJH#Qg%x({VpN3j@&+yV^H?f(KYBq4&eDJnf-ZG<BbwE^S;`doZl1{zjdMZR3<h
z&IiCgOwU$|IdMML9alq_roBG$WZI{@1et&utLt_5_l~f$b4De_ioWU2lq4^o;U`+X
zI;V!wq7hcC>Am$H3Fz%p;{!+jk|1$!IwFovDNet9VVHS?TIO-v#CL>CNg%rF94Y8|
z<j0n&>TbvNz$iLV`XEW22K^h~qOWizwJW!tdWde}D>uL0_8OL(crI7d$OP^H7$*CC
z#l}v1gthX7&e_{hd(rv*bS7+u_xTYtE^69(H98wYI;4aBc&rUFML+$~8U|-$Kq%zY
zaR~_2(Xu_I7&hZ>UJx%k$XuMk%cADh#fBrU<okY9>Fs{Y@G6Nn=EHbL(E!$Pm9Y5i
z$2fZl-<uh`lH&HGw6&5#p;`inj1Q--;)v85Qo>6Mj6v$>i*5~m!{n;gR#i7!rZsp@
zF?@SeZbYoBo3206ZMs>7i$J`o`*LB2>s@tWkg>_fxDpNT-tM4WK2;BTb~VS%j|<kl
zhKa#k-=@kWu1?H9v@7B3-sAFpBo-B-tAHV9wfxK@NB*6e8-d*Vw$|U{0aCCr5)j=R
n&_Kh1tzA`=wu`3;-e>wv6PJVjU@iuU`Uov`eYF}D`_TUZ*`T<B

literal 23890
zcmce;byQW|8!ozN=`KNG(}FY-g0zIBq9CDkhjdCvcXyYBbc1w*w6t_cDk&ZN&iy;*
z-ZSpFzccRr>yGc+%3!TM*PL_B`OfEg-sd$$Raq7n>me2dLAdgA(r+LL2@`^lsUDz%
z-&|%|nuEX44HRUhAvof{?AF3K2%?4Lr6u0FrvF)T`~3E-RqTE?#dF9gtJKICQ;%#M
zi}igroo@`kdb?cML+d&(%O|4a+7&0`H?1o_KXRhkU7dLy8|<U2=R2!;EU}uslt6tp
zkQg2D$Ad?kC*}9)jUi7^%F{S`9*5DC&AZPcC$0=N>8F|UTM1)V>0?))1^XyaVE*9}
zOwLID1m=0swEn0sVG<88UvW?4&ZU=`Rb`56z%~B~aTttSe;JyjiTw3|FkZ4C;MHTl
z_fGsob!c+DI(V%-@BUOv_bb(JR4;j9B`kT%6y80B_HGy^34<7xJ`XFg_{nRqICJNw
z*vieN|Gg~OAgz5Lg<%sM*PX5Cr=0R2K#^*O4wKM#XcE7<23y?}o5BHOG0EhTj6<RA
zk^5Kq{JkFDoamy%8v@e5oE;<SZH4qNb^V`iyvpARdqO=>yL$33Z{++LM=E~Kh&qz4
zg68Ox*GAv5=c`J3*j4plfvDY0<pQ?l`%$;-c6&M`sXt<hGRQkm9uR6AisQ2W(v`jt
zXY|(gTEuM}c4QW`rBi20x0CYyvKE$DIAJ7&1x4H0>m+_=w%<@6OBM(jw!*=wYdzdZ
zi%eRje2z01tQpGovwk>utfLWjtkf^6v*U&hWykN^8UIpe*eAn!Lk)ZLbJ`m(OF#@W
zXaNUGexw^Z6e|#-^KKLE5%cSn3m6RnYZKD!=(P*h10F+03+zg(nGMxJT*wFe#iyLM
zL#ddO&=zi~t}QFsmp9nU7<Trb+5RH+6!D<3g%dmpeQj(Yf9)4-w+xffZD@z~^-2cb
zy_`u#^o8wKGkhraP`dhnr!$mJ`Ug?nsh#G@BM8EGSa;m^ieU>aeJz!{<P}PTL0B;;
zYqMw}5k@Dy2L?+2F%BOxt9mTkd>21J`f{`g_ImzoJLgakOvFw2PA8)gouDlXUjm9$
zR>Y5k_Fyd)hKL84`+988Z^n?JH~)I&rpO+AB!NxPO7LPlxu%1}3-55OMtA20xak<Q
zteID-^b?JBV75a3(n$(ggn?xHnA{2>$%L?pXH%i8f<mALUvg<VKKY3xpN&nZWrL+4
zj}WHs%m+a@Klr|rf$_2!X;H+3EmgCTJ1{NX7aUDtdw~o&{xIqcgE2hZjSqo3qI%M8
zWc>XXcppHj15>`_QgVDJb&Ve~kz&|F!e1+Yx#swtd}}^7Gox-x9W**RD*wr_I+5c;
z=ysO3sKEmHX`Rx${FStnp$pBF%s9>o>LmZ@Y!-$GFp1Z41d_g33Ualzwb`|`Br<t~
z*kn&Ts6Mq2+Io9<2zwp*(R3K`z!(|PT$bIKzc)7{L7!TV(YHpL`I@H<qh6p#Zm6oM
zp+JJpe<%zL4cF|OAc&EX(e+PNf2GAVD@BCNaGC)AVe7?mavj=&02H5?=(`~}V8pYz
zwPkQ~{`V-$z_4YOY?yaU#BXs?XXniQscsuJvq~n8TRUiH?z<CPBBw5%U#AZmHreW2
zmEl~SB{>f-FCi6Gn8#r&`Qs?&RiP-+YZk;^c@x3CVdNVFG4zHrrgd6X#zSOArl#~9
z9C%;9el4n~z%Rbn>+={>c=f8%dV#<6eHAh{H@EBGx>;YFF)Mz<p+xq9k&&05KZ|&s
z#AS7u)C9CtR4vE7@Ho$|<g)c$`1XyJg(TGHLch<j`}XP<{e1hBYHoW(1-IQ&aVUw?
zbOnBYp{cD+)oi<l+`JyjMgh%COmtEh{#jVL=htqqd1Pr}VL;CL(TGi>+-QHM%rKmL
zW@%}}h=;PIqQW$syWVm44ZrCq_4%U17<V7VLYt?scDvV$_KNj&gT#b{-pEJ7eOCNb
zh~M+3C=PENbM;YZR~un2G`n!ZFZFKDx9ywe2IH9L|IF9S-{0Lxd086@dEbkuu_pY9
zQxVm_ySw{SGbU<?|KgwOzzsVGhl!Ao(4R2QHa)VifF-Bd4^Nqx0+$@dUX+%UguPQ&
zub!HEdw#uNfg!>yDw_G|xnuCz*;y5HrmHVygv`wHvgn?Nn!0-5O!<c)3k!?)y1FzT
zN1Yh+xi7<#7yjZk-A{yHWRjDU*MMf6HwOr}?3?<QmaotD=c|o}=5{9wHC0sbJr0_-
z=h8m4QJ%E*xvM-S!{&V$f#~cS4SdxPznaRX5tcu@d+K(ocDrrzJk?%Kr_uHclAg7-
z^{q9{=OZMz#JBQt6X?CQHM=*wSgjDu`QqX*nDbD!a=rGOr9(uw!XhG!5kJqdH!OBh
z7+Up)lKx3C&0NdU*3lVu{`;#Jz6jm}RN2=j)AxQA0~YUzfAMcpr3ROZ-~Zn)-{Rt8
zefQSPcW>XKdM=vXoVAWJXMK)^UybKTg>ML&)M;HUcwKhWRD0jedgHo|(npC9RW4nf
zZl8YHhcEN-@o_<=#l<1sr3-&eWb$G_Gm4E~S*pvY;I-C!-ke9*Yv}5ZL6zUWeUm?A
zoAa=T-(A!wrSXF$Kt(~J7ZMWkCqiKP!POZL|DBY<k07duh=}q1Gp-a4rDvI0S!3QS
z<Ks|(<d^hx>ihcn8q?DYqz>>hgYZQ!p&-0RUGFqL1UT)_taamy`A=K)nr3+h?w2=n
z=w;pC{IqD@F1opq<#<5yqYeMD2x9wm>v8#P2wKfoqk-qZTI==f9UP8>#BPz`C!BC!
zw(>?~mlaQew)<<#`+L2cGkN7UzHFtu3Gu>7iHcc_MgCi-?ccv6F5NDjk+SRS$)M<%
z7^KLJ4m;{id!b<y-o3rOzB2EpIW5~zbV9<jgL){tyd2NI>GRaZiz!bu4;8QL$*lD#
z?_2us-@n@)txB+vU@baMD#51t)f9yoz}DBVnIB(X9$nemSAl#qYfL(S+pn$nDoCkw
z>NIw&V7N-HgOT>!9JWVImuS#Gdq%puyX(4FTo|3491Pxy%D4LC^QD=Yzz8aV_2YgT
zSp@}bk;nMXhsz@u-r*O&`Wz;e1lBTKmODZ4jC@z3zV^$qB4Eje#-&|t?dIraHZ4WS
zUZ(2LA1e^W9G#tg-L&IxlMbbL)bBd|Pj1kmNNj6rWo2c&MH_){B_+(Q6?%t*zG&E$
zMuS8xm+N73HKzDKhK6$9vPylkE=abQ+uYvXNVP2Q9P>Kob#!#hE+{~c5;=L`?fvoN
z<MP&XtwnG6ote40gp?GD*Zpah;oo0%atf!BZo2hWlwd+Xy8R|?o3;h}cTJ%EY9v^_
zM>@RW@c!P*RpfC`U!UaHH)}f+d2_8EE&~<p$rmf$G>CA?q0<NzPGUAJj2wPyxl``V
zeBp64AxqO~P^Gs$nqg*TC9SDBAKY(jY^;BGea6DcDQj%Z_{Ui|l141Dx|&CjIx_nV
zgZRgx2VHe_wW^j@X!BtkmFZaKOR(L}50=6jmfhJlJtHnMZ~qmFAtKk&ZeiAXzu5h;
zzh(MCm%Z~w#}|}Jt+Ii!F<Eo-CkKrik%SjiIOrs#q-!TboU$@9=pVhVjPJebv?7d$
z5+(8`j#@`bG%5n;tuo)pfdPWm{%5WVg-XE2f5NP1rcB%JbVNX9r!L|*BHFI6uU9(%
z)#~Z*H@rAla=km7)#sv+{B>xw1P+b4dTXkmlap26aIcoT^97_J_It#$NJvQZz}#}B
zD9*LG@giQ4dWqkRSmv?U3US@16;Tp0GJ}!SX9Gh+-66!xmG-}XL|;5x_IRVNj-H|z
zn82oS62!I{OQ^O7|9Zj?iOUSXyHx*0_Bxa<PVLPb-=N3t57PLR;O5Ixq(3~?Z3Uw<
zGb2~-&l?*5)-N!%L~XFE<PDxsLaQDQep#atGJMIQ!)D>!x91J*0qP~a7wvG*s-YML
ztPpvys5Zv1aNw+*oaD_d!I&5OWH+8uyN;J5pS=89Jucn^{iYx>ASWoZx3}+Ls;Bkn
z@jRQ>AY74c)OE>U=|5hMn^4Y(6Q|cAYAbFG<ZM-bK$&q^vwrhOQGi}jQi$(M;G`jO
z3x#Cv#Ok=|OChB~4{Aapt(Qbl2hZG7S8ji4`h7iO0E3b<)kGs7guHjcgY-J4QPOHW
zFPHoY#Q05x(RG&H^dt7HVoE~70oM7c``xj=_qr*&mw?FnR*b$NC&0ZRjSv=-tBWeM
zoq^g=eu%<_N)xCspxC=A@nHo6f|?W~NIXLTUh89dl=R%_VFl9ahm(r(3zW_<I);Z+
zXI{{Lwu^bYCihTw{H}C43y;hr#dp!J*qc&nds(~BeIy!Qj^{pzd0w~>Sn~k`39?rX
zXu_oD%uVBv!Nn}2Lvq+?$L_c>`8<6uQn2s1=C4TIo%9zz0zXYpJ9@DbFHbj1B4mg+
zl$oK5)yhK(javx?@@8P5vV{^n5uS8|MiLDn2wbQke)Y1PrMeFXQ>d`(XL!)%Mk&CM
z+21c7bz;#=hko-|kubi{g<NkA6HP==g$jw9z71fxf6)kMC0=>u?L%YZ{_XDN=jr;S
zK&v>)piaNZjEeQQH(?Nj$D@;Z&f8NYGkX1ODLh%lfDd;|<;Zx!;fRYFqLptT=q;du
z$s{~JM#dyeGp?l6ZGhutoKHd!WnoWle3o9KUCKZLCVhT1<Wqj{AUM+!c32u?XTRCI
z<RgT+5};)hZWiMo+_}b|_wA;lXx9@XGiRm-a3RKBe7e`#wDwM2m_iIt$Cg$1;0!zn
zG;wRqqa5<~&LICG8NG4_b_P$1u5n7V+4{-9?t?$l6?y1o^>Jo(nVZ^UP;?P{$NCf;
zx0UB*4{LxxPV|v^U4}RS{FTCapNy>~nO@}u_jlz-Bpd5QDzF8QQO99nLbe{%jb`^0
zXPz{<v#*8ki3j3sZP+)<r6C{f2{fj{!8dg5%5gzf8?THgD}G~;k4nekVS3+{b2y%5
z`OVuA;x$lm;NKwyr7aL)$SQC^;u-4LZi*EHq)K8~DP$H+gfdQKfHUO0V+j5b%izz*
zAh+q{=(swZ!V9%v{|JAkBnn%TAzmYr^v(UhsAH(4F98ur04j`u1q)MBPL+h{{|1`>
z|GW{a3Y(TbWyIv)*%{iRNzMG_Ve|LzTwGiPw%%4&Ps3&MXwPC&0wg7U1tX=Dltz*-
z8tUpI8m*7ldt;u44C^^I!XyCF9k-~1iG3`Yrek7a@+FN)373@2Rb*0=eylJc{aQ{A
z3^fJ|3p3>Bt|J!(&W7ly9v3*&F;xjuidh&Kp2m|Q*U`!4gB#z!diA3*DkqvYMg|7c
zXHCGWs;V+vrXeTCsMBKCduha!8y(%K$Bt(4k^rVECzn2GgxqgOZ?i3kCoeBg_g32E
zA$W=!3yGYZ9EF{Sq$G0utFI40e*z`xu)>|+O9VZXW+5SZP0P(qXy23$*JO%=adW@!
z2^~=E;_geHd#RYPWY|AjUvX6T*HXuEDzAGQsd)h}u*loIW#3(czTKN2%GUBgqUmYn
zw12tQ{l!nYT&kLma(<7RWH(H;l=F+Sj9*Va?Ki31q3HlIr`9hjBeJV{cvV9oMbxr*
zGmaH#P)pj8SdrRnh^BH+vCy+}{*QiX#O+biXmzPQBndF?0rX?%3++qo3td@%sTR7&
z=HK{w1`MHa5jKJ{!M?TXR7oGCLQ`)Pd=Y~r5*Zw_1~hg*_8q%3)Wy85srOk&9~P5U
zu}BMvirZ4y_at-8D+z_uoO4I!f2<^ad)4b=P|@9hqtTV04n%{5gapW^$zeNGM}D(b
zc)@P*TIhb_0!a&l^Da^?zSxyz17=jj^Rm>&B=lRfps`p$VOo~&(niKtdCu958_b5)
z>&s`+BR-;Y%gZ03<(S0DM=0IQTiyoV{i4ZBCXkOzLGM=W$ou?4OlN<RXE3`SdsGiC
zIJV6eI`lL|)0ZaY;EROleL^gQyXKPmZMi3Bq-G=%w3$wQ@%5f$wnvBF-k4YRt$)we
zy~Cx`M#ZX;GSq=<C$Q=~nXy{%Itzu83Z*;i`*H{PKq!9caT_t=vQ^>@s(*f(pbj=n
zEM)w3t#%`)A#h3lVHZ@Kj%<Lw*0FXI(tv0Hf&?5kb`uN753I<Ws#7F>!a6%D3(w%4
z>-Er4J*`b}v&81N;P>EfB+EcAIGASm^fg?mq>Aee<8Jij@X3?Wvn({|={S22)8r#M
z4e1`|=3TsduDt4YqAX2O(x%*9m1@}9k>HU<zZbMT`mI?>ES1odOU{;Oz_wvmHrioX
zf3L#%Pf#~+E5^?drRuEjQ6n@t3)8qzBg}^V=eu3dW<K4Agi#u2$L8<HDyRK)8howt
z{0w*(kB}i2Ax4{5?>X(CNn6Y?e<pu5>QQ`~(}w@D+{8W3NY1h8yXtlk3iOo!Y2a(+
zq1hO5nI^(8++~S(PLa>SMd@<0>sTYX^nJ1Z3$4kW=R9O9E9fZQP4^CT8oZwJJPZ%1
z$*&Gi`L5{HCG($ZWb}Kl?3fW$#qKJ_!X~!A*XBCM`fk}V<SD3syk6LGxIlAbNWqd1
z^oRdmv7l6<RFNr6G`~E2l!-*hma@!1Npvsy$m;_DDu9s$IIYCYF=5ic+i@SdPzuH3
zV-h|3pK8L#KRj}%s&c`bc~PQWxB`nlb93*FjEq(b#qORAo7Bu1EB%_tlRe&`fxrKs
zcNzhf?+SR~#Q3<+#j*!JjrT1#|EJ}r&YJ$=T<lU^HVqriD|Z|=Eypr*R?C{Dul^tG
z9KcJg$PL=K!RWNKu)hlphNZjD0zXY!)EOWc`{<~Qjt=!J1%=muMTxcL=c7iwIHyoA
z(?SDsfZOTT8qgj#4grR~sB%BE0D{C*okoI-MF;%*t1<7uf7giTIqj<>WCwIVB!v1=
zW!PV7Im=;WVnWByPX_wTDUzvhsuy{o1(buMoxCW6tCQbc4<p{UxN=8Q3lW{%b>j>4
zdE6-}DZK|QKU{{M?CE<Sz_ZAx`*Uh)c=IoO9t6vePmZWmMQjUHf{*`gIv{`NKiDcN
z6BEgtdr37aZw{KHnsmy2Zq(G&=40q(k!^q?kTle*oGCJBGL|`Vez-#OlYi*PkGWrU
zmYPaRxcmG2hJfPHYS)?(Iy5icI@DBG1AU}FdBntUq2ZG$Q(TCfNapK(PBu0}0OMip
zGXOH5_mb;!h4pqFeBb9FBPQ+!?ECS|^mH#P8=Izu1*-=D%CaH?bCwZNQKo=98hCno
z{t02u)C0V=uAw2w5gyB^Ft^<5fl^QY=S<gO<k_G41slV^fB%+#|DO86?RNqWw7;|S
zVE4t*@m+?<((ROgrmUnundEwm>|_0=rY1yV6leF~C1R``{)b_6{B<a`=KnuQa{I_%
zXWqPt0ajMl%k6_-bz$x8&CO{@dVq@3pWgtLsM6mb)p@NeAX;}Hs04%X&pYF=K0E3f
zt+HEdvD-EL`S$z$cIC^u>ohTMQG~c4`Q5uVnqvP<<K4T62mao-8#E+DM9<3b1iauk
zD^i7%Yxg&YG-vmvrKLVu|BV4}*wp-Y7JJ!$#o1dpZGi*<T?J{u`+VN?cu4o22%$=x
zoJ!GrNKH>4_O6&P%bwiLp4~^WIbG3Usd&c8`Kf2@K8o`2eyz_Pv1Gtmi-i3ce}z9L
z(wvk?MdTP23mY4;RR8_^7v8wy?Q~FI&u_KZNEjt{FQ}!ZwR-GY>2YDxs8ep&kdl#s
z3%JMVs4~|l%W(Mj-GVg9@(Z#14Y8wrUHC%;`v+<a)77_r@;%G5fGicTZUBRpY7=`)
zNl6Ll7t$U6vuDqUm+=VuYOyeZh;Vmvu~9w5(fuQVZDLvUoH`f`?#NXnI3gn8)z>bt
zwW~ZX4x;N*5)uN=_Gj~2TByMRRk`q2(Cb$4$B!SYw*LG`KkBU)Dow{8f4)8Lf8WSe
zP5eFZTI=G^ydNN*56HsMgk27#4GrnR?UJA)HKt>I2#I1OO&~8X4+V6`bu&h`;NL^}
zO~sOEs3mOoV5ynBM7^x5ZuX<FiGv_BGlsD9pN_r=Dt*3(RbcBbem)(6eLDS}q$?vK
zfdu3z?6^UHM022b7H5~;17+%LUU&Pt8|%Gc$-*ui-UGQ4W__LqM*i1YK$-k#wNQ@>
zG=jNyZ?R>so4-EYsmBLd!6+Db*$oZkS65e!$9+_G`(+Kt&|6lmuL>3nLSOHB*;O`*
ze)B>dB@Vj8O{pn4AnpKNjey_!7hmyB;T{M$!r*8BgM$Oi7l#-L4M<R8pH4tlp>>F~
zId7)qALM~y$JGubpl;}R-<=f|7k2{HB7DK7S?N#p087ErnoMm8AbR*>f!+y8Nnsy8
z&gr-;ISINR(N@>gyat3DC=>d#<sS@^Udl+YV}=Y44pKTynKB@_p4xZsTq0uP<6oAJ
zER?tm^RY)+&sQ4GnPJ^maO-h<>=^n%7j@>z<CTRM&V+2RHzrhCA09urO@pm54o1tp
zWja|Az~>Knj~P?F)oF5n!@#KIK=C9NCxqIG1AcdPe~LJ9N`D@HqSwx#{|K8*XOPMj
z*Y4nKv0rr8*|Z3L>uGaG?c;(}h;033U|LZ(76-FVF~YzT6Uug9MYg~&(-FgbE3E35
z`o#hg5Ah;YN~V?o_dxF-xx9ei-7BYtC!(If(;7K!>Vgv#y<>4hBtO7H|MfyXyyv`v
zCPJ+CFQr){wM4rqZz!P-$t6jWJ*=1IX6|uTa!^OX=E4=@mhPTwjIMF|u+CDsP0Qjj
z5hOl3Xjiz)5yO^x&+v#S<(pz@h&Bqe<8-zzpd`#C9#%R09wig$w!j?2{X;9{^UTgN
zx;XXnGntVAxE-?9{)t~H-T*<Wheh3!?9ESDOtO*2piG<ji0ho`E%F_*)%tvzVC^X!
z*q}mhP|f$U%Z9-Iah^G3XyA?MT28p``12fI>8KJ6;WY2=tlvCOlrGyf7xd$)UY1*#
z1cw5e#&1e>U$ZMV{(KG#3Rde`8{M=A_>0xvm?0J*uJx~x<X2MRZ{M*#9(6^1@`EIX
zElntwi2?c)wqBgbe3fb4vGC_s;wRIlxf$K`ZoWx2dWG`=)p4^Itu-5ty<c#`h{$VF
zB52isqh;obb@{KSz$$Bph>~bIpH7I|FE=^0uidl);|X70ccI{y+OTP%r`ff^MMN9C
zM)Bj3TTHoUddfPj<;8q_^X75=$(&$olRR_b8qYuWY1AK$I*8{Rf3blbD7F#TOlfY2
zB}+?B1^SOYxq0$={N{06wI>?0L+FRm_}_S&205(+W#7osr!&7O*-*jdy9ZLJ9niNV
z|GwU^^!yi46swji-Tq*<x2)jH8zO=;*xJUCplvyvdhe0bj;(XYK~*=(*riH*^6<H)
z+}>Gcolu$s8Qye{%Ef4_ApUoxM<P7<%G;hO4T`^rF9vA+lnbP)dH#d^cd)XzcC>Jc
zllfuXAJPTwkkv~_UwtLg(DgjauLszqgVQ-KDJcl(i2*gzJl(2enf{GSHeRHTd3Gm;
z5Ri*tNghEp0?(d>@R%~Chyq5`W5s_;vs3Kvufrh=&Q7Rf%@*}(q3nOSRPemjR(n)L
zM8?m05O1&QRHz<4EU0DYsR8s!4oGCsVOJkuWNN<>W%48pa$U+*!+MDb#Qhaf1N{Bp
zKP7|26%}!es*B+kw;H#PEtTF%_DR8Dg#2l^97)(6Q`hvjy?uQr?6Dy7<KT=>*BGsX
z4t2Q{A^CGMK(zGqC{PE5lo~O+ia1lGq$FL}y!q~!5syUKIi8}0x%rwlo4<c3`2A;C
z4mh9Q6nE8sh}-~z6kdlgUS3_@GphwAUX%cT)J7eSe-{@h9r0rp;eqHHF~!-@(a?$}
zE-eo%N0lWyc0D8CSWnLfT*1tVj`ooYLM3p09{-$cP#W+)pJ|KV?E(~Zy!)~0CBHE=
zK=NQ>m6eDG3lsCGj=}NyBa+a8krwGPOdd)SB07iX8Mm~Ba&>f{fp&N434~BEpVE%r
zM()|s1Ste}g!iAzFdyo?lza(;@#IK#8Sxx%aHXcDtvM@r%&^jlVqwN$PMGgTfxd*~
zf^SqX=FIM2A*sY9#>8~$8vmM`lk+P<ka)U>)YO~8_yK}bN0g$CKulAp^o-j9vrCtQ
z|Lk@`hnV3lxama69orROz(0R-HyVt&L%8urJ4yn9H@HN^%K#xdg7`}F5+0;l{8p7U
z!S_%MBuVfK&(EE~MH$dbI$gQoiO{2C8lCCI#iv@2q`$K;NdH_}8N)XMO_<q|QsM{r
z%k>;Y9mNb9$tftHtY+L6l$9yfY6bJXmJ99?19OxSoDfc}^D<Zr3{UPWBN7CbEK?k&
z&jnX7x&|SlH^)v|7JLso0}U~Vt!$@PS7|LQEhiQh*c>&bk?91wF)4`+6^TswZ+Fk!
zff|}uScuWu+Inj?zO`jiTUXb)aV%ak9je1f2wwLCpznIWPIxPcd{ocm?(Pmjg~}OS
ztE+k)cglro;nl$dJGN4&Z}y^&?3$M-C@5An=x81j7%s^ah*`)7cQo{&)83~9acbKC
zpI!jmpzbdP1qIRS7rBW&!_qJqGCZ2#RIt6Z^$`%6vE4*5u|iTp@C2k+u`v@~G47>A
zY;GEPrQWHk$_*=mu^k2Y&zWKiMuKeHDIpCF&CiV|3?@uim|vQ7IPSX(Cd{PE`-Gp~
z0K9^2&gg(>OHxwr&2H4uHg@Q-Nxyyb5`Zqq?_TEng5S3VxI(-BsH+(l)kQ^Si#6<1
zsmX3E45(W)L>6^gJ+EZmuqLpuvSPVYNW-{KRplNGd!I8u`6rK4s9y5=?OVPrMNJYS
zUhv8~KEpcgsKw^Prp)TJNXW^fzPoY<^bCXLz_qd#`0DF=khnt3#|l|}{k32_YQ%RU
z8cC8X7zvA|aQl2}GMqop8%Q}dphTEpTxUEMd=aPp)iRNl%yPq>Ht6CCgZ0<ZRbjnd
zCgamG$v}!a>Uld05(aZSx9>>B=xfYmndP9*Jro;o;-DMV?%(>Z7m}RIP2*vB+L!kW
z0yy7}C3LCFqyC~{pyM*P3US?hc>J$f#H>Ncu4ORPQ`be$s~XSvlvp*H?x2o)5-Gsn
z=e8mj$5amVsarwUDSP^%YeIoKOe*ko!21Z~SMzW2tPN}@@?;WANK@Q}68o?k81z}L
zKRkAv&oHYJTr<JJ=}5s79(9~MF2g~w;ZzQkS78qu1RF3Ke*9T*W}d>4_m9wWs0tNF
zS=-llKPp8Qf{it~lQXh=<Evrf4^vZdcK-b7xn8fewdN}Y)A4!9q&r88msQJJ4~i7f
zJbqV#>%z{X|L)*2@716j2@&!Men@dWgFA-KoLfF6`S;dGIn+MJ^D<VfuVhM@c*rA+
zjf~{Z!*Nz|2fn6ozfYy~OU*=Txil7LZAM>p<h{Khw{D!<?#Sq6l51>#A1f%cKZ;!d
z)+0z=0HFXdLm*Mb{ZcMm3h@@6^5JN9xyOk67=ls$O6p_FzrGK_A>6BXd*DYWj76zO
z4GO%5mB!`|(RxwGpQs{TUC1k*+vctO?u=APz4A$pE9&IbFn%o_?z`c$Z`!|B^~toW
z=)Ar>l3%M5{x)bJ;Uzg1CX!N}N>{g!X=MGXLDmJIg?=brl(&a^4<2Vhm@fnSV_j}+
z^n?pf_x;cKqNRU{o4)Nxz+l<M=khHMIT*V2uKg_e{Y6I|KlxaGPubwTEO;G&QK1}U
zP{e!@5cijU6g_6*wcLXNaw6*fi07L^6gAxu0?HobBNHq}uCAKs|5z;~6nk!s*bi8g
z(ILSXI5%w1fuj8!EdPO7X6_WJ2$U7auC0Hgzg79gke=}6+P+cW?uUtWE_geD1*K-~
z9K#k1VlUE_77;OS$TAW+-fRjI^aP!8W(3#zyATgiKhkeTrc1n^_x9!5Q|`Hl6~`pZ
zaATX1A{KDb>g)d`GLyl9=o!navvL>vf~81xwhy&rIN+|&`&x>%V(UgVE`u-X(z~ZM
z`zmLj5tj`dw?*M}gydW#g@cog*5=|Xb{-Q?#C>+!aULsqvZLzce0U{`{IrxPU+$ic
zDO@lra~|v%p804q9{ets1Q$`<WGt$(H-WVjpH`wjEn-qW3h)<aq9XE)R8Tl%oJa`Q
zPbfNV%i2QP{cz902v%H*m7JhXQbA>*RK(Fw))w!36b>yWS_%+`6!{r$E82+na`V3`
zB&}a<XVIK)?{-~y{UnX-1hZ~b4U-6-0}q#kN#v4(r?4={)q<@NJPy<6PeZs9fC++5
zRP?df)u4)Ajavn6omSagwJ|n8_=M!-K|g=KnVOvqYWW)*ON8JkZ0e;5Sn$!~@3a4>
zjbg0mf1`YSvasm-?zFE5xRPEcvdGP!npHu(jEoG}w1}1xg9zvzouk|$;5~wFCk%l9
zSWnH&tb-I>e~wfT1i38QVSvQ6?d6faPKzrc8X6i48(Z4AK}S3M?(i5vGQn|zNMRk#
zXn#7c`2ycn@$ORKZ1qQwailS~tKUh-J;W;6b#<hOrfk~poJHmMt>zHA(OV6Tjk1R2
zt~Spb<V>npBi)vC`dz`az)LW<)*UntJ}FB!_*ZUO&ywc@XUA%AE3!<%&r<Hno}MpI
zIzYE%7H0u+gDMLOnC|&OE)z&EB}GMgz)As<t@SR4AMfwi#1Iw)gy2xN22zkFRQy&C
zTt~}4G+$;lH#bv4GjnqTpr!xe)mVXp#Is*Jdwi-?v3X;msO8p*HV?mr{DU62Sf(P`
zd_(Jha@Ev;6w)7*l$D{aW=th+2-;F(H0j{g%!h-Nb@W9{LIUa0X{R4XmFuwq1r9oJ
z<gjbkXIE8muW|!X2EN>o>+bC>mYSNX$3=m>bvryXlxB+<{2JKV1Y0hjAMgIY1G&3Z
z=jPWRKD=0O`(LSMZn7gMkev=_!H3U||JM|@?l^yDcsS1cGW9k%5(K7_Nv9@0Nh#a}
zEM!6+hW~A{7F$zO^F1(|fVAgpO-;<^rO1u`sJznBr+U4oAv=eMLH!#NAl2}el{E74
zi_oQJm!R8Q;5FFzR#M)zHIg<lG4Ule^`Xeg06kI#^Ww9(aj^cS2LP`Da$-(pC4uEk
zsRYPpE2j&70hv<dBWGH&|B`NHuB-U(d0jIq3_NP_PoFqXPEYMNA_UgKYD2R%KZvlM
zRg{$7w|TG$AcC2-HHhKb^-ni>sb#6yUH59ppbiv`ulnW%wTW|K@rWfmS8GoEy_sIX
zVQNxV`)GcA&$MFcxq!h<h;yxPlDNN(ymT5M{^B{RtHAgo3*?f=UYGjMBc2d~90~ze
z$ZC1>!E<U6SAzNZc@}o|-f!<p5K>{)5M6enza9&NuY#gt{_9wxm+Y8dE+q|ekzf}d
zEkW*4T|WexD$^x}K_&?iHEMq-w9_rnj%1T4w>c@^t{CzVwF)Bw4Z|*nlIE;cPVq{2
z@!+2iPoHS2$S!q)XbfUWOs>WWe0OxRbX0%R#v#|GLzs?FII&L)6(A2gY7CN8N66<_
zCX(Y^(KABe(fg=n+1;Ru|DW(yU@v1hI1aI*uimA$alPYnaHBZt9KR`2A5fKq5t0B*
z!^GQh_CpcH;Mp=^>Y@5s_M~!INbzNM0ePAFC-0u>Qi`3T4IUPE7u0o2c||6Mcpkil
zr*f!};3CdV+X3}9rP0%R2?4y!17xUZllsRNbFfa#KST&*g&{#JgJDw2=?#8=&GOJ>
zIkdXe7Zf|8+lvtA_teX3gDY%u4+K4=Wn^Kn=;A>CaFie9DXZG5pU23{iuN8p&~W4J
z`ts?yUFif>c`-WUtL@ipbR=LgA0IZRTd4wMR8=epvgQD0+}2{Awen?2vMd+x_3Dng
zSFlV!F?QWa#VIm-SsM-JkbxR>W`C>4(8-G$%Kp?5fjHthQ_D6)EVoX$R;Sf6T#rkf
zp=Gl9vBZ4XWD!wQHR7<1whcgq;*%H*H4_PaTpkTEi&^)T6h1ds8q!Z?_q&|#kGNbA
z`h+d{WaDU(O|42WLfK6jHA0qDPEbmcW5X66`!>Iy#qP+FTm<KGp~>d9W;r|}K)%sL
z9cQyTWg(tlc=2+-$p#$fN$tUGGVJ|+8ijeZ@@)1_6G0{gL~`%mkph~71OcY{EdIyQ
zzi%{_wd(<#3s<l{h@kMb-tJSB&^P}ELf^sE%Y5t~(s*A8zu2i2em%L-F-S(G%&)!n
zui2=cRz3`VSN1laVn?yh2+YN1R{*w|g#|LC<23#5b}?dY)z<B3>+13CnT|_GkYPdC
zENf*I7v@k+L~<J;r5jlN(YB9m02Usw9qN+SNi*#6Aa_3=e5oKlL>J33tC_v(qnt!E
zjW-fs|2597a!OC;w+~r_UtIeRE9XbQgeDoCG;4n?i6t8~z>EmsXl_i^>C4i||6W<K
zD)-@s#lBt;_Sri?;!DBMcW_^Ilr0FTvaLj6Z5$sfjxJTq{O24$9B@_cK9E8sq(wgZ
zgm?|}7~Zb_#P2n`ta|Cg)3`dh@t;{vf)mY82;k92y5xLBf}=Mpe4Jhu@cI4?=jP)<
zW{^iK&40gGNo)OTLD*$95Xh=UDZ~O_pM$glRV2?K$!l#z+IzJf*>8+6zUHM-?}}NK
zyIKP;FVU5p1z@o%N$B&I1NcS!R*LQ?J7&&hkiT+a+R1tRE5>$o7DJqO@7}2`Go?HS
zTl~QUGpyD&2o=gNC_o(WkRE^9#Lu5ZiGO1U^P&j`9Bt%nsrxI49^*M|4X;Vn0r7n1
zhJ+HdU0|rtWm1C#@jX=P*iU0EQx5|%7@}}+a-^e1#EynU|Nf264xfuRXSR-7cuBw(
zNYjOI4V9Fz{kfsd$w9PkDGyltsb5#uG|gJnhTw39hdJR2IONO;%O`>XXqqfzBn(j=
zS_6j7n8d9|9&5IOsz8*8xr<&!K&2(%47q<mYY%pdo15FM69-V=`J5$D!LG|m?AZj8
zC9o`^97Sdnm6qb%)NwKhf}XLEB*}C%>vZXSCY5iC9yjAdLZZL~R5c`IdA^IC4BLC~
z1tB^ZpkU+%zEJK91`5NS!wU`}ia~Y%c7$n7|E;#Rf*~_1V2QN4mUO?Q41ln3s6oie
z!1oXr03sw;{8^BtK%3_TLySLM|7wPhne&`IXlQuYzf%u_99>-UYU0SA5FrEXSfHRl
zx2WMA_(Q<COW=zNcr#P&NfSPjlH!xx4E|Q~|B+XKrh^3e`S}%<ln^_@c?l7i6Sj8j
zn(JN)RFt=@?>aQ8asWb;EIU{JG&?ngS~LID6_*zi(f*LRs;=CFrO>08q2I|bJow?f
z5gEZx5okUr8o`V){6c`*79Ah&pP$bFEk{lPYvF`N$^n>OzDJUhrOHDSz<Utnt+Kzj
zcUkgA-W37T#Te3+3xVR9nVgZ>UHq1Hb8{0qIzJtEbcq3Bh!!3lJhLy5PXgKnmb$!&
zW)2G%7lB_33qbq429pvE|LHZc9IMJgqW>YliuJZ%82~KVzd7k||3~BK7#J^0jZS(*
zYq%e_evASr0b0JOD=3iJ3@tzqkt_IiL|<YLkPvhm=0FdAgQ4dgbI45n{OJpl$3Qv-
zsuya$D$Avb9bY{|{tV5U3R9f^Xu8nt7?|PLFZ7gNfg83gm81<7B!7U_gNcbLr+i*6
zYtgU(6gFD>my<wc==gj`G!+{hj(F*&F&rOTC{%e<5NrFTgF=@}NTVXtMil(3%-1)^
z3TQv)LXLp^1IY85b93H7^8AIarUmF4u=Bz|Y7QD-SO}Y$nIVj-TKKzja6tCGwg{}B
zO0yTZd-hG2?qA)D);=99HX$jXT?5MtH}GPv_Jk1Ej+zA{I_mw9FIAH6ArRAc9iM}2
zAMz2pj+4_fcMlJ{+e^Etsi}^Q<8j6<7?Br`4<(0|><1ZbIY`{ung6-4us#?P0ATg?
z^*%Qk7#Q4KT(tA|q{RRQbmTgTC%iw^QVswk;bf*!(ACWnpO)rCjL<U6zk(5n2erWX
zHXUBk-cCbGO4<lu;&}fAtp5_oD|&6_vyk-kFT(p-t4o=PS1}ca)opE}`8Bdru@p3Q
z45$TfiZAgsYyCkOSYvjKxz3T%&>#n<N=eaHtD5<pZxePPJKHhKNyrW(RLV#Mbe84G
zlaz7eKV)HyzN9aKkVJTiCzShDrK^4N%^pfI)M3U4yvpU`IyyRXQH4^GAOuLS(hyB>
z4LR`DF?<HmEi^Qg3*a|98ikA`z-xkOe?8~S`#T(n-){%Za8e-WB6e-hXHp}?+NJdr
z$Tq?Cuao{00wlz&-Xz4v`T|AI$M$^NxfunoST1|#CPD>eVk%ZIJO@mG_&;ik@IKH7
zKsjh?vV8G``hcs%*9;3_&{2WjJRt_3)jN_YHzEFqij2Ny*qAgDV^&<~H}f@>o>z?2
z)6=$m{9ThP_+$k+f2z>XxO6?(lXdW*op0qbzuVy+@9Wu_l#Bfp3;mwcqwL*&-XUlA
zwYmSShlPR|CxMbDk!04q9tXMmiYIyNVGD|>tZdJDp0Eqvj{}>3rJ5)Wosf$nj)?mU
zqu0v<o$1PrH`jWH`+j%Bl>b_;nBoTqgPYgTd&)FXY>2Q$)Z~K2nc^gh-*)XfzVb4E
z4wLFS|DCksy32@zm&PDdFfEx7gY?qssbIUMZWj!s71^7bDyeXy*>xk6S+b1NgfeVX
zMkuH)+>m@~@=zXCwD`7NtjL~ZxJb5}P59T#!(c=aGAM<UPp-Ogbt~Gn$^t(ZnLoC%
zvLz_<IPW;wEd(yDGP1tkLxeR}l(jXcD1;&<v7Hn^5$xpQjY-U+sk(dcV?)CG9qCiq
z$d21FZ!mFDoipluciY}{TYDujU=~&-sS{rPj|YYIA_sLNMfKAUs)gN~^3#FSWbg0G
z)6ooyM%zvgl>W{}E6P{_Yv0diSl{JNBML!2(f5xE0S{&E>6V1>r^iI_S-9jZ4Lo@H
zVi`r`@q5ub62Fm=fy-XbY~cLyRzr?gkXaL(2zjebjDmu48}KGZaLU%%d40X!`m;ET
z5|h#0o`zg2+^ZA0E2~qF;B%H_G!+h4LK3~@jWf6m`Q(-3k<)nKfO-eJEEUjacyzQy
zyEMZMy~y32*>V+1c{vB<V=_u@ba#?8jx*w@)TI)a6jZ8vhxO~~6bS;C`Cc5OiflX;
z7Ds%0GMkr!LF93*$SDrB6mi!M7B=_(asNy67sGrf$rMJwHR~7<0Qq$G$<&J6JSEut
z=?+v`>Fza|{DRVbx9vxBZMQ^F_A3?HUnuzgcco~QRE2NpJonX$g3uG@!L=8MZNghX
z!jvXb3Zi=Tl}GPaYq4$G$d3C4sE|?2lj!TlmwJqrl%*m7-r_F)3)K1X6@4&&4=yOA
zCc)R}l7_DEGpD5J(oOlF<5T;X76rtrs-qjfdNo(C#3Yjv>+4_51NrouNNs;X$rA<g
zh;-YGKZ#V=nr+8lXOsskIe{e&<XhcANUm`4joC8nA?Lx(-W6B+x8|Vw<aDju_UvD{
zE6`qo!8vFv$RLm<!SI}YBnaOR7fq$>qD}UWfT-gMNw9AFW2j@%CRyy>wZ{<bB8J~y
zA##pdS}K{SkgdhDa1Gr@iPo{jVNKT-wo;}GrOe9Vjai^G_pmjpc^1;Ow(B@tyc53y
zM{Keq?|A9YJarGhqhUi33OPr3<IhCIoob!(WsGasm`ysOIVpwxJabb$Sz)t^N&EB#
zgkA(`{Tp{5uE3EO<1Hsw$4FStOU2PH{~><kX{)S%;n7V-W1vz8LY}YF8sVIx{~B!z
zk_*qjt^wux5|<)R3U@c=>e01(V4Ve+)lIRR+IUGiI(qiIv1K{e6meL5e7xRDo2Nk%
z;Q-u)=Z_*)fd9a)lq74RM4nv+E|Cxjai<w;dg1b05Ai0p>cV{xrg+Y_OM|IHDTHht
zXR!U1lfj5bv%_4AhZh7)#UC(OfD|qe+JO*2D=bW9XJ-f4<4Yi8K-o=Aluw>KLF&H{
zyPk*wuHsi9?X>8;U@d63j*75p0Qmr@OUOs(nEx*t5K@r0Ne!iTy_JNG4afS%#&KNM
zEh>MS^{{97HUJy%+dc~+tSOuy!|7!sk1irK6y)VG>ur`oe-9-A)4yJ)FB+nX2h>9Z
z3=b;;>-hSz$04qp@tGYr9V-aNcr>EJh!3!i(>e<c|F%CqOBZrrvRZiNeNHLdu8)HF
z@OqzX4vet@&xz%1xiLuQmsV6ny|`TUvzo|#ISkAleH0$RilYg1EMbQ&9FN_vNx)8s
zWeJi}S>8Y_sv-aA3e!vL?d^T~>{-GiA$$M-m|}D|$c2GCl?I^J0!Y()-~4aNNQAaT
zeV>5BmgD2&KcGD0KMx1`)36y|_4)aEv<2eY|F@!-ARV>J75q8|X^>`MaC-Rm6<e?X
zKmYoe_dRc>_q`jyg<WQR2K|wbiptCTKrssvH2cBj5n?(Iy)K$B=f}JP0b?TtwIdrg
zH>P4Yl;v&LdxUW}KYrUk)vA4vCh(~bxW5IU4p4G&+|Yi9%h_^-jPMOLHVQ5RlR8)*
z8UHMStNy0apcf0+mPBrkx(5aZI<nxm+jf@6SHQg#ImFqHFfAdJwNiC9P{I%a>@nb7
zW2{__y4c#AQQQLT7YvG2?i*J`NBImSqkpDE{Q9K@-03ptf{`fwcF{w>xza`e1m2(l
zWgQneZEcUk$k@Apt|9r$SzTSdV+;fTaSt#~0RKFw;i$Ko_XSWE694ew5vb=l=@xv$
z_i2vL6TuVieW%ys{+H(kS@J{Pg#X_xJdj7c6b-*89t(Z>3KsLf94mduZ8qO`K^O;w
z29#Tb0J-z+yLW2{r+Wu~Uur=5DHZvD6}fPehR~pa!ND&Je`TDU&WaXNhZVQmpnqVl
zB}`1V8ta0;08{B_8kxT2omtyU$u95gr1wDis`R>Zk55X<tF9(;Zhq7sMI)=JN$LIF
z6&Tda%*;B#WP;G;Ns2FW1hrjlQF&3Bo0}IE6+O6y?f(}63}Xu6!uYRc4>%17_shQt
z*~<4%=b9XtA5u}hR#)e@VK+eJPvP)60~-6wYld1a>ke=2s+QZ6Ar=;v4&dw3=Sit_
zJ2e5Flqyr-01FuLZM?@K4**^#Wm8`zZ@)ydX+2ZFce-6CZ|{KLj=@3tF4Aoa_Fqjg
zNKx|*pJ)(vB9oDao4<dr0r302$=-P2hT;J1?Ox#1K~y0iJU@RMR%C$YC|CC&!cdW}
z`__aD$eEl$Oo1aKBaiG_o{~iM`>BXtp@wraFf$u=j{ojn(-U$hVOM#92FZD>BK7!R
z>eF>SIKRnB^hX7mN`Q~APLB;PWC?Z=V-Aq)9Gj<gmb+AyQ&a|P$D7IIQp3%yY3{cY
zRv8*A;qweUz{G&*mxGyEmWO;V0J{#6&t~fU>m25sqmfUxfdq|ukH-!ax(%}2dND6n
zA^}B{2o~UlxdKW=tmia@lCCn8oo)gMW6&E`Lieim3)`N6Cd3$eC^APVHZG__q;TO+
z_R~j3^jAbvQYG3~LVkYYV+IF5<-L@JHQjCDS=K)$I#^6>7d&VWn8*GsFst#ZYGQUQ
zgsP@0B3*#Yy+1%)l52lu$><sA=4p_iRY5Pt{V%_?1cje>wd3<V8I8ol!NDb-B_)eY
z{unJODfyX3nOjman3sxMA<?y6AII~sohHUJI%MAi?&<YW;ofC42ys^sHOT6N@%tWV
z2S;=1xG`>4RY5+PE-L}RJxF&0%W-ga&fQ*eL4r=^-cyvf*dvZz2I*lhOkKH4nsa{y
z&NxoghM?g!@xm#S@XRmIb=}accH%vLmNi6v7i9ycf=f6CIU57ri(u9R;gv7XnK67W
z+>ydoYOST;C(_I62|43H*`tFJe<&OPfshM+&yERqdrBwz^9_?<aSJuY!=Q=prugXJ
zzR@+S@N|j4BL#-8<9n_@E<Dtr@uIh^EJ3Lrl7Z4aV^%nM>@4CZ1xgUK<(O-}tt=SG
z)W8_CT~r}EIht|X)iIdHFQKi<g+M|KeY2?q_ETRe_N{s<w1XO_OOT+0Hc`IYh4#+t
zUUJ_*9!xc!ch4T)kHNoqn6-}0C9n~;+k6<`23-t4l-hG{Moatpsua69c4$anryj@0
z<!*3`IZJxGq$2WtSgc}(sUDP3(H2?&zg2M!l$m*$#O}A-FZTGN$&s|E=Mv7`03hqr
z$PH}FuWtrv4jz1o8;Ws<->DW9=IyUabZkgmtlXoYiorwjBd7?0+mW7wpN_bD(dK<5
zwZt~fJ*1%$bs-ZewO-ahS5^8n-$@fOBt5R9740&0hN};!1W$4~`nv7pTCPlrczMR}
zyRdD~&by{3{bu0ToQ`eRtT+lulDcnE->H+4R8{3==F%r|6%vCP5ajsiUzUqJlP3!x
z_wPfEp59K!*$-UdJZ2VvVG-rc?gJJ{VOV+nA%*-2UXWi_$Gc%61{{S%ag8^=nF1@)
z7rJn)Eyu3ug|KCpWr;)KLq)G{d!gih6r0qMW3JcfI+1hJB{8-7-N7Xy{QxR)^Q7Q_
zO~{|71ndq!*E;|v3u#zH-l&_+y=cAAyV{KNf%_8o3gWd&ZQpOekE1Asq5|kR@VJK(
zVF%ayvO0~VC;VMH#F!|4olx2cIv@^(leTVBo)AQRi1>E_C?~v-pNz_U<x7cfF(;1o
zzLdh5nlZ@!{?JcJ>1fXC*1Y+c3o4tRr;w9_pt+6p=%3>Ro!`EGQDcQo?&tg%@L>|8
zNnKowzJBBjtR}ReAQ<R((6U#^<>h7YUxiRu=Z2u!$w@Y4{jYZ{Kq%5TH%D6i8=cYY
zT=wsyZhW>{HW6RTDNpQY7%T}<*+u`IGY9A+dB!ZXBv@!5Mn0h}00NP(KMv-K+0gC@
z>|0sc@7a;~q2G;vs)q=OiRta%O+<hjz};e^bg{5C$LDL*&-=)mCwZv%_V?|M*Iz=*
zc&kGk%{Wz3Nd<90=!<62wFLg=?!V5mMl`VpQOTgTkICz+UF1fk?V4myZ*Pe96d#aw
zUf%~%$9$i&{O&JpX~~8t&Fi2dINctT?Hbp_<#7TpoKd>ne_X>`MiP`4kKQPiYOAXH
zZ0gs%h${w@!2*-)nvIPfH1gG<C$a&lJtQP<mjj(-CLz7xaM0!4DT`<AqGtJ0l7*9B
z($;;ba?bw!TLneJw>%KYWC805NGtCG??l&UQ)(-I?YY^cf4a(Czwi)J$nl84%2ACu
z5QFG=dDS+*6#yXv^YoFut4L<0iX?GaMj{~ov<Ooo$a^u`zncVT+5ZY38S4Tj%NK|!
zI0aR?mug+WZ#qDk`Zh@#-~s=a)u%t<!!mq0`PK7Q;D}x2v;@}FUeKkN<rXI3z~CxV
z$G#dLR*bO#LMihVFBPz%BJPt7D#*{*TW)cq(|G29s4b~@reF2G>-z^?Ibg;Z=u3X}
z0gD<B17RN~9f^&NWuZl7T588bUVS46VD&$ICB5hG9!CXb8EO2uBg6|r0q!qST}yx#
zw#Kq(oC+=TKr*=J%H?C~$X2D*q)o$V;oGkdiIfY8fll*T98pdPyvMONXNnsCA{Ejn
z%r@KcP311-swRK_w$I7U^{tpR<9j0>9K7rl0{rQ>|D4wLlA=#`RT>r|LPN3I@@Dk7
zvMVd24?7sU@}h&0+obSHrhnkmrDDOO$CYijHswxSMJ~6}K3#H6?VkZRO6VNxHUl3x
z7dyy_)>2JY$cY|C$nd~(C=CTYuld}AO!{Xm>cD+Oj#acg&#^*S2u8gy`zX8<rCEa>
zw)p@}41Kk=v8<>lxV<AHI1CinTn6>Ly<xn*xw(=ed*Z0Y(`S3IDCFqmgmi>1EiWIk
ziQziJ0G<ajU`L)9YS!{{Ws}w4zF`52H`JoGLQYEhT3ik%Ksx@YjtLzd{c<8G4)!&=
z2;7l;-Bwg2_b+t-xHMjOd8<yp#S_X0R_kZa%xrAXS2GZoSyp}d=^laWbUGPHZ6#vw
zSQE?&$$$nr&Q-gasmLUyuMaDWfaxPz0AZ9KukdH=QN}z$$z*j^6(KN?K^#h+Dwc+F
zRG<f|f;K-i{K1KPL|h+iS2VG>7{0e>0VN^(7PKXag1K0?jBVB_msc`nHu07Q8wV)h
zkSj`Vb~XfRs(oj~nSvzgLU9h0^uj^eE6C3h7OG@zMV%rYTKz<Lq@>w>Twx%wNyv3}
z2Z)Z@-VKYS-+ErKx0ocTHV3<upb|A3UgZh&H;~JPT>EKu9KZXh6|ViM{c~^-IJqkg
z>ZF2iKu#FBpe>8n6i>;M#u%L2R<^bTzy%Gg^#FMznLd-DVgvE$>hKPwch@nuqJnd^
zidi|`M~5RwxzO)p1^81+My4;Hqu<8N43Po_T!@E<=W@Zr-Q9L;m{OGX<m3dvIMKDg
z#CC`>E<+q$;3)RLe%yx@QUz8$uoHs+5o>p*RFk-T(xB>y-1tMIEmAl)5IwuB_&5IT
zPTmq6rKhLMTW1AFfq(%lSBp&!$I}|R0k_m}>|7@IP+nkMmyEhFx3a>yZ2JEFA=r>+
zpFVBl2LOK~0QE15{}La+?*Hl!e2L0MZU-x|fLXxCNMmASd5R|@fxfe|vjeKV92|JX
z&O8D80Et}Y7Hh;}AWBL~B0pNA348VRA-9ATOBrV522*Q?lA)pD_-_oS=a0%FxN#AC
zU5BF|yoWwegD*k!N)A+=DDHhzNE!+N3UD?;0Tu*7Z*G>Gu`3sBE%1uv0I|GI9`yH@
z%t`+DJQW~Wq(a^PpEENu5`@257;<|+Yrc`z6xL*g$JdmAATT|9kq%_lem(zOge7P+
z9dqb5UD_3_Mo>i!6A*A2zLB+*zvLtq{Izk{&!;Hu;c?@?RSP1oYRNRXD^&T5Ow7N3
zj<pR9Q4|zt;mfg5OGZ%M2ZF@7INn{Sr-51L)Y$!Ya!N`sot>TKGAg7~ix>%wLH=A|
zFUX@5f6eTU$i3BT3O1Fqv$u!!KIStYbwA?Y-q85y#<(?_p@2mA8}Wr&Ep|jAA1plE
zoA)$56W5HOMxVJg)1*?}pOYGdV)M)&=Kf%_gSwBLygd3<G4~?&kh!@zdEMN<VyGUC
zz-9*s>??~Z8luP4c@AoE>$UY=zwD9kGECRFbp03fzx0!4zH68I)y_kj!M%bah(}E&
zZE<lZ<Cz{bna#ddo|8pEbaRiIP~!RK<_~vipU<yPwj_q*f|dk^aB8fJowc>@!T9JW
zPO4PA*^y&GqQ-=d@~22zFrAYkMsA7obG02&xapkmC^EtSQOuRNL)HH8LyRTcASQ&-
zB*`8cyKF<22$Af{5@KxGvW|U?>|~7)g=F8iUS(ghWJ#2L$eQ){%=>-+ho9?mU1!X>
z<~im(=XvhW{kiX3&@8F{!7^Ks#W!PEoz1!|@nzP4uU280!eHwU9>YXGlDo|1HyWCQ
z@7yxH7<}r=Gb4kP$@a>0mI6HNa&Xg6DsSF7-2Ig3+7ni~lonWK^cmxuNF#cr%hc2m
zcJ-2BMjYAqeyj_R)o{)zw?ZM^r{ax3Huu=S+Sm)9^-K^uSk3;)4-M3xb+SVeTs5AW
zZS-sG)+gpBK8%0o5SpGb@zwC_Puv%a?wmTTQk41=Rb`i<tid9IbUjB@B@aqr(BJ?$
z)#69=bt7XbB3Skfd3R>gU`8ZTH}W~#?ATaHY%C4%l}G<g1?q^}na%jn=W*R2uK=hO
zKKJ&fAH5s@8hp0NYseDY>bspy6bMiB61y+hLYtYHe2_>_8Igmi?{5w)ukv4X(&<@h
z*E6PZT#$yZQ9c&WxKQ|swY;i|K_y?u#ooT2tZZ5G7_&RxNG61rzv=EkBT{}w%4n3%
zX~4^a>TX9E$@;S-7v@8d7B>d`3*lc(G_xEn#0PbQlLxYcMt*Gw>ew;}uT7uRyb(Cu
z<5fa1(pxQ~t7&EQoq*l%uFP=qvk(EV+|T-&W}9~|rpL)fob^{hP?9ji!@0AT_#1YU
zauq}2UvzfIUU=T%)PsFJ+HcX7S4uU$6#UhmJ)~cc972fR&RaUHI<X*!(}r{kX+1hV
zpPS7h!#w=u1)Vp)xR&Mie7KI5lZ@y>6@s3QE00Trrk;q|UN1)*Zr@c=pl~Dk%>$iB
z*B*_}qp=^K+L)NMu|~R^$5%R6q`EUvEfBke-Nea%9;=gF*>pSd+>hJ*NYRrK-}uk;
z%wNBf`(rDOr_C*HMJ-;(UfCBkF}I1xeLFvARx`oApp!~jSW#u{539_SqOS=t7v}#U
zpAzsbb<yvPuT|OEzNcs)eBa5R5^Hy!<DzU8rQ)PCp0$=UL|X4&lX)h1_+8QL_*G~e
zawx27#q%wP(mQv{oR<kIS+cTM)N1&NphFp&2`xwcy1a@Q<Pb)EY=54gqPRw`trWpq
zsda=wXap+zu8W;ta5|Xx_DJ}HpuZzyLY<quceu-iNOYQ&h){W5Fw`dLB@D@vbF8PF
zm4l05R^<Au<4@jXCCpd1qgNI}{PpKA`C*t!jmH?r{krsuC?tH;hY6`>)LC??*qE9q
zK!rKDcC;7@*!;BfqP}ay)>4(EZX@tg-QF(^{T@qg|BCVX&$>S__kPb`pS!jsgbMQA
zZ1p8Ss?|%nncM8vZB}pXGxKd=L+xrD625o<v-TgimEf>KuWSesL4Hm(kx9`eR1xv>
zbWEoERD!3bv^2NwUr-DRe=LmB6LtNi;V|1M@h(=FMNH?hg(}@kzR*q~fI4!4MF;S4
zsu~&~Z{o6mNj(YYhn#2L-jcFFr#84h0I2xQ2E6Q{uPmQQJtM)-G;&XlS}lQK34~H*
zUr3tzpSlwghW=wd!H1yKf`FzTXpMl%Y|x3w6iAu={BZ&7M;kB<?yZhFquFlDboYIC
zI1Y?8GcX7v1T%o`Shq;43(#(4Y6<35lMn=WHvzD((s6La5h$K8T8;<5NOOjes^rMd
zwD;`HHqG9~#;4m^cjT=9Nw~JqM#jN7Ha3=*pRd@sJFK2pTWbie8HuCw*<XiSS3S&>
zbiYfmLvhK-m=H95>~dD!R26n3g?`6;0KEZlY<Yfm+P=28f1LJh?GhM{2}tc0b_V2V
zXIemikbvj0e-_n1&yjo9|NO=F-Z!(kU4+Zxr<TcWJYb0{Kz7j3=qQRn&RX}SUxUJd
zz#9wT0Z_qr0f8Ov%Mv|sYFW<Iy9bx|_`MO?otk*BM{|TNVC%P%RWc|yZrk6O)&buK
zL2vM{xvJWTFrr3=I5oi(31Wi6!#Mm9)YR0#Wk?1P2<-d8MZv}Z3D;l7&s!dpDr2$2
z0AK`XNj)d{Bj1*lb@gXSVF9{iWF#5y^aTF6q|+x)V*Srfyw>MhIKXzSs-|`aI45R(
zcQgqhCm>S6lophaQC&em9S9_jG@dGoKSDTehb{vG5()r1IMoCawS=6pr+{8M=5GTo
z&Ve7pZ`64N1iHbBN>+`hVBp?8_M86X2%4UOpddo2f#?!i{u%?2Q3bRVAh&~eCu%0(
z`!>Lw<|1kF34hd!icU^W1~(cTrF{Ya><NB_!E}9RR85JAW4}^iq~=8xf$Rlrqe^~Y
zpLH-@-rP6fse>TD7LI!|dyK%vMnKR6w(oQwTczK0Ts|^6F%b?zO9;s+AayEi4v$e*
zCT%no3}{`Qm(8YS1~=(P^E3CQE&Cdd<wGDPBkcCoa!}xnlVc-b=Ohrh!DO_SXD5Ga
zf4}ybcblE6zf!;++DWIGDnt~;EZ7a~dD#8+hv+P=6A)Bn2tuH~Z?+Pnfw-|1u=zmj
zl06S@7=cp6E_6l=$^wvv1#u~ZteYwTKA!l=(bLld^`SFxpy}!9?Un+i9~Hr32Z(Hf
zln?kyp$3l)mR;eadJn>L0?JJ(d?N!v#Rm`^FimW)mc9@5YX&@L<NlOA8l+5t3>{xt
zGuv!N<ftP(1&5+t?Z@d2!hGYBlQRS8GYT~PqpnDKkRx#u4bR^L><g}pA$McW^Cz{A
zp&<{z$v8TN_34^>AZUd$OY1stz4GJ8MUDNAR*FtzcYxwA0$?k^Lo3<Y6&p5qINJIk
zaR7rd56GQ2BINuU0p6nr5i!X!p_#0Xa)aCU_V!&s<`gpNz!VY^0!W%!dPoU_33G0k
zSpY0^6Chpb!0rhmXCi<;l=e)*y5r3%`i<Y<WD6fDl-e^B@%7;nuK~j(fej|4g_V_+
zb<7&r%n*&9AJRaauKPx*pye(x<>?+A>Iee823OoX=L5;KO-y0{Vk1>g5zueoyH7ri
z>W&8$!eCOWeanM#V~NF60mBavn52pzB?!zPA^$U9LJ&>wC9RT$v`$0<usOdxbW6+3
zj0XK8o@O&jTIodc1Qb6cfB1seK;d-vVO!~eSl&=qJo#!?Wj`MK)|g^%X>EmaW_%f4
zmcs%zkfxD>JvUSRI{MX8{910@@6n*A=BgxJs9(fT<Ba1LI(?KsRH6P+KQVcx^77AN
zy>e>@upxAj8C1an%1g=g-{HKyGW(XF(MG?FP|xTtCe?3`CyyN9q2VVP!EQ?lcyYia
zOAd0Lo2t9+JGe((?f_%5ykO(|i6^Er{PX^F;W@8?=qImC@sB2lOi)gYTEGpT<laj$
zV2_YZC^}(cF`0MBTUvZ@=q;&VZo6K2<(#pd8NrhxvZtfU()8bnZrv!u>vB}kmKU3?
z<R2tD=6HFnv5_OoU5*&Cq<484FIDS>wtXywDt{?jOy#X>zW=trp2I?_PJbz~J9%^5
z)fRn%4|GCN4;Q{CL7k<QL=2pXp~{FR-+;}#hX^tnSeHKznc+1M6R(vL$Swavn;R0S
zTT~VxT&KNM5{|@P0NCJhpAqXS?7N%WEtWW62s!b@rvS|oxA5oSoY>5{X#n^A*qq-}
zb*Y3LLTBTsj+b88O7F_z<hHW;1@;V7GtQ`}e(@#UjAHk5x@}Z?7BueKppcTq|MNH3
zi*7up9s0plHX#&j{%LXhSZ|G@fg~!1DT0BS%kEFdV7H-Oxqu5r3vHIceuu|`x@W_5
z(7|2R*GD`F7gHefo?_>=cmzpYKAigez^2xyMBzY<MP}iax_K|pooF#yZ>y)a@d%T9
zhtgYhQuCj_wGVkxnYfe9Z#<(tHD=BT|Cm=~VOdoCp(DPQH1<f*R<fRgy~uGs#!eet
z1BF+MO7CdT<w}c4BsS{A^!9qSKL*ohS{wY6vOUHigDRVQD>Q1`Sf?(Xb)<{CUD{88
zeupDK_VtCD_RETvh{kfJS_ggSY5O0p(?1SsM+GP#?YYD#t(HrWki>p??-+@yk&Nh(
zCxUM>Tr)G=(4Ku_lkPHtUT1l<SeHN;K!he3uYuyr*i%%vD%1av#Q*2P%BVm<Xc1ru
zWMpJcH(l$DbEi`T&6+ob)6&ugR}P0q=C=f|wM($Yvcm4X2Z9{Gxt{KB%ag<Ht0qj!
zaKG>2&Y+!iwO$6U$km>v!423yYHy!Vk{RAmB}T+L>l{c~l$G_vmFC)Zfbun%n&P$c
zptcYyFJQ<PH|fCc+yDegI&VYss1>>HQn@7qnigp2Cv-|e^C-Yy3f{cAlYpAcW}qeo
zuYl?t#mzmtWs`sc<>QlAH}h=U;={RaOFaS_4PZFWH>Os;2*w5Kpg<MZQ}y0B7Ev~;
z2%bFPc6;?|6fYa25)5j@B;GvR*7$IdZ?DBb*T+?enK}xEqkGCMJdQqPKUueJ)xlg4
zsGA;IcW+<WkvBgS3^7&ptQ01N!E1-N9WBX9Vm2-C%uqDTm9JBX#ZFY-U~16iLcYh#
znvv@n?aYdnjMbi5hb2pl`(U0hHN&O)PdAt}Ji78QS3gMf!Lmg~1S?3)?;7(aqcqz-
z*6zY3V8wArVM=ctZG+Lk{QENfZy~|@HcEwUBvs<D+xR7Cdp;UD?s2an%b^@`#kx2a
zffi<d_Uo%MSz9JMHm+eeSnm}uAvFgokVBzJ;r8;~iS4lZQ`;@Kkj*bbsUJ8kxUADE
zF^ihlaPlDTtWYD3xOA-K@XW-IHdc~l`}VOio2w{J7PWGX|Fzc5?h~AJSDf0ag=%!p
z&wiCg*J^s27BYzLz1Vz>n(j8MJ&|Z+*6r_xKtv8YYma>_cysF;s53HR=N+D_FE@uo
zByQ;$!3*GLSM1z`P%59#`i)K=b+irI{dL$upSVs@rGCsGDOMvFULb-?GLh_mG;8hY
z!~9_IgXD|7*m`fNUuM(^KnfF=7>l2*CE<TiG+T7{`j7LbQ2RF?U082!9eX9R=4klR
zyP;Qq$hjgL*Pbp-)A(X9Ok4h)Mn-Is-AKMHCzJ#3$==W3A^pi7)md$`u~EDR${k(t
z+VRlV@6hbQ%P05hg|PHY+*<c*-s*_=o42Vybj?X5_BYB%r^(MPvJb%MpsiGSmc#mu
zGCjmDKz^4}La&cR>XoZr(Ty(l6cO8M@WF9pPsbJ;!>P#>6_C$bn6qz_%~Bbu1=|eY
zRXL$lK_9y>C}~7fM_>J0TuRfE6~k+wqzEqI^TEEl?H-J&%S)&NdKem5lo(}AUts=7
zqcwJ%SAQ)x7mT~;)CQAmDrj3MP)I7JpiQ()#QONcp!ru-#b#k5k!(~Hq#r%A-eQ6O
z{;tNu54Ki%<vhM$s}_mLMOWEZ>r0;Ui;9AC^y(aP%m2ByomMhV|E#dbMxJ$jRDY=w
z6i(oIQXs0{j2+yV?Utkzdb<00lx)i8NcJA11cIJ&dCMd0S<y1AWpUQ<<vUvG>mFtY
z(4+fkOI4m6{1zTTZ4+3ZEPR;hb_~`s1;w^_ZA0{4G{HFlu(an09;5D*;zmOssX;}-
zmCzN>$@TDm2jS*`x`{_ou*ASXYklH_#Raqs`HdLOZMXyQ{6kRoK$ule?2n2bc1561
z2HB_OE>9RWJ-OkefE$X8iXt?8*T2{4Zn*ID3Zb|_;@!0N{rkj;{{Z-`ZE6||5=h^I
zW$ALL67H#kLnjF2Bs9lCWzvB^$j{3oHWifOds&H~hXc7n8~)%b5=jJf1_Td=vU14O
z6CFm&jwiU@zP>Jy!cgHbDFUpdgaiaaZXxKsj0wc#Q5B6Ev}Ui;=2Y&8K;~Z-G5Y1)
zCtH6b98PNQD1lE_LPa6}J)m5ca&L~)l>WA2!l5U1*FG@;yh|BAvaDE>b;f?_CdIv`
z(h}BV>Hog)tk=}gDgX`dP|{<26GTvPy(cJ8bInzGI0d<d-HxejaGOQ{{FL``rWwpk
z1q{`{?}1rP+*CkHXE+?|hyAdYQh{o^xTg&&Q65f}{Eppu)_LFOH%l6(!R(MeL~fa2
z!~)I+;L1#)I0bgqOho-@+Q!?+BwQSRs&r_O!Enl{+)JSaW=fb}AsSKY7#-W0FV<|!
zY}1OLt~9ed*h^4ALaIi5YUz0{%A$H;g2}uzVqCrWq3*A$ZPIpy3UnA(sJOgaM+BX}
z(hFylVdjq{oE3A+a4Vxz4GQpZx-CAw!J2q+*r7VBHLmSeF;x@A6SbQE9wLh`x`h@`
zjd`J*?wQ!gqh8@lj1AKR7ML|VC{W9Ktr8!E^jr$#Vo+4DkW>q1zV(}Pgw7Ck@HU@l
zO%NZ_x29KD`En_&mHE@piSN6&0^|+$m_=-?GTZW8o`@P}-m}Dsde?7R&zy%E9Wc08
z7^WFT-`_ze-PD~Od#!b1Gh&hHCQbzHCcsKZ@U6yQNRn<|y#`h=?UeUq{_oC-iZc6h
zj|;osSSsIz|FJ6LeNaf%Fc8!7>4C-b<G+KP0${BceA0I(S6F#zRrLl{1pL<}KVJ)}
zSf}ZMJyxWousB7P#$;_@Y7k%WW$v=vIoo09#XmmgJ7}GaXB`$88Jg!NA=eQ!@;Sd(
z@FJV?^|J+*Nd=;zoji3@BN6w~{ksQZVb$t7nff-Jm9Ok-rxO@{31h&shj;?kmP7ph
z#ly)VC~m9Rr2oTWj}bQe8ts9h3tj$?%-*3$WG;QpTohPC#Wp=eeb}6jWVWt0no;Jf
z&_;>F7%b_9x>6%iSvngDwv0jqTym^N;4(<y{|pmN6nemw7@N;HVrGTh*QA~`LEuMC
MSxc#0!93{y0PaztKmY&$

diff --git a/env.yaml b/env.yaml
index 1eb9404..1c13e3d 100644
--- a/env.yaml
+++ b/env.yaml
@@ -10,5 +10,6 @@ dependencies:
   - parallel-fastq-dump
   - pandas
   - snakemake
+  - seaborn
   - pip:
     - synapseclient
\ No newline at end of file
diff --git a/rules/cellranger.smk b/rules/cellranger.smk
index ec2159e..476ca35 100644
--- a/rules/cellranger.smk
+++ b/rules/cellranger.smk
@@ -1,20 +1,23 @@
 rule cellranger:
     input:
-        i1 = expand("data/{sample}_test.txt", sample=samples)
+        i1 = "results/kraken2/{sample}.report.txt"
     output:
-        o1 = "results/cellranger/{sample}/{sample}_finished.txt"
-    priority: 90
+        o1 = temp(directory("results/cellranger/{sample}/{sample}/")),
+        o2 = "results/cellranger/{sample}/possorted_genome_bam.bam"
+    priority: 80
     resources:
         mem_mb = 26000
     threads: 30
     log:
         "results/cellranger/{sample}/{sample}.cellranger.log"
     params:  
-        p3 = "/data/manke/processing/momin/virome-scan/sc-virome-scan/data/{sample}/"
+        p1 = "../../../data/{sample}/"
     shell:
         """
-        module load cellranger
-        touch {output.o1}
         cd results/cellranger/{wildcards.sample}/ 
-        cellranger count --id {wildcards.sample} --fastqs {params.p3} --transcriptome {config[transcriptome]} --localcores {threads}
-        """
+        {config[cellranger]} count --id {wildcards.sample} --fastqs {params.p1} --transcriptome {config[transcriptome]} --localcores {threads}
+        mv {wildcards.sample}/outs/filtered_feature_bc_matrix/ .
+        mv {wildcards.sample}/outs/raw_feature_bc_matrix/ .
+        mv {wildcards.sample}/outs/*.h5 .
+        mv {wildcards.sample}/outs/possorted_genome_bam* .
+        """
\ No newline at end of file
diff --git a/rules/download_samples_or_copy.smk b/rules/download_samples_or_copy.smk
index 7ba9146..2e1cf04 100644
--- a/rules/download_samples_or_copy.smk
+++ b/rules/download_samples_or_copy.smk
@@ -4,7 +4,8 @@ rule download_samples_or_copy:
         o2 = "data/{sample}/{sample}_S1_L001_R2_001.fastq.gz"
     params:
         outdir = "data/{sample}/",
-        filetype = config["files"]
+        filetype = config["mode"],
+        samplesheet = config["samplesheet"]
     threads: 16
     resources:
         mem_mb = 20000
@@ -20,7 +21,7 @@ rule download_samples_or_copy:
             done
         
         elif [ $filetype == "synapse" ]; then
-            result=$(grep "{wildcards.sample}" "metadata.tsv")
+            result=$(grep "{wildcards.sample}" {config[samplesheet]})
             R1=$(echo "$result" | awk '{{print $2}}')
             R2=$(echo "$result" | awk '{{print $3}}')
             synapse get $R1 --multiThreaded --downloadLocation {params.outdir} 
@@ -29,8 +30,10 @@ rule download_samples_or_copy:
             mv data/{wildcards.sample}/*_R2_* data/{wildcards.sample}/{wildcards.sample}_S1_L001_R2_001.fastq.gz
         
         else
-            parallel-fastq-dump --sra-id {wildcards.sample} --split-files --threads {threads} --outdir {params.outdir}  --gzip --tmpdir /data/manke/processing/momin/virome-scan/sc-virome-scan/tmp
+            mkdir tmp/
+            parallel-fastq-dump --sra-id {wildcards.sample} --split-files --threads {threads} --outdir {params.outdir}  --gzip --tmpdir tmp/
             mv data/{wildcards.sample}/{wildcards.sample}_2.fastq.gz data/{wildcards.sample}/{wildcards.sample}_S1_L001_R1_001.fastq.gz 
             mv data/{wildcards.sample}/{wildcards.sample}_3.fastq.gz data/{wildcards.sample}/{wildcards.sample}_S1_L001_R2_001.fastq.gz 
+            rm -rf tmp/
         fi     
         """
diff --git a/rules/extract_bam.smk b/rules/extract_bam.smk
index b81b174..37bf776 100644
--- a/rules/extract_bam.smk
+++ b/rules/extract_bam.smk
@@ -1,11 +1,9 @@
 rule extract_bam:
     input:
-        i1 = "results/cellranger/{sample}/{sample}_finished.txt"
+        i1 = "results/cellranger/{sample}/possorted_genome_bam.bam"
     output:
         temp("results/cellranger/{sample}/unmapped_reads.sam")
-    log:
-        "results/samtools/{sample}.log"
     params:
         "results/cellranger/{sample}/{sample}/outs/possorted_genome_bam.bam"
     shell:
-        "samtools view -@ 16 -f 4 {params} > {output}"
\ No newline at end of file
+        "samtools view -@ 16 -f 4 {input.i1} > {output}"
\ No newline at end of file
diff --git a/rules/extract_tags.smk b/rules/extract_tags.smk
index 47763ee..a9321bc 100644
--- a/rules/extract_tags.smk
+++ b/rules/extract_tags.smk
@@ -1,7 +1,6 @@
 rule extract_tags:
     input:
-        i1 = "results/cellranger/{sample}/unmapped_reads.sam",
-        i2 = "results/kraken2/{sample}/{sample}.kraken"
+        "results/cellranger/{sample}/unmapped_reads.sam"
     output:
         "results/count_matrix/{sample}/count_matrix.tsv"
     threads: 16
@@ -9,8 +8,9 @@ rule extract_tags:
         mem_mb = 40000
     params:
         p1 = "results/count_matrix/{sample}/",
-        p2 = "results/cellranger/{sample}/{sample}/outs/filtered_feature_bc_matrix/barcodes.tsv.gz"
+        p2 = "results/cellranger/{sample}/filtered_feature_bc_matrix/barcodes.tsv.gz",
+        p3 = "results/kraken2/{sample}.kraken"
     log:
         "results/logs/count_matrix/{sample}_bam_extract.log"
     shell:
-        "python3 scripts/bam_extract.py -i {input.i1} -k {input.i2} -b {params.p2} -o {params.p1}"
\ No newline at end of file
+        "python3 {config[scripts_dir]}/bam_extract.py -i {input} -k {params.p3} -b {params.p2} -o {params.p1}"
\ No newline at end of file
diff --git a/rules/kraken2_mapping.smk b/rules/kraken2_mapping.smk
index e3c48b2..9338281 100644
--- a/rules/kraken2_mapping.smk
+++ b/rules/kraken2_mapping.smk
@@ -2,11 +2,9 @@ rule kraken2_mapping:
     input:
         i1 = "data/{sample}/{sample}_S1_L001_R2_001.fastq.gz"
     output:
-        o1 = "results/kraken2/{sample}/{sample}.kraken",
-        o2 = "results/kraken2/{sample}/{sample}.report.txt",
-        #o3 = "results/kraken2/{sample}/{sample}_classified_out.fastq",
-        o4 = temp("data/{sample}_test.txt")
-    priority: 95
+        o1 = "results/kraken2/{sample}.kraken",
+        o2 = "results/kraken2/{sample}.report.txt",
+    priority: 90
     resources:
         mem_mb = 20000
     threads: 16
@@ -17,5 +15,4 @@ rule kraken2_mapping:
     shell:
         """
         kraken2 --use-names --threads {threads} --db {params.p1} --report {output.o2} --output {output.o1} {input.i1} 2> {log}
-        touch {output.o4}
         """
\ No newline at end of file
diff --git a/rules/report.smk b/rules/report.smk
new file mode 100644
index 0000000..5ce3644
--- /dev/null
+++ b/rules/report.smk
@@ -0,0 +1,20 @@
+rule kraken_reports:
+    input:
+        i1 = expand("results/count_matrix/{sample}/count_matrix.tsv",sample=samples)
+    output:
+        o1 = "results/kraken_plots/Familywise_tax_readcounts.tsv",
+        o2 = "results/kraken_plots/Specieswise_tax_readcounts.tsv",
+        o3 = "results/kraken_plots/Clustermap_Familywise_log10.png",
+        o4 = "results/kraken_plots/Clustermap_Specieswise_log10.png"
+    priority: 10
+    resources:
+        mem_mb = 1000
+    params:
+        p1 = "results/kraken_plots/",
+        p2 = "results/kraken2/"
+    log:
+        "results/logs/plots/kraken_plots.log"
+    shell:
+        """
+        python3 scripts/kraken_plot.py -i {params.p2} -o {params.p1}
+        """
diff --git a/scripts/synapse_fetch.py b/scripts/synapse_fetch.py
index e1463d7..60c7aab 100644
--- a/scripts/synapse_fetch.py
+++ b/scripts/synapse_fetch.py
@@ -104,7 +104,7 @@
                                                             regex=True)
 df2_pivoted['Samples'] = df2_pivoted['Samples'].str.replace(r'L0*(\d+)', r'L\1',
                                                             regex=True)
-df2_pivoted.to_csv(args.output_file_dir + "metadata.tsv",
+df2_pivoted.to_csv(args.output_file_dir + "synapse_samplesheet.tsv",
                    sep="\t", index=False)
 
 print("\nRetrieving Data Successfull...")

From 51a5b28ee7c202ea9ad937e06462bf9f2400c07d Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Wed, 9 Aug 2023 15:14:09 +0200
Subject: [PATCH 30/33] Updated config.yaml

---
 config.yaml     | 12 ++++++------
 samplesheet.tsv |  2 ++
 2 files changed, 8 insertions(+), 6 deletions(-)
 create mode 100644 samplesheet.tsv

diff --git a/config.yaml b/config.yaml
index 89116d8..ce92ccf 100644
--- a/config.yaml
+++ b/config.yaml
@@ -1,7 +1,7 @@
-"samplesheet" : 
+"samplesheet" : "samplesheet.tsv"
 "mode" : "synapse"
-"local_files_dir" : 
-"kraken_db": 
-"cellranger": 
-"transcriptome" : 
-"scripts_dir": 
\ No newline at end of file
+"local_files_dir" : None
+"kraken_db":  "Path to Custom KrakenDB"
+"cellranger":  "Path of CellRanger Executable"
+"transcriptome" : "Path to CellRanger Reference Transcriptome"
+"scripts_dir": "scripts/"
\ No newline at end of file
diff --git a/samplesheet.tsv b/samplesheet.tsv
new file mode 100644
index 0000000..6668501
--- /dev/null
+++ b/samplesheet.tsv
@@ -0,0 +1,2 @@
+Samples	R1	R2
+D17-8765_S1L1	 syn18641014	 syn18641249
\ No newline at end of file

From 37d30d9f386216effbe25d75ff1d0e70eb997551 Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Mon, 2 Oct 2023 13:40:24 +0200
Subject: [PATCH 31/33] Added additional Count-matrix reporting based on
 Kraken-classified reads

---
 Snakefile                          |  7 +++++--
 env.yaml                           |  4 ++--
 rules/download_samples_or_copy.smk |  3 +--
 rules/extract_tags.smk             | 11 ++++++++---
 rules/kraken_processing.smk        | 23 +++++++++++++++++++++++
 rules/report.smk                   |  4 ++--
 scripts/bam_extract.py             |  3 ++-
 7 files changed, 43 insertions(+), 12 deletions(-)
 create mode 100644 rules/kraken_processing.smk

diff --git a/Snakefile b/Snakefile
index e15be4e..832afa5 100644
--- a/Snakefile
+++ b/Snakefile
@@ -11,6 +11,7 @@ samples = list(list_of_samples.Samples.unique())
 include: "rules/download_samples_or_copy.smk"
 include: "rules/kraken2_mapping.smk"
 include: "rules/cellranger.smk"
+include: "rules/kraken_processing.smk"
 include: "rules/extract_bam.smk"
 include: "rules/extract_tags.smk"
 include: "rules/report.smk"
@@ -21,10 +22,12 @@ rule all:
             expand("data/{sample}/{sample}_S1_L001_R2_001.fastq.gz", sample=samples),
             expand("results/kraken2/{sample}.kraken",sample=samples),
             expand("results/kraken2/{sample}.report.txt",sample=samples),
-            directory(expand("results/cellranger/{sample}/{sample}/",sample=samples)),
+            expand("results/cellranger/{sample}/{sample}/",sample=samples),
+            expand("results/kraken_reads/{sample}_kraken_reads.sam", sample=samples),
             expand("results/cellranger/{sample}/possorted_genome_bam.bam", sample=samples),
             expand("results/cellranger/{sample}/unmapped_reads.sam", sample=samples),
             expand("results/count_matrix/{sample}/count_matrix.tsv", sample=samples),
+            expand("results/count_matrix/{sample}/kraken_reads_count_matrix.tsv",sample=samples),
             "results/kraken_plots/Familywise_tax_readcounts.tsv",
             "results/kraken_plots/Specieswise_tax_readcounts.tsv",
             "results/kraken_plots/Clustermap_Familywise_log10.png",
@@ -34,4 +37,4 @@ onsuccess:
     print("sc-VirusScan Pipeline finished successfully!")
 
 onerror:
-    print("sc-VirusScan Pipeline has failed!")
\ No newline at end of file
+    print("sc-VirusScan Pipeline has failed!")
diff --git a/env.yaml b/env.yaml
index 1c13e3d..76d6d62 100644
--- a/env.yaml
+++ b/env.yaml
@@ -5,11 +5,11 @@ channels:
   - defaults
 dependencies:
   - kraken2
-  - samtools
+  - samtools==1.12
   - entrez-direct
   - parallel-fastq-dump
   - pandas
   - snakemake
   - seaborn
   - pip:
-    - synapseclient
\ No newline at end of file
+    - synapseclient
diff --git a/rules/download_samples_or_copy.smk b/rules/download_samples_or_copy.smk
index 2e1cf04..d6c6292 100644
--- a/rules/download_samples_or_copy.smk
+++ b/rules/download_samples_or_copy.smk
@@ -30,10 +30,9 @@ rule download_samples_or_copy:
             mv data/{wildcards.sample}/*_R2_* data/{wildcards.sample}/{wildcards.sample}_S1_L001_R2_001.fastq.gz
         
         else
-            mkdir tmp/
+            mkdir -p tmp/
             parallel-fastq-dump --sra-id {wildcards.sample} --split-files --threads {threads} --outdir {params.outdir}  --gzip --tmpdir tmp/
             mv data/{wildcards.sample}/{wildcards.sample}_2.fastq.gz data/{wildcards.sample}/{wildcards.sample}_S1_L001_R1_001.fastq.gz 
             mv data/{wildcards.sample}/{wildcards.sample}_3.fastq.gz data/{wildcards.sample}/{wildcards.sample}_S1_L001_R2_001.fastq.gz 
-            rm -rf tmp/
         fi     
         """
diff --git a/rules/extract_tags.smk b/rules/extract_tags.smk
index a9321bc..f438a9c 100644
--- a/rules/extract_tags.smk
+++ b/rules/extract_tags.smk
@@ -1,8 +1,10 @@
 rule extract_tags:
     input:
-        "results/cellranger/{sample}/unmapped_reads.sam"
+        i1 = "results/cellranger/{sample}/unmapped_reads.sam",
+        i2 = "results/kraken_reads/{sample}_kraken_reads.sam"
     output:
-        "results/count_matrix/{sample}/count_matrix.tsv"
+        o1 = "results/count_matrix/{sample}/count_matrix.tsv",
+        o2 = "results/count_matrix/{sample}/kraken_reads_count_matrix.tsv",
     threads: 16
     resources:
         mem_mb = 40000
@@ -13,4 +15,7 @@ rule extract_tags:
     log:
         "results/logs/count_matrix/{sample}_bam_extract.log"
     shell:
-        "python3 {config[scripts_dir]}/bam_extract.py -i {input} -k {params.p3} -b {params.p2} -o {params.p1}"
\ No newline at end of file
+        """
+        python3 {config[scripts_dir]}/bam_extract.py -i {input.i1} -k {params.p3} -b {params.p2} -o {output.o1}
+        python3 {config[scripts_dir]}/bam_extract.py -i {input.i2} -k {params.p3} -b {params.p2} -o {output.o2}
+        """
\ No newline at end of file
diff --git a/rules/kraken_processing.smk b/rules/kraken_processing.smk
new file mode 100644
index 0000000..802dde6
--- /dev/null
+++ b/rules/kraken_processing.smk
@@ -0,0 +1,23 @@
+rule kraken2_processing:
+    input:
+        i1 = "results/cellranger/{sample}/possorted_genome_bam.bam",
+        i2 = "results/kraken2/{sample}.kraken"
+    output:
+        o1 = "results/kraken_reads/{sample}_kraken_reads.sam",
+    priority: 90
+    resources:
+        mem_mb = 20000
+    threads: 16
+    params:
+        p1 = "results/kraken_reads/{sample}_ReadIds.txt",
+        p2 = "results/kraken_reads/{sample}_krakenReads.bam"
+    log:
+        "results/logs/kraken2/{sample}.kraken.log"
+    shell:
+        """
+        mkdir -p results/kraken_reads
+        awk -F'\t' '$3 != "unclassified (taxid 0)" && $3 != "Homo sapiens (taxid 9606)" {{print $2}}' {input.i2} > {params.p1}
+        samtools view -N {params.p1} -o {params.p2} {input.i1}
+        samtools index {params.p2}
+        samtools view -h {params.p2} > {output.o1}
+        """
\ No newline at end of file
diff --git a/rules/report.smk b/rules/report.smk
index 5ce3644..4b0f3ee 100644
--- a/rules/report.smk
+++ b/rules/report.smk
@@ -8,7 +8,7 @@ rule kraken_reports:
         o4 = "results/kraken_plots/Clustermap_Specieswise_log10.png"
     priority: 10
     resources:
-        mem_mb = 1000
+        mem_mb = 40000
     params:
         p1 = "results/kraken_plots/",
         p2 = "results/kraken2/"
@@ -16,5 +16,5 @@ rule kraken_reports:
         "results/logs/plots/kraken_plots.log"
     shell:
         """
-        python3 scripts/kraken_plot.py -i {params.p2} -o {params.p1}
+        python3 {config[scripts_dir]}/kraken_plot.py -i {params.p2} -o {params.p1}
         """
diff --git a/scripts/bam_extract.py b/scripts/bam_extract.py
index f3b8dde..2193d44 100644
--- a/scripts/bam_extract.py
+++ b/scripts/bam_extract.py
@@ -13,6 +13,7 @@
                     help="Filtered Barcodes TSV file from CellRanger")
 parser.add_argument("-o", "--output-file",
                     metavar="PATH",
+                    default="count_matrix.tsv",
                     help="Path to your output file")
 
 args = parser.parse_args()
@@ -69,4 +70,4 @@
 result = merged_barcodes.pivot_table(index='Tax_ID', columns='CR',
                                      values='Read Name',
                                      aggfunc='count').fillna(0.).astype(int)
-result.to_csv(args.output_file + "count_matrix.tsv", sep='\t')
+result.to_csv(args.output_file, sep='\t')

From 5c476ad768efff0afbdd9cc0807f72ec791906b2 Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Mon, 2 Oct 2023 13:51:38 +0200
Subject: [PATCH 32/33] Minor Updations to Slurm Resources

---
 Snakefile              | 2 ++
 rules/cellranger.smk   | 5 +++--
 rules/extract_bam.smk  | 6 +++++-
 rules/extract_tags.smk | 4 ++--
 4 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/Snakefile b/Snakefile
index 832afa5..7e84105 100644
--- a/Snakefile
+++ b/Snakefile
@@ -16,6 +16,8 @@ include: "rules/extract_bam.smk"
 include: "rules/extract_tags.smk"
 include: "rules/report.smk"
 
+localrules: download_samples_or_copy
+
 rule all:
     input:
             expand("data/{sample}/{sample}_S1_L001_R1_001.fastq.gz", sample=samples),
diff --git a/rules/cellranger.smk b/rules/cellranger.smk
index 476ca35..70cec00 100644
--- a/rules/cellranger.smk
+++ b/rules/cellranger.smk
@@ -6,8 +6,9 @@ rule cellranger:
         o2 = "results/cellranger/{sample}/possorted_genome_bam.bam"
     priority: 80
     resources:
-        mem_mb = 26000
-    threads: 30
+        mem_mb = 80000,
+        runtime = 1200
+    threads: 20
     log:
         "results/cellranger/{sample}/{sample}.cellranger.log"
     params:  
diff --git a/rules/extract_bam.smk b/rules/extract_bam.smk
index 37bf776..79ba725 100644
--- a/rules/extract_bam.smk
+++ b/rules/extract_bam.smk
@@ -3,7 +3,11 @@ rule extract_bam:
         i1 = "results/cellranger/{sample}/possorted_genome_bam.bam"
     output:
         temp("results/cellranger/{sample}/unmapped_reads.sam")
+    resources:
+        mem_mb = 4000,
+        runtime = 120
+    threads: 16
     params:
         "results/cellranger/{sample}/{sample}/outs/possorted_genome_bam.bam"
     shell:
-        "samtools view -@ 16 -f 4 {input.i1} > {output}"
\ No newline at end of file
+        "samtools view -@ {threads} -f 4 {input.i1} > {output}"
\ No newline at end of file
diff --git a/rules/extract_tags.smk b/rules/extract_tags.smk
index f438a9c..d2d3715 100644
--- a/rules/extract_tags.smk
+++ b/rules/extract_tags.smk
@@ -5,9 +5,9 @@ rule extract_tags:
     output:
         o1 = "results/count_matrix/{sample}/count_matrix.tsv",
         o2 = "results/count_matrix/{sample}/kraken_reads_count_matrix.tsv",
-    threads: 16
+    threads: 8
     resources:
-        mem_mb = 40000
+        mem_mb = 60000
     params:
         p1 = "results/count_matrix/{sample}/",
         p2 = "results/cellranger/{sample}/filtered_feature_bc_matrix/barcodes.tsv.gz",

From 41f50ad547ae1cf002ca5e8152318c1162a544cf Mon Sep 17 00:00:00 2001
From: Saim <mominsaim12@gmail.com>
Date: Mon, 2 Oct 2023 13:54:25 +0200
Subject: [PATCH 33/33] Minor Update to Snakemake rule

---
 rules/kraken_processing.smk | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rules/kraken_processing.smk b/rules/kraken_processing.smk
index 802dde6..92eca73 100644
--- a/rules/kraken_processing.smk
+++ b/rules/kraken_processing.smk
@@ -12,7 +12,7 @@ rule kraken2_processing:
         p1 = "results/kraken_reads/{sample}_ReadIds.txt",
         p2 = "results/kraken_reads/{sample}_krakenReads.bam"
     log:
-        "results/logs/kraken2/{sample}.kraken.log"
+        "results/logs/kraken2_processing/{sample}.log"
     shell:
         """
         mkdir -p results/kraken_reads