Merge pull request #585 from mvdbeek/haploid_variant_calling

Add haploid variant calling workflow

workflows/variant-calling/haploid-variant-calling-wgs-pe/.dockstore.yml

@@ -0,0 +1,11 @@
+version: 1.2
+workflows:
+- name: main
+  subclass: Galaxy
+  publish: true
+  primaryDescriptorPath: /WGS-PE-variant-calling-in-haploid-system.ga
+  testParameterFiles:
+  - /WGS-PE-variant-calling-in-haploid-system-tests.yml
+  authors:
+  - name: Anton Nekrutenko
+    orcid: 0000-0002-5987-8032

workflows/variant-calling/haploid-variant-calling-wgs-pe/CHANGELOG.md

@@ -0,0 +1,6 @@
+# Changelog
+
+
+## [0.1]
+
+- Initial version of Paired end variant calling in haploid system workflow

workflows/variant-calling/haploid-variant-calling-wgs-pe/README.md

@@ -0,0 +1,22 @@
+# Haploid variant calling for whole genome sequencing paired end data
+
+This workflow uses Illumina or Element read data to discover variants (short nucleotide polymorphisms, SNPs, and small indels) in haploid genomes with multiple genomic sequences (contigs, scaffolds, or chromosomes).
+
+## Inputs dataset
+
+- The workflow needs a list of paired end fastq files
+- A GTF containtaing the Gene annotation for the selected haploid genome
+- A fasta file for the haploid genome to call variants against
+
+## Outputs
+
+- Tab-delimited summary of annotated variants
+- Report summarizing the quality of input data and mapping results
+
+## Processing
+
+- The workflow will remove adapters using fastp
+- The filtered reads are aligned with bwa-mem.
+- Only properly aligned mate pairs are retained, PCR duplicates are removed.
+- Alignments are re-aligned using lofreq viterbi and variants are called with lofreq call.
+- Variants are annotated with snpeff eff

workflows/variant-calling/haploid-variant-calling-wgs-pe/WGS-PE-variant-calling-in-haploid-system-tests.yml

@@ -0,0 +1,49 @@
+- doc: Test outline for WGS-PE-variant-calling-in-haploid-system
+  job:
+    Annotation GTF:
+      class: File
+      location: https://zenodo.org/records/14009320/files/Annotation%20GTF.gtf?download=1
+      filetype: gtf
+    Genome fasta:
+      class: File
+      location: https://zenodo.org/records/14009320/files/Genome%20fasta.fasta.gz?download=1
+      filetype: fasta.gz
+    Paired Collection:
+      class: Collection
+      collection_type: list:paired
+      elements:
+      - class: Collection
+        type: paired
+        identifier: ERR018930
+        elements:
+        - class: File
+          identifier: forward
+          location: https://zenodo.org/records/14009320/files/ERR018930_forward.fastqsanger.gz?download=1
+        - class: File
+          identifier: reverse
+          location: https://zenodo.org/records/14009320/files/ERR018930_reverse.fastqsanger.gz?download=1
+      - class: Collection
+        type: paired
+        identifier: ERR1035492
+        elements:
+        - class: File
+          identifier: forward
+          location: https://zenodo.org/records/14009320/files/ERR1035492_forward.fastqsanger.gz?download=1
+        - class: File
+          identifier: reverse
+          location: https://zenodo.org/records/14009320/files/ERR1035492_reverse.fastqsanger.gz?download=1
+  outputs:
+    Annotated Variants:
+      path: test-data/Annotated Variants.tabular
+    SnpEff variants:
+      element_tests:
+        ERR018930:
+          asserts:
+            - has_line:
+                line: 'NC_009906.1	3204	.	A	G	120.0	PASS	DP=22;AF=0.727273;SB=2;DP4=2,3,3,14;EFF=INTRAGENIC(MODIFIER|||||PVX_087665||NON_CODING|||G)'
+            - has_line:
+                line: 'NC_009906.1	3261	.	C	A	52.0	PASS	DP=15;AF=0.333333;SB=0;DP4=3,7,2,3;EFF=INTRAGENIC(MODIFIER|||||PVX_087665||NON_CODING|||A)'
+        ERR1035492:
+          asserts:
+            has_line:
+              line: 'NC_009906.1	2975	.	A	G	75.0	PASS	DP=26;AF=0.692308;SB=0;DP4=5,3,12,6;EFF=INTRAGENIC(MODIFIER|||||PVX_087665||NON_CODING|||G)'