varlociraptor workflow compatibility

.github/workflows/main.yaml

@@ -8,33 +8,42 @@ on:
 
 
 jobs:
+  Formatting:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - name: Formatting
+        uses: github/super-linter@v4
+        env:
+          VALIDATE_ALL_CODEBASE: false
+          DEFAULT_BRANCH: master
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          VALIDATE_SNAKEMAKE_SNAKEFMT: true
+
+
   Linting:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v1
+    - uses: actions/checkout@v2
     - name: Lint workflow
-      uses: snakemake/snakemake-github-action@v1.17.0
+      uses: snakemake/snakemake-github-action@v1.22.0
       with:
         directory: .
         snakefile: workflow/Snakefile
         args: "--lint"
-        stagein: |
-          export TMPDIR=/tmp
 
 
   Testing:
     runs-on: ubuntu-latest
-    needs: Linting
+    needs:
+      - Linting
+      - Formatting
     steps:
-    - uses: actions/checkout@v1
-    - name: Checkout submodules
-      uses: textbook/[email protected]
+    - uses: actions/checkout@v2
 
     - name: Test workflow (local FASTQs)
-      uses: snakemake/snakemake-github-action@v1.17.0
+      uses: snakemake/snakemake-github-action@v1.22.0
       with:
         directory: .test
         snakefile: workflow/Snakefile
         args: "--use-conda --show-failed-logs -j 10 --conda-cleanup-pkgs cache --conda-frontend mamba"
-        stagein: |
-          export TMPDIR=/tmp

.gitignore

@@ -1,23 +1,21 @@
 *
-!scripts
-!scripts/*
-!scripts/common
-!scripts/common/*
-scripts/.snakemake*
-!Snakefile
-!config.yaml
-!samples.tsv
-!resources
-!resources/*
-!envs
-!envs/*
-!environment.yaml
+!.github/workflows/*
+!.test
+!.test/*
+!.test/config/*
+!.test/data/*
+!config
+!config/*
+!config/HLA_Data/*
+!workflow
+!workflow/*
+!workflow/report/*
+!workflow/envs/*
+!workflow/schemas/*
+!workflow/scripts/*
+!workflow/rules/*
+!workflow/rules/annotation/*
+!workflow/resources/*
+!.gitignore
 !LICENSE
 !README.md
-!rules
-!rules/*
-!.gitignore
-!.editorconfig
-!.gitattributes
-!.test
-!.test/data

.test/config/config.yaml

@@ -1,84 +1,10 @@
 samples: "config/samples.tsv"
 units: "config/units.tsv"
 
-# boolean if read trimming should be skipped
-trimming:
-  activate: false
 
-remove_duplicates:
+neoantigen_prediction:
   activate: true
 
-calling:
-  freebayes:
-    activate: false
-  # See https://varlociraptor.github.io/docs/calling/#generic-variant-calling
-  scenario: config/scenario.yaml
-  filter:
-    # Filter candidate variants (this filter helps to keep the number of evaluated candidates small).
-    # It should ideally generate a superset of all other filters defined below.
-    # Annotation of candidate variants tries to be as fast as possible, only using VEP
-    # default parameters.
-    candidates: ""
-    # Add any number of named filters here. They will be applied independenty,
-    # and can be referred in FDR control below to generate calls for different events.
-    # In particular, you can also filter by ID or dbsnp annotations here.
-    # See http://snpeff.sourceforge.net/SnpSift.html#filter
-    filtername: "ANN['IMPACT'] != 'MODIFIER'"
-  fdr-control:
-    threshold: 0.05
-    events: 
-      complete:
-        varlociraptor: 
-          - "somatic"
-          - "germline"
-      somatic:
-        varlociraptor:
-          - "somatic"
-      germline:
-        varlociraptor:
-          - "germline"
-
-fusion:
-  arriba:
-    activate: false
-    blacklist:
-     "arriba_blacklist"
-    params:
-      "-T -P"
-
-tmb:
-  activate: false
-  coding_genome_size: 3e7
-  # Name of the tumor sample in the scenario.yaml.
-  tumor_sample: tumor
-  somatic_events:
-    - somatic
-
-
-epitope_prediction:
-  activate: false
-
-
-affinity:
-  netMHCpan:
-    activate: false
-    params: "-BA -l 9 -s -xls"
-    location: "../netMHCpan-4.0"
-  netMHCIIpan:
-    activate: false
-    params: "-length 15 -s -xls"
-    location: "../netMHCIIpan-4.0"
-
-
-HLAtyping:
-  # activate to use razers3 to pre-filter reads before using optitype
-  optitype_prefiltering:
-    activate: false
-  optitype_data: "config/HLA_Data/hla_reference_dna.fasta"
-  # activate to predict MHC-I and MHC-II alleles with HLA-LA
-  HLA_LA:
-    activate: false
-
 
 ref:
   # Number of chromosomes to consider for calling.
@@ -87,49 +13,42 @@ ref:
   # Ensembl species name
   species: homo_sapiens
   # Ensembl release
-  release: 100
+  release: 108
   # Genome build
   build: GRCh38
 
 
-annotations:
-  vep:
-    params: "--everything"
-    plugins:
-      # Add any plugin from https://www.ensembl.org/info/docs/tools/vep/script/vep_plugins.html
-      # Plugin args can be passed as well, e.g. "LoFtool,path/to/custom/scores.txt".
-      - LoFtool
-
 params:
-  cutadapt: ""
-  bwa:
-    "-M"
-  picard:
-    MarkDuplicates:
-      "VALIDATION_STRINGENCY=LENIENT"
-  gatk:
-    BaseRecalibrator: "--tmp-dir tmp"
-    applyBQSR: ""
-  strelka:
-    config:
-      "--exome"
-    run:
-      "--mode local"
-  razers3:
-    "-i 95 -m 1 -dr 0"
-  optitype:
-    ""
   microphaser:
-    window_len:
-        33
-    peptide_len:
-      netMHCpan:
-          9
-      netMHCIIpan:
-          15
-  kallisto:
-    "-b 100"
-  star: >-
-    --outSAMmapqUnique 60 --outSAMtype BAM Unsorted --chimSegmentMin 10 --chimOutType WithinBAM SoftClip
-    --chimJunctionOverhangMin 10 --chimScoreMin 1 --chimScoreDropMax 30 --chimScoreJunctionNonGTAG 0
-    --chimScoreSeparation 1 --alignSJstitchMismatchNmax 5 -1 5 5 --chimSegmentReadGapMax 3
+    events:
+      tumor: "tumor_only"
+      normal: "normal_only"
+  net_mhc_pan:
+    activate: true
+    peptide_len: 9
+    extra: ""
+    # Please download netMHCpan manually from:
+    # https://services.healthtech.dtu.dk/service.php?NetMHCpan-4.1
+    # To make the `netMHCpan` script work, you need to fix its first line in
+    # in addition to the other edits described for a complete install. To use
+    # the conda-provided tcsh installation, it needs to read (without quotes):
+    # "#!/usr/bin/env tcsh"
+    location: "../netMHCpan-4.1"
+  net_mhc_two_pan:
+    activate: false
+    peptide_len: 15
+    extra: ""
+    # Please download netMHCIIpan manually from:
+    # https://services.healthtech.dtu.dk/service.php?NetMHCIIpan-4.1
+    # To make the `netMHCIIpan` script work, you need to fix its first line in
+    # in addition to the other edits described for a complete install. To use
+    # the conda-provided tcsh installation, it needs to read (without quotes):
+    # "#!/usr/bin/env tcsh"
+    location: "../netMHCIIpan-4.1"
+  neo_fox:
+    activate: false
+    # This should be at least as long as the desired net_mhc_two_pan peptide length
+    peptide_len: 15
+    # update the version number to get a newer release of the reference set of HLA Alleles
+    hla_alleles: "https://raw.githubusercontent.com/ANHIG/IMGTHLA/Latest/allelelist/Allelelist.3480.txt"
+    extra: ""

.test/config/groups.tsv

@@ -0,0 +1,2 @@
+group	tumorType
+A	LUSC

.test/config/samples.tsv

@@ -1,3 +1,3 @@
-sample	type	matched_normal	purity	platform
-A_normal	normal			ILLUMINA
-A_tumor	tumor	A_normal	1	ILLUMINA
+sample_name	group	alias	purity	platform
+A_normal	A	normal	1	ILLUMINA
+A_tumor	A	tumor	.99	ILLUMINA

.test/config/units.tsv

@@ -1,3 +1,3 @@
-sample	sequencing_type	unit	fq1	fq2	sra	adapters
+sample_name	sequencing_type	unit_name	fq1	fq2	sra	adapters
 A_normal	DNA	lane1	data/reads/A_normal.1.fastq.gz	data/reads/A_normal.2.fastq.gz		
 A_tumor	DNA	lane1	data/reads/A_tumor.1.fastq.gz	data/reads/A_tumor.2.fastq.gz