From 6e1f428e45819844b181bdb23f53c8b50864a3fa Mon Sep 17 00:00:00 2001 From: ashwini06 Date: Tue, 26 Apr 2022 16:54:20 +0200 Subject: [PATCH 1/7] remove gatk haplotypecallers --- .../variant_calling/germline.rule | 64 ------------------- 1 file changed, 64 deletions(-) diff --git a/BALSAMIC/snakemake_rules/variant_calling/germline.rule b/BALSAMIC/snakemake_rules/variant_calling/germline.rule index 8af31a0f1..6234bd106 100644 --- a/BALSAMIC/snakemake_rules/variant_calling/germline.rule +++ b/BALSAMIC/snakemake_rules/variant_calling/germline.rule @@ -1,70 +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 " - "targeted-panel sample {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: - "Concatenate haplotyper outputs of multiple chr vcfs using bcftools for sample {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", From 85e73a9d5f8a4ceaed51afd74c507c03be5446fe Mon Sep 17 00:00:00 2001 From: ashwini06 Date: Tue, 26 Apr 2022 16:59:11 +0200 Subject: [PATCH 2/7] remove haplotypecaller and tnsnv from cluster json --- BALSAMIC/config/cluster.json | 16 ---------------- 1 file changed, 16 deletions(-) diff --git a/BALSAMIC/config/cluster.json b/BALSAMIC/config/cluster.json index edd6965f1..d1e1a6a17 100644 --- a/BALSAMIC/config/cluster.json +++ b/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 From 0fd84001c8fa26db79f7d07e8783c7725fbdcf71 Mon Sep 17 00:00:00 2001 From: ashwini06 Date: Tue, 26 Apr 2022 17:00:16 +0200 Subject: [PATCH 3/7] remove haplotypecaller from models --- BALSAMIC/utils/models.py | 1 - 1 file changed, 1 deletion(-) diff --git a/BALSAMIC/utils/models.py b/BALSAMIC/utils/models.py index 173d7ad37..401244efc 100644 --- a/BALSAMIC/utils/models.py +++ b/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 From 23aaded2698931d8d0602cedcb428b014da8c9d5 Mon Sep 17 00:00:00 2001 From: ashwini06 Date: Tue, 26 Apr 2022 17:00:50 +0200 Subject: [PATCH 4/7] remove haplotypecaller from workflow params --- BALSAMIC/constants/workflow_params.py | 7 ------- 1 file changed, 7 deletions(-) diff --git a/BALSAMIC/constants/workflow_params.py b/BALSAMIC/constants/workflow_params.py index 575457923..485143529 100644 --- a/BALSAMIC/constants/workflow_params.py +++ b/BALSAMIC/constants/workflow_params.py @@ -64,13 +64,6 @@ "sequencing_type": ["targeted", "wgs"], "workflow_solution": ["BALSAMIC"], }, - "haplotypecaller": { - "mutation": "germline", - "type": "SNV", - "analysis_type": ["paired", "single"], - "sequencing_type": ["targeted"], - "workflow_solution": ["BALSAMIC"], - }, "delly": { "mutation": "somatic", "type": "SV", From 4ee0ff8e3ebcbdd1555c5af3a3746d58495ee132 Mon Sep 17 00:00:00 2001 From: ashwini06 Date: Tue, 26 Apr 2022 17:01:36 +0200 Subject: [PATCH 5/7] remove haplotypcaller and tnsnv from analysis json --- BALSAMIC/config/analysis.json | 8 -------- 1 file changed, 8 deletions(-) diff --git a/BALSAMIC/config/analysis.json b/BALSAMIC/config/analysis.json index 3e46e0b1d..6484acccd 100644 --- a/BALSAMIC/config/analysis.json +++ b/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" From 0f3cc8e16c1e5db42666d1a7cae19efb495fa82e Mon Sep 17 00:00:00 2001 From: ashwini06 Date: Tue, 26 Apr 2022 17:02:25 +0200 Subject: [PATCH 6/7] remove unused callers from tests --- tests/conftest.py | 2 -- tests/test_data/config.json | 24 ------------------------ 2 files changed, 26 deletions(-) diff --git a/tests/conftest.py b/tests/conftest.py index 9286aaf1a..213683a44 100644 --- a/tests/conftest.py +++ b/tests/conftest.py @@ -600,11 +600,9 @@ 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": { diff --git a/tests/test_data/config.json b/tests/test_data/config.json index a9e5ba822..3619e0789 100644 --- a/tests/test_data/config.json +++ b/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", From c0fcdd668e1a8239d8bc0363623b1d2bda8bfbe5 Mon Sep 17 00:00:00 2001 From: ashwini06 Date: Tue, 26 Apr 2022 17:04:09 +0200 Subject: [PATCH 7/7] update changelog --- CHANGELOG.rst | 1 + 1 file changed, 1 insertion(+) diff --git a/CHANGELOG.rst b/CHANGELOG.rst index e5a0c7fd6..49f363b36 100644 --- a/CHANGELOG.rst +++ b/CHANGELOG.rst @@ -51,6 +51,7 @@ Removed * bcftools_stats from vep #898 * QC delivery report workflow (generating the ``_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] --------