def standardpipeline(config, run_info_yaml, parallel, dirs, samples): ## Alignment and preparation requiring the entire input file (multicore cluster) with prun.start(_wres(parallel, ["aligner", "samtools", "sambamba"]), samples, config, dirs, "multicore") as run_parallel: with profile.report("organize samples", dirs): samples = run_parallel("organize_samples", [[ dirs, config, run_info_yaml, [x[0]["description"] for x in samples] ]]) with profile.report("alignment", dirs): samples = run_parallel("process_alignment", samples) with profile.report("callable regions", dirs): samples = run_parallel("prep_samples", [samples]) samples = run_parallel("postprocess_alignment", samples) samples = run_parallel("combine_sample_regions", [samples]) samples = region.clean_sample_data(samples) ## Quality control with prun.start( _wres(parallel, ["fastqc", "qsignature", "kraken", "gatk", "samtools"]), samples, config, dirs, "multicore2") as run_parallel: with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) with profile.report("upload", dirs): samples = run_parallel("upload_samples", samples) for sample in samples: run_parallel("upload_samples_project", [sample]) logger.info("Timing: finished") return samples
def run(self, config, run_info_yaml, parallel, dirs, samples): with prun.start(_wres(parallel, ["aligner"], ensure_mem={"tophat": 8, "tophat2": 8, "star": 2}), [samples[0]], config, dirs, "organize_samples") as run_parallel: with profile.report("organize samples", dirs): samples = run_parallel("organize_samples", [[dirs, config, run_info_yaml, [x[0]["description"] for x in samples]]]) with prun.start(_wres(parallel, ["picard", "cutadapt"]), samples, config, dirs, "trimming") as run_parallel: with profile.report("adapter trimming", dirs): samples = run_parallel("prepare_sample", samples) samples = run_parallel("trim_sample", samples) with prun.start(_wres(parallel, ["aligner", "picard"], ensure_mem={"tophat": 8, "tophat2": 8, "star": 2}), samples, config, dirs, "alignment", multiplier=alignprep.parallel_multiplier(samples)) as run_parallel: with profile.report("alignment", dirs): samples = run_parallel("disambiguate_split", [samples]) samples = run_parallel("process_alignment", samples) with prun.start(_wres(parallel, ["samtools", "cufflinks"]), samples, config, dirs, "rnaseqcount") as run_parallel: with profile.report("disambiguation", dirs): samples = disambiguate.resolve(samples, run_parallel) with profile.report("transcript assembly", dirs): samples = rnaseq.assemble_transcripts(run_parallel, samples) with profile.report("estimate expression", dirs): samples = rnaseq.estimate_expression(samples, run_parallel) with prun.start(_wres(parallel, ["picard", "fastqc", "rnaseqc", "kraken"]), samples, config, dirs, "qc") as run_parallel: with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) logger.info("Timing: finished") return samples
def run(self, config, run_info_yaml, parallel, dirs, samples): with prun.start(_wres(parallel, ["aligner"], ensure_mem={"tophat": 8, "tophat2": 8, "star": 2}), [samples[0]], config, dirs, "organize_samples") as run_parallel: with profile.report("organize samples", dirs): samples = run_parallel("organize_samples", [[dirs, config, run_info_yaml, [x[0]["description"] for x in samples]]]) with prun.start(_wres(parallel, ["picard", "cutadapt"]), samples, config, dirs, "trimming") as run_parallel: with profile.report("adapter trimming", dirs): samples = run_parallel("prepare_sample", samples) samples = run_parallel("trim_sample", samples) with prun.start(_wres(parallel, ["aligner", "picard"], ensure_mem={"tophat": 8, "tophat2": 8, "star": 2}), samples, config, dirs, "alignment", multiplier=alignprep.parallel_multiplier(samples)) as run_parallel: with profile.report("alignment", dirs): samples = disambiguate.split(samples) samples = run_parallel("process_alignment", samples) with prun.start(_wres(parallel, ["samtools", "cufflinks"]), samples, config, dirs, "rnaseqcount") as run_parallel: with profile.report("disambiguation", dirs): samples = disambiguate.resolve(samples, run_parallel) with profile.report("transcript assembly", dirs): samples = rnaseq.assemble_transcripts(run_parallel, samples) with profile.report("estimate expression", dirs): samples = rnaseq.estimate_expression(samples, run_parallel) with prun.start(_wres(parallel, ["picard", "fastqc", "rnaseqc", "kraken"]), samples, config, dirs, "qc") as run_parallel: with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) logger.info("Timing: finished") return samples
def run(self, config, config_file, parallel, dirs, samples): with prun.start(_wres(parallel, ["picard"]), samples, config, dirs, "trimming") as run_parallel: samples = run_parallel("process_lane", samples) samples = run_parallel("trim_lane", samples) with prun.start(_wres(parallel, ["aligner"], ensure_mem={"tophat": 8, "tophat2": 8, "star": 30}), samples, config, dirs, "multicore", multiplier=alignprep.parallel_multiplier(samples)) as run_parallel: samples = disambiguate.split(samples) samples = run_parallel("process_alignment", samples) samples = disambiguate.resolve(samples, run_parallel) with prun.start(_wres(parallel, ["samtools", "cufflinks"]), samples, config, dirs, "rnaseqcount") as run_parallel: samples = rnaseq.estimate_expression(samples, run_parallel) #samples = rnaseq.detect_fusion(samples, run_parallel) combined = combine_count_files([x[0].get("count_file") for x in samples]) gtf_file = utils.get_in(samples[0][0], ('genome_resources', 'rnaseq', 'transcripts'), None) annotated = annotate_combined_count_file(combined, gtf_file) for x in samples: x[0]["combined_counts"] = combined if annotated: x[0]["annotated_combined_counts"] = annotated with prun.start(_wres(parallel, ["picard", "fastqc", "rnaseqc"]), samples, config, dirs, "persample") as run_parallel: samples = qcsummary.generate_parallel(samples, run_parallel) return samples
def run(self, config, config_file, parallel, dirs, samples): with prun.start(parallel, samples, config, dirs, "trimming") as run_parallel: samples = run_parallel("trim_lane", samples) with prun.start( _wprogs(parallel, ["aligner"], {"tophat": 8, "tophat2": 8, "star": 30}), samples, config, dirs, "multicore", multiplier=alignprep.parallel_multiplier(samples), ) as run_parallel: samples = disambiguate.split(samples) samples = run_parallel("process_alignment", samples) samples = disambiguate.resolve(samples, run_parallel) with prun.start( _wprogs(parallel, ["samtools", "gatk", "cufflinks"]), samples, config, dirs, "rnaseqcount" ) as run_parallel: samples = rnaseq.estimate_expression(samples, run_parallel) # samples = rnaseq.detect_fusion(samples, run_parallel) combined = combine_count_files([x[0].get("count_file") for x in samples]) organism = utils.get_in(samples[0][0], ("genome_resources", "aliases", "ensembl"), None) annotated = annotate_combined_count_file(combined, organism) for x in samples: x[0]["combined_counts"] = combined x[0]["annotated_combined_counts"] = annotated with prun.start( _wprogs(parallel, ["picard", "fastqc", "rnaseqc"]), samples, config, dirs, "persample" ) as run_parallel: samples = qcsummary.generate_parallel(samples, run_parallel) return samples
def run(self, config, config_file, parallel, dirs, lane_items): ## Alignment and preparation requiring the entire input file (multicore cluster) with prun.start(_wres(parallel, ["aligner"]), lane_items, config, dirs, "multicore") as run_parallel: with profile.report("alignment", dirs): samples = run_parallel("process_alignment", lane_items) with profile.report("callable regions", dirs): samples = run_parallel("postprocess_alignment", samples) regions = run_parallel("combine_sample_regions", [samples])[0] samples = region.add_region_info(samples, regions) samples = region.clean_sample_data(samples) ## Processing on sub regions with prun.start(_wres(parallel, ["gatk", "picard", "samtools"]), samples, config, dirs, "full", multiplier=len(regions["analysis"]), max_multicore=1) as run_parallel: with profile.report("alignment post-processing", dirs): samples = region.parallel_prep_region(samples, regions, run_parallel) samples = region.parallel_variantcall_region(samples, run_parallel) print len(samples) ## Finalize BAMs and QC with prun.start(_wres(parallel, ["fastqc", "bamtools", "samtools"]), samples, config, dirs, "multicore2") as run_parallel: with profile.report("prepped BAM merging", dirs): samples = region.delayed_bamprep_merge(samples, run_parallel) print len(samples) with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) logger.info("Timing: finished") return samples
def run(self, config, config_file, parallel, dirs, samples): with prun.start(_wres(parallel, ["picard", "AlienTrimmer"]), samples, config, dirs, "trimming") as run_parallel: with profile.report("adapter trimming", dirs): samples = run_parallel("prepare_sample", samples) samples = run_parallel("trim_sample", samples) with prun.start(_wres(parallel, ["aligner", "picard"], ensure_mem={"tophat": 8, "tophat2": 8, "star": 40}), samples, config, dirs, "multicore", multiplier=alignprep.parallel_multiplier(samples)) as run_parallel: with profile.report("alignment", dirs): samples = disambiguate.split(samples) samples = run_parallel("process_alignment", samples) with prun.start(_wres(parallel, ["samtools", "cufflinks"]), samples, config, dirs, "rnaseqcount") as run_parallel: with profile.report("disambiguation", dirs): samples = disambiguate.resolve(samples, run_parallel) with profile.report("transcript assembly", dirs): samples = rnaseq.assemble_transcripts(run_parallel, samples) with profile.report("estimate expression", dirs): samples = rnaseq.estimate_expression(samples, run_parallel) with prun.start(_wres(parallel, ["picard", "fastqc", "rnaseqc","kraken"]), samples, config, dirs, "persample") as run_parallel: with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) logger.info("Timing: finished") return samples
def run(self, config, config_file, parallel, dirs, samples): ## Alignment and preparation requiring the entire input file (multicore cluster) with prun.start(_wres(parallel, ["aligner", "samtools", "sambamba"], (["reference", "fasta"], ["reference", "aligner"], ["files"])), samples, config, dirs, "multicore", multiplier=alignprep.parallel_multiplier(samples)) as run_parallel: with profile.report("alignment preparation", dirs): samples = run_parallel("prep_align_inputs", samples) samples = disambiguate.split(samples) with profile.report("alignment", dirs): samples = run_parallel("process_alignment", samples) samples = alignprep.merge_split_alignments(samples, run_parallel) samples = disambiguate.resolve(samples, run_parallel) with profile.report("callable regions", dirs): samples = run_parallel("postprocess_alignment", samples) samples = run_parallel("combine_sample_regions", [samples]) samples = region.clean_sample_data(samples) with profile.report("coverage", dirs): samples = coverage.summarize_samples(samples, run_parallel) ## Variant calling on sub-regions of the input file (full cluster) with prun.start(_wres(parallel, ["gatk", "picard", "variantcaller"]), samples, config, dirs, "full", multiplier=region.get_max_counts(samples), max_multicore=1) as run_parallel: with profile.report("alignment post-processing", dirs): samples = region.parallel_prep_region(samples, run_parallel) with profile.report("variant calling", dirs): samples = genotype.parallel_variantcall_region(samples, run_parallel) ## Finalize variants (per-sample cluster) with prun.start(_wres(parallel, ["gatk", "gatk-vqsr", "snpeff", "bcbio_variation"]), samples, config, dirs, "persample") as run_parallel: with profile.report("joint squaring off/backfilling", dirs): samples = joint.square_off(samples, run_parallel) with profile.report("variant post-processing", dirs): samples = run_parallel("postprocess_variants", samples) samples = run_parallel("split_variants_by_sample", samples) with profile.report("validation", dirs): samples = run_parallel("compare_to_rm", samples) samples = genotype.combine_multiple_callers(samples) ## Finalizing BAMs and population databases, handle multicore computation with prun.start(_wres(parallel, ["gemini", "samtools", "fastqc", "bamtools", "bcbio_variation", "bcbio-variation-recall"]), samples, config, dirs, "multicore2") as run_parallel: with profile.report("prepped BAM merging", dirs): samples = region.delayed_bamprep_merge(samples, run_parallel) with profile.report("ensemble calling", dirs): samples = ensemble.combine_calls_parallel(samples, run_parallel) with profile.report("validation summary", dirs): samples = validate.summarize_grading(samples) with profile.report("structural variation", dirs): samples = structural.run(samples, run_parallel) with profile.report("population database", dirs): samples = population.prep_db_parallel(samples, run_parallel) with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) with profile.report("archive", dirs): samples = archive.compress(samples, run_parallel) logger.info("Timing: finished") return samples
def run(self, config, config_file, run_parallel, parallel, dirs, lane_items): lane_items = run_parallel("trim_lane", lane_items) samples = run_parallel("process_alignment", lane_items) samples = run_parallel("generate_transcript_counts", samples) samples = qcsummary.generate_parallel(samples, run_parallel) #run_parallel("generate_bigwig", samples, {"programs": ["ucsc_bigwig"]}) return samples
def chipseqpipeline(config, run_info_yaml, parallel, dirs, samples): with prun.start(_wres(parallel, ["aligner", "picard"]), samples, config, dirs, "multicore", multiplier=alignprep.parallel_multiplier(samples)) as run_parallel: with profile.report("organize samples", dirs): samples = run_parallel("organize_samples", [[dirs, config, run_info_yaml, [x[0]["description"] for x in samples]]]) with profile.report("alignment", dirs): samples = run_parallel("prepare_sample", samples) samples = run_parallel("trim_sample", samples) samples = run_parallel("disambiguate_split", [samples]) samples = run_parallel("process_alignment", samples) with profile.report("disambiguation", dirs): samples = disambiguate.resolve(samples, run_parallel) samples = run_parallel("clean_chipseq_alignment", samples) with prun.start(_wres(parallel, ["peakcaller"]), samples, config, dirs, "peakcalling", multiplier = peaks._get_multiplier(samples)) as run_parallel: with profile.report("peakcalling", dirs): samples = peaks.peakcall_prepare(samples, run_parallel) with prun.start(_wres(parallel, ["picard", "fastqc"]), samples, config, dirs, "qc") as run_parallel: with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) with profile.report("upload", dirs): samples = run_parallel("upload_samples", samples) for sample in samples: run_parallel("upload_samples_project", [sample]) logger.info("Timing: finished") return samples
def run(self, config, config_file, run_parallel, parallel, dirs, lane_items): lane_items = run_parallel("trim_lane", lane_items) samples = disambiguate.split(lane_items) samples = run_parallel("process_alignment", samples) samples = run_parallel("clean_chipseq_alignment", samples) samples = qcsummary.generate_parallel(samples, run_parallel) return samples
def run(self, config, run_info_yaml, parallel, dirs, samples): with prun.start(_wres(parallel, ["aligner", "picard"]), samples, config, dirs, "multicore", multiplier=alignprep.parallel_multiplier( samples)) as run_parallel: with profile.report("organize samples", dirs): samples = run_parallel("organize_samples", [[ dirs, config, run_info_yaml, [x[0]["description"] for x in samples] ]]) samples = run_parallel("prepare_sample", samples) samples = run_parallel("trim_sample", samples) samples = run_parallel("disambiguate_split", [samples]) samples = run_parallel("process_alignment", samples) with prun.start(_wres(parallel, ["picard", "fastqc"]), samples, config, dirs, "persample") as run_parallel: with profile.report("disambiguation", dirs): samples = disambiguate.resolve(samples, run_parallel) samples = run_parallel("clean_chipseq_alignment", samples) samples = qcsummary.generate_parallel(samples, run_parallel) with profile.report("upload", dirs): samples = run_parallel("upload_samples", samples) for sample in samples: run_parallel("upload_samples_project", [sample]) return samples
def chipseqpipeline(config, run_info_yaml, parallel, dirs, samples): with prun.start(_wres(parallel, ["aligner", "picard"]), samples, config, dirs, "multicore", multiplier=alignprep.parallel_multiplier(samples)) as run_parallel: with profile.report("organize samples", dirs): samples = run_parallel("organize_samples", [[dirs, config, run_info_yaml, [x[0]["description"] for x in samples]]]) with profile.report("alignment", dirs): samples = run_parallel("prepare_sample", samples) samples = run_parallel("trim_sample", samples) samples = run_parallel("disambiguate_split", [samples]) samples = run_parallel("process_alignment", samples) with profile.report("disambiguation", dirs): samples = disambiguate.resolve(samples, run_parallel) samples = run_parallel("clean_chipseq_alignment", samples) with prun.start(_wres(parallel, ["peakcaller"]), samples, config, dirs, "peakcalling", multiplier = peaks._get_multiplier(samples)) as run_parallel: with profile.report("peakcalling", dirs): samples = peaks.peakcall_prepare(samples, run_parallel) with prun.start(_wres(parallel, ["picard", "fastqc"]), samples, config, dirs, "qc") as run_parallel: with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) with profile.report("upload", dirs): samples = run_parallel("upload_samples", samples) for sample in samples: run_parallel("upload_samples_project", [sample]) return samples
def run(self, config, run_info_yaml, parallel, dirs, samples): ## Alignment and preparation requiring the entire input file (multicore cluster) with prun.start(_wres(parallel, ["aligner"]), samples, config, dirs, "multicore") as run_parallel: with profile.report("organize samples", dirs): samples = run_parallel( "organize_samples", [[dirs, config, run_info_yaml, [x[0]["description"] for x in samples]]] ) with profile.report("alignment", dirs): samples = run_parallel("process_alignment", samples) with profile.report("callable regions", dirs): samples = run_parallel("prep_samples", [samples]) samples = run_parallel("postprocess_alignment", samples) samples = run_parallel("combine_sample_regions", [samples]) samples = region.clean_sample_data(samples) ## Quality control with prun.start( _wres(parallel, ["fastqc", "bamtools", "samtools", "qsignature", "kraken"]), samples, config, dirs, "multicore2", ) as run_parallel: with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) with profile.report("upload", dirs): for sample in samples: run_parallel("upload_samples", [sample]) logger.info("Timing: finished") return samples
def run(self, config, run_info_yaml, parallel, dirs, samples): with prun.start( _wres(parallel, ["aligner", "picard"]), samples, config, dirs, "multicore", multiplier=alignprep.parallel_multiplier(samples), ) as run_parallel: with profile.report("organize samples", dirs): samples = run_parallel( "organize_samples", [[dirs, config, run_info_yaml, [x[0]["description"] for x in samples]]] ) samples = run_parallel("prepare_sample", samples) samples = run_parallel("trim_sample", samples) samples = run_parallel("disambiguate_split", [samples]) samples = run_parallel("process_alignment", samples) with prun.start(_wres(parallel, ["picard", "fastqc"]), samples, config, dirs, "persample") as run_parallel: with profile.report("disambiguation", dirs): samples = disambiguate.resolve(samples, run_parallel) samples = run_parallel("clean_chipseq_alignment", samples) samples = qcsummary.generate_parallel(samples, run_parallel) with profile.report("upload", dirs): for sample in samples: run_parallel("upload_samples", [sample]) return samples
def rnaseqpipeline(config, run_info_yaml, parallel, dirs, samples): samples = rnaseq_prep_samples(config, run_info_yaml, parallel, dirs, samples) with prun.start( _wres(parallel, ["aligner", "picard", "samtools"], ensure_mem={ "tophat": 10, "tophat2": 10, "star": 2, "hisat2": 8 }), samples, config, dirs, "alignment", multiplier=alignprep.parallel_multiplier(samples)) as run_parallel: with profile.report("alignment", dirs): samples = run_parallel("disambiguate_split", [samples]) samples = run_parallel("process_alignment", samples) with prun.start(_wres(parallel, ["samtools", "cufflinks"]), samples, config, dirs, "rnaseqcount") as run_parallel: with profile.report("disambiguation", dirs): samples = disambiguate.resolve(samples, run_parallel) with profile.report("transcript assembly", dirs): samples = rnaseq.assemble_transcripts(run_parallel, samples) with profile.report("estimate expression (threaded)", dirs): samples = rnaseq.quantitate_expression_parallel( samples, run_parallel) with prun.start(_wres(parallel, ["dexseq", "express"]), samples, config, dirs, "rnaseqcount-singlethread", max_multicore=1) as run_parallel: with profile.report("estimate expression (single threaded)", dirs): samples = rnaseq.quantitate_expression_noparallel( samples, run_parallel) samples = rnaseq.combine_files(samples) with prun.start(_wres(parallel, ["gatk", "vardict"]), samples, config, dirs, "rnaseq-variation") as run_parallel: with profile.report("RNA-seq variant calling", dirs): samples = rnaseq.rnaseq_variant_calling(samples, run_parallel) with prun.start( _wres( parallel, ["samtools", "fastqc", "qualimap", "kraken", "gatk", "preseq"], ensure_mem={"qualimap": 4}), samples, config, dirs, "qc") as run_parallel: with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) with profile.report("upload", dirs): samples = run_parallel("upload_samples", samples) for sample in samples: run_parallel("upload_samples_project", [sample]) logger.info("Timing: finished") return samples
def smallrnaseqpipeline(config, run_info_yaml, parallel, dirs, samples): # causes a circular import at the top level from bcbio.srna.group import report as srna_report samples = rnaseq_prep_samples(config, run_info_yaml, parallel, dirs, samples) with prun.start( _wres(parallel, ["aligner", "picard", "samtools"], ensure_mem={ "bowtie": 8, "bowtie2": 8, "star": 2 }), [samples[0]], config, dirs, "alignment") as run_parallel: with profile.report("prepare", dirs): samples = run_parallel("seqcluster_prepare", [samples]) with profile.report("seqcluster alignment", dirs): samples = run_parallel("srna_alignment", [samples]) with prun.start( _wres(parallel, ["aligner", "picard", "samtools"], ensure_mem={ "tophat": 10, "tophat2": 10, "star": 2, "hisat2": 8 }), samples, config, dirs, "alignment_samples", multiplier=alignprep.parallel_multiplier(samples)) as run_parallel: with profile.report("alignment", dirs): samples = run_parallel("process_alignment", samples) with prun.start(_wres(parallel, ["picard", "miraligner"]), samples, config, dirs, "annotation") as run_parallel: with profile.report("small RNA annotation", dirs): samples = run_parallel("srna_annotation", samples) with prun.start( _wres(parallel, ["seqcluster", "mirge"], ensure_mem={"seqcluster": 8}), [samples[0]], config, dirs, "cluster") as run_parallel: with profile.report("cluster", dirs): samples = run_parallel("seqcluster_cluster", [samples]) with prun.start(_wres(parallel, ["picard", "fastqc"]), samples, config, dirs, "qc") as run_parallel: with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) with profile.report("report", dirs): srna_report(samples) with profile.report("upload", dirs): samples = run_parallel("upload_samples", samples) for sample in samples: run_parallel("upload_samples_project", [sample]) return samples
def run(self, config, config_file, parallel, dirs, samples): ## Alignment and preparation requiring the entire input file (multicore cluster) with prun.start(_wres(parallel, ["aligner", "samtools", "sambamba"], (["reference", "fasta"], ["reference", "aligner"], ["files"])), samples, config, dirs, "multicore", multiplier=alignprep.parallel_multiplier(samples)) as run_parallel: with profile.report("alignment preparation", dirs): samples = run_parallel("prep_align_inputs", samples) samples = disambiguate.split(samples) with profile.report("alignment", dirs): samples = run_parallel("process_alignment", samples) samples = alignprep.merge_split_alignments(samples, run_parallel) samples = disambiguate.resolve(samples, run_parallel) with profile.report("callable regions", dirs): samples = run_parallel("postprocess_alignment", samples) samples = run_parallel("combine_sample_regions", [samples]) samples = region.clean_sample_data(samples) with profile.report("coverage", dirs): samples = coverage.summarize_samples(samples, run_parallel) ## Variant calling on sub-regions of the input file (full cluster) with prun.start(_wres(parallel, ["gatk", "picard", "variantcaller"]), samples, config, dirs, "full", multiplier=region.get_max_counts(samples), max_multicore=1) as run_parallel: with profile.report("alignment post-processing", dirs): samples = region.parallel_prep_region(samples, run_parallel) with profile.report("variant calling", dirs): samples = genotype.parallel_variantcall_region(samples, run_parallel) ## Finalize variants (per-sample cluster) with prun.start(_wres(parallel, ["gatk", "gatk-vqsr", "snpeff", "bcbio_variation"]), samples, config, dirs, "persample") as run_parallel: with profile.report("variant post-processing", dirs): samples = run_parallel("postprocess_variants", samples) samples = run_parallel("split_variants_by_sample", samples) with profile.report("validation", dirs): samples = run_parallel("compare_to_rm", samples) samples = genotype.combine_multiple_callers(samples) ## Finalizing BAMs and population databases, handle multicore computation with prun.start(_wres(parallel, ["gemini", "samtools", "fastqc", "bamtools", "bcbio_variation", "bcbio-variation-recall"]), samples, config, dirs, "multicore2") as run_parallel: with profile.report("prepped BAM merging", dirs): samples = region.delayed_bamprep_merge(samples, run_parallel) with profile.report("ensemble calling", dirs): samples = ensemble.combine_calls_parallel(samples, run_parallel) with profile.report("validation summary", dirs): samples = validate.summarize_grading(samples) with profile.report("structural variation", dirs): samples = structural.run(samples, run_parallel) with profile.report("population database", dirs): samples = population.prep_db_parallel(samples, run_parallel) with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) with profile.report("archive", dirs): samples = archive.compress(samples, run_parallel) logger.info("Timing: finished") return samples
def run(self, config, config_file, run_parallel, dirs, lane_items): lane_items = run_parallel("trim_lane", lane_items) align_items = run_parallel("process_alignment", lane_items) # process samples, potentially multiplexed across multiple lanes samples = organize_samples(align_items, dirs, config_file) samples = run_parallel("merge_sample", samples) samples = run_parallel("generate_transcript_counts", samples) run_parallel("generate_bigwig", samples, {"programs": ["ucsc_bigwig"]}) samples = qcsummary.generate_parallel(samples, run_parallel) return samples
def run(self, config, config_file, run_parallel, parallel, dirs, lane_items): ## Alignment and preparation requiring the entire input file (multicore cluster) with global_parallel(parallel, "multicore", ["align_prep_full"], lane_items, dirs, config) as parallel: run_parallel = parallel_runner(parallel, dirs, config) logger.info("Timing: alignment") samples = run_parallel( "align_prep_full", [list(x) + [config_file] for x in lane_items]) regions = callable.combine_sample_regions(samples) samples = region.add_region_info(samples, regions) samples = region.clean_sample_data(samples) logger.info("Timing: coverage") samples = coverage.summarize_samples(samples, run_parallel) ## Variant calling on sub-regions of the input file (full cluster) with global_parallel(parallel, "full", ["piped_bamprep", "variantcall_sample"], samples, dirs, config, multiplier=len(regions["analysis"])) as parallel: run_parallel = parallel_runner(parallel, dirs, config) logger.info("Timing: alignment post-processing") samples = region.parallel_prep_region(samples, regions, run_parallel) logger.info("Timing: variant calling") samples = region.parallel_variantcall_region(samples, run_parallel) ## Finalize variants (per-sample cluster) with global_parallel(parallel, "persample", ["postprocess_variants"], samples, dirs, config) as parallel: run_parallel = parallel_runner(parallel, dirs, config) logger.info("Timing: variant post-processing") samples = run_parallel("postprocess_variants", samples) logger.info("Timing: validation") samples = run_parallel("compare_to_rm", samples) samples = combine_multiple_callers(samples) logger.info("Timing: ensemble calling") samples = ensemble.combine_calls_parallel(samples, run_parallel) samples = validate.summarize_grading(samples) logger.info("Timing: quality control") samples = qcsummary.generate_parallel(samples, run_parallel) ## Finalizing BAMs and population databases, handle multicore computation with global_parallel(parallel, "multicore2", ["prep_gemini_db", "delayed_bam_merge"], samples, dirs, config) as parallel: run_parallel = parallel_runner(parallel, dirs, config) logger.info("Timing: prepped BAM merging") samples = region.delayed_bamprep_merge(samples, run_parallel) logger.info("Timing: population database") samples = population.prep_db_parallel(samples, run_parallel) logger.info("Timing: finished") return samples
def run(self, config, config_file, run_parallel, parallel, dirs, samples): ## Alignment and preparation requiring the entire input file (multicore cluster) with global_parallel(parallel, "multicore", ["process_alignment", "postprocess_alignment"], samples, dirs, config, multiplier=alignprep.parallel_multiplier(samples)) as parallel: run_parallel = parallel_runner(parallel, dirs, config) logger.info("Timing: alignment") samples = run_parallel("prep_align_inputs", samples) samples = disambiguate.split(samples) samples = run_parallel("process_alignment", samples) samples = alignprep.merge_split_alignments(samples, run_parallel) samples = disambiguate.resolve(samples, run_parallel) samples = run_parallel("postprocess_alignment", samples) regions = callable.combine_sample_regions(samples) samples = region.add_region_info(samples, regions) samples = region.clean_sample_data(samples) logger.info("Timing: coverage") samples = coverage.summarize_samples(samples, run_parallel) ## Variant calling on sub-regions of the input file (full cluster) with global_parallel(parallel, "full", ["piped_bamprep", "variantcall_sample"], samples, dirs, config, multiplier=len(regions["analysis"]), max_multicore=1) as parallel: run_parallel = parallel_runner(parallel, dirs, config) logger.info("Timing: alignment post-processing") samples = region.parallel_prep_region(samples, regions, run_parallel) logger.info("Timing: variant calling") samples = region.parallel_variantcall_region(samples, run_parallel) ## Finalize variants (per-sample cluster) with global_parallel(parallel, "persample", ["postprocess_variants"], samples, dirs, config) as parallel: run_parallel = parallel_runner(parallel, dirs, config) logger.info("Timing: variant post-processing") samples = run_parallel("postprocess_variants", samples) logger.info("Timing: validation") samples = run_parallel("compare_to_rm", samples) samples = combine_multiple_callers(samples) logger.info("Timing: ensemble calling") samples = ensemble.combine_calls_parallel(samples, run_parallel) samples = validate.summarize_grading(samples) ## Finalizing BAMs and population databases, handle multicore computation with global_parallel(parallel, "multicore2", ["prep_gemini_db", "delayed_bam_merge"], samples, dirs, config) as parallel: run_parallel = parallel_runner(parallel, dirs, config) logger.info("Timing: prepped BAM merging") samples = region.delayed_bamprep_merge(samples, run_parallel) logger.info("Timing: structural variation") samples = structural.run(samples, run_parallel) logger.info("Timing: population database") samples = population.prep_db_parallel(samples, run_parallel) logger.info("Timing: quality control") samples = qcsummary.generate_parallel(samples, run_parallel) logger.info("Timing: finished") return samples
def run(self, config, config_file, parallel, dirs, lane_items): ## Alignment and preparation requiring the entire input file (multicore cluster) with prun.start(_wprogs(parallel, ["aligner"]), lane_items, config, dirs, "multicore") as run_parallel: logger.info("Timing: alignment") samples = run_parallel("process_alignment", lane_items) ## Finalize (per-sample cluster) with prun.start(_wprogs(parallel, ["fastqc", "bamtools"]), samples, config, dirs, "persample") as run_parallel: logger.info("Timing: quality control") samples = qcsummary.generate_parallel(samples, run_parallel) logger.info("Timing: finished") return samples
def run(self, config, config_file, run_parallel, parallel, dirs, lane_items): lane_items = run_parallel("trim_lane", lane_items) samples = disambiguate.split(lane_items) samples = run_parallel("process_alignment", samples) samples = disambiguate.resolve(samples, run_parallel) samples = run_parallel("generate_transcript_counts", samples) combined = combine_count_files([x[0].get("count_file") for x in samples]) for x in samples: x[0]["combined_counts"] = combined samples = qcsummary.generate_parallel(samples, run_parallel) #run_parallel("generate_bigwig", samples, {"programs": ["ucsc_bigwig"]}) return samples
def run(self, config, config_file, parallel, dirs, lane_items): ## Alignment and preparation requiring the entire input file (multicore cluster) with prun.start(_wres(parallel, ["aligner"]), lane_items, config, dirs, "multicore") as run_parallel: logger.info("Timing: alignment") samples = run_parallel("process_alignment", lane_items) ## Finalize (per-sample cluster) with prun.start(_wres(parallel, ["fastqc", "bamtools"]), samples, config, dirs, "persample") as run_parallel: logger.info("Timing: quality control") samples = qcsummary.generate_parallel(samples, run_parallel) logger.info("Timing: finished") return samples
def run(self, config, config_file, parallel, dirs, samples): with prun.start(_wres(parallel, ["aligner", "picard"]), samples, config, dirs, "multicore", multiplier=alignprep.parallel_multiplier(samples)) as run_parallel: samples = run_parallel("process_lane", samples) samples = run_parallel("trim_lane", samples) samples = disambiguate.split(samples) samples = run_parallel("process_alignment", samples) with prun.start(_wres(parallel, ["picard", "fastqc"]), samples, config, dirs, "persample") as run_parallel: samples = run_parallel("clean_chipseq_alignment", samples) samples = qcsummary.generate_parallel(samples, run_parallel) return samples
def run(self, config, config_file, run_parallel, parallel, dirs, lane_items): ## Alignment and preparation requiring the entire input file (multicore cluster) with global_parallel(parallel, "multicore", ["align_prep_full"], lane_items, dirs, config) as parallel: run_parallel = parallel_runner(parallel, dirs, config) logger.info("Timing: alignment") samples = run_parallel("process_alignment", lane_items) ## Finalize (per-sample cluster) with global_parallel(parallel, "persample", ["postprocess_variants"], samples, dirs, config) as parallel: run_parallel = parallel_runner(parallel, dirs, config) logger.info("Timing: quality control") samples = qcsummary.generate_parallel(samples, run_parallel) logger.info("Timing: finished") return samples
def run(self, config, run_info_yaml, parallel, dirs, samples): # causes a circular import at the top level from bcbio.srna.group import report as srna_report with prun.start(_wres(parallel, ["picard", "cutadapt"]), samples, config, dirs, "trimming") as run_parallel: with profile.report("organize samples", dirs): samples = run_parallel("organize_samples", [[ dirs, config, run_info_yaml, [x[0]["description"] for x in samples] ]]) with profile.report("adapter trimming", dirs): samples = run_parallel("prepare_sample", samples) samples = run_parallel("trim_srna_sample", samples) with prun.start( _wres(parallel, ["aligner", "picard", "samtools"], ensure_mem={ "bowtie": 8, "bowtie2": 8, "star": 2 }), [samples[0]], config, dirs, "alignment") as run_parallel: with profile.report("prepare", dirs): samples = run_parallel("seqcluster_prepare", [samples]) with profile.report("alignment", dirs): samples = run_parallel("srna_alignment", [samples]) with prun.start(_wres(parallel, ["picard", "miraligner"]), samples, config, dirs, "annotation") as run_parallel: with profile.report("small RNA annotation", dirs): samples = run_parallel("srna_annotation", samples) with prun.start( _wres(parallel, ["seqcluster"], ensure_mem={"seqcluster": 8}), [samples[0]], config, dirs, "cluster") as run_parallel: with profile.report("cluster", dirs): samples = run_parallel("seqcluster_cluster", [samples]) with prun.start(_wres(parallel, ["picard", "fastqc"]), samples, config, dirs, "qc") as run_parallel: with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) with profile.report("report", dirs): srna_report(samples) with profile.report("upload", dirs): samples = run_parallel("upload_samples", samples) for sample in samples: run_parallel("upload_samples_project", [sample]) return samples
def fastrnaseqpipeline(config, run_info_yaml, parallel, dirs, samples): samples = rnaseq_prep_samples(config, run_info_yaml, parallel, dirs, samples) with prun.start(_wres(parallel, ["samtools"]), samples, config, dirs, "fastrnaseq") as run_parallel: with profile.report("fastrnaseq", dirs): samples = rnaseq.fast_rnaseq(samples, run_parallel) with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) with profile.report("upload", dirs): samples = run_parallel("upload_samples", samples) for samples in samples: run_parallel("upload_samples_project", [samples]) logger.info("Timing: finished") return samples
def singlecellrnaseqpipeline(config, run_info_yaml, parallel, dirs, samples): samples = rnaseq_prep_samples(config, run_info_yaml, parallel, dirs, samples) with prun.start(_wres(parallel, ["samtools", "rapmap"]), samples, config, dirs, "singlecell-rnaseq") as run_parallel: with profile.report("singlecell-rnaseq", dirs): samples = rnaseq.singlecell_rnaseq(samples, run_parallel) with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) with profile.report("upload", dirs): samples = run_parallel("upload_samples", samples) for samples in samples: run_parallel("upload_samples_project", [samples]) logger.info("Timing: finished") return samples
def run(self, config, run_info_yaml, parallel, dirs, samples): with prun.start(_wres(parallel, ["picard", "cutadapt"]), samples, config, dirs, "trimming") as run_parallel: with profile.report("organize samples", dirs): samples = run_parallel( "organize_samples", [[dirs, config, run_info_yaml, [x[0]["description"] for x in samples]]] ) with profile.report("adapter trimming", dirs): samples = run_parallel("prepare_sample", samples) samples = run_parallel("trim_sample", samples) with prun.start( _wres(parallel, ["aligner", "picard"], ensure_mem={"tophat": 8, "tophat2": 8, "star": 2}), samples, config, dirs, "alignment", multiplier=alignprep.parallel_multiplier(samples), ) as run_parallel: with profile.report("alignment", dirs): samples = run_parallel("disambiguate_split", [samples]) samples = run_parallel("process_alignment", samples) with prun.start( _wres(parallel, ["samtools", "cufflinks"]), samples, config, dirs, "rnaseqcount" ) as run_parallel: with profile.report("disambiguation", dirs): samples = disambiguate.resolve(samples, run_parallel) with profile.report("transcript assembly", dirs): samples = rnaseq.assemble_transcripts(run_parallel, samples) with profile.report("estimate expression (threaded)", dirs): samples = rnaseq.quantitate_expression_parallel(samples, run_parallel) with prun.start( _wres(parallel, ["dexseq", "express"]), samples, config, dirs, "rnaseqcount-singlethread", max_multicore=1 ) as run_parallel: with profile.report("estimate expression (single threaded)", dirs): samples = rnaseq.quantitate_expression_noparallel(samples, run_parallel) samples = rnaseq.combine_files(samples) with prun.start(_wres(parallel, ["gatk"]), samples, config, dirs, "rnaseq-variation") as run_parallel: with profile.report("RNA-seq variant calling", dirs): samples = rnaseq.rnaseq_variant_calling(samples, run_parallel) with prun.start( _wres(parallel, ["picard", "fastqc", "rnaseqc", "kraken"]), samples, config, dirs, "qc" ) as run_parallel: with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) with profile.report("upload", dirs): for sample in samples: run_parallel("upload_samples", [sample]) logger.info("Timing: finished") return samples
def run(self, config, config_file, run_parallel, parallel, dirs, lane_items): ## Alignment and preparation requiring the entire input file (multicore cluster) with global_parallel(parallel, "multicore", ["align_prep_full"], lane_items, dirs["work"], config) as parallel: run_parallel = parallel_runner(parallel, dirs, config) logger.info("Timing: alignment") samples = run_parallel( "align_prep_full", [list(x) + [config_file] for x in lane_items]) regions = callable.combine_sample_regions(samples) samples = region.add_region_info(samples, regions) samples = region.clean_sample_data(samples) ## Variant calling on sub-regions of the input file (full cluster) with global_parallel( parallel, "full", ["piped_bamprep", "variantcall_sample"], samples, dirs["work"], config, multiplier=len(regions["analysis"])) as parallel: run_parallel = parallel_runner(parallel, dirs, config) logger.info("Timing: alignment post-processing") samples = region.parallel_prep_region(samples, regions, run_parallel) logger.info("Timing: variant calling") samples = region.parallel_variantcall_region(samples, run_parallel) ## Finalize variants (per-sample cluster) with global_parallel(parallel, "persample", ["postprocess_variants"], samples, dirs["work"], config) as parallel: run_parallel = parallel_runner(parallel, dirs, config) logger.info("Timing: variant post-processing") samples = run_parallel("postprocess_variants", samples) samples = combine_multiple_callers(samples) logger.info("Timing: ensemble calling") samples = ensemble.combine_calls_parallel(samples, run_parallel) logger.info("Timing: prepped BAM merging") samples = region.delayed_bamprep_merge(samples, run_parallel) logger.info("Timing: validation") samples = run_parallel("compare_to_rm", samples) samples = validate.summarize_grading(samples) logger.info("Timing: population database") samples = population.prep_db_parallel(samples, run_parallel) logger.info("Timing: quality control") samples = qcsummary.generate_parallel(samples, run_parallel) logger.info("Timing: finished") return samples
def run(self, config, config_file, run_parallel, parallel, dirs, lane_items): ## Alignment and preparation requiring the entire input file (multicore cluster) with global_parallel(parallel, "multicore", ["process_alignment"], lane_items, dirs, config) as parallel: run_parallel = parallel_runner(parallel, dirs, config) logger.info("Timing: alignment") samples = run_parallel("process_alignment", lane_items) ## Finalize (per-sample cluster) with global_parallel(parallel, "persample", ["postprocess_variants"], samples, dirs, config) as parallel: run_parallel = parallel_runner(parallel, dirs, config) logger.info("Timing: quality control") samples = qcsummary.generate_parallel(samples, run_parallel) logger.info("Timing: finished") return samples
def run(self, config, config_file, run_parallel, dirs, lane_items): lane_items = run_parallel("trim_lane", lane_items) align_items = run_parallel("process_alignment", lane_items) # process samples, potentially multiplexed across multiple lanes samples = organize_samples(align_items, dirs, config_file) samples = run_parallel("merge_sample", samples) samples = run_parallel("prep_recal", samples) samples = recalibrate.parallel_write_recal_bam(samples, run_parallel) samples = parallel_realign_sample(samples, run_parallel) samples = parallel_variantcall(samples, run_parallel) samples = run_parallel("postprocess_variants", samples) samples = combine_multiple_callers(samples) samples = ensemble.combine_calls_parallel(samples, run_parallel) samples = run_parallel("detect_sv", samples) samples = qcsummary.generate_parallel(samples, run_parallel) run_parallel("generate_bigwig", samples, {"programs": ["ucsc_bigwig"]}) return samples
def fastrnaseqpipeline(config, run_info_yaml, parallel, dirs, samples): samples = rnaseq_prep_samples(config, run_info_yaml, parallel, dirs, samples) ww = initialize_watcher(samples) with prun.start(_wres(parallel, ["samtools"]), samples, config, dirs, "fastrnaseq") as run_parallel: with profile.report("fastrnaseq", dirs): samples = rnaseq.fast_rnaseq(samples, run_parallel) ww.report("fastrnaseq", samples) with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) ww.report("qcsummary", samples) with profile.report("upload", dirs): samples = run_parallel("upload_samples", samples) for samples in samples: run_parallel("upload_samples_project", [samples]) logger.info("Timing: finished") return samples
def run(self, config, config_file, parallel, dirs, lane_items): ## Alignment and preparation requiring the entire input file (multicore cluster) with prun.start(_wres(parallel, ["aligner"]), lane_items, config, dirs, "multicore") as run_parallel: with profile.report("alignment", dirs): samples = run_parallel("process_alignment", lane_items) with profile.report("callable regions", dirs): samples = run_parallel("postprocess_alignment", samples) samples = run_parallel("combine_sample_regions", [samples]) samples = region.clean_sample_data(samples) ## Quality control with prun.start(_wres(parallel, ["fastqc", "bamtools", "samtools"]), samples, config, dirs, "multicore2") as run_parallel: with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) logger.info("Timing: finished") return samples
def run(self, config, config_file, run_parallel, dirs, lane_items): # Handle alignment and preparation requiring the entire input file samples = run_parallel("align_prep_full", (list(x) + [config_file] for x in lane_items)) regions = callable.combine_sample_regions(samples) samples = region.add_region_info(samples, regions) # Handle all variant calling on sub-regions of the input file samples = region.clean_sample_data(samples) samples = region.parallel_prep_region(samples, regions, run_parallel) samples = region.parallel_variantcall_region(samples, run_parallel) samples = run_parallel("postprocess_variants", samples) samples = combine_multiple_callers(samples) samples = ensemble.combine_calls_parallel(samples, run_parallel) samples = population.prep_db_parallel(samples, run_parallel) samples = region.delayed_bamprep_merge(samples, run_parallel) samples = qcsummary.generate_parallel(samples, run_parallel) samples = validate.summarize_grading(samples) return samples
def rnaseqpipeline(config, run_info_yaml, parallel, dirs, samples): samples = rnaseq_prep_samples(config, run_info_yaml, parallel, dirs, samples) with prun.start(_wres(parallel, ["aligner", "picard", "samtools"], ensure_mem={"tophat": 10, "tophat2": 10, "star": 2, "hisat2": 8}), samples, config, dirs, "alignment", multiplier=alignprep.parallel_multiplier(samples)) as run_parallel: with profile.report("alignment", dirs): samples = run_parallel("disambiguate_split", [samples]) samples = run_parallel("process_alignment", samples) with prun.start(_wres(parallel, ["samtools", "cufflinks"]), samples, config, dirs, "rnaseqcount") as run_parallel: with profile.report("disambiguation", dirs): samples = disambiguate.resolve(samples, run_parallel) with profile.report("transcript assembly", dirs): samples = rnaseq.assemble_transcripts(run_parallel, samples) with profile.report("estimate expression (threaded)", dirs): samples = rnaseq.quantitate_expression_parallel(samples, run_parallel) with prun.start(_wres(parallel, ["ericscript"]), samples, config, dirs, "fusion-standalone-callers") as run_parallel: with profile.report("Detect gene fusions", dirs): rnaseq.detect_fusions(samples) with prun.start(_wres(parallel, ["dexseq", "express"]), samples, config, dirs, "rnaseqcount-singlethread", max_multicore=1) as run_parallel: with profile.report("estimate expression (single threaded)", dirs): samples = rnaseq.quantitate_expression_noparallel(samples, run_parallel) samples = rnaseq.combine_files(samples) with prun.start(_wres(parallel, ["gatk"]), samples, config, dirs, "rnaseq-variation") as run_parallel: with profile.report("RNA-seq variant calling", dirs): samples = rnaseq.rnaseq_variant_calling(samples, run_parallel) with prun.start(_wres(parallel, ["samtools", "fastqc", "qualimap", "kraken", "gatk", "preseq"], ensure_mem={"qualimap": 4}), samples, config, dirs, "qc") as run_parallel: with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) with profile.report("upload", dirs): samples = run_parallel("upload_samples", samples) for sample in samples: run_parallel("upload_samples_project", [sample]) logger.info("Timing: finished") return samples
def wgbsseqpipeline(config, run_info_yaml, parallel, dirs, samples): with prun.start( _wres(parallel, ["fastqc", "picard"], ensure_mem={"fastqc": 4}), samples, config, dirs, "trimming") as run_parallel: with profile.report("organize samples", dirs): samples = run_parallel("organize_samples", [[ dirs, config, run_info_yaml, [x[0]["description"] for x in samples] ]]) samples = run_parallel("prepare_sample", samples) samples = run_parallel("trim_bs_sample", samples) with prun.start( _wres(parallel, ["aligner", "bismark", "picard", "samtools"]), samples, config, dirs, "multicore", multiplier=alignprep.parallel_multiplier(samples)) as run_parallel: with profile.report("alignment", dirs): samples = run_parallel("process_alignment", samples) with prun.start(_wres(parallel, ['samtools']), samples, config, dirs, 'deduplication') as run_parallel: with profile.report('deduplicate', dirs): samples = run_parallel('deduplicate_bismark', samples) with prun.start(_wres(parallel, ["caller"], ensure_mem={"caller": 5}), samples, config, dirs, "multicore2", multiplier=24) as run_parallel: with profile.report("cpg calling", dirs): samples = run_parallel("cpg_calling", samples) with prun.start(_wres(parallel, ["picard", "fastqc", "samtools"]), samples, config, dirs, "qc") as run_parallel: with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) with profile.report("upload", dirs): samples = run_parallel("upload_samples", samples) for sample in samples: run_parallel("upload_samples_project", [sample]) logger.info("Timing: finished") return samples
def run(self, config, config_file, parallel, dirs, samples): with prun.start(_wres(parallel, ["picard", "AlienTrimmer"]), samples, config, dirs, "trimming") as run_parallel: with profile.report("adapter trimming", dirs): samples = run_parallel("process_lane", samples) samples = run_parallel("trim_lane", samples) with prun.start(_wres(parallel, ["aligner", "picard"], ensure_mem={ "tophat": 8, "tophat2": 8, "star": 40 }), samples, config, dirs, "multicore", multiplier=alignprep.parallel_multiplier( samples)) as run_parallel: with profile.report("alignment", dirs): samples = disambiguate.split(samples) samples = run_parallel("process_alignment", samples) with prun.start(_wres(parallel, ["samtools", "cufflinks"]), samples, config, dirs, "rnaseqcount") as run_parallel: with profile.report("disambiguation", dirs): samples = disambiguate.resolve(samples, run_parallel) with profile.report("estimate expression", dirs): samples = rnaseq.estimate_expression(samples, run_parallel) combined = combine_count_files( [x[0].get("count_file") for x in samples]) gtf_file = utils.get_in(samples[0][0], ('genome_resources', 'rnaseq', 'transcripts'), None) annotated = annotate_combined_count_file(combined, gtf_file) for x in samples: x[0]["combined_counts"] = combined if annotated: x[0]["annotated_combined_counts"] = annotated with prun.start(_wres(parallel, ["picard", "fastqc", "rnaseqc"]), samples, config, dirs, "persample") as run_parallel: with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) logger.info("Timing: finished") return samples
def run(self, config, config_file, parallel, dirs, samples): ## Alignment and preparation requiring the entire input file (multicore cluster) with prun.start(_wres(parallel, ["aligner"]), samples, config, dirs, "multicore") as run_parallel: with profile.report("alignment", dirs): samples = run_parallel("process_alignment", samples) with profile.report("callable regions", dirs): samples = run_parallel("postprocess_alignment", samples) samples = run_parallel("combine_sample_regions", [samples]) samples = region.clean_sample_data(samples) ## Quality control with prun.start(_wres(parallel, ["fastqc", "bamtools", "samtools"]), samples, config, dirs, "multicore2") as run_parallel: with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) logger.info("Timing: finished") return samples
def run(self, config, config_file, run_parallel, parallel, dirs, lane_items): lane_items = run_parallel("trim_lane", lane_items) samples = disambiguate.split(lane_items) samples = run_parallel("process_alignment", samples) samples = disambiguate.resolve(samples, run_parallel) samples = rnaseq.estimate_expression(samples, run_parallel) #samples = rnaseq.detect_fusion(samples, run_parallel) combined = combine_count_files([x[0].get("count_file") for x in samples]) organism = utils.get_in(samples[0][0], ('genome_resources', 'aliases', 'ensembl'), None) annotated = annotate_combined_count_file(combined, organism) for x in samples: x[0]["combined_counts"] = combined x[0]["annotated_combined_counts"] = annotated samples = qcsummary.generate_parallel(samples, run_parallel) #run_parallel("generate_bigwig", samples, {"programs": ["ucsc_bigwig"]}) return samples
def smallrnaseqpipeline(config, run_info_yaml, parallel, dirs, samples): # causes a circular import at the top level from bcbio.srna.group import report as srna_report samples = rnaseq_prep_samples(config, run_info_yaml, parallel, dirs, samples) with prun.start(_wres(parallel, ["aligner", "picard", "samtools"], ensure_mem={"bowtie": 8, "bowtie2": 8, "star": 2}), [samples[0]], config, dirs, "alignment") as run_parallel: with profile.report("prepare", dirs): samples = run_parallel("seqcluster_prepare", [samples]) with profile.report("seqcluster alignment", dirs): samples = run_parallel("srna_alignment", [samples]) with prun.start(_wres(parallel, ["aligner", "picard", "samtools"], ensure_mem={"tophat": 10, "tophat2": 10, "star": 2, "hisat2": 8}), samples, config, dirs, "alignment_samples", multiplier=alignprep.parallel_multiplier(samples)) as run_parallel: with profile.report("alignment", dirs): samples = run_parallel("process_alignment", samples) with prun.start(_wres(parallel, ["picard", "miraligner"]), samples, config, dirs, "annotation") as run_parallel: with profile.report("small RNA annotation", dirs): samples = run_parallel("srna_annotation", samples) with prun.start(_wres(parallel, ["seqcluster", "mirge"], ensure_mem={"seqcluster": 8}), [samples[0]], config, dirs, "cluster") as run_parallel: with profile.report("cluster", dirs): samples = run_parallel("seqcluster_cluster", [samples]) with prun.start(_wres(parallel, ["picard", "fastqc"]), samples, config, dirs, "qc") as run_parallel: with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) with profile.report("report", dirs): srna_report(samples) with profile.report("upload", dirs): samples = run_parallel("upload_samples", samples) for sample in samples: run_parallel("upload_samples_project", [sample]) return samples
def run(self, config, run_info_yaml, parallel, dirs, samples): # causes a circular import at the top level from bcbio.srna.group import report as srna_report with prun.start(_wres(parallel, ["picard", "cutadapt"]), samples, config, dirs, "trimming") as run_parallel: with profile.report("organize samples", dirs): samples = run_parallel("organize_samples", [[dirs, config, run_info_yaml, [x[0]["description"] for x in samples]]]) with profile.report("adapter trimming", dirs): samples = run_parallel("prepare_sample", samples) samples = run_parallel("trim_srna_sample", samples) with prun.start(_wres(parallel, ["aligner", "picard", "samtools"], ensure_mem={"bowtie": 8, "bowtie2": 8, "star": 2}), [samples[0]], config, dirs, "alignment") as run_parallel: with profile.report("prepare", dirs): samples = run_parallel("seqcluster_prepare", [samples]) with profile.report("alignment", dirs): samples = run_parallel("srna_alignment", [samples]) with prun.start(_wres(parallel, ["picard", "miraligner"]), samples, config, dirs, "annotation") as run_parallel: with profile.report("small RNA annotation", dirs): samples = run_parallel("srna_annotation", samples) with prun.start(_wres(parallel, ["seqcluster"], ensure_mem={"seqcluster": 8}), [samples[0]], config, dirs, "cluster") as run_parallel: with profile.report("cluster", dirs): samples = run_parallel("seqcluster_cluster", [samples]) with prun.start(_wres(parallel, ["picard", "fastqc"]), samples, config, dirs, "qc") as run_parallel: with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) with profile.report("report", dirs): srna_report(samples) with profile.report("upload", dirs): samples = run_parallel("upload_samples", samples) for sample in samples: run_parallel("upload_samples_project", [sample]) return samples
def run(self, config, config_file, run_parallel, parallel, dirs, lane_items): raise NotImplementedError("`variant` processing is deprecated: please use `variant2`" "The next version will alias variant to the new variant2 pipeline") lane_items = run_parallel("trim_lane", lane_items) align_items = run_parallel("process_alignment", lane_items) # process samples, potentially multiplexed across multiple lanes samples = organize_samples(align_items, dirs, config_file) samples = run_parallel("merge_sample", samples) samples = run_parallel("prep_recal", samples) samples = recalibrate.parallel_write_recal_bam(samples, run_parallel) samples = parallel_realign_sample(samples, run_parallel) samples = parallel_variantcall(samples, run_parallel) samples = run_parallel("postprocess_variants", samples) samples = combine_multiple_callers(samples) samples = ensemble.combine_calls_parallel(samples, run_parallel) samples = run_parallel("detect_sv", samples) samples = qcsummary.generate_parallel(samples, run_parallel) run_parallel("generate_bigwig", samples, {"programs": ["ucsc_bigwig"]}) return samples
def rnaseqpipeline(config, run_info_yaml, parallel, dirs, samples): samples = rnaseq_prep_samples(config, run_info_yaml, parallel, dirs, samples) with prun.start( _wres(parallel, ["aligner", "picard", "samtools"], ensure_mem={ "tophat": 10, "tophat2": 10, "star": 2, "hisat2": 8 }), samples, config, dirs, "alignment", multiplier=alignprep.parallel_multiplier(samples)) as run_parallel: with profile.report("alignment", dirs): samples = run_parallel("disambiguate_split", [samples]) samples = run_parallel("process_alignment", samples) with prun.start(_wres(parallel, ["samtools", "cufflinks"]), samples, config, dirs, "rnaseqcount") as run_parallel: with profile.report("disambiguation", dirs): samples = disambiguate.resolve(samples, run_parallel) with profile.report("transcript assembly", dirs): samples = rnaseq.assemble_transcripts(run_parallel, samples) with profile.report("estimate expression (threaded)", dirs): samples = rnaseq.quantitate_expression_parallel( samples, run_parallel) with prun.start(_wres(parallel, ["dexseq", "express"]), samples, config, dirs, "rnaseqcount-singlethread", max_multicore=1) as run_parallel: with profile.report("estimate expression (single threaded)", dirs): samples = rnaseq.quantitate_expression_noparallel( samples, run_parallel) samples = rnaseq.combine_files(samples) with prun.start(_wres(parallel, ["gatk", "vardict"]), samples, config, dirs, "rnaseq-variation") as run_parallel: with profile.report("RNA-seq variant calling", dirs): samples = rnaseq.rnaseq_variant_calling(samples, run_parallel) with prun.start( _wres( parallel, ["samtools", "fastqc", "qualimap", "kraken", "gatk", "preseq"], ensure_mem={"qualimap": 4}), samples, config, dirs, "qc") as run_parallel: with profile.report("quality control", dirs): samples = qcsummary.generate_parallel(samples, run_parallel) with profile.report("create SummarizedExperiment object", dirs): samples = rnaseq.load_summarizedexperiment(samples) with profile.report("upload", dirs): samples = run_parallel("upload_samples", samples) for sample in samples: run_parallel("upload_samples_project", [sample]) with profile.report("bcbioRNAseq loading", dirs): tools_on = dd.get_in_samples(samples, dd.get_tools_on) bcbiornaseq_on = tools_on and "bcbiornaseq" in tools_on if bcbiornaseq_on: if len(samples) < 3: logger.warn( "bcbioRNASeq needs at least three samples total, skipping." ) elif len(samples) > 100: logger.warn("Over 100 samples, skipping bcbioRNASeq.") else: run_parallel("run_bcbiornaseqload", [sample]) logger.info("Timing: finished") return samples
def variant2pipeline(config, run_info_yaml, parallel, dirs, samples): ## Alignment and preparation requiring the entire input file (multicore cluster) with prun.start( _wres( parallel, ["aligner", "samtools", "sambamba"], (["reference", "fasta"], ["reference", "aligner"], ["files"])), samples, config, dirs, "multicore", multiplier=alignprep.parallel_multiplier(samples)) as run_parallel: with profile.report("organize samples", dirs): samples = run_parallel("organize_samples", [[ dirs, config, run_info_yaml, [x[0]["description"] for x in samples] ]]) ww = initialize_watcher(samples) with profile.report("alignment preparation", dirs): samples = run_parallel("prep_align_inputs", samples) ww.report("prep_align_inputs", samples) samples = run_parallel("disambiguate_split", [samples]) with profile.report("alignment", dirs): samples = run_parallel("process_alignment", samples) ww.report("process_alignment", samples) samples = disambiguate.resolve(samples, run_parallel) samples = alignprep.merge_split_alignments(samples, run_parallel) with profile.report("callable regions", dirs): samples = run_parallel("prep_samples", [samples]) ww.report("prep_samples", samples) samples = run_parallel("postprocess_alignment", samples) ww.report("postprocess_alignment", samples) samples = run_parallel("combine_sample_regions", [samples]) samples = region.clean_sample_data(samples) ww.report("combine_sample_regions", samples) with profile.report("hla typing", dirs): samples = hla.run(samples, run_parallel) ww.report("call_hla", samples) ## Variant calling on sub-regions of the input file (full cluster) with prun.start(_wres(parallel, ["gatk", "picard", "variantcaller"]), samples, config, dirs, "full", multiplier=region.get_max_counts(samples), max_multicore=1) as run_parallel: with profile.report("alignment post-processing", dirs): samples = region.parallel_prep_region(samples, run_parallel) with profile.report("variant calling", dirs): samples = genotype.parallel_variantcall_region( samples, run_parallel) ## Finalize variants, BAMs and population databases (per-sample multicore cluster) with prun.start(_wres(parallel, [ "gatk", "gatk-vqsr", "snpeff", "bcbio_variation", "gemini", "samtools", "fastqc", "sambamba", "bcbio-variation-recall", "qsignature", "svcaller" ]), samples, config, dirs, "multicore2", multiplier=structural.parallel_multiplier( samples)) as run_parallel: with profile.report("joint squaring off/backfilling", dirs): samples = joint.square_off(samples, run_parallel) with profile.report("variant post-processing", dirs): samples = run_parallel("postprocess_variants", samples) samples = run_parallel("split_variants_by_sample", samples) with profile.report("prepped BAM merging", dirs): samples = region.delayed_bamprep_merge(samples, run_parallel) with profile.report("validation", dirs): samples = run_parallel("compare_to_rm", samples) samples = genotype.combine_multiple_callers(samples) with profile.report("ensemble calling", dirs): samples = ensemble.combine_calls_parallel(samples, run_parallel) with profile.report("validation summary", dirs): samples = validate.summarize_grading(samples) with profile.report("structural variation precall", dirs): samples = structural.run(samples, run_parallel, "precall") with profile.report("structural variation", dirs): samples = structural.run(samples, run_parallel, "initial") with profile.report("structural variation", dirs): samples = structural.run(samples, run_parallel, "standard") with profile.report("structural variation ensemble", dirs): samples = structural.run(samples, run_parallel, "ensemble") with profile.report("structural variation validation", dirs): samples = run_parallel("validate_sv", samples) with profile.report("heterogeneity", dirs): samples = heterogeneity.run(samples, run_parallel) with profile.report("population database", dirs): samples = population.prep_db_parallel(samples, run_parallel) with profile.report("quality control", dirs): ww.report("pre_qc", samples) samples = qcsummary.generate_parallel(samples, run_parallel) ww.report("qc_summary", samples) with profile.report("archive", dirs): samples = archive.compress(samples, run_parallel) with profile.report("upload", dirs): samples = run_parallel("upload_samples", samples) for sample in samples: run_parallel("upload_samples_project", [sample]) logger.info("Timing: finished") return samples
def variant2pipeline(config, run_info_yaml, parallel, dirs, samples): ## Alignment and preparation requiring the entire input file (multicore cluster) with prun.start(_wres(parallel, ["aligner", "samtools", "sambamba"], (["reference", "fasta"], ["reference", "aligner"], ["files"])), samples, config, dirs, "multicore", multiplier=alignprep.parallel_multiplier(samples)) as run_parallel: with profile.report("organize samples", dirs): samples = run_parallel("organize_samples", [[dirs, config, run_info_yaml, [x[0]["description"] for x in samples]]]) ww = WorldWatcher(dirs["work"], is_on=any([dd.get_cwl_reporting(d[0]) for d in samples])) ww.initialize(samples) with profile.report("alignment preparation", dirs): samples = run_parallel("prep_align_inputs", samples) ww.report("prep_align_inputs", samples) samples = run_parallel("disambiguate_split", [samples]) with profile.report("alignment", dirs): samples = run_parallel("process_alignment", samples) ww.report("process_alignment", samples) samples = disambiguate.resolve(samples, run_parallel) samples = alignprep.merge_split_alignments(samples, run_parallel) with profile.report("callable regions", dirs): samples = run_parallel("prep_samples", [samples]) ww.report("prep_samples", samples) samples = run_parallel("postprocess_alignment", samples) ww.report("postprocess_alignment", samples) samples = run_parallel("combine_sample_regions", [samples]) samples = region.clean_sample_data(samples) ww.report("combine_sample_regions", samples) with profile.report("structural variation initial", dirs): samples = structural.run(samples, run_parallel, "initial") ww.report("sv_initial", samples) with profile.report("hla typing", dirs): samples = hla.run(samples, run_parallel) ww.report("call_hla", samples) ## Variant calling on sub-regions of the input file (full cluster) with prun.start(_wres(parallel, ["gatk", "picard", "variantcaller"]), samples, config, dirs, "full", multiplier=region.get_max_counts(samples), max_multicore=1) as run_parallel: with profile.report("alignment post-processing", dirs): samples = region.parallel_prep_region(samples, run_parallel) with profile.report("variant calling", dirs): samples = genotype.parallel_variantcall_region(samples, run_parallel) ## Finalize variants, BAMs and population databases (per-sample multicore cluster) with prun.start(_wres(parallel, ["gatk", "gatk-vqsr", "snpeff", "bcbio_variation", "gemini", "samtools", "fastqc", "bamtools", "bcbio-variation-recall", "qsignature", "svcaller"]), samples, config, dirs, "multicore2", multiplier=structural.parallel_multiplier(samples)) as run_parallel: with profile.report("joint squaring off/backfilling", dirs): samples = joint.square_off(samples, run_parallel) with profile.report("variant post-processing", dirs): samples = run_parallel("postprocess_variants", samples) samples = run_parallel("split_variants_by_sample", samples) with profile.report("prepped BAM merging", dirs): samples = region.delayed_bamprep_merge(samples, run_parallel) with profile.report("validation", dirs): samples = run_parallel("compare_to_rm", samples) samples = genotype.combine_multiple_callers(samples) with profile.report("ensemble calling", dirs): samples = ensemble.combine_calls_parallel(samples, run_parallel) with profile.report("validation summary", dirs): samples = validate.summarize_grading(samples) with profile.report("structural variation final", dirs): samples = structural.run(samples, run_parallel, "standard") with profile.report("structural variation ensemble", dirs): samples = structural.run(samples, run_parallel, "ensemble") with profile.report("structural variation validation", dirs): samples = run_parallel("validate_sv", samples) with profile.report("heterogeneity", dirs): samples = heterogeneity.run(samples, run_parallel) with profile.report("population database", dirs): samples = population.prep_db_parallel(samples, run_parallel) with profile.report("quality control", dirs): ww.report("pre_qc", samples) samples = qcsummary.generate_parallel(samples, run_parallel) ww.report("qc_summary", samples) with profile.report("archive", dirs): samples = archive.compress(samples, run_parallel) with profile.report("upload", dirs): samples = run_parallel("upload_samples", samples) for sample in samples: run_parallel("upload_samples_project", [sample]) logger.info("Timing: finished") return samples