refactor: Remove gatk haplotypcaller

BALSAMIC/config/analysis.json

@@ -30,10 +30,6 @@
             "mutation": "somatic",
             "type": "SNV"
         },
-        "tnsnv": {
-            "mutation": "somatic",
-            "type": "SNV"
-        },
         "tnhaplotyper": {
             "mutation": "somatic",
             "type": "SNV"
@@ -46,10 +42,6 @@
               "mutation": "germline",
               "type": "SV"
         }, 
-        "haplotypecaller": {
-            "mutation": "germline",
-            "type": "SNV"
-        },
         "vcfmerge":{
             "mutation": "somatic",
             "type": "SNV"

BALSAMIC/config/cluster.json

@@ -52,14 +52,6 @@
 		"time": "12:00:00",
 		"n": 5
 	},
-	"gatk_haplotypecaller": {
-		"time": "03:00:00",
-		"n": 10
-	},
-	"haplotypecaller_merge": {
-		"time": "01:30:00",
-		"n": 8
-	},
 	"manta_germline": {
 		"time": "05:00:00",
 		"n": 16
@@ -128,14 +120,6 @@
 		"time": "24:00:00",
 		"n": 24
 	},
-	"sentieon_TNsnv": {
-		"time": "24:00:00",
-		"n": 24
-	},
-	"sentieon_TNsnv_tumor_only": {
-		"time": "24:00:00",
-		"n": 24
-	},
 	"sentieon_align_sort": {
 		"time": "24:00:00",
 		"n": 24

BALSAMIC/snakemake_rules/variant_calling/germline.rule

@@ -1,69 +1,6 @@
 # vim: syntax=python tabstop=4 expandtab
 # coding: utf-8
 
-
-
-rule gatk_haplotypecaller:
-    input:
-        fa = config["reference"]["reference_genome"],
-        bam = bam_dir + "{sample_type}.merged.bam",
-        bed = vcf_dir + "split_bed/{bedchrom}." + capture_kit,
-    output:
-        vcf_dir + "haplotypecaller/split_vcf/{sample_type}.{bedchrom}_haplotypecaller.vcf.gz"
-    benchmark:
-        Path(benchmark_dir,'gatk_haplotypecaller_' + "{sample_type}.{bedchrom}.tsv").as_posix()
-    singularity:
-        Path(singularity_image, config["bioinfo_tools"].get("gatk") + ".sif").as_posix()
-    params:
-        tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
-        sample = '{sample_type}',
-        gatk_path = '/opt/conda/opt/gatk-3.8' 
-    threads:
-        get_threads(cluster_config,'gatk_haplotypecaller')
-    message:
-        ("Calling germline variants using gatk haplotypecaller for {params.sample}")
-    shell:
-        """
-mkdir -p {params.tmpdir};
-export TMPDIR={params.tmpdir};
-
-java -jar -Djava.io.tmpdir={params.tmpdir} -Xms8G -Xmx32G {params.gatk_path}/GenomeAnalysisTK.jar \
--T HaplotypeCaller \
--R {input.fa} \
--I {input.bam} \
--L {input.bed} \
-| bgzip > {output}; 
-
-rm -rf {params.tmpdir};
-        """
-
-
-rule haplotypecaller_merge:
-    input:
-        expand(vcf_dir + "haplotypecaller/split_vcf/{{sample_type}}.{chrom}_haplotypecaller.vcf.gz", chrom=chromlist)
-    output:
-        vcf_dir + "SNV.germline.{sample_type}.haplotypecaller.vcf.gz"
-    benchmark:
-        Path(benchmark_dir, 'haplotypecaller_merge_' + "SNV.germline.{sample_type}.tsv").as_posix()
-    singularity:
-        Path(singularity_image, config["bioinfo_tools"].get("gatk") + ".sif").as_posix()
-    params:
-        tmpdir = tempfile.mkdtemp(prefix = tmp_dir),
-        sample = '{sample_type}'
-    message:
-        "Concatenating haplotyper outputs from multiple VCF files using bcftools for {params.sample}"
-    shell:
-        """
-mkdir -p {params.tmpdir};
-export TMPDIR={params.tmpdir};
-
-bcftools concat {input} | bcftools sort --temp-dir {params.tmpdir} - | bgzip > {output};
-tabix -f -p vcf {output};
-
-rm -rf {params.tmpdir};
-        """
-
-
 rule sentieon_DNAscope:
     input:
         bam = bam_dir + "{sample_type}.merged.bam",

BALSAMIC/utils/models.py

@@ -184,7 +184,6 @@ class VCFModel(BaseModel):
     tnscope: VarcallerAttribute
     dnascope: VarcallerAttribute
     tnhaplotyper: VarcallerAttribute
-    haplotypecaller: VarcallerAttribute
     TNscope_umi: VarcallerAttribute
     manta_germline: VarcallerAttribute
     manta: VarcallerAttribute

CHANGELOG.rst

@@ -52,6 +52,7 @@ Removed
 * bcftools_stats from vep #898
 * QC delivery report workflow (generating the ``<case>_qc_report.html`` file) #878
 * ``--sample-id-map`` and ``--case-id-map`` flags from the ``balsamic report deliver`` command #878
+* Removed `gatk_haplotypecaller` for reporting panel germline variants #918 
 
 [8.2.10]
 --------

tests/conftest.py

@@ -603,11 +603,9 @@ def sample_config():
             "vardict": {"mutation": "somatic", "type": "SNV"},
             "mutect": {"mutation": "somatic", "type": "SNV"},
             "tnscope": {"mutation": "somatic", "type": "SNV"},
-            "tnsnv": {"mutation": "somatic", "type": "SNV"},
             "tnhaplotyper": {"mutation": "somatic", "type": "SNV"},
             "dnascope": {"mutation": "germline", "type": "SNV"},
             "manta_germline": {"mutation": "germline", "type": "SV"},
-            "haplotypecaller": {"mutation": "germline", "type": "SNV"},
         },
         "samples": {
             "S1_R": {

tests/test_data/config.json

@@ -24,36 +24,12 @@
             "merged": "manta_germline.vcf.gz",
             "type": "SV"
         },
-        "strelka_germline": {
-            "default": ["variants.vcf.gz", "germline.S1.vcf.gz"],
-            "mutation": "germline",
-            "merged": "strelka_germline.vcf.gz",
-            "type": "SNV"
-        },
-        "strelka": {
-            "default": ["somatic.snvs.vcf.gz", "somatic.indels.vcf.gz"],
-            "mutation": "somatic",
-            "merged": "strelka.vcf.gz",
-            "type": "SNV"
-        },
         "mutect": {
             "default": "mutect.vcf.gz",
             "mutation": "somatic",
             "merged": "mutect.vcf.gz",
             "type": "SNV"
         },
-        "freebayes": {
-            "default": "freebayes.vcf.gz",
-            "mutation": "germline",
-            "merged": "freebayes.vcf.gz",
-            "type": "SNV"
-        },
-        "haplotypecaller": {
-            "default": "haplotypecaller.vcf.gz",
-            "mutation": "germline",
-            "merged": "haplotypecaller.vcf.gz",
-            "type": "SNV"
-        },
         "vardict": {
             "default": "vardict.vcf.gz",
             "mutation": "somatic",