def variant_call(ex, aligned_tasks, target_bed_tasks):
"""
Alignments -> Variants
:param Execution execution:
:param list[Task] aligned_tasks:
:param list[Task] target_bed_tasks:
:return:
"""
mkdir('work output', ex.output_dir)
contig_to_targets = {t.tags['contig']: t for t in target_bed_tasks}
hapcall_tasks = [
ex.add_task(gatk.haplotype_caller,
tags=dict(contig=contig, **tags),
parents=parents + [target_bed_task],
out_dir='SM_{sample_name}/work/contigs/{contig}')
for tags, parents in group(aligned_tasks, ['sample_name'])
for contig, target_bed_task in contig_to_targets.items()
]
# combine_gvcf_tasks = many2one(gatk.combine_gvcfs, hapcall_tasks, groupby=['sample_name'], out_dir='SM_{sample_name}')
genotype_task = many2one(gatk.genotype_gvcfs,
hapcall_tasks,
groupby=[],
out_dir='work/variants_raw.vcf')[0]
select_snps_task = ex.add_task(gatk.select_variants,
tags=dict(
in_vcfs=[genotype_task.output_files[0]],
out_vcf='work/snps_raw.vcf',
select_type='SNP'),
parents=genotype_task)
filter_snps_task = ex.add_task(
gatk.variant_filtration,
tags=dict(in_vcfs=[select_snps_task.output_files[0]],
out_vcf='work/snps_filtered.vcf',
filters=[('Qual', 'QUAL < 30'), ('QD', 'QD < 2.0'),
('FS_snp', 'FS > 60.0'), ('MQ', 'MQ < 40.0'),
('MQRankSum', 'MQRankSum < -12.5'),
('ReadPosRankSum', 'ReadPosRankSum < -8.0')]),
parents=select_snps_task)
select_indels_task = ex.add_task(
gatk.select_variants,
tags=dict(in_vcfs=[genotype_task.output_files[0]],
out_vcf='work/indels_raw.vcf',
select_type='INDEL'),
parents=genotype_task)
filter_indels_task = ex.add_task(
gatk.variant_filtration,
tags=dict(in_vcfs=[select_indels_task.output_files[0]],
out_vcf='work/indels_filtered.vcf',
filters=[('Qual', 'QUAL < 30'), ('QD', 'QD < 2.0'),
('FS_indel', 'FS > 200.0'),
('ReadPosRankSum_indel', 'ReadPosRankSum < -2')]),
parents=select_indels_task)
combine_variants_task = ex.add_task(
gatk.combine_variants,
tags=dict(in_vcfs=[
filter_indels_task.tags['out_vcf'],
filter_snps_task.tags['out_vcf']
],
out_vcf='output/variants.vcf',
genotype_merge_option='PRIORITIZE'),
parents=[filter_snps_task, filter_indels_task])
variant_stats_task = ex.add_task(
picard.collect_variant_calling_metrics,
tags=dict(in_vcf=combine_variants_task.tags['out_vcf'],
out_path='output/picard'),
parents=[combine_variants_task])
# Run VQSR?
return combine_variants_task
def variant_call(ex, aligned_tasks, target_bed_tasks):
"""
Alignments -> Variants
:param Execution execution:
:param list[Task] aligned_tasks:
:param list[Task] target_bed_tasks:
:return:
"""
mkdir('work output', ex.output_dir)
contig_to_targets = {t.tags['contig']: t for t in target_bed_tasks}
hapcall_tasks = [ex.add_task(gatk.haplotype_caller,
tags=dict(contig=contig, **tags),
parents=parents + [target_bed_task],
out_dir='SM_{sample_name}/work/contigs/{contig}')
for tags, parents in group(aligned_tasks, ['sample_name'])
for contig, target_bed_task in contig_to_targets.items()]
# combine_gvcf_tasks = many2one(gatk.combine_gvcfs, hapcall_tasks, groupby=['sample_name'], out_dir='SM_{sample_name}')
genotype_tasks = many2one(gatk.genotype_gvcfs, hapcall_tasks, groupby=['contig'], out_dir='work/contigs/{contig}/variants_raw.vcf')
combine_variants_task1 = ex.add_task(gatk.combine_variants,
stage_name='Combine_Raw_Variants',
tags=dict(in_vcfs=[t.output_files[0] for t in genotype_tasks],
out_vcf='work/variants.combined.raw.vcf',
genotype_merge_option='UNSORTED'),
parents=genotype_tasks)
select_snps_task = ex.add_task(gatk.select_variants,
parents=[combine_variants_task1],
tags=dict(select_type='SNP',
in_vcfs=[combine_variants_task1.output_files[0]],
out_vcf='work/variants.raw.snps.vcf'))
filter_snps_task = ex.add_task(gatk.variant_filtration,
tags=dict(in_vcfs=[select_snps_task.output_files[0]],
out_vcf='work/variants.filtered.snps.vcf',
filters=[('Qual', 'QUAL < 30'),
('QD', 'QD < 2.0'),
('FS_snp', 'FS > 60.0'),
('MQ', 'MQ < 40.0'),
('MQRankSum', 'MQRankSum < -12.5'),
('ReadPosRankSum', 'ReadPosRankSum < -8.0')]),
parents=select_snps_task)
select_indels_task = ex.add_task(gatk.select_variants,
parents=[combine_variants_task1],
tags=dict(select_type='INDEL',
in_vcfs=[combine_variants_task1.output_files[0]],
out_vcf='work/variants.raw.indels.vcf'))
filter_indels_task = ex.add_task(gatk.variant_filtration,
tags=dict(in_vcfs=[select_indels_task.output_files[0]],
out_vcf='work/variants.filtered.indels.vcf',
filters=[('Qual', 'QUAL < 30'),
('QD', 'QD < 2.0'),
('FS_indel', 'FS > 200.0'),
('ReadPosRankSum_indel', 'ReadPosRankSum < -2')]),
parents=select_indels_task)
combine_variants_task2 = ex.add_task(gatk.combine_variants,
tags=dict(in_vcfs=[filter_indels_task.tags['out_vcf'], filter_snps_task.tags['out_vcf']],
out_vcf='output/variants.vcf',
genotype_merge_option='PRIORITIZE'),
parents=[filter_snps_task, filter_indels_task])
variant_stats_task = ex.add_task(picard.collect_variant_calling_metrics,
tags=dict(in_vcf=combine_variants_task2.tags['out_vcf'],
out_path='output/picard'),
parents=[combine_variants_task2])
# Run VQSR?
return combine_variants_task2
def align(execution, fastq_tasks, target_bed_tasks):
"""
Reads -> Alignments
:param Execution execution: The Execution instance to create Tasks in
:param list[Task] | [(str, dict)] fastq_tasks: Fastq input (file_path, dict) tuples or Tasks
:param list[Task] target_bed_tasks: target beds to parallelize/split on
:return: Indel Realigned Tasks
"""
# Do we need to split fastqs into smaller pieces?
aligns = []
for tags, fastq_task_group in group(fastq_tasks,
by=[
'sample_name', 'library',
'platform', 'platform_unit',
'rgid', 'chunk'
]):
# trim_task = execution.add_task(fastq.trim_galore,
# tags=dict(**tags),
# parents=fastq_task_group,
# out_dir='SM_{sample_name}/work/RG_{rgid}/CH_{chunk}')
align_task = execution.add_task(
bwa.bwa_mem,
tags=dict(**tags),
parents=fastq_task_group,
out_dir='SM_{sample_name}/work/RG_{rgid}/CH_{chunk}')
aligns.append(align_task)
dedupe = many2one(picard.mark_duplicates,
aligns,
groupby=['sample_name', 'library'],
out_dir='SM_{sample_name}/work/LB_{library}')
# Note, could get slightly improved results by indel realigning over multiple samples, especially if low coverage
# for tags, parents in group(dedupe, ['sample_name']):
# for target_bed_task in target_bed_tasks:
# d = dict(contig=target_bed_task.tags['contig'],
# in_target_bed=target_bed_task.output_files[0],
# **tags)
#
rtc_tasks = [
execution.add_task(gatk.realigner_target_creator,
dict(contig=target_bed_task.tags['contig'],
in_target_bed=target_bed_task.output_files[0],
**tags),
parents + [target_bed_task],
out_dir='SM_{sample_name}/work/contigs/{contig}')
for tags, parents in group(dedupe, ['sample_name']) # Many2one
for target_bed_task in target_bed_tasks
] # One2many
realigned_by_sample_contig_tasks = one2one(gatk.indel_realigner, rtc_tasks)
realigned_by_sample_contig_tasks += [
execution.add_task(samtools.view,
dict(out_bam=out_dir('both_pairs_unmapped.bam' %
lb_task),
f='12',
sample_name=tags['sample_name'],
contig='BOTH_PAIRS_UNMAPPED',
library=lb_task.tags['library']),
parents=lb_task,
out_dir='SM_{sample_name}/work/LB_{library}',
stage_name='Filter_Both_Pairs_Unmapped')
for tags, sm_tasks in group(dedupe, ['sample_name'])
for lb_task in sm_tasks
]
# Skipping BQSR. Will improve results only slightly, if at all.
# Merge bams so we have a sample bam. Returning realign, so bams remained split by contig for downstream
# parallelization
merged = many2one(picard.merge_sam_files,
realigned_by_sample_contig_tasks, ['sample_name'],
out_dir='SM_{sample_name}',
stage_name="Merge_Sample_Bams")
one2one(picard.collect_multiple_metrics,
merged,
out_dir='SM_{sample_name}/metrics')
return merged
def align(execution, fastq_tasks, target_bed_tasks):
"""
Reads -> Alignments
:param Execution execution: The Execution instance to create Tasks in
:param list[Task] | [(str, dict)] fastq_tasks: Fastq input (file_path, dict) tuples or Tasks
:param list[Task] target_bed_tasks: target beds to parallelize/split on
:return: Indel Realigned Tasks
"""
# Do we need to split fastqs into smaller pieces?
aligns = []
for tags, fastq_task_group in group(fastq_tasks, by=['sample_name', 'library', 'platform', 'platform_unit', 'rgid', 'chunk']):
# trim_task = execution.add_task(fastq.trim_galore,
# tags=dict(**tags),
# parents=fastq_task_group,
# out_dir='SM_{sample_name}/work/RG_{rgid}/CH_{chunk}')
align_task = execution.add_task(bwa.bwa_mem,
tags=dict(**tags),
parents=fastq_task_group,
out_dir='SM_{sample_name}/work/RG_{rgid}/CH_{chunk}')
aligns.append(align_task)
dedupe = many2one(picard.mark_duplicates, aligns, groupby=['sample_name', 'library'], out_dir='SM_{sample_name}/work/LB_{library}')
# Note, could get slightly improved results by indel realigning over multiple samples, especially if low coverage
# for tags, parents in group(dedupe, ['sample_name']):
# for target_bed_task in target_bed_tasks:
# d = dict(contig=target_bed_task.tags['contig'],
# in_target_bed=target_bed_task.output_files[0],
# **tags)
#
rtc_tasks = [execution.add_task(gatk.realigner_target_creator,
dict(contig=target_bed_task.tags['contig'],
in_target_bed=target_bed_task.output_files[0], **tags),
parents + [target_bed_task],
out_dir='SM_{sample_name}/work/contigs/{contig}')
for tags, parents in group(dedupe, ['sample_name']) # Many2one
for target_bed_task in target_bed_tasks] # One2many
realigned_by_sample_contig_tasks = one2one(gatk.indel_realigner, rtc_tasks)
realigned_by_sample_contig_tasks += [execution.add_task(samtools.view,
dict(out_bam=out_dir('both_pairs_unmapped.bam' % lb_task),
f='12',
sample_name=tags['sample_name'],
contig='BOTH_PAIRS_UNMAPPED',
library=lb_task.tags['library']),
parents=lb_task,
out_dir='SM_{sample_name}/work/LB_{library}',
stage_name='Filter_Both_Pairs_Unmapped')
for tags, sm_tasks in group(dedupe, ['sample_name'])
for lb_task in sm_tasks]
# Skipping BQSR. Will improve results only slightly, if at all.
# Merge bams so we have a sample bam. Returning realign, so bams remained split by contig for downstream
# parallelization
merged = many2one(picard.merge_sam_files, realigned_by_sample_contig_tasks, ['sample_name'], out_dir='SM_{sample_name}', stage_name="Merge_Sample_Bams")
one2one(picard.collect_multiple_metrics, merged, out_dir='SM_{sample_name}/metrics')
one2one(picard.collect_wgs_metrics, merged, out_dir='SM_{sample_name}/metrics')
return merged
