From 588803a1de6bfd95f60d28d9d14caabf2407ccbb Mon Sep 17 00:00:00 2001 From: Paul Stretenowich Date: Thu, 19 Oct 2023 15:47:43 -0400 Subject: [PATCH] Adding digest_unanalyzed route + debug Operation being linked to Readset when ingesting transfer and GenPipes --- project_tracking/api/project.py | 34 ++++++++--- project_tracking/db_action.py | 90 ++++++++++++++++++++++++---- project_tracking/model.py | 23 +++++++ tests/data/genpipes_rnaseqlight.json | 2 +- tests/data/genpipes_tumourpair.json | 2 +- 5 files changed, 131 insertions(+), 20 deletions(-) diff --git a/project_tracking/api/project.py b/project_tracking/api/project.py index c72381d..1299897 100644 --- a/project_tracking/api/project.py +++ b/project_tracking/api/project.py @@ -433,13 +433,14 @@ def ingest_transfer(project_id: str): Add new location to file that has already been moved before the db was created """ - try: - ingest_data = request.get_json(force=True) - except: - flash('Data does not seems to be json') - return redirect(request.url) + if request.method == 'POST': + try: + ingest_data = request.get_json(force=True) + except: + flash('Data does not seems to be json') + return redirect(request.url) - return [i.flat_dict for i in db_action.ingest_transfer(project_id=project_id, ingest_data=ingest_data)] + return [i.flat_dict for i in db_action.ingest_transfer(project_id=project_id, ingest_data=ingest_data)] @bp.route('//ingest_genpipes', methods=['GET', 'POST']) # @capitalize @@ -463,13 +464,30 @@ def ingest_genpipes(project_id: str): return redirect(request.url) project_id_from_name = db_action.name_to_id("Project", ingest_data[vc.PROJECT_NAME].upper()) - if project_id != project_id_from_name: + if [int(project_id)] != project_id_from_name: return abort( 400, - f"project name in POST {ingest_data[vc.PROJECT_NAME].upper()} not Valid, {project_id} requires" + f"project name in POST {ingest_data[vc.PROJECT_NAME].upper()} not in the database, {project_id} required" ) output = db_action.ingest_genpipes(project_id=project_id, ingest_data=ingest_data) operation = output[0].flat_dict jobs = [job.flat_dict for job in output[1]] return [operation, jobs] + +@bp.route('//digest_unanalyzed', methods=['POST']) +def digest_unanalyzed(project_id: str): + """ + POST: list of Readset/Sample Name or id + return: Readsets or Samples unanalyzed + """ + logger.debug(f"\n\n{project_id}\n\n") + if request.method == 'POST': + try: + ingest_data = request.get_json(force=True) + except: + flash('Data does not seems to be json') + return redirect(request.url) + + return db_action.digest_unanalyzed(project_id=project_id, digest_data=ingest_data) + # return [i.flat_dict for i in db_action.digest_unanalyzed(project_id=project_id, digest_data=ingest_data)] diff --git a/project_tracking/db_action.py b/project_tracking/db_action.py index f0a301b..c0c3a4e 100644 --- a/project_tracking/db_action.py +++ b/project_tracking/db_action.py @@ -521,7 +521,7 @@ def create_project(project_name, fms_id=None, session=None): return session.scalars(select(Project).where(Project.name == project_name)).one() -def ingest_run_processing(project_id, ingest_data, session=None): +def ingest_run_processing(project_id: str, ingest_data, session=None): """Ingesting run for MoH""" if not isinstance(ingest_data, dict): ingest_data = json.loads(ingest_data) @@ -658,7 +658,7 @@ def ingest_run_processing(project_id, ingest_data, session=None): return [operation, job] -def ingest_transfer(project_id, ingest_data, session=None, check_readset_name=True): +def ingest_transfer(project_id: str, ingest_data, session=None, check_readset_name=True): """Ingesting transfer""" if not isinstance(ingest_data, dict): ingest_data = json.loads(ingest_data) @@ -682,9 +682,10 @@ def ingest_transfer(project_id, ingest_data, session=None, check_readset_name=Tr stop=datetime.now(), operation=operation ) - + readset_list = [] for readset_json in ingest_data[vb.READSET]: readset_name = readset_json[vb.READSET_NAME] + readset_list.append(session.scalars(select(Readset).where(Readset.name == readset_name)).unique().first()) for file_json in readset_json[vb.FILE]: src_uri = file_json[vb.SRC_LOCATION_URI] dest_uri = file_json[vb.DEST_LOCATION_URI] @@ -692,8 +693,8 @@ def ingest_transfer(project_id, ingest_data, session=None, check_readset_name=Tr file = session.scalars( select(File) .join(File.readsets) - .where(Readset.name == readset_name ) - .join(File.locations ) + .where(Readset.name == readset_name) + .join(File.locations) .where(Location.uri == src_uri) ).unique().first() if not file: @@ -712,6 +713,7 @@ def ingest_transfer(project_id, ingest_data, session=None, check_readset_name=Tr new_location = Location.from_uri(uri=dest_uri, file=file, session=session) file.jobs.append(job) session.add(new_location) + operation.readsets = readset_list session.add(job) session.flush() @@ -733,7 +735,7 @@ def ingest_transfer(project_id, ingest_data, session=None, check_readset_name=Tr return [operation, job] -def digest_readset_file(project_id, digest_data, session=None): +def digest_readset_file(project_id: str, digest_data, session=None): """Digesting readset file fields for GenPipes""" if not session: session = database.get_session() @@ -840,7 +842,7 @@ def digest_readset_file(project_id, digest_data, session=None): output.append(readset_line) return json.dumps(output) -def digest_pair_file(project_id, digest_data, session=None): +def digest_pair_file(project_id: str, digest_data, session=None): """Digesting pair file fields for GenPipes""" if not session: session = database.get_session() @@ -904,7 +906,7 @@ def digest_pair_file(project_id, digest_data, session=None): return json.dumps(output) -def ingest_genpipes(project_id, ingest_data, session=None): +def ingest_genpipes(project_id: str, ingest_data, session=None): """Ingesting GenPipes run""" if not isinstance(ingest_data, dict): ingest_data = json.loads(ingest_data) @@ -914,7 +916,7 @@ def ingest_genpipes(project_id, ingest_data, session=None): project = projects(project_id=project_id, session=session)[0] - operation_config = OperationConfig( + operation_config = OperationConfig.from_attributes( name=ingest_data[vb.OPERATION_CONFIG_NAME], version=ingest_data[vb.OPERATION_CONFIG_VERSION], md5sum=ingest_data[vb.OPERATION_CONFIG_MD5SUM], @@ -930,6 +932,7 @@ def ingest_genpipes(project_id, ingest_data, session=None): operation_config=operation_config ) + readset_list = [] for sample_json in ingest_data[vb.SAMPLE]: sample = session.scalars( select(Sample) @@ -942,6 +945,7 @@ def ingest_genpipes(project_id, ingest_data, session=None): select(Readset) .where(Readset.name == readset_json[vb.READSET_NAME]) ).unique().first() + readset_list.append(readset) if not readset: raise DidNotFindError(f"No readset named {readset_json[vb.READSET_NAME]}") if readset.sample != sample: @@ -1007,7 +1011,7 @@ def ingest_genpipes(project_id, ingest_data, session=None): session.add(job) session.flush() - + operation.readsets = readset_list operation_id = operation.id job_ids = [job.id for job in operation.jobs] try: @@ -1022,3 +1026,69 @@ def ingest_genpipes(project_id, ingest_data, session=None): jobs = [session.scalars(select(Job).where(Job.id == job_id)).first() for job_id in job_ids] return [operation, jobs] + + +def digest_unanalyzed(project_id: str, digest_data, session=None): + """ + Getting unanalyzed samples or readsets + """ + if not session: + session = database.get_session() + + session = database.get_session() + + if isinstance(project_id, str): + project_id = [project_id] + + sample_name_flag = digest_data["sample_name"] + sample_id_flag = digest_data["sample_id"] + readset_name_flag = digest_data["readset_name"] + readset_id_flag = digest_data["readset_id"] + run_id = digest_data["run_id"] + run_name = digest_data["run_name"] + if run_name: + run_id = name_to_id("Run", run_name)[0] + experiment_sequencing_technology = digest_data["experiment_sequencing_technology"] + location_endpoint = digest_data["location_endpoint"] + + if sample_name_flag: + stmt = select(Sample.name) + key = "sample_name" + elif sample_id_flag: + stmt = select(Sample.id) + key = "sample_id" + elif readset_name_flag: + stmt = select(Readset.name) + key = "readset_name" + elif readset_id_flag: + stmt = select(Readset.id) + key = "readset_id" + + stmt = ( + stmt.join(Sample.readsets) + .join(Readset.operations) + .where(Operation.name.ilike(f"%genpipes%")) + .join(Sample.patient) + .join(Patient.project) + .where(Project.id.in_(project_id)) + ) + + if run_id: + stmt = ( + stmt.where(Run.id == run_id) + .join(Readset.run) + ) + if experiment_sequencing_technology: + stmt = ( + stmt.where(Experiment.sequencing_technology == experiment_sequencing_technology) + .join(Readset.experiment) + ) + + # logger.debug(f"\n\n{stmt}\n\n") + output = { + "location_endpoint": location_endpoint, + key: session.scalars(stmt).unique().all() + } + # logger.debug(f"\n\n{session.scalars(stmt).unique().all()}\n\n") + + return json.dumps(output) diff --git a/project_tracking/model.py b/project_tracking/model.py index 4abbc71..2b74951 100644 --- a/project_tracking/model.py +++ b/project_tracking/model.py @@ -556,6 +556,29 @@ def config_data(cls, data): """ pass + @classmethod + def from_attributes(cls, name=None, version=None, md5sum=None, data=None, session=None): + """ + get operation_config if it exist, set it if it does not exist + """ + if not session: + session = database.get_session() + operation_config = session.scalars( + select(cls) + .where(cls.name == name) + .where(cls.version == version) + .where(cls.md5sum == md5sum) + .where(cls.data == data) + ).first() + if not operation_config: + operation_config = cls( + name=name, + version=version, + md5sum=md5sum, + data=data + ) + return operation_config + class Job(BaseTable): """ diff --git a/tests/data/genpipes_rnaseqlight.json b/tests/data/genpipes_rnaseqlight.json index 516b6c1..beb4d21 100644 --- a/tests/data/genpipes_rnaseqlight.json +++ b/tests/data/genpipes_rnaseqlight.json @@ -6,7 +6,7 @@ "operation_config_data": "[DEFAULT]\ncluster_server = beluga.genome.mcgill.ca\nsequencing_center = McGill Genome Centre\ncluster_submit_cmd_suffix = | grep \"[0-9]\" | cut -d\\ -f4\ncluster_other_arg = --mail-type=END,FAIL --mail-user=$JOB_MAIL -A $RAP_ID\ncluster_work_dir_arg = -D\ncluster_output_dir_arg = -o\ncluster_job_name_arg = -J\ncluster_cmd_produces_job_id = true\ncluster_dependency_arg = --depend=afterok:\ncluster_dependency_sep = :\ncluster_max_jobs = 3000\ntmp_dir = ${SLURM_TMPDIR}\nportal_output_dir = $PORTAL_OUTPUT_DIR\ncluster_walltime = 24:00:00\ncluster_cpu = 1\ncluster_node = 1\nALL_CPU = 40\nHALF_CPU = 20\nQUART_CPU = 10\nPINT_CPU = 5\nALL_MEM = 187G\nHALF_MEM = 90G\nQUART_MEM = 60G\nPINT_MEM = 30G\ncluster_mem = 4700M per cpu\ncluster_queue = \nLARGE_QUEUE = \nmodule_java = mugqic/java/openjdk-jdk1.8.0_72\nmodule_mugqic_R_packages = mugqic/mugqic_R_packages/1.0.6\nmodule_mugqic_tools = mugqic/mugqic_tools/2.8.1\nmodule_pandoc = mugqic/pandoc/2.16.1\nmodule_picard = mugqic/picard/2.0.1\nmodule_python = mugqic/python/2.7.11\nmodule_R = mugqic/R_Bioconductor/3.5.0_3.7\nmodule_trimmomatic = mugqic/trimmomatic/0.35\nmodule_kallisto = mugqic/kallisto/0.44.0\nmodule_perl = mugqic/perl/5.22.1\nscientific_name = Homo_sapiens\nassembly = GRCh38\nsource = Ensembl\nversion = 104\nassembly_dir = $MUGQIC_INSTALL_HOME/genomes/species/%(scientific_name)s.%(assembly)s\nannotations_prefix = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.%(source)s%(version)s\ngenome_fasta = %(assembly_dir)s/genome/%(scientific_name)s.%(assembly)s.fa\ngtf = %(annotations_prefix)s.gtf\ngtf_transcript_id = %(annotations_prefix)s.transcript_id.gtf\nribosomal_fasta = %(assembly_dir)s/annotations/rrna_bwa_index/%(scientific_name)s.%(assembly)s.%(source)s%(version)s.rrna.fa\nchromosome_size = %(assembly_dir)s/genome/%(scientific_name)s.%(assembly)s.fa.fai\ngenes = %(annotations_prefix)s.genes.tsv\ngene_size = %(annotations_prefix)s.genes.length.tsv\ngene_ontology = %(annotations_prefix)s.GO.tsv\nannotation_flat = %(annotations_prefix)s.ref_flat.tsv\njava_other_options = -XX:ParallelGCThreads=4\nprotocol = TrueSeq mRNA\ncycle_number = 100\nstrand_info = fr-firststrand\nALL_MEM_EPS = 180G\nGPU_QUEUE = \ncommon_name = Human\nassembly_synonyms = hg38\ndbsnp_version = 142\ngnomad_exome = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.gnomad.exomes.r2.0.2.sites.no-VEP.nohist.tidy.vcf.gz\ndbnsfp = %(assembly_dir)s/annotations/dbNSFPv3.5a/dbNSFPv3.5a.txt.gz.txt.gz\naf_gnomad = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.af-only-gnomad.vcf.gz\nCTAT_bundle_version = GRCh38_gencode_v32_CTAT_lib_Dec062019\ngenome_mappability_bed_indexed = %(assembly_dir)s/annotations/mappabilityGC/GRCh38_100bpPAIREDEND.exclusion.bed\npopulation_AF = 1000Gp1_EUR_AF\nexcluded_chromosome = chrM,chr1_KI270706v1_random,chr1_KI270707v1_random,chr1_KI270708v1_random,chr1_KI270709v1_random,chr1_KI270710v1_random,chr1_KI270711v1_random,chr1_KI270712v1_random,chr1_KI270713v1_random,chr1_KI270714v1_random,chr2_KI270715v1_random,chr2_KI270716v1_random,chr3_GL000221v1_random,chr4_GL000008v2_random,chr5_GL000208v1_random,chr9_KI270717v1_random,chr9_KI270718v1_random,chr9_KI270719v1_random,chr9_KI270720v1_random,chr11_KI270721v1_random,chr14_GL000009v2_random,chr14_GL000225v1_random,chr14_KI270722v1_random,chr14_GL000194v1_random,chr14_KI270723v1_random,chr14_KI270724v1_random,chr14_KI270725v1_random,chr14_KI270726v1_random,chr15_KI270727v1_random,chr16_KI270728v1_random,chr17_GL000205v2_random,chr17_KI270729v1_random,chr17_KI270730v1_random,chr22_KI270731v1_random,chr22_KI270732v1_random,chr22_KI270733v1_random,chr22_KI270734v1_random,chr22_KI270735v1_random,chr22_KI270736v1_random,chr22_KI270737v1_random,chr22_KI270738v1_random,chr22_KI270739v1_random,chrY_KI270740v1_random,chrUn_KI270302v1,chrUn_KI270304v1,chrUn_KI270303v1,chrUn_KI270305v1,chrUn_KI270322v1,chrUn_KI270320v1,chrUn_KI270310v1,chrUn_KI270316v1,chrUn_KI270315v1,chrUn_KI270312v1,chrUn_KI270311v1,chrUn_KI270317v1,chrUn_KI270412v1,chrUn_KI270411v1,chrUn_KI270414v1,chrUn_KI270419v1,chrUn_KI270418v1,chrUn_KI270420v1,chrUn_KI270424v1,chrUn_KI270417v1,chrUn_KI270422v1,chrUn_KI270423v1,chrUn_KI270425v1,chrUn_KI270429v1,chrUn_KI270442v1,chrUn_KI270466v1,chrUn_KI270465v1,chrUn_KI270467v1,chrUn_KI270435v1,chrUn_KI270438v1,chrUn_KI270468v1,chrUn_KI270510v1,chrUn_KI270509v1,chrUn_KI270518v1,chrUn_KI270508v1,chrUn_KI270516v1,chrUn_KI270512v1,chrUn_KI270519v1,chrUn_KI270522v1,chrUn_KI270511v1,chrUn_KI270515v1,chrUn_KI270507v1,chrUn_KI270517v1,chrUn_KI270529v1,chrUn_KI270528v1,chrUn_KI270530v1,chrUn_KI270539v1,chrUn_KI270538v1,chrUn_KI270544v1,chrUn_KI270548v1,chrUn_KI270583v1,chrUn_KI270587v1,chrUn_KI270580v1,chrUn_KI270581v1,chrUn_KI270579v1,chrUn_KI270589v1,chrUn_KI270590v1,chrUn_KI270584v1,chrUn_KI270582v1,chrUn_KI270588v1,chrUn_KI270593v1,chrUn_KI270591v1,chrUn_KI270330v1,chrUn_KI270329v1,chrUn_KI270334v1,chrUn_KI270333v1,chrUn_KI270335v1,chrUn_KI270338v1,chrUn_KI270340v1,chrUn_KI270336v1,chrUn_KI270337v1,chrUn_KI270363v1,chrUn_KI270364v1,chrUn_KI270362v1,chrUn_KI270366v1,chrUn_KI270378v1,chrUn_KI270379v1,chrUn_KI270389v1,chrUn_KI270390v1,chrUn_KI270387v1,chrUn_KI270395v1,chrUn_KI270396v1,chrUn_KI270388v1,chrUn_KI270394v1,chrUn_KI270386v1,chrUn_KI270391v1,chrUn_KI270383v1,chrUn_KI270393v1,chrUn_KI270384v1,chrUn_KI270392v1,chrUn_KI270381v1,chrUn_KI270385v1,chrUn_KI270382v1,chrUn_KI270376v1,chrUn_KI270374v1,chrUn_KI270372v1,chrUn_KI270373v1,chrUn_KI270375v1,chrUn_KI270371v1,chrUn_KI270448v1,chrUn_KI270521v1,chrUn_GL000195v1,chrUn_GL000219v1,chrUn_GL000220v1,chrUn_GL000224v1,chrUn_KI270741v1,chrUn_GL000226v1,chrUn_GL000213v1,chrUn_KI270743v1,chrUn_KI270744v1,chrUn_KI270745v1,chrUn_KI270746v1,chrUn_KI270747v1,chrUn_KI270748v1,chrUn_KI270749v1,chrUn_KI270750v1,chrUn_KI270751v1,chrUn_KI270752v1,chrUn_KI270753v1,chrUn_KI270754v1,chrUn_KI270755v1,chrUn_KI270756v1,chrUn_KI270757v1,chrUn_GL000214v1,chrUn_KI270742v1,chrUn_GL000216v2,chrUn_GL000218v1,chrEBV\n\n[picard_sam_to_fastq]\njava_other_options = -XX:ParallelGCThreads=1 -Dsamjdk.buffer_size=4194304\nram = 16000G\ncluster_mem = 16G\n\n[trimmomatic]\ncluster_mem = 20G\nram = 20G\ncluster_cpu = %(QUART_CPU)s\nthreads = %(cluster_cpu)s\ntrailing_min_quality = 30\nmin_length = 32\nillumina_clip_settings = :2:30:15:8:true\ncluster_walltime = --time=24:00:0\njava_other_options = -XX:ParallelGCThreads=5 -Dsamjdk.buffer_size=1048576\n\n[kallisto]\ntranscriptome_idx = $MUGQIC_INSTALL_HOME/genomes/species/%(scientific_name)s.%(assembly)s/annotations/cdna_kallisto_index/%(scientific_name)s.%(assembly)s.%(source)s%(version)s.cdna.fa.idx\ntranscript2genes = $MUGQIC_INSTALL_HOME/genomes/species/%(scientific_name)s.%(assembly)s/annotations/cdna_kallisto_index/%(scientific_name)s.%(assembly)s.%(source)s%(version)s.tx2gene\ncluster_walltime = 23:00:0\ncluster_cpu = 10\nbootstraps = 120\nfragment_length = 120\nfragment_length_sd = 20\ncluster_mem = 42G\n\n[kallisto_count_matrix]\ncluster_walltime = --time=23:30:0\ncluster_cpu = 2\ncluster_mem = 24G\n\n[gq_seq_utils_exploratory_analysis_rnaseq_light]\ncluster_walltime = 00:30:0\ncluster_cpu = 2\ncluster_mem = 24G\n\n[sleuth_differential_expression]\ntx2gene = $MUGQIC_INSTALL_HOME/genomes/species/%(scientific_name)s.%(assembly)s/annotations/%(scientific_name)s.%(assembly)s.%(source)s%(version)s.tx2gene.csv\ncluster_mem = 16G\n\n[report]\ntitle = RNA-Seq Light Analysis Report\ncluster_walltime = 30:00\n\n[run_checkmate]\nbed = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.SNP_GRCh38_hg19_woChr.bed\n\n[compute_effects]\nsnpeff_genome = %(assembly_synonyms)s\n\n[conpair_concordance_contamination]\nmarkers_bed = ${CONPAIR_DATA}/markers/%(assembly)s.autosomes.phase3_shapeit2_mvncall_integrated.20130502.SNV.genotype.sselect_v4_MAF_0.4_LD_0.8.liftover.bed\nmarkers_txt = ${CONPAIR_DATA}/markers/%(assembly)s.autosomes.phase3_shapeit2_mvncall_integrated.20130502.SNV.genotype.sselect_v4_MAF_0.4_LD_0.8.liftover.txt\n\n[gatk_mutect2]\npon = \n\n[amber]\nloci = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.GermlineHetPon.vcf.gz\n\n[cobalt]\ngc_profile = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.GC_profile.1000bp.cnp\n\n[purple]\ngc_profile = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.GC_profile.1000bp.cnp\n\n[report_cpsr]\nassembly = grch38\n\n[report_pcgr]\nassembly = grch38\n\n[delly_call_filter]\nexclude_list = ${DELLY_PATH}/excludeTemplates/human.hg38.excl.tsv\n\n[cnvkit_batch]\naccess = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.access-5k-mappable.bed\nrefFlat = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.UCSC.ref_flat.tsv\n\n[wham_call_sv]\nexclude = chr1_KI270706v1_random,chr1_KI270707v1_random,chr1_KI270708v1_random,chr1_KI270709v1_random,chr1_KI270710v1_random,chr1_KI270711v1_random,chr1_KI270712v1_random,chr1_KI270713v1_random,chr1_KI270714v1_random,chr2_KI270715v1_random,chr2_KI270716v1_random,chr3_GL000221v1_random,chr4_GL000008v2_random,chr5_GL000208v1_random,chr9_KI270717v1_random,chr9_KI270718v1_random,chr9_KI270719v1_random,chr9_KI270720v1_random,chr11_KI270721v1_random,chr14_GL000009v2_random,chr14_GL000225v1_random,chr14_KI270722v1_random,chr14_GL000194v1_random,chr14_KI270723v1_random,chr14_KI270724v1_random,chr14_KI270725v1_random,chr14_KI270726v1_random,chr15_KI270727v1_random,chr16_KI270728v1_random,chr17_GL000205v2_random,chr17_KI270729v1_random,chr17_KI270730v1_random,chr22_KI270731v1_random,chr22_KI270732v1_random,chr22_KI270733v1_random,chr22_KI270734v1_random,chr22_KI270735v1_random,chr22_KI270736v1_random,chr22_KI270737v1_random,chr22_KI270738v1_random,chr22_KI270739v1_random,chrY_KI270740v1_random,chrUn_KI270302v1,chrUn_KI270304v1,chrUn_KI270303v1,chrUn_KI270305v1,chrUn_KI270322v1,chrUn_KI270320v1,chrUn_KI270310v1,chrUn_KI270316v1,chrUn_KI270315v1,chrUn_KI270312v1,chrUn_KI270311v1,chrUn_KI270317v1,chrUn_KI270412v1,chrUn_KI270411v1,chrUn_KI270414v1,chrUn_KI270419v1,chrUn_KI270418v1,chrUn_KI270420v1,chrUn_KI270424v1,chrUn_KI270417v1,chrUn_KI270422v1,chrUn_KI270423v1,chrUn_KI270425v1,chrUn_KI270429v1,chrUn_KI270442v1,chrUn_KI270466v1,chrUn_KI270465v1,chrUn_KI270467v1,chrUn_KI270435v1,chrUn_KI270438v1,chrUn_KI270468v1,chrUn_KI270510v1,chrUn_KI270509v1,chrUn_KI270518v1,chrUn_KI270508v1,chrUn_KI270516v1,chrUn_KI270512v1,chrUn_KI270519v1,chrUn_KI270522v1,chrUn_KI270511v1,chrUn_KI270515v1,chrUn_KI270507v1,chrUn_KI270517v1,chrUn_KI270529v1,chrUn_KI270528v1,chrUn_KI270530v1,chrUn_KI270539v1,chrUn_KI270538v1,chrUn_KI270544v1,chrUn_KI270548v1,chrUn_KI270583v1,chrUn_KI270587v1,chrUn_KI270580v1,chrUn_KI270581v1,chrUn_KI270579v1,chrUn_KI270589v1,chrUn_KI270590v1,chrUn_KI270584v1,chrUn_KI270582v1,chrUn_KI270588v1,chrUn_KI270593v1,chrUn_KI270591v1,chrUn_KI270330v1,chrUn_KI270329v1,chrUn_KI270334v1,chrUn_KI270333v1,chrUn_KI270335v1,chrUn_KI270338v1,chrUn_KI270340v1,chrUn_KI270336v1,chrUn_KI270337v1,chrUn_KI270363v1,chrUn_KI270364v1,chrUn_KI270362v1,chrUn_KI270366v1,chrUn_KI270378v1,chrUn_KI270379v1,chrUn_KI270389v1,chrUn_KI270390v1,chrUn_KI270387v1,chrUn_KI270395v1,chrUn_KI270396v1,chrUn_KI270388v1,chrUn_KI270394v1,chrUn_KI270386v1,chrUn_KI270391v1,chrUn_KI270383v1,chrUn_KI270393v1,chrUn_KI270384v1,chrUn_KI270392v1,chrUn_KI270381v1,chrUn_KI270385v1,chrUn_KI270382v1,chrUn_KI270376v1,chrUn_KI270374v1,chrUn_KI270372v1,chrUn_KI270373v1,chrUn_KI270375v1,chrUn_KI270371v1,chrUn_KI270448v1,chrUn_KI270521v1,chrUn_GL000195v1,chrUn_GL000219v1,chrUn_GL000220v1,chrUn_GL000224v1,chrUn_KI270741v1,chrUn_GL000226v1,chrUn_GL000213v1,chrUn_KI270743v1,chrUn_KI270744v1,chrUn_KI270745v1,chrUn_KI270746v1,chrUn_KI270747v1,chrUn_KI270748v1,chrUn_KI270749v1,chrUn_KI270750v1,chrUn_KI270751v1,chrUn_KI270752v1,chrUn_KI270753v1,chrUn_KI270754v1,chrUn_KI270755v1,chrUn_KI270756v1,chrUn_KI270757v1,chrUn_GL000214v1,chrUn_KI270742v1,chrUn_GL000216v2,chrUn_GL000218v1,chrEBV\n\n[run_arriba]\nblacklist = $ARRIBA_HOME/database/blacklist_hg38_GRCh38_2018-01-13.tsv", "operation_platform": "beluga", "operation_cmd_line": "module purge\nmodule load python/3.10.2 mugqic/genpipes/4.2.0\nrnaseq_light.py \n -j slurm \n -r readset.txt \n -s 1-5 \n -c $MUGQIC_PIPELINES_HOME/pipelines/rnaseq_light/rnaseq_light.base.ini \n $MUGQIC_PIPELINES_HOME/pipelines/common_ini/beluga.ini \n $MUGQIC_PIPELINES_HOME/resources/genomes/config/Homo_sapiens.GRCh38.ini \n RNA_light.custom.ini \n > RNASeq_light_run.sh\nrm -r RNA_CHUNKS;\nmkdir RNA_CHUNKS;\n$MUGQIC_PIPELINES_HOME/utils/chunk_genpipes.sh -n 100 RNASeq_light_run.sh RNA_CHUNKS", - "operation_name": "genpipes_rnaseq_light", + "operation_name": "GenPipes_RnaSeq.cancer", "sample": [ { "sample_name": "MoHQ-CM-1-3-6929-1RT", diff --git a/tests/data/genpipes_tumourpair.json b/tests/data/genpipes_tumourpair.json index dc201de..526b011 100644 --- a/tests/data/genpipes_tumourpair.json +++ b/tests/data/genpipes_tumourpair.json @@ -5,7 +5,7 @@ "operation_config_data": "\\\n[DEFAULT]\\\ncluster_server = beluga.genome.mcgill.ca\\\nsequencing_center = McGill Genome Centre\\\ncluster_submit_cmd_suffix = | grep \"[0-9]\" | cut -d\\ -f4\\\ncluster_other_arg = --mail-type=FAIL --mail-user=$JOB_MAIL -A $RAP_ID\\\ncluster_work_dir_arg = -D\\\ncluster_output_dir_arg = -o\\\ncluster_job_name_arg = -J\\\ncluster_cmd_produces_job_id = true\\\ncluster_dependency_arg = --depend=afterok:\\\ncluster_dependency_sep = :\\\ncluster_max_jobs = 3000\\\ntmp_dir = ${SLURM_TMPDIR}\\\nportal_output_dir = $PORTAL_OUTPUT_DIR\\\ncluster_walltime = 24:00:00\\\ncluster_cpu = 1\\\ncluster_node = 1\\\nALL_CPU = 40\\\nHALF_CPU = 20\\\nQUART_CPU = 10\\\nPINT_CPU = 5\\\nALL_MEM = 187G\\\nHALF_MEM = 90G\\\nQUART_MEM = 60G\\\nPINT_MEM = 30G\\\ncluster_mem = 4700M per cpu\\\ncluster_queue = \\\nLARGE_QUEUE = \\\nmodule_bvatools = mugqic/bvatools/1.6\\\nmodule_bwa = mugqic/bwa/0.7.17\\\nmodule_bwakit = mugqic/bwakit/0.7.15\\\nmodule_gatk = mugqic/GenomeAnalysisTK/4.1.8.1\\\nmodule_sambamba = mugqic/sambamba/0.8.0\\\nmodule_igvtools = mugqic/igvtools/2.3.14\\\nmodule_java = mugqic/java/openjdk-jdk1.8.0_72\\\nmodule_mugqic_R_packages = mugqic/mugqic_R_packages/1.0.4\\\nmodule_mugqic_tools = mugqic/mugqic_tools/2.10.5\\\nmodule_pandoc = mugqic/pandoc/2.16.1\\\nmodule_perl = mugqic/perl/5.34.0\\\nmodule_picard = mugqic/picard/2.9.0\\\nmodule_python = mugqic/python/3.9.1\\\nmodule_R = mugqic/R_Bioconductor/3.5.0_3.7\\\nmodule_samtools = mugqic/samtools/1.12\\\nmodule_bcftools = mugqic/bcftools/1.15\\\nmodule_snpeff = mugqic/snpEff/4.3\\\nmodule_trimmomatic = mugqic/trimmomatic/0.35\\\nmodule_vcftools = mugqic/vcftools/0.1.14\\\nmodule_skewer = mugqic/skewer/0.2.2\\\nmodule_qualimap = mugqic/qualimap/2.2.2dev\\\nmodule_fastqc = mugqic/fastqc/0.11.5\\\nmodule_htslib = mugqic/htslib/1.14\\\nmodule_verify_bam_id = mugqic/verifyBamID/1.1.3\\\nmodule_vt = mugqic/vt/0.57\\\nmodule_gemini = mugqic/gemini/0.20.1\\\nmodule_multiqc = mugqic/MultiQC/1.9\\\nmodule_checkmate = mugqic/NGSCheckMate/1.0.0_rjme\\\nmodule_variantBam = mugqic/variantbam/1.4.3\\\nmodule_cnvkit = mugqic/CNVkit/0.9.9\\\nmodule_delly = mugqic/Delly/0.8.1\\\nmodule_sv_annotations = mugqic/simple_sv_annotation/1.0.0\\\nmodule_manta = mugqic/Manta/1.5.0\\\nmodule_samblaster = mugqic/samblaster/0.1.24\\\nmodule_lumpy = mugqic/LUMPY-SV/0.2.13\\\nmodule_wham = mugqic/WHAM/1.8.0\\\nmodule_breakseq2 = mugqic/breakseq2/2.2\\\nmodule_vcflib = mugqic/vcflib/1.0.0\\\nmodule_spades = mugqic/SPAdes/3.10.0\\\nmodule_age = mugqic/AGE/master-20181210\\\nmodule_bedtools = mugqic/bedtools/2.26.0\\\nmodule_vawk = mugqic/vawk/0.0.2\\\nmodule_svaba = mugqic/SvABA/1.1.0\\\nscientific_name = Homo_sapiens\\\nassembly = GRCh38\\\nsource = Ensembl\\\nversion = 102\\\nassembly_alias = b37\\\ndbsnp_version = 142\\\nassembly_dir = $MUGQIC_INSTALL_HOME/genomes/species/%(scientific_name)s.%(assembly)s\\\ngenome_fasta = %(assembly_dir)s/genome/%(scientific_name)s.%(assembly)s.fa\\\ngenome_dictionary = %(assembly_dir)s/genome/%(scientific_name)s.%(assembly)s.dict\\\ngenome_bwa_index = %(assembly_dir)s/genome/bwa_index/%(scientific_name)s.%(assembly)s.fa\\\nknown_variants = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.dbSNP%(dbsnp_version)s.vcf.gz\\\nigv_genome = %(genome_fasta)s.fai\\\nsnpeff_genome = %(assembly)s.%(version)s\\\nhapmap = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.hapmap_3.3.vcf.gz\\\n1000G = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.1000G_phase1.snps.high_confidence.vcf.gz\\\ndbsnp = %(known_variants)s\\\nomni = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.1000G_omni2.5.vcf.gz\\\nmills = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.Mills_and_1000G_gold_standard.indels.vcf.gz\\\ngenome_mappability_bed_indexed = %(assembly_dir)s/annotations/mappabilityGC/GRCh38_100bpPAIREDEND.exclusion.bed\\\ndbnsfp = %(assembly_dir)s/annotations/dbNSFPv3.5a/dbNSFPv3.5a.txt.gz.txt.gz\\\ncommon_snp_positions = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.1000G_phase1.snps.high_confidence.allpop_q200.tsv\\\ngnomad_exome = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.gnomad.exomes.r2.0.2.sites.no-VEP.nohist.tidy.vcf.gz\\\naf_gnomad = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.af-only-gnomad.vcf.gz\\\nvcf_header = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.vcf_header.tsv\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=1 -Dsamjdk.buffer_size=4194304\\\ngatk4_java_options = -XX:+UseParallelGC -XX:ParallelGCThreads=1 -Dsamjdk.buffer_size=4194304 -Dsamjdk.use_async_io_read_samtools=true -Dsamjdk.use_async_io_write_samtools=true -Dsamjdk.use_async_io_write_tribble=false\\\nexperiment_type = wholeGenome\\\nexperiment_type_abrev = wgs\\\npopulation_AF = 1000Gp1_EUR_AF\\\nverifyBamID_variants_file = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.dbSNP%(dbsnp_version)s_1000Gp1_%(population_AF)s_AF.vcf\\\nspecies_vcf_format_descriptor = %(assembly_dir)s/annotations/HumanVCFformatDescriptor.tsv\\\nexcluded_chromosome = chrM,chr1_KI270706v1_random,chr1_KI270707v1_random,chr1_KI270708v1_random,chr1_KI270709v1_random,chr1_KI270710v1_random,chr1_KI270711v1_random,chr1_KI270712v1_random,chr1_KI270713v1_random,chr1_KI270714v1_random,chr2_KI270715v1_random,chr2_KI270716v1_random,chr3_GL000221v1_random,chr4_GL000008v2_random,chr5_GL000208v1_random,chr9_KI270717v1_random,chr9_KI270718v1_random,chr9_KI270719v1_random,chr9_KI270720v1_random,chr11_KI270721v1_random,chr14_GL000009v2_random,chr14_GL000225v1_random,chr14_KI270722v1_random,chr14_GL000194v1_random,chr14_KI270723v1_random,chr14_KI270724v1_random,chr14_KI270725v1_random,chr14_KI270726v1_random,chr15_KI270727v1_random,chr16_KI270728v1_random,chr17_GL000205v2_random,chr17_KI270729v1_random,chr17_KI270730v1_random,chr22_KI270731v1_random,chr22_KI270732v1_random,chr22_KI270733v1_random,chr22_KI270734v1_random,chr22_KI270735v1_random,chr22_KI270736v1_random,chr22_KI270737v1_random,chr22_KI270738v1_random,chr22_KI270739v1_random,chrY_KI270740v1_random,chrUn_KI270302v1,chrUn_KI270304v1,chrUn_KI270303v1,chrUn_KI270305v1,chrUn_KI270322v1,chrUn_KI270320v1,chrUn_KI270310v1,chrUn_KI270316v1,chrUn_KI270315v1,chrUn_KI270312v1,chrUn_KI270311v1,chrUn_KI270317v1,chrUn_KI270412v1,chrUn_KI270411v1,chrUn_KI270414v1,chrUn_KI270419v1,chrUn_KI270418v1,chrUn_KI270420v1,chrUn_KI270424v1,chrUn_KI270417v1,chrUn_KI270422v1,chrUn_KI270423v1,chrUn_KI270425v1,chrUn_KI270429v1,chrUn_KI270442v1,chrUn_KI270466v1,chrUn_KI270465v1,chrUn_KI270467v1,chrUn_KI270435v1,chrUn_KI270438v1,chrUn_KI270468v1,chrUn_KI270510v1,chrUn_KI270509v1,chrUn_KI270518v1,chrUn_KI270508v1,chrUn_KI270516v1,chrUn_KI270512v1,chrUn_KI270519v1,chrUn_KI270522v1,chrUn_KI270511v1,chrUn_KI270515v1,chrUn_KI270507v1,chrUn_KI270517v1,chrUn_KI270529v1,chrUn_KI270528v1,chrUn_KI270530v1,chrUn_KI270539v1,chrUn_KI270538v1,chrUn_KI270544v1,chrUn_KI270548v1,chrUn_KI270583v1,chrUn_KI270587v1,chrUn_KI270580v1,chrUn_KI270581v1,chrUn_KI270579v1,chrUn_KI270589v1,chrUn_KI270590v1,chrUn_KI270584v1,chrUn_KI270582v1,chrUn_KI270588v1,chrUn_KI270593v1,chrUn_KI270591v1,chrUn_KI270330v1,chrUn_KI270329v1,chrUn_KI270334v1,chrUn_KI270333v1,chrUn_KI270335v1,chrUn_KI270338v1,chrUn_KI270340v1,chrUn_KI270336v1,chrUn_KI270337v1,chrUn_KI270363v1,chrUn_KI270364v1,chrUn_KI270362v1,chrUn_KI270366v1,chrUn_KI270378v1,chrUn_KI270379v1,chrUn_KI270389v1,chrUn_KI270390v1,chrUn_KI270387v1,chrUn_KI270395v1,chrUn_KI270396v1,chrUn_KI270388v1,chrUn_KI270394v1,chrUn_KI270386v1,chrUn_KI270391v1,chrUn_KI270383v1,chrUn_KI270393v1,chrUn_KI270384v1,chrUn_KI270392v1,chrUn_KI270381v1,chrUn_KI270385v1,chrUn_KI270382v1,chrUn_KI270376v1,chrUn_KI270374v1,chrUn_KI270372v1,chrUn_KI270373v1,chrUn_KI270375v1,chrUn_KI270371v1,chrUn_KI270448v1,chrUn_KI270521v1,chrUn_GL000195v1,chrUn_GL000219v1,chrUn_GL000220v1,chrUn_GL000224v1,chrUn_KI270741v1,chrUn_GL000226v1,chrUn_GL000213v1,chrUn_KI270743v1,chrUn_KI270744v1,chrUn_KI270745v1,chrUn_KI270746v1,chrUn_KI270747v1,chrUn_KI270748v1,chrUn_KI270749v1,chrUn_KI270750v1,chrUn_KI270751v1,chrUn_KI270752v1,chrUn_KI270753v1,chrUn_KI270754v1,chrUn_KI270755v1,chrUn_KI270756v1,chrUn_KI270757v1,chrUn_GL000214v1,chrUn_KI270742v1,chrUn_GL000216v2,chrUn_GL000218v1,chrEBV\\\nALL_MEM_EPS = 180G\\\nGPU_QUEUE = \\\nmodule_vardict_java = mugqic/VarDictJava/1.4.8\\\nmodule_strelka2 = mugqic/Strelka2/2.9.10\\\nmodule_bcbio_variation_recall = mugqic/bcbio.variation.recall/0.2.6\\\nmodule_varscan = mugqic/VarScan/2.4.3\\\nmodule_conpair = mugqic/Conpair/0.2\\\nmodule_scones = mugqic/SCoNEs/2.1.2\\\nmodule_sequenza_utils = mugqic/Sequenza-utils/3.0.0\\\nmodule_gcc = mugqic/gcc/4.9.3\\\nmodule_amber = mugqic/amber/3.5\\\nmodule_cobalt = mugqic/cobalt/1.11\\\nmodule_purple = mugqic/purple/2.53\\\nmodule_circos = mugqic/circos/0.69-6\\\nmodule_cpsr = mugqic/cpsr/0.6.2\\\nmodule_pcgr = mugqic/pcgr/0.9.2\\\nstrelka2_bed_file = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.strelka2.bed.gz\\\ncommon_name = Human\\\nassembly_synonyms = hg38\\\nCTAT_bundle_version = GRCh38_gencode_v32_CTAT_lib_Dec062019\\\n\\\n[picard_sam_to_fastq]\\\ncluster_cpu = -c 12 -N 1\\\ncluster_mem = --mem=32G\\\nram = 18G\\\ncluster_walltime = --time=72:00:00\\\nother_options = --MAX_RECORDS_IN_RAM=5000000\\\n\\\n[samtools_cram_output]\\\noptions = -h -T %(genome_fasta)s -C\\\nvariantBam_options = --cram -strip-tags BI,OQ\\\ncluster_cpu = %(PINT_CPU)s\\\ncluster_walltime = 48:00:0\\\n\\\n[sym_link_fastq]\\\ncluster_walltime = 3:00:00\\\n\\\n[sym_link_bam]\\\ncluster_walltime = 3:00:00\\\n\\\n[trimmomatic]\\\ncluster_mem = 20G\\\nram = 19G\\\ncluster_cpu = 5\\\nthreads = %(cluster_cpu)s\\\ntrailing_min_quality = 30\\\nmin_length = 50\\\nillumina_clip_settings = :2:30:15\\\njava_other_options = -XX:ParallelGCThreads=5 -Dsamjdk.buffer_size=1048576\\\n\\\n[skewer_trimming]\\\ncluster_cpu = %(QUART_CPU)s\\\nthreads = %(cluster_cpu)s\\\noptions = --min 25 -q 25 --compress -f sanger\\\nadapter_fasta = \\\ncluster_walltime = 48:00:00\\\n\\\n[bwa_mem]\\\ncluster_cpu = %(HALF_CPU)s\\\nbwa_other_options = -t %(cluster_cpu)s -K 100000000 -Y\\\nsequencing_center = McGill University and Genome Quebec Innovation Centre\\\nsequencing_technology = Illumina\\\n\\\n[picard_sort_sam]\\\nram = 16G\\\nmax_records_in_ram = 3750000\\\n\\\n[sambamba_sort_sam]\\\noptions = -m 10G\\\n\\\n[bwa_mem_sambamba_sort_sam]\\\ncluster_cpu = %(HALF_CPU)s\\\ncluster_walltime = 48:00:00\\\ncluster_mem = 60G\\\n\\\n[bwakit_picard_sort_sam]\\\ncluster_cpu = 4\\\ncluster_walltime = 48:00:00\\\ncluster_mem = 60G\\\n\\\n[sambamba_merge_sam_extract_unmapped]\\\ncluster_cpu = 8\\\noptions = -t %(cluster_cpu)s\\\ncluster_walltime = 35:00:00\\\ncluster_mem = 32G\\\n\\\n[sambamba_extract_unmapped]\\\ncluster_cpu = %(PINT_CPU)s\\\noptions = -t %(PINT_CPU)s -f bam -F \"unmapped\"\\\ncluster_walltime = 3:00:00\\\n\\\n[gatk_indel_realigner]\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=1 -Dsamjdk.buffer_size=4194304\\\nnb_jobs = 23\\\nram = 12G\\\nmax_reads_in_memory = 500000\\\ncluster_cpu = 1\\\nother_options = \\\ncluster_walltime = 35:00:0\\\ncluster_mem = 12G\\\nmodule_gatk = mugqic/GenomeAnalysisTK/3.8\\\n\\\n[gatk_realigner_target_creator]\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=1 -Dsamjdk.buffer_size=4194304\\\nram = 12G\\\nknown_mills = %(mills)s\\\ncluster_cpu = 1\\\nother_options = -nt 1\\\nmodule_gatk = mugqic/GenomeAnalysisTK/3.8\\\nknown_indel_sites = %(mills)s\\\n\\\n[sambamba_merge_realigned]\\\ncluster_cpu = %(QUART_CPU)s\\\noptions = -t %(cluster_cpu)s\\\ncluster_walltime = 35:00:00\\\ncluster_mem = 48G\\\n\\\n[sambamba_merge_unmapped]\\\ncluster_cpu = %(QUART_CPU)s\\\noptions = -t %(cluster_cpu)s\\\ncluster_walltime = 12:00:00\\\n\\\n[merge_realigned]\\\ncluster_walltime = 35:00:00\\\ncluster_cpu = 3\\\ncluster_mem = --mem=32G\\\n\\\n[bvatools_groupfixmate]\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=1 -Dsamjdk.buffer_size=4194304\\\nram = 16G\\\n\\\n[samtools_sort]\\\ncluster_cpu = 5\\\nother_options = -@ %(cluster_cpu)s -m 20000M\\\ncluster_walltime = 71:00:00\\\n\\\n[fix_mate_by_coordinate]\\\ncluster_cpu = 4\\\ncluster_walltime = 71:00:00\\\ncluster_mem = 52G\\\n\\\n[samtools_fixmate]\\\nmodule_samtools = mugqic/samtools/1.9\\\n\\\n[fix_mate_by_coordinate_samtools]\\\ncluster_cpu = %(QUART_CPU)s\\\noptions = -m -O bam -@ %(cluster_cpu)s\\\ncluster_walltime = 35:00:00\\\ncluster_mem = 48G\\\n\\\n[picard_mark_duplicates]\\\ncluster_cpu = %(PINT_CPU)s\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=2 -Dsamjdk.buffer_size=4194304\\\nram = 14G\\\nmax_records_in_ram = 1000000\\\ncluster_walltime = 71:00:00\\\ncluster_mem = 15G\\\n\\\n[gatk_base_recalibrator]\\\ncluster_cpu = %(HALF_CPU)s\\\nthreads = %(cluster_cpu)s\\\ncluster_mem = 55G\\\nram = %(cluster_mem)s\\\noptions = --bqsr-baq-gap-open-penalty 30\\\nknown_dbsnp = %(dbsnp)s\\\nknown_gnomad = %(gnomad_exome)s\\\nknown_mills = %(mills)s\\\ncluster_walltime = 35:00:0\\\n\\\n[gatk_print_reads]\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=4 -Dsamjdk.buffer_size=4194304\\\ncluster_cpu = -l nodes=1:ppn=40\\\nthreads = %(cluster_cpu)s\\\ncluster_mem = 187G\\\nram = 180G\\\ncluster_walltime = 96:00:0\\\n\\\n[gatk_apply_bqsr]\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=2 -Dsamjdk.buffer_size=4194304 -Dsamjdk.use_async_io_read_samtools=true -Dsamjdk.use_async_io_write_samtools=true -Dsamjdk.use_async_io_write_tribble=false\\\ncluster_cpu = 40\\\nthreads = %(cluster_cpu)s\\\noptions = \\\ncluster_mem = 186G\\\nram = 180G\\\ncluster_walltime = 96:00:0\\\n\\\n[recalibration]\\\ncluster_walltime = 96:00:0\\\ncluster_mem = 51G\\\nram = 50G\\\n\\\n[sambamba_index]\\\ncluster_cpu = %(QUART_CPU)s\\\noptions = -t %(cluster_cpu)s\\\n\\\n[picard_collect_multiple_metrics]\\\nmodule_gatk = mugqic/GenomeAnalysisTK/4.2.2.0\\\ncluster_cpu = 1\\\ncluster_mem = 12G\\\nram = 11G\\\nmax_records_in_ram = 1000000\\\noptions = --FILE_EXTENSION \".txt\"\\\ncluster_walltime = 48:00:00\\\n\\\n[picard_calculate_hs_metrics]\\\nmodule_gatk = mugqic/GenomeAnalysisTK/4.2.2.0\\\ncluster_mem = 9G\\\nram = 8G\\\ncluster_walltime = 48:00:00\\\n\\\n[metrics]\\\nmodule_gatk = mugqic/GenomeAnalysisTK/4.2.2.0\\\ncluster_walltime = walltime=24:00:0\\\ncluster_mem = 12G\\\n\\\n[picard_collect_oxog_metrics]\\\nmodule_gatk = mugqic/GenomeAnalysisTK/4.2.2.0\\\ncluster_mem = 13G\\\nram = 12G\\\nmax_records_in_ram = 4000000\\\ncluster_walltime = 35:00:0\\\n\\\n[picard_collect_gcbias_metrics]\\\nmodule_gatk = mugqic/GenomeAnalysisTK/4.2.2.0\\\ncluster_mem = 13G\\\nram = 12G\\\nmax_records_in_ram = 4000000\\\ncluster_walltime = 35:00:0\\\n\\\n[dna_sample_qualimap]\\\ncluster_mem = 120G\\\nram = 120G\\\nuse_bed = false\\\ncluster_cpu = -l nodes=1:ppn=24\\\nqualimap_options = --skip-duplicated -nt 1 -gd HUMAN\\\ncluster_walltime = 35:00:0\\\n\\\n[dna_sambamba_flagstat]\\\ncluster_cpu = 6\\\nflagstat_options = -t %(cluster_cpu)s\\\ncluster_walltime = -l walltime=12:00:0\\\n\\\n[fastqc]\\\ncluster_cpu = 4\\\nthreads = %(cluster_cpu)s\\\ncluster_walltime = -l walltime=35:00:0\\\n\\\n[multiqc]\\\nmodule_python = mugqic/python/3.7.3\\\ncluster_walltime = -l walltime=2:00:0\\\noptions = \\\n\\\n[gatk_depth_of_coverage]\\\nmodule_gatk = mugqic/GenomeAnalysisTK/3.8\\\njava_other_options = -XX:ParallelGCThreads=2\\\nram = 8000M\\\ncluster_mem = 8G\\\nsummary_coverage_thresholds = 10,25,50,75,100,500\\\ncluster_cpu = 1\\\ncluster_walltime = 48:00:00\\\n\\\n[bvatools_depth_of_coverage]\\\ncoverage_targets = auto\\\nother_options = --gc --maxDepth 1001 --summaryCoverageThresholds 1,5,10,25,50,75,100,500,1000 --minMappingQuality 15 --minBaseQuality 15 --ommitN\\\ncluster_mem = 35G\\\nram = 35G\\\ncluster_cpu = %(QUART_CPU)s\\\nthreads = %(cluster_cpu)s\\\ncluster_walltime = 96:00:00\\\n\\\n[igvtools_compute_tdf]\\\nram = 6G\\\ncluster_walltime = 96:00:00\\\ncluster_cpu = 1\\\noption = -f min,max,mean -w 25\\\ncluster_mem = 7G\\\n\\\n[gatk_callable_loci]\\\nmodule_gatk = mugqic/GenomeAnalysisTK/3.8\\\njava_other_options = -XX:ParallelGCThreads=2\\\ncluster_mem = 11G\\\nram = 10G\\\nother_options = -dt none --minDepth 10 --maxDepth 500 --minDepthForLowMAPQ 10 --minMappingQuality 10 --minBaseQuality 15\\\ncluster_walltime = 35:00:00\\\n\\\n[bvatools_basefreq]\\\ncluster_mem = 8G\\\nthreads = 1\\\nram = 8G\\\n\\\n[extract_common_snp_freq]\\\ncluster_cpu = 2\\\ncluster_walltime = 35:00:00\\\ncluster_mem = 20G\\\n\\\n[bvatools_ratiobaf]\\\ncluster_cpu = 5\\\ncluster_mem = 71G\\\nram = 70G\\\nother_options = --plot --maxDepth 1000 --exclude %(excluded_chromosome)s\\\n\\\n[baf_plot]\\\ncluster_cpu = %(QUART_CPU)s\\\ncluster_walltime = 24:00:00\\\ncluster_mem = 48G\\\n\\\n[vcftools_missing_indv]\\\noptions = \\\ncluster_walltime = 24:00:00\\\n\\\n[vcftools_depth]\\\noptions = \\\ncluster_walltime = 24:00:00\\\n\\\n[gatk_crosscheck_fingerprint]\\\nmodule_gatk = mugqic/GenomeAnalysisTK/4.2.2.0\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=1 -Dsamjdk.buffer_size=4194304 -Dsamjdk.use_async_io_read_samtools=true -Dsamjdk.use_async_io_write_samtools=true -Dsamjdk.use_async_io_write_tribble=false\\\ncluster_cpu = 4\\\noptions = --NUM_THREADS %(cluster_cpu)s --EXIT_CODE_WHEN_MISMATCH 0\\\ncluster_mem = 16G\\\nram = 15G\\\nhaplotype_database = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.fingerprint.map\\\nlod_threshold = 3.0\\\ncluster_walltime = 24:00:00\\\n\\\n[gatk_cluster_crosscheck_metrics]\\\nmodule_gatk = mugqic/GenomeAnalysisTK/4.2.2.0\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=1 -Dsamjdk.buffer_size=4194304 -Dsamjdk.use_async_io_read_samtools=true -Dsamjdk.use_async_io_write_samtools=true -Dsamjdk.use_async_io_write_tribble=false\\\noptions = \\\ncluster_mem = 16G\\\nram = 15G\\\nlod_threshold = 5.0\\\ncluster_walltime = 24:00:00\\\n\\\n[verify_bam_id]\\\noptions = --verbose --ignoreRG --noPhoneHome\\\nvcf = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.1000G_phase1.snps.high_confidence.EUR.vcf\\\ncluster_walltime = 24:00:00\\\ncluster_cpu = 2\\\ncluster_mem = 20G\\\n\\\n[run_checkmate]\\\nmodule_python = mugqic/python/2.7.14\\\noptions = -V\\\nbed = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.SNP_GRCh38_hg19_woChr.bed\\\ncluster_walltime = 24:00:00\\\ncluster_mem = 12G\\\n\\\n[run_peddy]\\\noptions = \\\ncluster_cpu = %(QUART_CPU)s\\\nthreads = %(cluster_cpu)s\\\ncluster_walltime = 24:00:00\\\ncluster_mem = 24G\\\n\\\n[gatk_haplotype_caller]\\\ncluster_cpu = %(PINT_CPU)s\\\noptions = --useNewAFCalculator --emitRefConfidence GVCF -dt none -nct %(cluster_cpu)s -G StandardAnnotation -G StandardHCAnnotation\\\ncluster_mem = 36G\\\nram = 35G\\\nnb_jobs = 23\\\ncluster_walltime = 35:00:00\\\ninterval_padding = \\\n\\\n[gatk_cat_variants]\\\noptions = \\\ncluster_mem = 8G\\\nram = 8G\\\ncluster_walltime = 24:00:00\\\n\\\n[picard_merge_vcfs]\\\nmax_records_in_ram = 2000000\\\noptions = \\\nram = 12G\\\n\\\n[gatk_merge_and_call_individual_gvcfs]\\\noptions = -nt 1\\\n\\\n[gatk_merge_and_call_combined_gvcfs]\\\noptions = -nt 1 -G StandardAnnotation -G StandardHCAnnotation -A FisherStrand -A QualByDepth -A ChromosomeCounts\\\n\\\n[gatk_genotype_gvcf]\\\noptions = --useNewAFCalculator -G StandardAnnotation -G StandardHCAnnotation\\\ncluster_mem = 30G\\\nram = 30G\\\ncluster_walltime = 35:00:00\\\ncluster_cpu = 2\\\n\\\n[gatk_combine_gvcf]\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=4 -Dsamjdk.buffer_size=4194304\\\ncluster_mem = 25G\\\nram = 24G\\\nnb_haplotype = 4\\\nnb_batch = 1\\\ncluster_cpu = %(QUART_CPU)s\\\nother_options = \\\ncluster_walltime = 24:00:00\\\n\\\n[merge_and_call_combined_gvcf]\\\ncluster_mem = 25G\\\nram = 24G\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=2 -Dsamjdk.buffer_size=4194304\\\ncluster_walltime = 96:00:00\\\ncluster_cpu = 2\\\n\\\n[merge_and_call_individual_gvcf]\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=2 -Dsamjdk.buffer_size=4194304\\\ncluster_mem = 32G\\\nram = 32G\\\ncluster_walltime = 96:00:00\\\ncluster_cpu = 2\\\n\\\n[variant_recalibrator]\\\ntranch_other_options_snps = --resource:hapmap,known=false,training=true,truth=true,prior=15.0 %(hapmap)s --resource:omni,known=false,training=true,truth=false,prior=12.0 %(omni)s --resource:1000G,known=false,training=true,truth=false,prior=10.0 %(1000G)s --resource:dbsnp,known=true,training=false,truth=false,prior=6.0 %(dbsnp)s -an QD -an MQ -an MQRankSum -an ReadPosRankSum -an FS -an SOR --truth-sensitivity-tranche 100.0 --truth-sensitivity-tranche 99.95 --truth-sensitivity-tranche 99.9 --truth-sensitivity-tranche 99.95 --truth-sensitivity-tranche 99.5 --truth-sensitivity-tranche 99.0 --truth-sensitivity-tranche 90.0 -mode SNP\\\ntranch_other_options_indels = --resource:mills,known=false,training=true,truth=true,prior=12.0 %(mills)s --resource:dbsnp,known=true,training=false,truth=false,prior=2.0 %(dbsnp)s -an QD -an MQ -an MQRankSum -an ReadPosRankSum -an FS -an SOR --truth-sensitivity-tranche 100.0 --truth-sensitivity-tranche 99.9 --truth-sensitivity-tranche 99.4 --truth-sensitivity-tranche 99.0 --truth-sensitivity-tranche 90.0 -mode INDEL\\\napply_other_options_snps = --truth-sensitivity-filter-level 99.95 --mode SNP\\\napply_other_options_indels = --truth-sensitivity-filter-level 99.4 --mode INDEL\\\ncluster_walltime = 35:00:00\\\ncluster_cpu = 2\\\ncluster_mem = 30G\\\n\\\n[gatk_variant_recalibrator]\\\nsmall_sample_option = \\\ncluster_cpu = %(QUART_CPU)s\\\noptions = -nt %(cluster_cpu)s\\\ncluster_mem = 25G\\\nram = 24G\\\n\\\n[gatk_apply_recalibration]\\\ncluster_cpu = %(QUART_CPU)s\\\noptions = -nt %(cluster_cpu)s\\\ncluster_mem = 24G\\\nram = 24G\\\n\\\n[rawmpileup]\\\nnb_jobs = 25\\\nmpileup_other_options = -d 1000 -L 1000 -B -q 11 -Q 10\\\ncluster_walltime = -l walltime=12:00:0\\\ncluster_mem = 8G\\\n\\\n[snp_and_indel_bcf]\\\napproximate_nb_jobs = 15\\\nmpileup_other_options = -d 1000 -B -q 11 -Q 20 -Ou -a FORMAT/DP,FORMAT/AD,FORMAT/ADF,FORMAT/ADR,FORMAT/SP,FORMAT/SCR\\\nbcftools_other_options = -mvO b\\\ncluster_walltime = 48:00:00\\\ncluster_mem = 12G\\\n\\\n[snpsift_annotate]\\\ncluster_mem = 9G\\\nram = 8G\\\njava_other_options = -XX:ParallelGCThreads=2\\\ncluster_walltime = 24:00:00\\\n\\\n[snp_id_annotation]\\\ncluster_walltime = 24:00:00\\\ncluster_mem = 12G\\\n\\\n[mpileup_snp_id_annotation]\\\ncluster_walltime = 24:00:00\\\n\\\n[haplotype_caller_snp_id_annotation]\\\ncluster_walltime = 24:00:00\\\ncluster_mem = 16G\\\n\\\n[compute_effects]\\\njava_other_options = -XX:ParallelGCThreads=1\\\ncluster_mem = 12G\\\nram = 12000M\\\noptions = -lof\\\nsnpeff_genome = %(assembly_synonyms)s\\\ncluster_walltime = 12:00:0\\\n\\\n[mpileup_snp_effect]\\\ncluster_cpu = 2\\\ncluster_walltime = 24:00:00\\\ncluster_mem = 24G\\\n\\\n[haplotype_caller_snp_effect]\\\ncluster_cpu = 1\\\ncluster_walltime = 24:00:00\\\ncluster_mem = 16G\\\n\\\n[snpsift_dbnsfp]\\\ncluster_cpu = 2\\\nram = 24G\\\njava_other_options = -XX:ParallelGCThreads=2\\\n\\\n[dbnsfp_annotation]\\\ncluster_cpu = %(QUART_CPU)s\\\ncluster_walltime = 35:00:00\\\ncluster_mem = --mem=40G\\\n\\\n[gemini_annotations]\\\ncluster_cpu = %(QUART_CPU)s\\\noptions = -t snpEff --cores %(cluster_cpu)s --save-info-string\\\ncluster_walltime = -l walltime=72:00:0\\\ntmp_dir = ${SLURM_TMPDIR}\\\n\\\n[vcf_stats]\\\nmodule_python = mugqic/python/2.7.14\\\n\\\n[report]\\\ntitle = DNA-Seq Analysis Report\\\n\\\n[sv_annotation]\\\ncluster_walltime = 3:00:0\\\ncluster_mem = 12G\\\n\\\n[delly_call_filter]\\\ncluster_cpu = %(QUART_CPU)s\\\nthreads = %(cluster_cpu)s\\\noptions = -q 15\\\nsv_types_options = DEL,INS,DUP,INV,BND\\\nexclude_list = ${DELLY_PATH}/excludeTemplates/human.hg38.excl.tsv\\\ncluster_walltime = 35:00:0\\\ncluster_mem = 60G\\\n\\\n[delly_call_filter_germline]\\\ntype_options = germline\\\nDUP_options = -m 300 -a 0.1 -r 0.75\\\nDEL_options = -m 300 -a 0.1 -r 0.75\\\nINV_options = -m 300 -a 0.1 -r 0.75\\\nBND_options = -m 0 -a 0.1 -r 0.75\\\nINS_options = \\\nbcftools_options = \\\n\\\n[manta_sv]\\\nmodule_python = mugqic/python/2.7.14\\\noption_mode = local\\\ncluster_cpu = %(HALF_CPU)s\\\noption_nodes = %(cluster_cpu)s\\\ncluster_mem = 55G\\\nram = 55G\\\nexperiment_type_option = \\\ncluster_walltime = 24:00:0\\\n\\\n[extract_discordant_reads]\\\ncluster_cpu = %(QUART_CPU)s\\\nsambamba_options = -t %(cluster_cpu)s\\\ndiscordants_sort_option = -t %(cluster_cpu)s\\\ncluster_walltime = -l walltime=35:00:0\\\ncluster_mem = 32G\\\noptions = \\\n\\\n[extract_split_reads]\\\ncluster_cpu = %(QUART_CPU)s\\\nsambamba_options = -t %(cluster_cpu)s\\\nsplit_sort_option = -t %(cluster_cpu)s\\\ncluster_walltime = -l walltime=35:00:0\\\ncluster_mem = 32G\\\noptions = \\\n\\\n[lumpy_paired_sv_calls]\\\nmodule_python = mugqic/python/2.7.13\\\noptions = \\\nheader_options = -h %(vcf_header)s\\\ncluster_walltime = -l walltime=72:00:0\\\ncluster_cpu = 3\\\ncluster_mem = 16G\\\nmodule_samtools = mugqic/samtools/1.3\\\n\\\n[wham_call_sv]\\\nexclude = chr1_KI270706v1_random,chr1_KI270707v1_random,chr1_KI270708v1_random,chr1_KI270709v1_random,chr1_KI270710v1_random,chr1_KI270711v1_random,chr1_KI270712v1_random,chr1_KI270713v1_random,chr1_KI270714v1_random,chr2_KI270715v1_random,chr2_KI270716v1_random,chr3_GL000221v1_random,chr4_GL000008v2_random,chr5_GL000208v1_random,chr9_KI270717v1_random,chr9_KI270718v1_random,chr9_KI270719v1_random,chr9_KI270720v1_random,chr11_KI270721v1_random,chr14_GL000009v2_random,chr14_GL000225v1_random,chr14_KI270722v1_random,chr14_GL000194v1_random,chr14_KI270723v1_random,chr14_KI270724v1_random,chr14_KI270725v1_random,chr14_KI270726v1_random,chr15_KI270727v1_random,chr16_KI270728v1_random,chr17_GL000205v2_random,chr17_KI270729v1_random,chr17_KI270730v1_random,chr22_KI270731v1_random,chr22_KI270732v1_random,chr22_KI270733v1_random,chr22_KI270734v1_random,chr22_KI270735v1_random,chr22_KI270736v1_random,chr22_KI270737v1_random,chr22_KI270738v1_random,chr22_KI270739v1_random,chrY_KI270740v1_random,chrUn_KI270302v1,chrUn_KI270304v1,chrUn_KI270303v1,chrUn_KI270305v1,chrUn_KI270322v1,chrUn_KI270320v1,chrUn_KI270310v1,chrUn_KI270316v1,chrUn_KI270315v1,chrUn_KI270312v1,chrUn_KI270311v1,chrUn_KI270317v1,chrUn_KI270412v1,chrUn_KI270411v1,chrUn_KI270414v1,chrUn_KI270419v1,chrUn_KI270418v1,chrUn_KI270420v1,chrUn_KI270424v1,chrUn_KI270417v1,chrUn_KI270422v1,chrUn_KI270423v1,chrUn_KI270425v1,chrUn_KI270429v1,chrUn_KI270442v1,chrUn_KI270466v1,chrUn_KI270465v1,chrUn_KI270467v1,chrUn_KI270435v1,chrUn_KI270438v1,chrUn_KI270468v1,chrUn_KI270510v1,chrUn_KI270509v1,chrUn_KI270518v1,chrUn_KI270508v1,chrUn_KI270516v1,chrUn_KI270512v1,chrUn_KI270519v1,chrUn_KI270522v1,chrUn_KI270511v1,chrUn_KI270515v1,chrUn_KI270507v1,chrUn_KI270517v1,chrUn_KI270529v1,chrUn_KI270528v1,chrUn_KI270530v1,chrUn_KI270539v1,chrUn_KI270538v1,chrUn_KI270544v1,chrUn_KI270548v1,chrUn_KI270583v1,chrUn_KI270587v1,chrUn_KI270580v1,chrUn_KI270581v1,chrUn_KI270579v1,chrUn_KI270589v1,chrUn_KI270590v1,chrUn_KI270584v1,chrUn_KI270582v1,chrUn_KI270588v1,chrUn_KI270593v1,chrUn_KI270591v1,chrUn_KI270330v1,chrUn_KI270329v1,chrUn_KI270334v1,chrUn_KI270333v1,chrUn_KI270335v1,chrUn_KI270338v1,chrUn_KI270340v1,chrUn_KI270336v1,chrUn_KI270337v1,chrUn_KI270363v1,chrUn_KI270364v1,chrUn_KI270362v1,chrUn_KI270366v1,chrUn_KI270378v1,chrUn_KI270379v1,chrUn_KI270389v1,chrUn_KI270390v1,chrUn_KI270387v1,chrUn_KI270395v1,chrUn_KI270396v1,chrUn_KI270388v1,chrUn_KI270394v1,chrUn_KI270386v1,chrUn_KI270391v1,chrUn_KI270383v1,chrUn_KI270393v1,chrUn_KI270384v1,chrUn_KI270392v1,chrUn_KI270381v1,chrUn_KI270385v1,chrUn_KI270382v1,chrUn_KI270376v1,chrUn_KI270374v1,chrUn_KI270372v1,chrUn_KI270373v1,chrUn_KI270375v1,chrUn_KI270371v1,chrUn_KI270448v1,chrUn_KI270521v1,chrUn_GL000195v1,chrUn_GL000219v1,chrUn_GL000220v1,chrUn_GL000224v1,chrUn_KI270741v1,chrUn_GL000226v1,chrUn_GL000213v1,chrUn_KI270743v1,chrUn_KI270744v1,chrUn_KI270745v1,chrUn_KI270746v1,chrUn_KI270747v1,chrUn_KI270748v1,chrUn_KI270749v1,chrUn_KI270750v1,chrUn_KI270751v1,chrUn_KI270752v1,chrUn_KI270753v1,chrUn_KI270754v1,chrUn_KI270755v1,chrUn_KI270756v1,chrUn_KI270757v1,chrUn_GL000214v1,chrUn_KI270742v1,chrUn_GL000216v2,chrUn_GL000218v1,chrEBV\\\ncluster_cpu = %(QUART_CPU)s\\\ncores = %(cluster_cpu)s\\\nheader_options = -h %(vcf_header)s\\\ncluster_walltime = 24:00:0\\\ncluster_mem = %(HALF_MEM)s\\\n\\\n[cnvkit_batch]\\\nmin_background_samples = 20\\\nbatch_options = -m wgs --target-avg-size 5000 --short-names\\\nfix_options = --no-edge\\\nsegment_options = -m cbs -t 0.00001 --drop-low-coverage -p %(cluster_cpu)s\\\ncall_options = \\\nexport_options = vcf\\\nsegmetrics_options = --ci --pi\\\nmetrics_options = \\\nscatter_options = \\\ndiagram_options = \\\ncluster_cpu = 6\\\nthreads = 6\\\naccess = /cvmfs/soft.mugqic/CentOS6/genomes/species/Homo_sapiens.GRCh38/annotations/Homo_sapiens.GRCh38.access-5k-mappable.bed\\\nrefFlat = /cvmfs/soft.mugqic/CentOS6/genomes/species/Homo_sapiens.GRCh38/annotations/Homo_sapiens.GRCh38.Ensembl87.ref_flat.tsv\\\ncluster_walltime = -l walltime=48:00:0\\\nmodule_python = mugqic/python/2.7.14\\\nmodule_R = mugqic/R_Bioconductor/3.2.3_3.2\\\n\\\n[run_breakseq2]\\\nmodule_pyhton = mugqic/python/2.7.14\\\noptions = \\\nbcftools_options = -f PASS -Ov\\\ncluster_cpu = %(QUART_CPU)s\\\nthreads = %(cluster_cpu)s\\\ngff = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.breakseq2_bplib_20150129.gff\\\ncluster_walltime = 35:00:00\\\n\\\n[metasv_ensemble]\\\noptions = --boost_sc --filter_gaps --keep_standard_contigs --mean_read_length 150\\\ncluster_cpu = %(QUART_CPU)s\\\nthreads = %(cluster_cpu)s\\\nfilter_pass_options = \\\ncluster_walltime = 35:00:0\\\ncluster_mem = --mem=60G\\\n\\\n[svaba_run]\\\ncluster_cpu = %(HALF_CPU)s\\\noptions = -p %(cluster_cpu)s\\\nref = %(genome_bwa_index)s\\\ndbsnp = $SVABA_HOME/dbsnp_indel.vcf\\\ncluster_walltime = 35:00:0\\\ncluster_mem = 60G\\\n\\\n[haplotype_caller_dbnsfp_annotation]\\\ncluster_walltime = 24:00:00\\\ncluster_cpu = 3\\\ncluster_mem = 40G\\\n\\\n[sambamba_merge_sam_files]\\\ncluster_cpu = %(QUART_CPU)s\\\noptions = -t %(cluster_cpu)s\\\n\\\n[sym_link_pair]\\\ncluster_walltime = 3:00:0\\\n\\\n[sambamba_mark_duplicates]\\\ncluster_cpu = %(QUART_CPU)s\\\noptions = -t %(cluster_cpu)s\\\ntmp_dir = tmp_dir\\\ncluster_mem = 36G\\\ncluster_walltime = 35:00:0\\\n\\\n[conpair_concordance_contamination]\\\nmodule_gatk = mugqic/GenomeAnalysisTK/3.8\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=1 -Dsamjdk.buffer_size=4194304\\\nmarkers_bed = ${CONPAIR_DATA}/markers/%(assembly)s.autosomes.phase3_shapeit2_mvncall_integrated.20130502.SNV.genotype.sselect_v4_MAF_0.4_LD_0.8.liftover.bed\\\nmarkers_txt = ${CONPAIR_DATA}/markers/%(assembly)s.autosomes.phase3_shapeit2_mvncall_integrated.20130502.SNV.genotype.sselect_v4_MAF_0.4_LD_0.8.liftover.txt\\\nconcord_options = --normal_homozygous_markers_only\\\ncontam_options = \\\ncluster_mem = 6G\\\nram = 6G\\\ncluster_walltime = 24:00:0\\\n\\\n[picard_collect_sequencing_artifacts_metrics]\\\nFFPE = true\\\ncluster_mem = 12G\\\nram = 12000M\\\noptions = --FILE_EXTENSION \".txt\"\\\nmax_records_in_ram = 4000000\\\ncluster_walltime = -l walltime=35:00:0\\\n\\\n[qualimap]\\\ncluster_cpu = 4\\\ncluster_mem = 60G\\\nram = 60G\\\n\\\n[picard_ScatterIntervalsByNs]\\\ncluster_mem = 3G\\\nram = 3000M\\\n\\\n[gatk_splitInterval]\\\ncluster_mem = 3G\\\nram = 3000M\\\noptions = --subdivision-mode BALANCING_WITHOUT_INTERVAL_SUBDIVISION\\\n\\\n[gatk_interval_list2bed]\\\ncluster_mem = 3200M\\\nram = 3G\\\ncluster_walltime = -l walltime=3:00:0\\\ncluster_cpu = -l nodes=1:ppn=2\\\n\\\n[gatk_bed2interval_list]\\\ncluster_mem = 3200M\\\nram = 3G\\\n\\\n[gatk_preProcessInterval]\\\ncluster_mem = 3200M\\\nram = 3G\\\noptions = --interval-merging-rule OVERLAPPING_ONLY --bin-length 5000 --padding 250\\\n\\\n[rawmpileup_panel]\\\nnb_jobs = 25\\\nmodule_samtools = mugqic/samtools/1.3\\\npanel = test_rapid/SureSelectHumanAllExonV5.targets_ext1k.bed\\\nmpileup_other_options = -d 1000 -L 1000 -B -q 1 -Q 10\\\ncluster_walltime = 12:00:0\\\ncluster_cpu = 1\\\n\\\n[varscan2_somatic_panel]\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=1 -Dsamjdk.buffer_size=4194304\\\nother_options = --min-coverage 3 --min-var-freq 0.05 --p-value 1 --somatic-p-value 0.05 --strand-filter 0\\\ncluster_mem = 4300M\\\nram = 4G\\\ncluster_walltime = 12:00:0\\\ncluster_cpu = 2\\\n\\\n[merge_varscan2]\\\nmodule_python = mugqic/python/2.7.18\\\nsomatic_filter_options = -Oz -i 'SS=\"2\"'\\\ngermline_filter_options = -Oz -i 'SS=\"1\"|SS=\"3\"'\\\ngenotype_filter_options = -e 'GT[*]=\"RR\"'\\\ntabix_options = -pvcf\\\ncluster_walltime = -l walltime=3:00:0\\\ncluster_cpu = 2\\\ncluster_mem = 8G\\\n\\\n[preprocess_vcf_panel]\\\ncluster_walltime = -l walltime=3:00:0\\\ncluster_mem = 8G\\\n\\\n[rawmpileup_cat]\\\ncluster_walltime = -l walltime=35:00:0\\\ncluster_mem = 8G\\\n\\\n[varscan2_somatic]\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=1 -Dsamjdk.buffer_size=4194304\\\nother_options = --min-coverage 3 --min-var-freq 0.05 --p-value 0.10 --somatic-p-value 0.05 --strand-filter 0\\\ncluster_mem = 4G\\\nram = 4G\\\ncluster_walltime = -l walltime=12:00:0\\\ncluster_cpu = 2\\\n\\\n[varscan2_readcount_fpfilter]\\\nreadcount_options = -q 1 -b 20 -i -w 1000 -d 2500\\\nfpfilter_options = --dream3-settings --keep-failures\\\nsomatic_filter_options = -i 'SS=\"2\"'\\\ngermline_filter_options = -i 'SS=\"1\"|SS=\"3\"'\\\ngenotype_filter_options = -e 'GT[*]=\"RR\"'\\\nram = 12G\\\ncluster_cpu = 3\\\ncluster_mem = 12G\\\ncluster_walltime = -l walltime=3:00:0\\\n\\\n[gatk_mutect2]\\\ncluster_cpu = %(QUART_CPU)s\\\noptions = --pair-hmm-implementation AVX_LOGLESS_CACHING_OMP --native-pair-hmm-threads %(cluster_cpu)s --max-reads-per-alignment-start 0 --read-validation-stringency LENIENT --af-of-alleles-not-in-resource 0.0000025\\\ncluster_mem = 36G\\\nram = 36000M\\\nnb_jobs = 23\\\ncosmic = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.cosmic.coding.87.vcf.gz\\\nknown_sites = %(af_gnomad)s\\\npon = \\\ncluster_walltime = --time=72:00:0\\\n\\\n[gatk_learn_read_orientation_model]\\\noptions = \\\ncluster_mem = 16G\\\nram = 16000M\\\ncluster_walltime = 24:00:0\\\n\\\n[gatk_merge_stats]\\\nram = 6G\\\noptions = \\\ncluster_walltime = -l walltime=3:00:0\\\n\\\n[gatk_get_pileup_summaries]\\\noptions = \\\nknown_sites = %(af_gnomad)s\\\ncluster_mem = 16G\\\nram = 16000M\\\ncluster_walltime = 24:00:0\\\n\\\n[gatk_calculate_contamination]\\\noptions = \\\ncluster_mem = 16G\\\nram = 16000M\\\ncluster_walltime = 24:00:0\\\n\\\n[gatk_filter_mutect_calls]\\\noptions = \\\ncluster_mem = 16G\\\nram = 16000M\\\ncluster_walltime = -l walltime=24:00:0\\\n\\\n[gatk_merge_vcfs]\\\noptions = \\\ncluster_mem = 16G\\\nram = 16000M\\\ncluster_walltime = -l walltime=24:00:0\\\n\\\n[merge_filter_mutect2]\\\nbcftools_options = \\\nfilter_options = -f PASS\\\ncluster_mem = 18G\\\nram = 18G\\\ncluster_walltime = -l walltime=3:00:0\\\n\\\n[samtools_paired]\\\nmodule_bcftools = mugqic/bcftools/1.9\\\nnb_jobs = 23\\\nmpileup_other_options = -d 1000 -B -q 10 -Q 10 -Ou -a DP,AD,ADF,ADR,SP\\\nbcftools_calls_options = -mvO b\\\ncluster_walltime = -l walltime=24:00:0\\\n\\\n[merge_filter_paired_samtools]\\\nconcat_options = -Ob\\\nsomatic_filter_options = -i 'INFO/STATUS~\"somatic\"'\\\nsomatic_vcffilter_options = -g \"! ( GT = 1/1 )\"\\\ngermline_loh_filter_options = -i 'INFO/STATUS~\"germline\"|INFO/STATUS~\"loh\"'\\\ngenotype_filter_options = -e 'GT[*]=\"RR\"'\\\ncluster_mem = 12G\\\ncluster_walltime = -l walltime=3:00:0\\\n\\\n[vardict_paired]\\\nmodule_python = mugqic/python/2.7.18\\\ncluster_cpu = 4\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=1 -Dsamjdk.buffer_size=4194304\\\nuse_bed = false\\\ndict2bed_options = -c 5000 -o 250\\\nnb_jobs = 22\\\nvardict_options = -f 0.03 -Q 11 -c 1 -S 2 -E 3 -g 4 -th %(cluster_cpu)s\\\nvar2vcf_options = -f 0.03 -P 0.9 -m 4.25 -M\\\njava_options = -Xms768m\\\ncluster_mem = 16G\\\nram = 16000M\\\nclasspath = $VARDICT_HOME/lib/VarDict-1.4.8.jar:$VARDICT_HOME/lib/commons-cli-1.2.jar:$VARDICT_HOME/lib/jregex-1.2_01.jar:$VARDICT_HOME/lib/htsjdk-2.8.0.jar com.astrazeneca.vardict.Main\\\ncluster_walltime = -l walltime=72:00:0\\\n\\\n[merge_filter_paired_vardict]\\\nsomatic_filter_options = -f PASS -i 'INFO/STATUS~\".*Somatic\"'\\\ngermline_filter_options = -f PASS -i 'INFO/STATUS~\"Germline\"|INFO/STATUS~\".*LOH\"'\\\ngenotype_filter_options = -e 'GT[*]=\"RR\"'\\\ncluster_mem = 12G\\\ncluster_walltime = -l walltime=3:00:0\\\n\\\n[strelka2_paired_somatic]\\\nmodule_python = mugqic/python/2.7.18\\\noption_mode = local\\\ncluster_cpu = %(HALF_CPU)s\\\noption_nodes = %(cluster_cpu)s\\\ncluster_mem = 55G\\\nram = 55G\\\nbed_file = %(strelka2_bed_file)s\\\nexperiment_type_option = \\\nfilter_options = -f PASS -Oz\\\ncluster_walltime = -l walltime=24:00:0\\\n\\\n[strelka2_paired_germline]\\\nmodule_python = mugqic/python/2.7.18\\\noption_mode = local\\\ncluster_cpu = %(HALF_CPU)s\\\noption_nodes = %(cluster_cpu)s\\\ncluster_mem = 55G\\\nram = 55G\\\nbed_file = %(strelka2_bed_file)s\\\nexperiment_type_option = \\\nfilter_options = -f PASS -Oz -e 'GT[*]=\"RR\"'\\\ncluster_walltime = -l walltime=48:00:0\\\n\\\n[strelka2_paired_germline_snpeff]\\\nsplit_options = -Oz -i'GT=\"alt\"'\\\noptions = \\\ncluster_mem = 12G\\\nram = 12000M\\\ncluster_walltime = -l walltime=24:00:0\\\n\\\n[bcbio_ensemble]\\\ncluster_cpu = 2\\\ncluster_mem = 24G\\\nram = 24G\\\n\\\n[bcbio_ensemble_somatic]\\\ncluster_cpu = 6\\\noptions = --cores %(cluster_cpu)s --numpass 1 --names mutect2,strelka2,vardict,varscan2\\\ncluster_mem = 24G\\\nram = 24G\\\ncluster_walltime = -l walltime=3:00:0\\\n\\\n[bcbio_ensemble_germline]\\\ncluster_cpu = 6\\\noptions = --cores %(cluster_cpu)s --numpass 1 --names strelka2,vardict,varscan2\\\ncluster_mem = 24G\\\nram = 24G\\\ncluster_walltime = -l walltime=3:00:0\\\n\\\n[gatk_variant_annotator]\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=1 -Dsamjdk.buffer_size=4194304\\\nmodule_gatk = mugqic/GenomeAnalysisTK/3.7\\\ncluster_mem = 12G\\\nram = 12000M\\\nnb_jobs = 20\\\ncluster_walltime = -l walltime=12:00:0\\\n\\\n[gatk_variant_annotator_somatic]\\\ncluster_cpu = 2\\\nother_options = -nt 2 --dbsnp %(known_variants)s -G StandardAnnotation -G StandardSomaticAnnotation -A HomopolymerRun -A Coverage -A DepthPerAlleleBySample -A ClippingRankSumTest -A BaseQualityRankSumTest -A MappingQualityRankSumTest -A MappingQualityZeroBySample -A LowMQ -A ReadPosRankSumTest -A GCContent\\\n\\\n[gatk_variant_annotator_germline]\\\ncluster_cpu = 2\\\nother_options = -nt 2 --dbsnp %(known_variants)s -A HomopolymerRun -A Coverage -A DepthPerAlleleBySample -A ClippingRankSumTest -A BaseQualityRankSumTest -A MappingQualityRankSumTest -A MappingQualityZeroBySample -A LowMQ -A ReadPosRankSumTest -A GCContent\\\n\\\n[merge_gatk_variant_annotator]\\\ncluster_cpu = 2\\\ncluster_walltime = -l walltime=3:00:0\\\n\\\n[filter_ensemble]\\\nmodule_python = mugqic/python/3.10.4\\\ncall_filter = 2\\\nsomatic_filter_options = -Oz -i'TDP>=10 && TVAF>=0.05 && NDP>=10 && NVAF<=0.05'\\\ngermline_filter_options = -Oz -i'TDP>=10 && TVAF>=0.05 && NDP>=10 && NVAF>=0.05'\\\ncluster_mem = 12G\\\ncluster_walltime = -l walltime=3:00:0\\\n\\\n[report_cpsr]\\\noptions = --no_vcf_validate --force_overwrite --no_docker --secondary_findings --gwas_findings --panel_id 0\\\nassembly = grch38\\\ncluster_cpu = %(PINT_CPU)s\\\ncluster_mem = 36G\\\ncluster_walltime = -l walltime=3:00:0\\\n\\\n[report_pcgr]\\\noptions = --no_vcf_validate --force_overwrite --no_docker --vep_buffer_size 500 --vep_regulatory --show_noncoding --vcf2maf\\\ntumor_type = --tumor_site 0\\\ntumor_options = --call_conf_tag TAL --tumor_dp_tag TDP --tumor_af_tag TVAF --tumor_dp_min 10 --tumor_af_min 0.05\\\nnormal_options = --control_dp_tag NDP --control_af_tag NVAF --control_dp_min 10 --control_af_max 0.05\\\nmutsig_options = --estimate_signatures\\\ntmb_options = --estimate_tmb --tmb_algorithm nonsyn\\\nmsi_options = --estimate_msi_status\\\nassembly = grch38\\\nassay = --assay WGS\\\ncluster_cpu = %(HALF_CPU)s\\\ncluster_mem = 36G\\\ncluster_walltime = -l walltime=3:00:0\\\n\\\n[compute_cancer_effects_somatic]\\\njava_other_options = -XX:ParallelGCThreads=1\\\noptions = -cancer -lof\\\nsnpeff_genome = hg19\\\ncluster_walltime = 12:00:0\\\ncluster_mem = 12G\\\nram = 12000M\\\n\\\n[compute_cancer_effects_germline]\\\njava_other_options = -XX:ParallelGCThreads=1\\\noptions = -lof\\\nsnpeff_genome = hg19\\\ncluster_walltime = -l walltime=12:00:0\\\nram = 12000M\\\ncluster_mem = 12G\\\n\\\n[gatk_combine_variants]\\\n\\\n[decompose_and_normalize_mnps]\\\ncluster_walltime = 12:00:0\\\n\\\n[set_somatic_and_actionable_mutations]\\\nset_somatic = --min-depth 30 --min-tumor-depth 10 --min-norm-depth 10\\\ncluster_walltime = -l walltime=24:00:0\\\n\\\n[mpileup_sequenza]\\\ncluster_walltime = -l walltime=12:00:0\\\n\\\n[sequenza]\\\nnb_jobs = 23\\\ngc_file = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.gc50Base.txt\\\nbin_window_size = 50\\\nmpileup_options = -d 1000 -L 1000 -B -Q 25 -q 15\\\npileup_options = -q 20 -N 30\\\ncluster_walltime = -l walltime=24:00:0\\\ncluster_mem = 12G\\\n\\\n[amber]\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=1 -Dsamjdk.buffer_size=4194304\\\ncluster_mem = 16G\\\nram = 16000M\\\ncluster_cpu = %(PINT_CPU)s\\\nthreads = %(cluster_cpu)s\\\nloci = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.GermlineHetPon.vcf.gz\\\ncluster_walltime = -l walltime=12:00:0\\\n\\\n[cobalt]\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=1 -Dsamjdk.buffer_size=4194304\\\ncluster_mem = 16G\\\nram = 16000M\\\ncluster_cpu = %(PINT_CPU)s\\\nthreads = %(cluster_cpu)s\\\ngc_profile = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.GC_profile.1000bp.cnp\\\ncluster_walltime = -l walltime=12:00:0\\\n\\\n[purple]\\\njava_other_options = -XX:+UseParallelGC -XX:ParallelGCThreads=1 -Dsamjdk.buffer_size=4194304\\\nmodule_perl = mugqic/perl/5.34.0\\\ncluster_mem = 17G\\\nram = 16G\\\ncluster_cpu = %(PINT_CPU)s\\\nthreads = %(cluster_cpu)s\\\ngc_profile = %(assembly_dir)s/annotations/%(scientific_name)s.%(assembly)s.GC_profile.1000bp.cnp\\\ncluster_walltime = -l walltime=12:00:0\\\n\\\n[samtools_single]\\\nnb_jobs = 25\\\nmodule_samtools = mugqic/samtools/0.1.19\\\nmpileup_other_options = -B -q 15 -Q 25 -D -S -g\\\nbcftools_view_options = -bvcg\\\ncluster_walltime = -l walltime=12:00:0\\\n\\\n[merge_samtools_single]\\\ncluster_walltime = -l walltime=12:00:0\\\n\\\n[tabix_split]\\\ncluster_walltime = -l walltime=12:00:0\\\n\\\n[shapeit]\\\ncluster_cpu = %(PINT_CPU)s\\\ncheck_options = \\\ncheck_threads = %(cluster_cpu)s\\\nphase_options = \\\nphase_threads = %(cluster_cpu)s\\\ncluster_walltime = -l walltime=12:00:0\\\n\\\n[scnaphase]\\\ncluster_walltime = 12:00:0\\\ncluster_mem = 16G\\\n\\\n[delly_call_filter_somatic]\\\ntype_options = somatic\\\nDUP_options = -m 300 -a 0.1 -r 0.75\\\nDEL_options = -m 300 -a 0.1 -r 0.75\\\nINV_options = -m 300 -a 0.1 -r 0.75\\\nBND_options = -m 0 -a 0.1 -r 0.75\\\nINS_options = \\\nbcftools_options = -i 'FORMAT/DV[0]>4|(INFO/SR>1&INFO/PE>5)|(INFO/SR>5&INFO/PE>1)'\\\n\\\n[scones]\\\nwindow = 10000\\\nbest_model = 0\\\n\\\n[bvatools_bincounter]\\\nother_options = --minMapQ 15\\\ncluster_cpu = 2\\\njava_other_options = -XX:ParallelGCThreads=1\\\ncluster_mem = 31G\\\nram = 30G\\\ncluster_walltime = -l walltime=24:00:0\\\n\\\n[scones_pair]\\\ncluster_cpu = %(HALF_CPU)s\\\nother_options = -t %(cluster_cpu)s\\\ngc_map_bedfile = %(assembly_dir)s/annotations/mappabilityGC/hg1k_v37_bin10kb_GCMAP.bed\\\ncluster_walltime = -l walltime=24:00:0\\\n\\\n[scones_filter]\\\nbest_model = 3\\\ncluster_walltime = 3:00:0\\\ncluster_mem = 8G\\\n\\\n[scones_annotate]\\\nexcluded_regions_bed = %(assembly_dir)s/annotations/bed/%(scientific_name)s.%(assembly)s.TeloCentro_1Mb.bed\\\ngenes_bed = %(assembly_dir)s/annotations/bed/%(scientific_name)s.%(assembly)s.gene.bed\\\ndgv_bed = %(assembly_dir)s/annotations/bed/%(scientific_name)s.%(assembly)s.DGV.bed\\\nmicrosat_bed = %(assembly_dir)s/annotations/bed/%(scientific_name)s.%(assembly)s.microsat.bed\\\nrepeat_masker_bed = %(assembly_dir)s/annotations/bed/%(scientific_name)s.%(assembly)s.repeatMasker.bed\\\nautosome_size_file = %(assembly_dir)s/%(scientific_name)s.%(assembly)s.AutosomeSize.txt\\\ncluster_walltime = -l walltime=3:00:0\\\ncluster_mem = 8G\\\n\\\n[run_arriba]\\\nblacklist = $ARRIBA_HOME/database/blacklist_hg38_GRCh38_2018-01-13.tsv\\\n\\\n", "operation_platform": "beluga", "operation_cmd_line": "module purge\nmodule load python/3.10.2 mugqic/genpipes/4.2.0\ntumor_pair.py \\\n -j slurm \\\n -t ensemble \\\n -r readset.txt \\\n -p pair.txt \\\n -s 1-40 \\\n -c $MUGQIC_PIPELINES_HOME/pipelines/tumor_pair/tumor_pair.base.ini \\\n $MUGQIC_PIPELINES_HOME/pipelines/common_ini/beluga.ini \\\n $MUGQIC_PIPELINES_HOME/pipelines/tumor_pair/tumor_pair.extras.ini \\\n $MUGQIC_PIPELINES_HOME/resources/genomes/config/Homo_sapiens.GRCh38.ini \\\n > Tumour_Pair_run.sh\nrm -r Tumour_Pair_CHUNKS;\nmkdir Tumour_Pair_CHUNKS;\n$MUGQIC_PIPELINES_HOME/utils/chunk_genpipes.sh -n 100 Tumour_Pair_run.sh Tumour_Pair_CHUNKS", - "operation_name": "genpipes_tumour_pair", + "operation_name": "GenPipes_TumorPair.ensemble", "sample": [ { "sample_name": "MoHQ-CM-1-10-3393-1DT",