added files for make test

.github/workflows/cdiff_fbi_workflow.yml

@@ -0,0 +1,43 @@
+name: ecoli food bourne infection workflow
+
+on:
+  push:
+    branches: ["main"]
+  pull_request:
+    branches: ["main"]
+
+jobs:
+  build:
+    runs-on: ${{ matrix.os }}
+    defaults:
+      run:
+        shell: bash -l {0}
+    strategy:
+      matrix:
+        os: ["ubuntu-latest"]
+        python-version: ["3.11"]
+
+    steps:
+      # step 1: checkout repository
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      # step 2 use environment.yml dependencies to create conda environment
+      - name: Set up miniconda
+        uses: conda-incubator/setup-miniconda@v3
+        with:
+          auto-update-conda: true
+          python-version: ${{ matrix.python-version }}
+
+      # step 3: Create the conda environment manually
+      - name: Create conda environment
+        run: |
+          conda create --name cdiff_pipeline picard gatk4 biopython ruamel.yaml kraken bwa samtools
+
+      # step 4
+      - name: Run test script
+        run: |
+          conda activate cdiff_pipeline
+          make test
+      
+      # consider adding the webhook to https://github.com/ssi-dk/bifrost_sp_cdiff/

.gitignore

@@ -0,0 +1,54 @@
+# Secret files and resources
+.secret*
+resources/*
+
+# fastq and fasta files
+*.fasta
+*.fa
+*.fsa 
+*.fasta.gz
+*.fa.gz
+*.fsa.gz 
+*.fastq
+*.fq
+*.fastq.gz 
+*.fq.gz
+
+# Python cache files
+__pycache__/
+*.py[cod]
+.pytest_cache/
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# IDE or editor files
+.vscode/
+.idea/
+*.swp
+
+# Jupyter Notebook checkpoints
+.ipynb_checkpoints/
+
+# Log and temporary files
+*.log
+*.tmp
+*.temp
+
+# Environment files (pip and conda)
+.env
+.venv/
+env/
+venv/
+*.conda
+*.condarc
+
+# Distribution / packaging files
+bin/
+.Python
+build/
+dist/
+lib/
+lib64/
+*.egg-info/

Makefile

@@ -0,0 +1,33 @@
+# Makefile
+
+.PHONY: test update_db type process summarize
+
+clean:	
+	rm -rf test/ERR142064/
+
+# Combined test target to run all steps
+# test: serotyping processing summarizing
+test: serotyping md5serotypecheck processing md5processcheck
+
+# Step 1: Run the typing process
+serotyping:
+	@BIN_PATH=$$(dirname $$(which python)) && \
+	echo "Conda environment bin path: $$BIN_PATH" && \
+	bash cdifftyping.sh -i ERR142064 -R1 test/ERR142064_1_subset.fastq.gz -R2 test/ERR142064_2_subset.fastq.gz -c test/ERR142064_subset.fasta -o test -db db -update no
+
+# Step 2: Check MD5 checksum
+md5serotypecheck:
+	cd test && \
+	cat ERR142064/sp_cdiff_fbi/ERR142064.indel.vcf|grep -v '#'> ERR142064/sp_cdiff_fbi/ERR142064.indel.noheader.vcf && \
+	cat ERR142064/sp_cdiff_fbi/ERR142064.snp.vcf|grep -v '#'> ERR142064/sp_cdiff_fbi/ERR142064.snp.noheader.vcf && \
+	cat ERR142064/sp_cdiff_fbi/ERR142064.snp_indel.vcf|grep -v '#'>ERR142064/sp_cdiff_fbi/ERR142064.snp_indel.noheader.vcf && \
+	md5sum -c Serotypesums.md5
+
+# Step 3: Run the post-processing
+processing:
+	bash postcdifftyping.sh -i ERR142064 -d test -stbit "STNA;NA:NA"
+
+# Step 4: Check MD5 checksum - but remove variable date to accurately represent MD5sum
+md5processcheck:
+	cd test && \
+	md5sum -c Processsums.md5

cdifftyping.sh

@@ -133,7 +133,7 @@ mkdir -p $spcdifffbidir
 prefix="$spcdifffbidir/$sampleid"  # prefix for indexes
 
 
-Filtering reads with serum_readfilter
+#Filtering reads with serum_readfilter
 echo -e "\n# Filtering reads with serum_readfilter..."
 cmd="serum_readfilter runfilter kraken -R1 ${read1} -R2 ${read2} -o $spcdifffbidir/cdifffiltered -db $serumdb"
 r1="$spcdifffbidir/cdifffiltered_R1.fastq"

db/cdiff_toxins/tcdRegion.dict

@@ -0,0 +1,2 @@
+@HD	VN:1.6
+@SQ	SN:gi|126697566|ref|NC_009089.1|	LN:25706	M5:4ff8ab7d041b1792b7b30e73461ff926	UR:file:///home/rahenriksen443/cdiff_fbi/db/cdiff_toxins/tcdRegion.fasta

db/cdiff_toxins/tcdRegion.fasta.amb

@@ -0,0 +1 @@
+25706 1 0

db/cdiff_toxins/tcdRegion.fasta.ann

@@ -0,0 +1,3 @@
+25706 1 11
+0 gi|126697566|ref|NC_009089.1| Peptoclostridium difficile 630, complete genome
+0 25706 0

db/cdiff_toxins/tcdRegion.fasta.fai

@@ -0,0 +1 @@
+gi|126697566|ref|NC_009089.1|	25706	79	25706	25707

test/Processsums.md5

@@ -0,0 +1,2 @@
+13c0b9b029c6131e5e69be1b7b934555  ERR142064/ERR142064.csv
+01eb78d612b51d98b78e7fea67791da2  ERR142064/ERR142064.json

test/Serotypesums.md5

@@ -0,0 +1,21 @@
+57304e76422f88d12526b0a63ad47da4  ERR142064/sp_cdiff_fbi/ERR142064.bam
+9ddfaf45e2201214967389cf43da2f42  ERR142064/sp_cdiff_fbi/ERR142064.bam.bai
+97e3ec59fc737b3073557c74e54bfe0e  ERR142064/sp_cdiff_fbi/ERR142064.coverage
+bcca0bfab13062fa427aeea04b2c7038  ERR142064/sp_cdiff_fbi/ERR142064.coverage.sample_cumulative_coverage_counts
+4721790a8baec19dd0bc49119e231078  ERR142064/sp_cdiff_fbi/ERR142064.coverage.sample_cumulative_coverage_proportions
+918105797eae2632de3e408d7327d885  ERR142064/sp_cdiff_fbi/ERR142064.coverage.sample_interval_statistics
+385b9293fb26f90cba8f2d2f8e8b2f03  ERR142064/sp_cdiff_fbi/ERR142064.coverage.sample_interval_summary
+47365c24bfe25d8796e6d1540d8e6ad9  ERR142064/sp_cdiff_fbi/ERR142064.coverage.sample_statistics
+8c8d2703ddc82e2f060db5b04cc5b4e8  ERR142064/sp_cdiff_fbi/ERR142064.coverage.sample_summary
+4f30e930ce5c65caae21783c533c9505  ERR142064/sp_cdiff_fbi/ERR142064.indel.noheader.vcf
+e45d6433d00b4ac36ab62448e5fb37de  ERR142064/sp_cdiff_fbi/ERR142064.sam
+d7eda8c30011f4b9192211151de83e6c  ERR142064/sp_cdiff_fbi/ERR142064.snp.noheader.vcf
+ccbae19880ae00595370a548c2305844  ERR142064/sp_cdiff_fbi/ERR142064.snp_indel.noheader.vcf
+bb7b6ccf22fa698793fbf8b2624c64ed  ERR142064/sp_cdiff_fbi/ERR142064_TRST.fasta
+9a2156bb8ad2f8e23dff43970a42104d  ERR142064/sp_cdiff_fbi/ERR142064_cdtA.info
+0e1ec33a8d7c9658294bdb9a383b638f  ERR142064/sp_cdiff_fbi/ERR142064_cdtB.info
+2d0476ceeed860351baf3ebbb3db3daa  ERR142064/sp_cdiff_fbi/ERR142064_tcdA.info
+c23cf0f5cb848b7bf2eafbba4e4aa07f  ERR142064/sp_cdiff_fbi/ERR142064_tcdB.info
+a0a43ac74e5e823bcab99e6e2cdff4eb  ERR142064/sp_cdiff_fbi/ERR142064_tcdC.info
+4d5500e512d5896f36d4726f5491bdc2  ERR142064/sp_cdiff_fbi/cdifffiltered_R1.fastq
+0cffcfd0e88d2397b59612ef3e75fab0  ERR142064/sp_cdiff_fbi/cdifffiltered_R2.fastq