Merge branch 'master' into develop

Clinical-Genomics · Nov 21, 2024 · 67c6701 · 67c6701
2 parents 6e63310 + 92afcd0
commit 67c6701
Show file tree

Hide file tree

Showing 21 changed files with 39 additions and 28 deletions.
diff --git a/.bumpversion.cfg b/.bumpversion.cfg
@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 15.0.1
+current_version = 16.0.0
 commit = True
 tag = True
 tag_name = v{new_version}

diff --git a/.github/workflows/docker_build_publish_release.yml b/.github/workflows/docker_build_publish_release.yml
@@ -11,7 +11,7 @@ jobs:
     strategy:
       fail-fast: true
       matrix:
-        container-name: [align_qc, annotate, ascatNgs, cadd, cnvkit, cnvpytor, coverage_qc, delly, gatk, htslib, msisensorpro, purecn, somalier, varcall_py3, varcall_py27, vcf2cytosure]
+        container-name: [align_qc, annotate, ascatNgs, cadd, cnvkit, cnvpytor, coverage_qc, delly, gatk, htslib, msisensorpro, multiqc, purecn, somalier, varcall_py3, varcall_py27, vcf2cytosure]
     steps:
       - name: Git checkout
         id: git_checkout

diff --git a/BALSAMIC/__init__.py b/BALSAMIC/__init__.py
@@ -1 +1 @@
-__version__ = "15.0.1"
+__version__ = "16.0.0"
diff --git a/BALSAMIC/__version__.py b/BALSAMIC/__version__.py
@@ -1 +1 @@
-__version__ = "15.0.1"
+__version__ = "16.0.0"
diff --git a/BALSAMIC/constants/cluster_analysis.json b/BALSAMIC/constants/cluster_analysis.json
@@ -206,7 +206,7 @@
 	},
 	"vardict_tumor_only": {
 		"time": "10:00:00",
-		"n": 9
+		"n": 18
 	},
 	"sentieon_TNscope": {
 		"time": "24:00:00",

diff --git a/BALSAMIC/snakemake_rules/variant_calling/snv_quality_filter.rule b/BALSAMIC/snakemake_rules/variant_calling/snv_quality_filter.rule
@@ -221,7 +221,6 @@ elif config["analysis"]["sequencing_type"] == 'targeted' and config["analysis"][
       AF_min=[SNV_FILTER_SETTINGS.AF_min.tag_value, SNV_FILTER_SETTINGS.AF_min.filter_name],
       high_normal_tumor_af_frac_filter_name=SNV_FILTER_SETTINGS.high_normal_tumor_af_frac.filter_name,
       high_normal_tumor_af_frac_value=SNV_FILTER_SETTINGS.high_normal_tumor_af_frac.tag_value,
-      possible_germline="balsamic_possible_germline",
       case_name=config["analysis"]["case_id"],
     threads:
       get_threads(cluster_config,'bcftools_quality_filter_vardict_tumor_normal')
@@ -235,7 +234,6 @@ elif config["analysis"]["sequencing_type"] == 'targeted' and config["analysis"][
     bcftools filter --include 'INFO/DP >= {params.DP[0]}' --soft-filter '{params.DP[1]}' --mode '+' | \
     bcftools filter --include 'INFO/VD >= {params.AD[0]}' --soft-filter '{params.AD[1]}' --mode '+' | \
     bcftools filter --include 'INFO/AF >= {params.AF_min[0]}' --soft-filter '{params.AF_min[1]}' --mode '+' | \
-    bcftools filter --exclude 'INFO/STATUS ~ "germline/i"' --soft-filter '{params.possible_germline}' --mode '+' | \
     bcftools view -f PASS -o {output.vcf_filtered} -O z;
 
     tabix -p vcf -f {output.vcf_filtered};

diff --git a/BALSAMIC/snakemake_rules/variant_calling/snv_t_varcall_tga.rule b/BALSAMIC/snakemake_rules/variant_calling/snv_t_varcall_tga.rule
@@ -93,7 +93,8 @@ rule vardict_tumor_only:
 export PERL5LIB=;
 
 export TMPDIR={params.tmpdir};
-export VAR_DICT_OPTS='\"-Djava.io.tmpdir={params.tmpdir}\" \"-Xmx45G\"'; 
+export _JAVA_OPTIONS="-Djava.io.tmpdir={params.tmpdir}"; 
+export VAR_DICT_OPTS='\"-Xms45G\" \"-Xmx90G\"'; 
 
 vardict-java -I 600 \
 -G {input.fa} \

diff --git a/BALSAMIC/snakemake_rules/variant_calling/snv_tn_varcall_tga.rule b/BALSAMIC/snakemake_rules/variant_calling/snv_tn_varcall_tga.rule
@@ -94,7 +94,8 @@ rule vardict_tumor_normal:
     shell:
         """
 export TMPDIR={params.tmpdir};
-export VAR_DICT_OPTS='\"-Djava.io.tmpdir={params.tmpdir}\" \"-Xmx90G\"';
+export _JAVA_OPTIONS="-Djava.io.tmpdir={params.tmpdir}"; 
+export VAR_DICT_OPTS='\"-Xms45G\" \"-Xmx90G\"'; 
 
 vardict-java -I 600 -G {input.fa} -f {params.af} -N {params.case_name} \
 -b \"{input.bamT}|{input.bamN}\" \
@@ -118,6 +119,8 @@ rule post_process_vardict:
     params:
         tmpdir=tempfile.mkdtemp(prefix=tmp_dir),
         case_name=config["analysis"]["case_id"],
+        edit_vcf_script= get_script_path("edit_vcf_info.py"),
+        variant_caller= "vardict"
     benchmark:
         Path(benchmark_dir,'post_process_vardict_' + config["analysis"]["case_id"] + ".tsv").as_posix()
     singularity:
@@ -131,13 +134,18 @@ rule post_process_vardict:
 mkdir -p {params.tmpdir};
 export TMPDIR={params.tmpdir};
 
-bgzip {input.vcf_sorted} ; 
-tabix -f -p vcf {input.vcf_sorted}.gz ;
+python {params.edit_vcf_script} \
+--input_vcf {input.vcf_sorted} \
+--output_vcf {params.tmpdir}/vardict_merged_sorted.temp.vcf \
+--variant_caller {params.variant_caller};
+
+bgzip {params.tmpdir}/vardict_merged_sorted.temp.vcf  ; 
+tabix -f -p vcf {params.tmpdir}/vardict_merged_sorted.temp.vcf.gz ;
 
 echo \"TUMOR\" > {params.tmpdir}/reheader ;
 echo \"NORMAL\" >> {params.tmpdir}/reheader ;
 
-bcftools reheader -s {params.tmpdir}/reheader {input.vcf_sorted}.gz -o {output.vcf_vardict} ;
+bcftools reheader -s {params.tmpdir}/reheader {params.tmpdir}/vardict_merged_sorted.temp.vcf.gz -o {output.vcf_vardict} ;
 tabix -f -p vcf {output.vcf_vardict} ;
 
 echo -e \"tTUMOR\\tTUMOR\\nNORMAL\\tNORMAL\" > {output.namemap} ; 

diff --git a/BALSAMIC/snakemake_rules/variant_calling/somatic_sv_tumor_normal_tga.rule b/BALSAMIC/snakemake_rules/variant_calling/somatic_sv_tumor_normal_tga.rule
@@ -21,7 +21,7 @@ rule manta_tumor_normal:
         tumor = config_model.get_sample_name_by_type(SampleType.TUMOR),
         normal = config_model.get_sample_name_by_type(SampleType.NORMAL),
         case_name = case_id,
-        manta_install_path = "/opt/conda/share/manta-1.6.0-2",
+        manta_install_path = "/opt/conda/share/manta-1.6.0-3",
         low_pr_sr_count_value = MANTA_FILTERS.low_pr_sr_count.tag_value,
         low_pr_sr_count_filter_name = MANTA_FILTERS.low_pr_sr_count.filter_name,
     threads:

diff --git a/BALSAMIC/snakemake_rules/variant_calling/somatic_sv_tumor_normal_wgs.rule b/BALSAMIC/snakemake_rules/variant_calling/somatic_sv_tumor_normal_wgs.rule
@@ -21,7 +21,7 @@ rule manta_tumor_normal:
         tumor = config_model.get_sample_name_by_type(SampleType.TUMOR),
         normal = config_model.get_sample_name_by_type(SampleType.NORMAL),
         case_name = case_id,
-        manta_install_path = "/opt/conda/share/manta-1.6.0-2",
+        manta_install_path = "/opt/conda/share/manta-1.6.0-3",
         low_pr_sr_count_value = MANTA_FILTERS.low_pr_sr_count.tag_value,
         low_pr_sr_count_filter_name = MANTA_FILTERS.low_pr_sr_count.filter_name,
     threads:

diff --git a/BALSAMIC/snakemake_rules/variant_calling/somatic_sv_tumor_only_tga.rule b/BALSAMIC/snakemake_rules/variant_calling/somatic_sv_tumor_only_tga.rule
@@ -19,7 +19,7 @@ rule manta_tumor_only:
         runmode = "local",
         tumor = config_model.get_sample_name_by_type(SampleType.TUMOR),
         case_name = config["analysis"]["case_id"],
-        manta_install_path= "/opt/conda/share/manta-1.6.0-2",
+        manta_install_path= "/opt/conda/share/manta-1.6.0-3",
         low_pr_sr_count = [MANTA_FILTERS.low_pr_sr_count.tag_value,MANTA_FILTERS.low_pr_sr_count.filter_name],
     threads:
         get_threads(cluster_config, "manta_tumor_only")

diff --git a/BALSAMIC/snakemake_rules/variant_calling/somatic_sv_tumor_only_wgs.rule b/BALSAMIC/snakemake_rules/variant_calling/somatic_sv_tumor_only_wgs.rule
@@ -19,7 +19,7 @@ rule manta_tumor_only:
         runmode = "local",
         tumor = config_model.get_sample_name_by_type(SampleType.TUMOR),
         case_name = config["analysis"]["case_id"],
-        manta_install_path= "/opt/conda/share/manta-1.6.0-2",
+        manta_install_path= "/opt/conda/share/manta-1.6.0-3",
         low_pr_sr_count = [MANTA_FILTERS.low_pr_sr_count.tag_value,MANTA_FILTERS.low_pr_sr_count.filter_name],
     threads:
         get_threads(cluster_config, "manta_tumor_only")

diff --git a/BALSAMIC/snakemake_rules/variant_calling/tnscope_post_process.rule b/BALSAMIC/snakemake_rules/variant_calling/tnscope_post_process.rule
@@ -57,7 +57,7 @@ export TMPDIR={params.tmpdir};
 mkdir -p {params.tmpdir};
 
 python {params.modify_tnscope_infofield} {input.vcf_tnscope} {params.tmpdir}/vcf_tnscope_snvs_modified.vcf ;
-python {params.modify_tnscope_infofield} {params.tmpdir}/vcf_tnscope_snvs_modified.vcf {params.tmpdir}/vcf_tnscope_snvs_modified_found_in_added.vcf ;
+python {params.edit_vcf_script} -i {params.tmpdir}/vcf_tnscope_snvs_modified.vcf -o {params.tmpdir}/vcf_tnscope_snvs_modified_found_in_added.vcf -c {params.variant_caller};
 bgzip {params.tmpdir}/vcf_tnscope_snvs_modified_found_in_added.vcf ;
 mv {params.tmpdir}/vcf_tnscope_snvs_modified_found_in_added.vcf.gz {output.vcf_tnscope} ;
 tabix -p vcf -f {output.vcf_tnscope} ;

diff --git a/CHANGELOG.rst b/CHANGELOG.rst
@@ -1,4 +1,4 @@
-[X.X.X]
+[16.0.0]
 -------
 
 Added:
@@ -20,6 +20,7 @@ Added:
 * Added family-id to genmod in order to get ranked variants to Scout https://github.com/Clinical-Genomics/BALSAMIC/pull/1475
 * Added Raw TNscope calls and unfiltered research-annotated SNVs to delivery https://github.com/Clinical-Genomics/BALSAMIC/pull/1475
 * Argument for SNV Artefact LoqusDB to all workflows https://github.com/Clinical-Genomics/BALSAMIC/pull/1481
+* TNscope tag to variant info-field for TGA workflow https://github.com/Clinical-Genomics/BALSAMIC/pull/1497
 
 Changed:
 ^^^^^^^^
@@ -49,6 +50,7 @@ Removed:
 * ML model for TNscope  https://github.com/Clinical-Genomics/BALSAMIC/pull/1475
 * All code associated with TNhaplotyper https://github.com/Clinical-Genomics/BALSAMIC/pull/1475
 * Removed research.filtered.pass files from delivery https://github.com/Clinical-Genomics/BALSAMIC/pull/1475
+* Removed VarDict germline filter, replaced by relative normal af / tumor af filter https://github.com/Clinical-Genomics/BALSAMIC/pull/1497
 
 Fixed:
 ^^^^^^
@@ -58,6 +60,8 @@ Fixed:
 * CNVkit incorrect version in the documentation https://github.com/Clinical-Genomics/BALSAMIC/pull/1457
 * MSIsensor-pro container and updated msisensor to version 1.3.0  https://github.com/Clinical-Genomics/BALSAMIC/pull/1486
 * Somalier container and updated somalier to version 0.2.19 https://github.com/Clinical-Genomics/BALSAMIC/pull/1487
+* Vardict memory and tmpdir allocation https://github.com/Clinical-Genomics/BALSAMIC/pull/1492
+* Vardict tumor only allocates dynamic number of cores https://github.com/Clinical-Genomics/BALSAMIC/pull/1495
 
 [15.0.1]
 --------

diff --git a/CITATION.cff b/CITATION.cff
@@ -18,5 +18,5 @@ authors:
 - family-names: "Wirta"
   given-names: "Valtteri"
 title: "BALSAMIC: Bioinformatic Analysis pipeLine for SomAtic MutatIons in Cancer"
-version: v15.0.1
+version: v16.0.0
 url: "https://github.com/Clinical-Genomics/BALSAMIC"
diff --git a/README.rst b/README.rst
@@ -4,7 +4,7 @@
         <a href="https://github.com/Clinical-Genomics/BALSAMIC">
             <img  width=480 src="https://raw.githubusercontent.com/Clinical-Genomics/BALSAMIC/master/BALSAMIC/assets/images/balsamic_logo.png">
         </a>
-        <h3 align="center">Bioinformatic Analysis pipeLine for SomAtic MutatIons in Cancer (v 15.0.1)</h3>
+        <h3 align="center">Bioinformatic Analysis pipeLine for SomAtic MutatIons in Cancer (v 16.0.0)</h3>
         <h3 align="center">FastQ to Annotated VCF</h3>
     </p>
 
@@ -56,7 +56,7 @@ Snakemake cli given that there is a proper config file created.
 
 .. |docker_latest_build_status| image:: https://github.com/Clinical-Genomics/BALSAMIC/actions/workflows/docker_build_push.yml/badge.svg
 
-.. |docker_latest_release_status| image:: https://github.com/Clinical-Genomics/BALSAMIC/actions/workflows/docker_build_push_release.yml/badge.svg?tag=v15.0.1
+.. |docker_latest_release_status| image:: https://github.com/Clinical-Genomics/BALSAMIC/actions/workflows/docker_build_push_release.yml/badge.svg?tag=v16.0.0
 
 .. |snakemake_badge| image:: https://img.shields.io/badge/snakemake-%E2%89%A55.12.3-brightgreen.svg
 

diff --git a/docs/balsamic_methods.rst b/docs/balsamic_methods.rst
@@ -5,7 +5,7 @@ Method description
 Target Genome Analysis
 ~~~~~~~~~~~~~~~~~~~~~~
 
-BALSAMIC :superscript:`1` (**version** = 15.0.1) was used to analyze the data from raw FASTQ files.
+BALSAMIC :superscript:`1` (**version** = 16.0.0) was used to analyze the data from raw FASTQ files.
 We first quality controlled FASTQ files using FastQC v0.11.9 :superscript:`2`.
 Adapter sequences are trimmed using fastp v0.23.2 :superscript:`3` and then UMI sequences are extracted using the UMI extract tool from sentieon-tools (version 202308.03) :superscript:`15` and finally low-quality bases were trimmed using fastp v0.23.2 :superscript:`3`.
 Trimmed reads were mapped to the reference genome hg19 using sentieon-tools :superscript:`15`.
@@ -25,7 +25,7 @@ to annotate somatic variants for their population allele frequency from gnomAD v
 Whole Genome Analysis
 ~~~~~~~~~~~~~~~~~~~~~
 
-BALSAMIC :superscript:`1` (**version** = 15.0.1) was used to analyze the data from raw FASTQ files.
+BALSAMIC :superscript:`1` (**version** = 16.0.0) was used to analyze the data from raw FASTQ files.
 We first quality controlled FASTQ files using FastQC v0.11.9 :superscript:`2`.
 Adapter sequences and low-quality bases were trimmed using fastp v0.23.2 :superscript:`3`.
 Trimmed reads were mapped to the reference genome hg19 using sentieon-tools 202308.03 :superscript:`15`.
@@ -45,7 +45,7 @@ to annotate somatic single nucleotide variants for their population allele frequ
 UMI workflow
 ~~~~~~~~~~~~~~~~~~~~~
 
-BALSAMIC :superscript:`1` (**version** = 15.0.1) was used to analyze the data from raw FASTQ files.
+BALSAMIC :superscript:`1` (**version** = 16.0.0) was used to analyze the data from raw FASTQ files.
 We first quality controlled FASTQ files using FastQC v0.11.9 :superscript:`2`.
 Adapter sequences were trimmed using fastp v0.23.2 :superscript:`3`.
 UMI tag extraction and alignment and consensus-calling of UMI groups were performed using Sentieon tools 202308.03 :superscript:`15`.

diff --git a/docs/bioinfo_softwares.rst b/docs/bioinfo_softwares.rst
@@ -2,7 +2,7 @@
 Tools and software
 =================================
 
-BALSAMIC ( **version** = 15.0.1 ) uses myriad of tools and softwares to analyze fastq files. This section covers why each
+BALSAMIC ( **version** = 16.0.0 ) uses myriad of tools and softwares to analyze fastq files. This section covers why each
 one is included: usage and parameters, and relevant external links.
 
 ascatNgs

diff --git a/docs/install.rst b/docs/install.rst
@@ -2,7 +2,7 @@
 Installation
 ============
 
-This section describes steps to install BALSAMIC (**version** = 15.0.1)
+This section describes steps to install BALSAMIC (**version** = 16.0.0)
 
 
 

diff --git a/docs/user_guide.rst b/docs/user_guide.rst
@@ -2,7 +2,7 @@
 Short tutorial
 ==============
 
-Here a short tutorial is provided for BALSAMIC (**version** = 15.0.1).
+Here a short tutorial is provided for BALSAMIC (**version** = 16.0.0).
 
 Regarding fastq-inputs
 ---------------------

diff --git a/setup.py b/setup.py
@@ -122,7 +122,7 @@
 
 setup(
     name=NAME,
-    version="15.0.1",
+    version="16.0.0",
     url=URL,
     author=AUTHOR,
     author_email=EMAIL,