Merge branch 'dev' into nf-core-template-merge-2.13

nf-core · Feb 22, 2024 · 5d4effb · 5d4effb
2 parents 4c397c8 + c6ba2ad
commit 5d4effb
Show file tree

Hide file tree

Showing 148 changed files with 7,410 additions and 794 deletions.
diff --git a/README.md b/README.md
@@ -14,7 +14,7 @@
 [![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg?labelColor=000000)](https://sylabs.io/docs/)
 [![Launch on Nextflow Tower](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Nextflow%20Tower-%234256e7)](https://tower.nf/launch?pipeline=https://github.com/nf-core/variantbenchmarking)
 
-[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23variantbenchmarking-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/variantbenchmarking)[![Follow on Twitter](http://img.shields.io/badge/twitter-%40nf__core-1DA1F2?labelColor=000000&logo=twitter)](https://twitter.com/nf_core)[![Follow on Mastodon](https://img.shields.io/badge/mastodon-nf__core-6364ff?labelColor=FFFFFF&logo=mastodon)](https://mstdn.science/@nf_core)[![Watch on YouTube](http://img.shields.io/badge/youtube-nf--core-FF0000?labelColor=000000&logo=youtube)](https://www.youtube.com/c/nf-core)
+[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23benchmark-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/variantbenchmarking)[![Follow on Twitter](http://img.shields.io/badge/twitter-%40nf__core-1DA1F2?labelColor=000000&logo=twitter)](https://twitter.com/nf_core)[![Follow on Mastodon](https://img.shields.io/badge/mastodon-nf__core-6364ff?labelColor=FFFFFF&logo=mastodon)](https://mstdn.science/@nf_core)[![Watch on YouTube](http://img.shields.io/badge/youtube-nf--core-FF0000?labelColor=000000&logo=youtube)](https://www.youtube.com/c/nf-core)
 
 ## Introduction
 
@@ -30,14 +30,22 @@
      workflows use the "tube map" design for that. See https://nf-co.re/docs/contributing/design_guidelines#examples for examples.   -->
 <!-- TODO nf-core: Fill in short bullet-pointed list of the default steps in the pipeline -->
 
-1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/))
-2. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
+1. Standardization of SVs in test VCF files
+2. Normalization of SVs in test VCF files
+3. Normalization of SVs in truth VCF files
+4. SV stats and histograms
+5. Germline benchmarking of SVs
+6. Somatic benchmarking of SVs
+7. Final report and comparisons
 
 ## Usage
 
 > [!NOTE]
 > If you are new to Nextflow and nf-core, please refer to [this page](https://nf-co.re/docs/usage/installation) on how to set-up Nextflow. Make sure to [test your setup](https://nf-co.re/docs/usage/introduction#how-to-run-a-pipeline) with `-profile test` before running the workflow on actual data.
 
+Supported SV callers: Manta, SVaba, Dragen, Delly, Lumpy ..
+Available Truth samples: HG002, SEQC2
+
 <!-- TODO nf-core: Describe the minimum required steps to execute the pipeline, e.g. how to prepare samplesheets.
      Explain what rows and columns represent. For instance (please edit as appropriate):
 
@@ -46,12 +54,11 @@ First, prepare a samplesheet with your input data that looks as follows:
 `samplesheet.csv`:
 
 ```csv
-sample,fastq_1,fastq_2
-CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz
+caller,test_vcf
+caller1,test1.vcf.gz
+caller2,test2.vcf
 ```
 
-Each row represents a fastq file (single-end) or a pair of fastq files (paired end).
-
 -->
 
 Now, you can run the pipeline using:

diff --git a/assets/samplesheet.csv b/assets/samplesheet.csv
@@ -1,3 +1,3 @@
-sample,fastq_1,fastq_2
-SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz
-SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,
+test_vcf,caller,vartype
+"https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.vcf.gz",mutect,sv
+"https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/illumina/vcf/sv_query.vcf.gz",unknown,sv
diff --git a/assets/samplesheet_HG002.csv b/assets/samplesheet_HG002.csv
@@ -0,0 +1,5 @@
+test_vcf,caller,vartype
+"/Users/w620-admin/Desktop/nf-core/dataset/hg37/dragen_paper/HG002_delly_SV_hg19.vcf.gz",delly,sv
+"/Users/w620-admin/Desktop/nf-core/dataset/hg37/dragen_paper/HG002_lumpy_SV_hg19.sorted.vcf.gz",lumpy,sv
+"/Users/w620-admin/Desktop/nf-core/dataset/hg37/dragen_paper/HG002_manta_SV_hg19_genotype2.vcf",manta,sv
+"/Users/w620-admin/Desktop/nf-core/dataset/hg37/Broad_svaba_05052017/full.svaba.germline.sv.vcf",svaba,sv
diff --git a/assets/samplesheet_HG002_hg38.csv b/assets/samplesheet_HG002_hg38.csv
@@ -0,0 +1,7 @@
+test_vcf,caller,vartype
+"/Users/w620-admin/Desktop/nf-core/dataset/hg38/GIAB_GRCh38_SVs_06252018/ajtrio.lumpy.svtyper.HG002.md.sorted.recal.vcf.gz",lumpy,sv
+"/Users/w620-admin/Desktop/nf-core/dataset/hg38/GIAB_GRCh38_SVs_06252018/manta.HG002.vcf.gz",manta,sv
+"/Users/w620-admin/Desktop/nf-core/dataset/hg38/Ashkenazim_unnanotated/Ashkenazim_HG002.filtered.sv.vcf.gz",merged,sv
+"/Users/w620-admin/Desktop/nf-core/dataset/hg38/HG002_DRAGEN_SV_hg19.vcf.gz",dragen,sv
+
+
diff --git a/assets/samplesheet_SEQC2.csv b/assets/samplesheet_SEQC2.csv
@@ -0,0 +1,3 @@
+test_vcf,caller
+"/Users/w620-admin/Desktop/nf-core/dataset/hg38/SEQC_somatic_mutation_truth/test/WGS.bwa.dedup-IL_T_1_vs_IL_N_1-Strelka.indel.vcf.gz",strelka
+"/Users/w620-admin/Desktop/nf-core/dataset/hg38/SEQC_somatic_mutation_truth/test/WGS.bwa.dedup-IL_T_1_vs_IL_N_1-MuTect2.vcf.gz",mutect2
diff --git a/assets/schema_input.json b/assets/schema_input.json
@@ -1,33 +1,29 @@
 {
-    "$schema": "http://json-schema.org/draft-07/schema",
-    "$id": "https://raw.githubusercontent.com/nf-core/variantbenchmarking/master/assets/schema_input.json",
-    "title": "nf-core/variantbenchmarking pipeline - params.input schema",
-    "description": "Schema for the file provided with params.input",
-    "type": "array",
-    "items": {
-        "type": "object",
-        "properties": {
-            "sample": {
-                "type": "string",
-                "pattern": "^\\S+$",
-                "errorMessage": "Sample name must be provided and cannot contain spaces",
-                "meta": ["id"]
-            },
-            "fastq_1": {
-                "type": "string",
-                "format": "file-path",
-                "exists": true,
-                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
-                "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
-            },
-            "fastq_2": {
-                "type": "string",
-                "format": "file-path",
-                "exists": true,
-                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
-                "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
-            }
-        },
-        "required": ["sample", "fastq_1"]
-    }
+  "$schema": "http://json-schema.org/draft-07/schema",
+  "$id": "https://raw.githubusercontent.com/nf-core/variantbenchmarking/master/assets/schema_input.json",
+  "title": "nf-core/variantbenchmarking pipeline - params.input schema",
+  "description": "Schema for the file provided with params.input",
+  "type": "array",
+  "items": {
+    "type": "object",
+    "properties": {
+      "test_vcf": {
+        "type": "string",
+        "pattern": "",
+        "errorMessage": "Test VCF must be provided, cannot contain spaces and must have extension '.vcf.gz'"
+      },
+      "caller": {
+        "type": "string",
+        "pattern": "^\\S+$",
+        "errorMessage": "Name of the variant caller used to generate test file"
+      },
+      "vartype": {
+        "type": "string",
+        "pattern": "^\\S+$",
+        "errorMessage": "Variant type to benchmark"
+      }
+
+    },
+    "required": ["test_vcf","caller","vartype"]
+  }
 }
diff --git a/assets/svync/default.yaml b/assets/svync/default.yaml
diff --git a/assets/svync/delly.yaml b/assets/svync/delly.yaml
@@ -0,0 +1,69 @@
+id: delly_$INFO/SVTYPE
+alt:
+  BND: TRA
+info:
+  CALLER:
+    value: delly
+    number: 1
+    type: string
+    description: The caller used to determine this variant
+  SVLEN:
+    value: ~sub:$INFO/END,$POS
+    number: 1
+    type: integer
+    description: The length of the structural variant
+    alts:
+      DEL: -~sub:$INFO/END,$POS
+      INS: $INFO/SVLEN
+      TRA: 1
+  CIEND:
+    value: $INFO/CIEND
+    number: 2
+    type: integer
+    description: PE confidence interval around END
+  CIPOS:
+    value: $INFO/CIPOS
+    number: 2
+    type: integer
+    description: PE confidence interval around POS
+  SVTYPE:
+    value: $INFO/SVTYPE
+    number: 1
+    type: string
+    description: Type of structural variant
+  CHR2:
+    value:
+    number: 1
+    type: string
+    description: Chromosome for second position
+    alts:
+      TRA: $INFO/CHR2
+  END:
+    value: $INFO/END
+    number: 1
+    type: integer
+    description: End position of the structural variant
+    alts:
+      TRA: $INFO/POS2
+  IMPRECISE:
+    value: $INFO/IMPRECISE
+    number: 0
+    type: flag
+    description: Imprecise structural variation
+format:
+  GT:
+    value: $FORMAT/GT
+    number: 1
+    type: string
+    description: Genotype
+  PE:
+    value: $FORMAT/DR,$FORMAT/DV
+    number: 2
+    type: integer
+    description: Paired-read support for the ref and alt alleles in the order listed
+  SR:
+    value: $FORMAT/RR,$FORMAT/RV
+    number: 2
+    type: integer
+    description: Split-read support for the ref and alt alleles in the order listed
+
diff --git a/assets/svync/gridss.yaml b/assets/svync/gridss.yaml
@@ -0,0 +1,65 @@
+id: gridss_$INFO/SVTYPE
+info:
+  CALLER:
+    value: gridss
+    number: 1
+    type: string
+    description: The caller used to determine this variant
+  SVLEN:
+    value: ~sub:$INFO/END,$POS
+    number: 1
+    type: integer
+    description: The length of the structural variant
+    alts:
+      BND:
+      TRA: 0
+      DEL: -~sub:$INFO/END,$POS
+  CIEND:
+    value: $INFO/CIRPOS
+    number: 2
+    type: integer
+    description: PE confidence interval around END
+  CIPOS:
+    value: $INFO/CIPOS
+    number: 2
+    type: integer
+    description: PE confidence interval around POS
+  SVTYPE:
+    value: $INFO/SVTYPE
+    number: 1
+    type: string
+    description: Type of structural variant
+  CHR2:
+    value:
+    number: 1
+    type: string
+    description: Chromosome for second position
+    alts:
+      TRA: $INFO/CHR2
+  END:
+    value: $INFO/END
+    number: 1
+    type: integer
+    description: End position of the structural variant
+  IMPRECISE:
+    value: $INFO/IMPRECISE
+    number: 0
+    type: flag
+    description: Imprecise structural variation
+format:
+  GT:
+    value: $FORMAT/GT
+    number: 1
+    type: string
+    description: Genotype
+  PE:
+    value: $FORMAT/REFPAIR,$FORMAT/RP
+    number: 2
+    type: integer
+    description: Paired-read support for the ref and alt alleles in the order listed
+  SR:
+    value: .,$FORMAT/SR
+    number: 2
+    type: integer
+    description: Split-read support for the ref and alt alleles in the order listed
+
diff --git a/assets/svync/manta.yaml b/assets/svync/manta.yaml
@@ -0,0 +1,66 @@
+id: manta_$INFO/SVTYPE
+info:
+  CALLER:
+    value: manta
+    number: 1
+    type: string
+    description: The caller used to determine this variant
+  SVLEN:
+    value: $INFO/SVLEN
+    number: 1
+    type: integer
+    description: The length of the structural variant
+    alts:
+      INS: ~sum:~len:LEFT_SVINSSEQ,~len:RIGHT_SVINSSEQ
+      TRA: 1
+  CIEND:
+    value: $INFO/CIEND
+    number: 2
+    type: integer
+    description: PE confidence interval around END
+  CIPOS:
+    value: $INFO/CIPOS
+    number: 2
+    type: integer
+    description: PE confidence interval around POS
+  SVTYPE:
+    value: $INFO/SVTYPE
+    number: 1
+    type: string
+    description: Type of structural variant
+  CHR2:
+    value:
+    number: 1
+    type: string
+    description: Chromosome for second position
+    alts:
+      TRA: $INFO/CHR2
+  END:
+    value: $INFO/END
+    number: 1
+    type: integer
+    description: End position of the structural variant
+    alts:
+      TRA: $INFO/POS2
+  IMPRECISE:
+    value: $INFO/IMPRECISE
+    number: 0
+    type: flag
+    description: Imprecise structural variation
+format:
+  GT:
+    value: $FORMAT/GT
+    number: 1
+    type: string
+    description: Genotype
+  PE:
+    value: $FORMAT/PR
+    number: 2
+    type: integer
+    description: Paired-read support for the ref and alt alleles in the order listed
+  SR:
+    value: $FORMAT/SR
+    number: 2
+    type: integer
+    description: Split-read support for the ref and alt alleles in the order listed
+