def run_mutect(job, tumor_bam, normal_bam, univ_options, mutect_options):
"""
Spawn a MuTect job for each chromosome on the DNA bams.
:param dict tumor_bam: Dict of bam and bai for tumor DNA-Seq
:param dict normal_bam: Dict of bam and bai for normal DNA-Seq
:param dict univ_options: Dict of universal options used by almost all tools
:param dict mutect_options: Options specific to MuTect
:return: Dict of results from running MuTect on every chromosome
perchrom_mutect:
|- 'chr1': fsID
|- 'chr2' fsID
|
|-...
|
+- 'chrM': fsID
:rtype: dict
"""
# Get a list of chromosomes to handle
if mutect_options['chromosomes']:
chromosomes = mutect_options['chromosomes']
else:
chromosomes = sample_chromosomes(job, mutect_options['genome_fai'])
perchrom_mutect = defaultdict()
for chrom in chromosomes:
perchrom_mutect[chrom] = job.addChildJobFn(
run_mutect_perchrom, tumor_bam, normal_bam, univ_options, mutect_options, chrom,
memory='6G', disk=PromisedRequirement(mutect_disk,
tumor_bam['tumor_dna_fix_pg_sorted.bam'],
normal_bam['normal_dna_fix_pg_sorted.bam'],
mutect_options['genome_fasta'],
mutect_options['dbsnp_vcf'],
mutect_options['cosmic_vcf'])).rv()
return perchrom_mutect
def run_strelka(job,
tumor_bam,
normal_bam,
univ_options,
strelka_options,
split=True):
"""
Run the strelka subgraph on the DNA bams. Optionally split the results into per-chromosome
vcfs.
:param dict tumor_bam: Dict of bam and bai for tumor DNA-Seq
:param dict normal_bam: Dict of bam and bai for normal DNA-Seq
:param dict univ_options: Dict of universal options used by almost all tools
:param dict strelka_options: Options specific to strelka
:param bool split: Should the results be split into perchrom vcfs?
:return: Either the fsID to the genome-level vcf or a dict of results from running strelka
on every chromosome
perchrom_strelka:
|- 'chr1':
| |-'snvs': fsID
| +-'indels': fsID
|- 'chr2':
| |-'snvs': fsID
| +-'indels': fsID
|-...
|
+- 'chrM':
|-'snvs': fsID
+-'indels': fsID
:rtype: toil.fileStore.FileID|dict
"""
if strelka_options['chromosomes']:
chromosomes = strelka_options['chromosomes']
else:
chromosomes = sample_chromosomes(job, strelka_options['genome_fai'])
num_cores = min(len(chromosomes), univ_options['max_cores'])
strelka = job.wrapJobFn(run_strelka_full,
tumor_bam,
normal_bam,
univ_options,
strelka_options,
disk=PromisedRequirement(
strelka_disk,
tumor_bam['tumor_dna_fix_pg_sorted.bam'],
normal_bam['normal_dna_fix_pg_sorted.bam'],
strelka_options['genome_fasta']),
memory='6G',
cores=num_cores)
job.addChild(strelka)
if split:
unmerge_strelka = job.wrapJobFn(wrap_unmerge, strelka.rv(),
chromosomes, strelka_options,
univ_options).encapsulate()
strelka.addChild(unmerge_strelka)
return unmerge_strelka.rv()
else:
return strelka.rv()
def run_strelka(job, tumor_bam, normal_bam, univ_options, strelka_options, split=True):
"""
This module will spawn a strelka job for each chromosome on the DNA bams.
ARGUMENTS
1. tumor_bam: Dict of input tumor WGS/WSQ bam + bai
tumor_bam
|- 'tumor_fix_pg_sorted.bam': <JSid>
+- 'tumor_fix_pg_sorted.bam.bai': <JSid>
2. normal_bam: Dict of input normal WGS/WSQ bam + bai
normal_bam
|- 'normal_fix_pg_sorted.bam': <JSid>
+- 'normal_fix_pg_sorted.bam.bai': <JSid>
3. univ_options: Dict of universal arguments used by almost all tools
univ_options
+- 'dockerhub': <dockerhub to use>
4. strelka_options: Dict of parameters specific to strelka
strelka_options
|- 'dbsnp_vcf': <JSid for dnsnp vcf file>
|- 'dbsnp_idx': <JSid for dnsnp vcf index file>
|- 'cosmic_vcf': <JSid for cosmic vcf file>
|- 'cosmic_idx': <JSid for cosmic vcf index file>
|- 'genome_fasta': <JSid for genome fasta file>
+- 'genome_dict': <JSid for genome fasta dict file>
+- 'genome_fai': <JSid for genome fasta index file>
RETURN VALUES
1. perchrom_strelka: Dict of results of strelka per chromosome
perchrom_strelka
|- 'chr1'
| +- 'strelka_chr1.vcf': <JSid>
| +- 'strelka_chr1.out': <JSid>
|- 'chr2'
| |- 'strelka_chr2.vcf': <JSid>
| +- 'strelka_chr2.out': <JSid>
etc...
This module corresponds to node 11 on the tree
"""
chromosomes = sample_chromosomes(job, strelka_options['genome_fai'])
num_cores = min(len(chromosomes), univ_options['max_cores'])
strelka = job.wrapJobFn(run_strelka_full, tumor_bam, normal_bam, univ_options,
strelka_options,
disk=PromisedRequirement(strelka_disk,
tumor_bam['tumor_dna_fix_pg_sorted.bam'],
normal_bam['normal_dna_fix_pg_sorted.bam'],
strelka_options['genome_fasta']),
memory='6G',
cores=num_cores)
job.addChild(strelka)
if split:
unmerge_strelka = job.wrapJobFn(wrap_unmerge, strelka.rv(), strelka_options, univ_options
).encapsulate()
strelka.addChild(unmerge_strelka)
return unmerge_strelka.rv()
else:
return strelka.rv()
def run_somaticsniper(job, tumor_bam, normal_bam, univ_options, somaticsniper_options, split=True):
"""
Run the SomaticSniper subgraph on the DNA bams. Optionally split the results into
per-chromosome vcfs.
:param dict tumor_bam: Dict of bam and bai for tumor DNA-Seq
:param dict normal_bam: Dict of bam and bai for normal DNA-Seq
:param dict univ_options: Dict of universal options used by almost all tools
:param dict somaticsniper_options: Options specific to SomaticSniper
:param bool split: Should the results be split into perchrom vcfs?
:return: Either the fsID to the genome-level vcf or a dict of results from running SomaticSniper
on every chromosome
perchrom_somaticsniper:
|- 'chr1': fsID
|- 'chr2' fsID
|
|-...
|
+- 'chrM': fsID
:rtype: toil.fileStore.FileID|dict
"""
# Get a list of chromosomes to handle
if somaticsniper_options['chromosomes']:
chromosomes = somaticsniper_options['chromosomes']
else:
chromosomes = sample_chromosomes(job, somaticsniper_options['genome_fai'])
perchrom_somaticsniper = defaultdict()
snipe = job.wrapJobFn(run_somaticsniper_full, tumor_bam, normal_bam, univ_options,
somaticsniper_options,
disk=PromisedRequirement(sniper_disk,
tumor_bam['tumor_dna_fix_pg_sorted.bam'],
normal_bam['normal_dna_fix_pg_sorted.bam'],
somaticsniper_options['genome_fasta']),
memory='6G')
pileup = job.wrapJobFn(run_pileup, tumor_bam, univ_options, somaticsniper_options,
disk=PromisedRequirement(pileup_disk,
tumor_bam['tumor_dna_fix_pg_sorted.bam'],
somaticsniper_options['genome_fasta']),
memory='6G')
filtersnipes = job.wrapJobFn(filter_somaticsniper, tumor_bam, snipe.rv(), pileup.rv(),
univ_options, somaticsniper_options,
disk=PromisedRequirement(sniper_filter_disk,
tumor_bam['tumor_dna_fix_pg_sorted.bam'],
somaticsniper_options['genome_fasta']),
memory='6G')
job.addChild(snipe)
job.addChild(pileup)
snipe.addChild(filtersnipes)
pileup.addChild(filtersnipes)
if split:
unmerge_snipes = job.wrapJobFn(unmerge, filtersnipes.rv(), 'somaticsniper', chromosomes,
somaticsniper_options, univ_options)
filtersnipes.addChild(unmerge_snipes)
return unmerge_snipes.rv()
else:
return filtersnipes.rv()
def run_mutect(job, tumor_bam, normal_bam, univ_options, mutect_options):
"""
This module will spawn a mutect job for each chromosome on the DNA bams.
ARGUMENTS
1. tumor_bam: Dict of input tumor WGS/WSQ bam + bai
tumor_bam
|- 'tumor_fix_pg_sorted.bam': <JSid>
+- 'tumor_fix_pg_sorted.bam.bai': <JSid>
2. normal_bam: Dict of input normal WGS/WSQ bam + bai
normal_bam
|- 'normal_fix_pg_sorted.bam': <JSid>
+- 'normal_fix_pg_sorted.bam.bai': <JSid>
3. univ_options: Dict of universal arguments used by almost all tools
univ_options
+- 'dockerhub': <dockerhub to use>
4. mutect_options: Dict of parameters specific to mutect
mutect_options
|- 'dbsnp_vcf': <JSid for dnsnp vcf file>
|- 'dbsnp_idx': <JSid for dnsnp vcf index file>
|- 'cosmic_vcf': <JSid for cosmic vcf file>
|- 'cosmic_idx': <JSid for cosmic vcf index file>
|- 'genome_fasta': <JSid for genome fasta file>
+- 'genome_dict': <JSid for genome fasta dict file>
+- 'genome_fai': <JSid for genome fasta index file>
RETURN VALUES
1. perchrom_mutect: Dict of results of mutect per chromosome
perchrom_mutect
|- 'chr1'
| +- 'mutect_chr1.vcf': <JSid>
| +- 'mutect_chr1.out': <JSid>
|- 'chr2'
| |- 'mutect_chr2.vcf': <JSid>
| +- 'mutect_chr2.out': <JSid>
etc...
This module corresponds to node 11 on the tree
"""
# Get a list of chromosomes to handle
chromosomes = sample_chromosomes(job, mutect_options['genome_fai'])
perchrom_mutect = defaultdict()
for chrom in chromosomes:
perchrom_mutect[chrom] = job.addChildJobFn(
run_mutect_perchrom,
tumor_bam,
normal_bam,
univ_options,
mutect_options,
chrom,
memory='6G',
disk=PromisedRequirement(
mutect_disk, tumor_bam['tumor_dna_fix_pg_sorted.bam'],
normal_bam['normal_dna_fix_pg_sorted.bam'],
mutect_options['genome_fasta'], mutect_options['dbsnp_vcf'],
mutect_options['cosmic_vcf'])).rv()
return perchrom_mutect
def run_radia(job, rna_bam, tumor_bam, normal_bam, univ_options, radia_options):
"""
This module will spawn a radia job for each chromosome, on the RNA and DNA.
ARGUMENTS
1. rna_bam: Dict of input STAR bams
rna_bam
|- 'rnaAligned.sortedByCoord.out.bam': REFER run_star()
|- 'rna_fix_pg_sorted.bam': <JSid>
+- 'rna_fix_pg_sorted.bam.bai': <JSid>
2. tumor_bam: Dict of input tumor WGS/WSQ bam + bai
tumor_bam
|- 'tumor_fix_pg_sorted.bam': <JSid>
+- 'tumor_fix_pg_sorted.bam.bai': <JSid>
3. normal_bam: Dict of input normal WGS/WSQ bam + bai
normal_bam
|- 'normal_fix_pg_sorted.bam': <JSid>
+- 'normal_fix_pg_sorted.bam.bai': <JSid>
4. univ_options: Dict of universal arguments used by almost all tools
univ_options
+- 'dockerhub': <dockerhub to use>
5. radia_options: Dict of parameters specific to radia
radia_options
|- 'genome_fasta': <JSid for genome fasta file>
+- 'genome_fai': <JSid for genome fai file>
RETURN VALUES
1. perchrom_radia: Dict of results of radia per chromosome
perchrom_radia
|- 'chr1'
| +- 'radia_filtered_chr1.vcf': <JSid>
|- 'chr2'
| +- 'radia_filtered_chr2.vcf': <JSid>
etc...
This module corresponds to node 11 on the tree
"""
job.fileStore.logToMaster('Running spawn_radia on %s' % univ_options['patient'])
rna_bam_key = 'rnaAligned.sortedByCoord.out.bam' # to reduce next line size
bams = {'tumor_rna': rna_bam[rna_bam_key]['rna_fix_pg_sorted.bam'],
'tumor_rnai': rna_bam[rna_bam_key]['rna_fix_pg_sorted.bam.bai'],
'tumor_dna': tumor_bam['tumor_dna_fix_pg_sorted.bam'],
'tumor_dnai': tumor_bam['tumor_dna_fix_pg_sorted.bam.bai'],
'normal_dna': normal_bam['normal_dna_fix_pg_sorted.bam'],
'normal_dnai': normal_bam['normal_dna_fix_pg_sorted.bam.bai']}
# Get a list of chromosomes to process
chromosomes = sample_chromosomes(job, radia_options['genome_fai'])
perchrom_radia = defaultdict()
for chrom in chromosomes:
radia = job.addChildJobFn(run_radia_perchrom, bams, univ_options, radia_options, chrom,
disk='60G', memory='6G')
filter_radia = radia.addChildJobFn(run_filter_radia, bams, radia.rv(), univ_options,
radia_options, chrom, disk='60G', memory='6G')
perchrom_radia[chrom] = filter_radia.rv()
return perchrom_radia
def run_muse(job, tumor_bam, normal_bam, univ_options, muse_options):
"""
This module will spawn a muse job for each chromosome on the DNA bams.
ARGUMENTS
1. tumor_bam: Dict of input tumor WGS/WSQ bam + bai
tumor_bam
|- 'tumor_fix_pg_sorted.bam': <JSid>
+- 'tumor_fix_pg_sorted.bam.bai': <JSid>
2. normal_bam: Dict of input normal WGS/WSQ bam + bai
normal_bam
|- 'normal_fix_pg_sorted.bam': <JSid>
+- 'normal_fix_pg_sorted.bam.bai': <JSid>
3. univ_options: Dict of universal arguments used by almost all tools
univ_options
+- 'dockerhub': <dockerhub to use>
4. muse_options: Dict of parameters specific to muse
muse_options
|- 'dbsnp_vcf': <JSid for dnsnp vcf file>
|- 'dbsnp_idx': <JSid for dnsnp vcf index file>
|- 'cosmic_vcf': <JSid for cosmic vcf file>
|- 'cosmic_idx': <JSid for cosmic vcf index file>
|- 'genome_fasta': <JSid for genome fasta file>
+- 'genome_dict': <JSid for genome fasta dict file>
+- 'genome_fai': <JSid for genome fasta index file>
RETURN VALUES
1. perchrom_muse: Dict of results of muse per chromosome
perchrom_muse
|- 'chr1'
| +- <JSid for muse_chr1.vcf>
|- 'chr2'
| +- <JSid for muse_chr2.vcf>
etc...
This module corresponds to node 11 on the tree
"""
# Get a list of chromosomes to handle
chromosomes = sample_chromosomes(job, muse_options['genome_fai'])
perchrom_muse = defaultdict()
for chrom in chromosomes:
call = job.addChildJobFn(run_muse_perchrom, tumor_bam, normal_bam, univ_options,
muse_options, chrom,
disk=PromisedRequirement(muse_disk,
tumor_bam['tumor_dna_fix_pg_sorted.bam'],
normal_bam['normal_dna_fix_pg_sorted.bam'],
muse_options['genome_fasta']),
memory='6G')
sump = call.addChildJobFn(run_muse_sump_perchrom, call.rv(), univ_options, muse_options,
chrom,
disk=PromisedRequirement(muse_sump_disk,
muse_options['dbsnp_vcf']),
memory='6G')
perchrom_muse[chrom] = sump.rv()
return perchrom_muse
def run_mutect(job, tumor_bam, normal_bam, univ_options, mutect_options):
"""
This module will spawn a mutect job for each chromosome on the DNA bams.
ARGUMENTS
1. tumor_bam: Dict of input tumor WGS/WSQ bam + bai
tumor_bam
|- 'tumor_fix_pg_sorted.bam': <JSid>
+- 'tumor_fix_pg_sorted.bam.bai': <JSid>
2. normal_bam: Dict of input normal WGS/WSQ bam + bai
normal_bam
|- 'normal_fix_pg_sorted.bam': <JSid>
+- 'normal_fix_pg_sorted.bam.bai': <JSid>
3. univ_options: Dict of universal arguments used by almost all tools
univ_options
+- 'dockerhub': <dockerhub to use>
4. mutect_options: Dict of parameters specific to mutect
mutect_options
|- 'dbsnp_vcf': <JSid for dnsnp vcf file>
|- 'dbsnp_idx': <JSid for dnsnp vcf index file>
|- 'cosmic_vcf': <JSid for cosmic vcf file>
|- 'cosmic_idx': <JSid for cosmic vcf index file>
|- 'genome_fasta': <JSid for genome fasta file>
+- 'genome_dict': <JSid for genome fasta dict file>
+- 'genome_fai': <JSid for genome fasta index file>
RETURN VALUES
1. perchrom_mutect: Dict of results of mutect per chromosome
perchrom_mutect
|- 'chr1'
| +- 'mutect_chr1.vcf': <JSid>
| +- 'mutect_chr1.out': <JSid>
|- 'chr2'
| |- 'mutect_chr2.vcf': <JSid>
| +- 'mutect_chr2.out': <JSid>
etc...
This module corresponds to node 11 on the tree
"""
# Get a list of chromosomes to handle
chromosomes = sample_chromosomes(job, mutect_options['genome_fai'])
perchrom_mutect = defaultdict()
for chrom in chromosomes:
perchrom_mutect[chrom] = job.addChildJobFn(run_mutect_perchrom, tumor_bam, normal_bam,
univ_options, mutect_options, chrom, disk='60G',
memory='6G').rv()
return perchrom_mutect
def run_radia(job, rna_bam, tumor_bam, normal_bam, univ_options,
radia_options):
"""
Spawn a RADIA job for each chromosome on the input bam trios.
:param dict rna_bam: Dict of bam and bai for tumor DNA-Seq. It can be one of two formats
rna_bam: # Just the genomic bam and bai
|- 'rna_genome_sorted.bam': fsID
+- 'rna_genome_sorted.bam.bai': fsID
OR
rna_bam: # The output from run_star
|- 'rna_transcriptome.bam': fsID
|- 'rna_genome': # Only this part will be used
|- 'rna_genome_sorted.bam': fsID
+- 'rna_genome_sorted.bam.bai': fsID
:param dict tumor_bam: Dict of bam and bai for tumor DNA-Seq
:param dict normal_bam: Dict of bam and bai for normal DNA-Seq
:param dict univ_options: Dict of universal options used by almost all tools
:param dict radia_options: Options specific to RADIA
:return: Dict of results from running RADIA on every chromosome
perchrom_radia:
|- 'chr1': fsID
|- 'chr2' fsID
|
|-...
|
+- 'chrM': fsID
:rtype: dict
"""
if 'rna_genome' in rna_bam.keys():
rna_bam = rna_bam['rna_genome']
elif set(rna_bam.keys()) == {
'rna_genome_sorted.bam', 'rna_genome_sorted.bam.bai'
}:
pass
else:
raise RuntimeError(
'An improperly formatted dict was passed to rna_bam.')
bams = {
'tumor_rna': rna_bam['rna_genome_sorted.bam'],
'tumor_rnai': rna_bam['rna_genome_sorted.bam.bai'],
'tumor_dna': tumor_bam['tumor_dna_fix_pg_sorted.bam'],
'tumor_dnai': tumor_bam['tumor_dna_fix_pg_sorted.bam.bai'],
'normal_dna': normal_bam['normal_dna_fix_pg_sorted.bam'],
'normal_dnai': normal_bam['normal_dna_fix_pg_sorted.bam.bai']
}
# Get a list of chromosomes to process
if radia_options['chromosomes']:
chromosomes = radia_options['chromosomes']
else:
chromosomes = sample_chromosomes(job, radia_options['genome_fai'])
perchrom_radia = defaultdict()
for chrom in chromosomes:
radia = job.addChildJobFn(
run_radia_perchrom,
bams,
univ_options,
radia_options,
chrom,
memory='6G',
disk=PromisedRequirement(
radia_disk, tumor_bam['tumor_dna_fix_pg_sorted.bam'],
normal_bam['normal_dna_fix_pg_sorted.bam'],
rna_bam['rna_genome_sorted.bam'],
radia_options['genome_fasta']))
filter_radia = radia.addChildJobFn(
run_filter_radia,
bams,
radia.rv(),
univ_options,
radia_options,
chrom,
memory='6G',
disk=PromisedRequirement(
radia_disk, tumor_bam['tumor_dna_fix_pg_sorted.bam'],
normal_bam['normal_dna_fix_pg_sorted.bam'],
rna_bam['rna_genome_sorted.bam'],
radia_options['genome_fasta']))
perchrom_radia[chrom] = filter_radia.rv()
job.fileStore.logToMaster('Ran spawn_radia on %s successfully' %
univ_options['patient'])
return perchrom_radia
def run_strelka(job,
tumor_bam,
normal_bam,
univ_options,
strelka_options,
split=True):
"""
This module will spawn a strelka job for each chromosome on the DNA bams.
ARGUMENTS
1. tumor_bam: Dict of input tumor WGS/WSQ bam + bai
tumor_bam
|- 'tumor_fix_pg_sorted.bam': <JSid>
+- 'tumor_fix_pg_sorted.bam.bai': <JSid>
2. normal_bam: Dict of input normal WGS/WSQ bam + bai
normal_bam
|- 'normal_fix_pg_sorted.bam': <JSid>
+- 'normal_fix_pg_sorted.bam.bai': <JSid>
3. univ_options: Dict of universal arguments used by almost all tools
univ_options
+- 'dockerhub': <dockerhub to use>
4. strelka_options: Dict of parameters specific to strelka
strelka_options
|- 'dbsnp_vcf': <JSid for dnsnp vcf file>
|- 'dbsnp_idx': <JSid for dnsnp vcf index file>
|- 'cosmic_vcf': <JSid for cosmic vcf file>
|- 'cosmic_idx': <JSid for cosmic vcf index file>
|- 'genome_fasta': <JSid for genome fasta file>
+- 'genome_dict': <JSid for genome fasta dict file>
+- 'genome_fai': <JSid for genome fasta index file>
RETURN VALUES
1. perchrom_strelka: Dict of results of strelka per chromosome
perchrom_strelka
|- 'chr1'
| +- 'strelka_chr1.vcf': <JSid>
| +- 'strelka_chr1.out': <JSid>
|- 'chr2'
| |- 'strelka_chr2.vcf': <JSid>
| +- 'strelka_chr2.out': <JSid>
etc...
This module corresponds to node 11 on the tree
"""
chromosomes = sample_chromosomes(job, strelka_options['genome_fai'])
num_cores = min(len(chromosomes), univ_options['max_cores'])
strelka = job.wrapJobFn(run_strelka_full,
tumor_bam,
normal_bam,
univ_options,
strelka_options,
disk=PromisedRequirement(
strelka_disk,
tumor_bam['tumor_dna_fix_pg_sorted.bam'],
normal_bam['normal_dna_fix_pg_sorted.bam'],
strelka_options['genome_fasta']),
memory='6G',
cores=num_cores)
job.addChild(strelka)
if split:
unmerge_strelka = job.wrapJobFn(wrap_unmerge, strelka.rv(),
strelka_options,
univ_options).encapsulate()
strelka.addChild(unmerge_strelka)
return unmerge_strelka.rv()
else:
return strelka.rv()
def run_radia(job, rna_bam, tumor_bam, normal_bam, univ_options,
radia_options):
"""
This module will spawn a radia job for each chromosome, on the RNA and DNA.
ARGUMENTS
1. rna_bam: Dict of input STAR bams
rna_bam
|- 'rnaAligned.sortedByCoord.out.bam': REFER run_star()
|- 'rna_fix_pg_sorted.bam': <JSid>
+- 'rna_fix_pg_sorted.bam.bai': <JSid>
2. tumor_bam: Dict of input tumor WGS/WSQ bam + bai
tumor_bam
|- 'tumor_fix_pg_sorted.bam': <JSid>
+- 'tumor_fix_pg_sorted.bam.bai': <JSid>
3. normal_bam: Dict of input normal WGS/WSQ bam + bai
normal_bam
|- 'normal_fix_pg_sorted.bam': <JSid>
+- 'normal_fix_pg_sorted.bam.bai': <JSid>
4. univ_options: Dict of universal arguments used by almost all tools
univ_options
+- 'dockerhub': <dockerhub to use>
5. radia_options: Dict of parameters specific to radia
radia_options
|- 'genome_fasta': <JSid for genome fasta file>
+- 'genome_fai': <JSid for genome fai file>
RETURN VALUES
1. perchrom_radia: Dict of results of radia per chromosome
perchrom_radia
|- 'chr1'
| +- 'radia_filtered_chr1.vcf': <JSid>
|- 'chr2'
| +- 'radia_filtered_chr2.vcf': <JSid>
etc...
This module corresponds to node 11 on the tree
"""
job.fileStore.logToMaster('Running spawn_radia on %s' %
univ_options['patient'])
rna_bam_key = 'rnaAligned.sortedByCoord.out.bam' # to reduce next line size
bams = {
'tumor_rna': rna_bam[rna_bam_key]['rna_fix_pg_sorted.bam'],
'tumor_rnai': rna_bam[rna_bam_key]['rna_fix_pg_sorted.bam.bai'],
'tumor_dna': tumor_bam['tumor_dna_fix_pg_sorted.bam'],
'tumor_dnai': tumor_bam['tumor_dna_fix_pg_sorted.bam.bai'],
'normal_dna': normal_bam['normal_dna_fix_pg_sorted.bam'],
'normal_dnai': normal_bam['normal_dna_fix_pg_sorted.bam.bai']
}
# Get a list of chromosomes to process
chromosomes = sample_chromosomes(job, radia_options['genome_fai'])
perchrom_radia = defaultdict()
for chrom in chromosomes:
radia = job.addChildJobFn(
run_radia_perchrom,
bams,
univ_options,
radia_options,
chrom,
memory='6G',
disk=PromisedRequirement(
radia_disk, tumor_bam['tumor_dna_fix_pg_sorted.bam'],
normal_bam['normal_dna_fix_pg_sorted.bam'],
rna_bam[rna_bam_key]['rna_fix_pg_sorted.bam'],
radia_options['genome_fasta']))
filter_radia = radia.addChildJobFn(
run_filter_radia,
bams,
radia.rv(),
univ_options,
radia_options,
chrom,
memory='6G',
disk=PromisedRequirement(
radia_disk, tumor_bam['tumor_dna_fix_pg_sorted.bam'],
normal_bam['normal_dna_fix_pg_sorted.bam'],
rna_bam[rna_bam_key]['rna_fix_pg_sorted.bam'],
radia_options['genome_fasta']))
perchrom_radia[chrom] = filter_radia.rv()
return perchrom_radia
def run_somaticsniper(job, tumor_bam, normal_bam, univ_options, somaticsniper_options, split=True):
"""
This module will spawn a somaticsniper job for each chromosome on the DNA bams.
ARGUMENTS
1. tumor_bam: Dict of input tumor WGS/WSQ bam + bai
tumor_bam
|- 'tumor_fix_pg_sorted.bam': <JSid>
+- 'tumor_fix_pg_sorted.bam.bai': <JSid>
2. normal_bam: Dict of input normal WGS/WSQ bam + bai
normal_bam
|- 'normal_fix_pg_sorted.bam': <JSid>
+- 'normal_fix_pg_sorted.bam.bai': <JSid>
3. univ_options: Dict of universal arguments used by almost all tools
univ_options
+- 'dockerhub': <dockerhub to use>
4. somaticsniper_options: Dict of parameters specific to somaticsniper
somaticsniper_options
|- 'dbsnp_vcf': <JSid for dnsnp vcf file>
|- 'dbsnp_idx': <JSid for dnsnp vcf index file>
|- 'cosmic_vcf': <JSid for cosmic vcf file>
|- 'cosmic_idx': <JSid for cosmic vcf index file>
|- 'genome_fasta': <JSid for genome fasta file>
+- 'genome_dict': <JSid for genome fasta dict file>
+- 'genome_fai': <JSid for genome fasta index file>
RETURN VALUES
1. perchrom_somaticsniper: Dict of results of somaticsniper per chromosome
perchrom_somaticsniper
|- 'chr1'
| +- <JSid for somaticsniper_chr1.vcf>
|- 'chr2'
| +- <JSid for somaticsniper_chr2.vcf>
etc...
This module corresponds to node 11 on the tree
"""
# Get a list of chromosomes to handle
chromosomes = sample_chromosomes(job, somaticsniper_options['genome_fai'])
perchrom_somaticsniper = defaultdict()
snipe = job.wrapJobFn(run_somaticsniper_full, tumor_bam, normal_bam, univ_options,
somaticsniper_options,
disk=PromisedRequirement(sniper_disk,
tumor_bam['tumor_dna_fix_pg_sorted.bam'],
normal_bam['normal_dna_fix_pg_sorted.bam'],
somaticsniper_options['genome_fasta']),
memory='6G')
pileup = job.wrapJobFn(run_pileup, tumor_bam, univ_options, somaticsniper_options,
disk=PromisedRequirement(pileup_disk,
tumor_bam['tumor_dna_fix_pg_sorted.bam'],
somaticsniper_options['genome_fasta']),
memory='6G')
filtersnipes = job.wrapJobFn(filter_somaticsniper, tumor_bam, snipe.rv(), pileup.rv(),
univ_options, somaticsniper_options,
disk=PromisedRequirement(sniper_filter_disk,
tumor_bam['tumor_dna_fix_pg_sorted.bam'],
somaticsniper_options['genome_fasta']),
memory='6G')
job.addChild(snipe)
job.addChild(pileup)
snipe.addChild(filtersnipes)
pileup.addChild(filtersnipes)
if split:
unmerge_snipes = job.wrapJobFn(unmerge, filtersnipes.rv(), 'somaticsniper',
somaticsniper_options, univ_options)
filtersnipes.addChild(unmerge_snipes)
return unmerge_snipes.rv()
else:
return filtersnipes.rv()
