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, 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 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"]), 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 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)
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 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 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,
"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 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
