Update WGS Germline GATK Janis metadata

janis_pipelines/wgs_germline_gatk/wgsgermlinegatk.py

@@ -1,13 +1,14 @@
 import operator
 import os
+from datetime import date
 from typing import Optional, List
 
 from janis_bioinformatics.data_types import FastqGzPair, Bam, Vcf, CompressedVcf, BamBai
 from janis_bioinformatics.tools import BioinformaticsTool
 from janis_bioinformatics.tools.babrahambioinformatics import FastQC_0_11_8
 from janis_bioinformatics.tools.common import BwaAligner, MergeAndMarkBams_4_1_3
 from janis_bioinformatics.tools.pmac import ParseFastqcAdaptors
-from janis_core import String, Array, File
+from janis_core import String, Array, File, WorkflowMetadata
 from janis_core.tool.test_classes import (
     TTestCase,
     TTestExpectedOutput,
@@ -26,7 +27,7 @@ def id(self):
         return "WGSGermlineGATK"
 
     def friendly_name(self):
-        return "WGS Germline (GATK)"
+        return "Janis Germline Variant-Calling Workflow (GATK)"
 
     def constructor(self):
         self.add_inputs()
@@ -148,6 +149,43 @@ def tests(self) -> Optional[List[TTestCase]]:
             )
         ]
 
+    def bind_metadata(self):
+        meta: WorkflowMetadata = self.metadata
+
+        meta.keywords = ["wgs", "cancer", "germline", "variants", "gatk"]
+        meta.contributors = ["Richard Lupat", "Michael Franklin", "Jiaan Yu"]
+        meta.dateCreated = date(2018, 12, 24)
+        meta.dateUpdated = date(2021, 11, 10)
+        meta.short_documentation = "A variant-calling pipeline using the GATK HaplotypeCaller"
+        meta.documentation = """\
+This is a genomics pipeline to do a single germline sample variant-calling, adapted from GATK Best Practice Workflow.
+
+This workflow is a reference pipeline for using the Janis Python framework (pipelines assistant).
+- Alignment: bwa-mem
+- Variant-Calling: GATK HaplotypeCaller
+- Outputs the final variants in the VCF format.
+
+**Resources**
+
+This pipeline has been tested using the HG38 reference set, available on Google Cloud Storage through:
+
+- https://console.cloud.google.com/storage/browser/genomics-public-data/references/hg38/v0/
+
+This pipeline expects the assembly references to be as they appear in that storage \
+    (".fai", ".amb", ".ann", ".bwt", ".pac", ".sa", "^.dict").
+The known sites (snps_dbsnp, snps_1000gp, known_indels, mills_indels) should be gzipped and tabix indexed.
+"""
+        meta.sample_input_overrides = {
+            "fastqs": [
+                ["sample1_R1.fastq.gz", "sample1_R2.fastq.gz"],
+                ["sample1_R1-TOPUP.fastq.gz", "sample1_R2-TOPUP.fastq.gz"],
+            ],
+            "reference": "Homo_sapiens_assembly38.fasta",
+            "snps_dbsnp": "Homo_sapiens_assembly38.dbsnp138.vcf.gz",
+            "snps_1000gp": "1000G_phase1.snps.high_confidence.hg38.vcf.gz",
+            "known_indels": "Homo_sapiens_assembly38.known_indels.vcf.gz",
+            "mills_indels": "Mills_and_1000G_gold_standard.indels.hg38.vcf.gz",
+        }
 
 if __name__ == "__main__":
     # from toolbuilder.runtest.runner import run_test_case, EngineType