Merge pull request friendsofstrandseq#52 from friendsofstrandseq/dev

Watchdog update, jbrowse mode

.gitignore

@@ -223,3 +223,4 @@ args.output
 scNOVA_env_costea.yaml
 .keras/keras.json
 hs_err_pid2227945.log
+input_subclonality.txt

README.md

@@ -102,12 +102,12 @@ the workflow goes through the following steps:
 
 # 📕 References
 
+> MosaiCatcher v2 publication: Weber Thomas, Marco Raffaele Cosenza, and Jan Korbel. 2023. ‘MosaiCatcher v2: A Single-Cell Structural Variations Detection and Analysis Reference Framework Based on Strand-Seq’. Bioinformatics 39 (11): btad633. https://doi.org/10.1093/bioinformatics/btad633.
+
 > Strand-seq publication: Falconer, E., Hills, M., Naumann, U. et al. DNA template strand sequencing of single-cells maps genomic rearrangements at high resolution. Nat Methods 9, 1107–1112 (2012). https://doi.org/10.1038/nmeth.2206
 
 > scTRIP/MosaiCatcher original publication: Sanders, A.D., Meiers, S., Ghareghani, M. et al. Single-cell analysis of structural variations and complex rearrangements with tri-channel processing. Nat Biotechnol 38, 343–354 (2020). https://doi.org/10.1038/s41587-019-0366-x
 
 > ArbiGent publication: Porubsky, David, Wolfram Höps, Hufsah Ashraf, PingHsun Hsieh, Bernardo Rodriguez-Martin, Feyza Yilmaz, Jana Ebler, et al. 2022. “Recurrent Inversion Polymorphisms in Humans Associate with Genetic Instability and Genomic Disorders.” Cell 185 (11): 1986-2005.e26. https://doi.org/10.1016/j.cell.2022.04.017.
 
 > scNOVA publication: Jeong, Hyobin, Karen Grimes, Kerstin K. Rauwolf, Peter-Martin Bruch, Tobias Rausch, Patrick Hasenfeld, Eva Benito, et al. 2022. “Functional Analysis of Structural Variants in Single Cells Using Strand-Seq.” Nature Biotechnology, November, 1–13. https://doi.org/10.1038/s41587-022-01551-4.
-
-> scNOVA publication: Jeong, Hyobin, Karen Grimes, Kerstin K. Rauwolf, Peter-Martin Bruch, Tobias Rausch, Patrick Hasenfeld, Eva Benito, et al. 2022. “Functional Analysis of Structural Variants in Single Cells Using Strand-Seq.” Nature Biotechnology, November, 1–13. https://doi.org/10.1038/s41587-022-01551-4.

config/config.yaml

@@ -14,9 +14,6 @@ email: ""
 # List of samples to process if multiple are specified
 samples_to_process: []
 
-# Plate size
-plate_size: 96
-
 # --------------------------------------------------------
 # Data location & I/O
 # --------------------------------------------------------
@@ -250,7 +247,7 @@ scTRIP_multiplot: False
 # StrandScape
 # --------------------------------------------------------
 
-use_strandscape_labels: False
+strandscape_labels_path: ""
 
 # --------------------------------------------------------
 # Internal Parameters

config/config_metadata.yaml

@@ -3,141 +3,155 @@ email:
   type: string
   required: False
   default: '""'
+  category: "Others"
 data_location:
   desc: "Input BAM location"
   type: string
   required: True
   default: '""'
+  category: "I/O"
 reference:
   desc: "Reference assembly selected"
   type: string
   required: True
   default: hg38
-hand_selection:
-  desc: "Enable / Disable low-quality libraries hand selection through Jupyter Notebook"
-  type: bool
-  required: False
-  default: False
+  category: "Reference genome"
 MultiQC:
   desc: "Enable / Disable MultiQC aggregation"
   type: bool
   required: False
   default: False
+  category: "Quality Control"
 multistep_normalisation:
   desc: "Enable / Disable multistep normalisation"
   type: bool
   required: False
   default: False
+  category: "Normalisation"
 multistep_normalisation_for_SV_calling:
   desc: "Enable / Disable multistep normalisation to be used in SV calling"
   type: bool
   required: False
   default: False
+  category: "Normalisation"
 ashleys_threshold:
   desc: "Ashleys-qc binary classification threshold"
   type: bool
   required: False
   default: 0.5
+  category: "Quality Control"
 window:
   desc: "Mosaic bin window size"
   type: int
   required: True
   default: 200000
+  category: "Counts"
 chromosomes:
   desc: List of chromosomes to be processed in the pipeline
   type: list
   required: True
   default: "[chr1..22,chrX,chrY]"
+  category: "Reference genome"
 chromosomes_to_exclude:
   desc: List of chromosomes to be excluded
   type: list
   required: True
   default: "[]"
+  category: "Reference genome"
 genecore:
   desc: Enable / Disable genecore option to work on GeneCore folder. Required genecore_date_folder
   type: bool
   required: False
   default: False
+  category: "Data processing"
 genecore_date_folder:
   desc: Genecore folder to be processed under /g/korbel/shared/genecore
   type: str
   required: False
   default: '""'
+  category: "Data processing"
 samples_to_process:
   desc: Optional list of samples to be specifically processed in genecore_date_folder
   type: list
   required: True
   default: "[]"
+  category: "Data processing"
 hgsvc_based_normalized_counts:
   desc: Normalize or not mosaic counts
   type: bool
   required: False
   default: True
+  category: "Normalisation"
 input_bam_legacy:
   desc: Mutually exclusive with ashleys_pipeline
   type: bool
   required: False
   default: False
+  category: "I/O"
 ashleys_pipeline:
   desc: Enable/Disable ashleys-qc-pipeline module loading to start pipeline from FASTQ files
   type: bool
   required: False
   default: False
+  category: "Quality Control"
 ashleys_pipeline_only:
   desc: Stop execution at the output of ashleys-pipeline in order to procede to manual & additional selection of cells
   type: bool
   required: False
   default: False
+  category: "Quality Control"
 blacklist_regions:
   desc: Enable/Disable blacklisting during counting step
   type: bool
   required: False
   default: False
+  category: "Counts"
 arbigent:
   desc: Enable ArbiGent mode of execution to genotype specific regions of Strand Seq libraries
   type: bool
   required: False
   default: False
+  category: "Downstream"
   lint_check: False
 arbigent_bed_file:
   desc: ArbiGent BED file path that would be used to perform arbitrary segmentation
   type: str
   required: False
   default: "workflow/data/arbigent/manual_segmentation.bed"
+  category: "Downstream"
   lint_check: False
 scNOVA:
   desc: Enable scNOVA downstream module to perform nucleosome occupancy based SV analysis
   type: bool
   required: False
   default: False
+  category: "Downstream"
   lint_check: False
 genome_browsing_files_generation:
   desc: Enable genome browsing files generation (UCSC + IGV)
   type: bool
   required: False
   default: False
+  category: "Downstream"
   lint_check: False
 genecore_prefix:
   desc: ""
   type: str
   required: False
   default: "/g/korbel/shared/genecore"
+  category: "Data processing"
   lint_check: False
 scTRIP_multiplot:
   desc: "Enable scTRIP multiplot (W/C, depth, phased het SNPs, SV) for all chrom of all cells for every sample"
   type: bool
   required: False
   default: "/g/korbel/shared/genecore"
+  category: "Downstream"
   lint_check: False
-use_strandscape_labels::
-  desc: "Use StrandScape labels instead of cell_selection/labels.tsv"
-  type: bool
+strandscape_labels_path:
+  desc: "Use StrandScape labels instead of cell_selection/labels.tsv, need to specify path"
+  type: str
   required: False
-  default: False
-  lint_check: False
-plate_size::
-  desc: "Plate size used for the sequencing (96/384)"
-  type: int
-  required: True
-  default: 96
+  default: ""
+  category: "Data processing"
   lint_check: False