def create_hla_type_workflow(
normal_bam_file,
hla_type_file):
workflow = Workflow()
workflow.commandline(
name='extract_chr6',
args=(
'samtools', 'view', '-bh', '-f', '2', '-F', '4',
pypeliner.managed.InputFile(normal_bam_file),
'6',
'|',
'samtools', 'collate', '-O', '-', pypeliner.managed.TempSpace('chr6_collate_temp'),
'|',
'samtools', 'bam2fq',
'-1', pypeliner.managed.TempOutputFile('chr6_reads_1.fq'),
'-2', pypeliner.managed.TempOutputFile('chr6_reads_2.fq'),
'-',
),
)
workflow.transform(
name='optitype',
ctx={'mem': 24},
func=tasks.run_optitype,
args=(
pypeliner.managed.TempInputFile('chr6_reads_1.fq'),
pypeliner.managed.TempInputFile('chr6_reads_2.fq'),
pypeliner.managed.OutputFile(hla_type_file),
pypeliner.managed.TempSpace('optitype_temp'),
)
)
return workflow
def create_mappability_wig_file(config, out_file):
workflow = Workflow()
workflow.subworkflow(
name='download_mappability_bigwig',
func=biowrappers.components.io.download.create_download_workflow,
args=(
config['mappability_url'],
pypeliner.managed.OutputFile(out_file + '.bigwig'),
))
workflow.commandline(
name='convert_mappability_to_wig',
ctx={'mem': 4},
args=(
'mapCounter',
'-w',
config['window_size'],
pypeliner.managed.InputFile(out_file + '.bigwig'),
'>',
pypeliner.managed.OutputFile(out_file),
),
)
return workflow
def create_setup_theta_workflow(config, databases, **kwargs):
mappability_dir = os.path.realpath(
os.path.join(os.path.dirname(config['mappability_template']),
os.pardir))
map_extract_log = os.path.join(mappability_dir, 'mappability_extract.log')
chromosomes_dir = os.path.dirname(config['chromosome_template'])
utils.make_directory(mappability_dir)
utils.make_directory(chromosomes_dir)
workflow = Workflow()
workflow.subworkflow(
name='download_mappability',
func=biowrappers.components.io.download.create_download_workflow,
args=(
config['mappability_url'],
pypeliner.managed.TempOutputFile('mappability.tar.gz'),
))
workflow.commandline(
name='extract_mappability',
args=(
'tar',
'-xzvf',
pypeliner.managed.TempInputFile('mappability.tar.gz'),
'-C',
mappability_dir,
'>',
pypeliner.managed.OutputFile(map_extract_log),
),
)
for chromosome in config['chromosomes']:
workflow.subworkflow(
name='download_chromosome_{}'.format(chromosome),
func=biowrappers.components.io.download.create_download_workflow,
args=(
config['chromosome_url_template'].format(chromosome),
pypeliner.managed.TempOutputFile(
'chromosome_{}.fa.gz'.format(chromosome)),
))
workflow.commandline(
name='extract_chromosome_{}'.format(chromosome),
args=(
'gunzip',
'-c',
pypeliner.managed.TempInputFile(
'chromosome_{}.fa.gz'.format(chromosome)),
'>',
pypeliner.managed.OutputFile(
config['chromosome_template'].format(chromosome)),
),
)
return workflow
def realignment_readgroups_pipeline(
config,
in_file,
out_file):
workflow = Workflow()
workflow.transform(
name='get_read_group_configs',
func=tasks.get_read_group_configs,
ret=pypeliner.managed.TempOutputObj('read_group_config', 'read_group_id'),
args=(
pypeliner.managed.InputFile(in_file),
)
)
workflow.commandline(
name='create_read_group_bam',
axes=('read_group_id',),
args=(
'samtools', 'view', '-b',
'-r', pypeliner.managed.InputInstance('read_group_id'),
pypeliner.managed.InputFile(in_file),
'>',
pypeliner.managed.TempOutputFile('read_group_bam', 'read_group_id'),
)
)
workflow.subworkflow(
name='realignment_pipeline',
axes=('read_group_id',),
func=realignment_pipeline,
args=(
config,
pypeliner.managed.TempInputFile('read_group_bam', 'read_group_id'),
pypeliner.managed.TempOutputFile('realigned_read_group_bam', 'read_group_id'),
),
kwargs={
'read_group_info': pypeliner.managed.TempInputObj('read_group_config', 'read_group_id'),
}
)
workflow.transform(
name='merge_and_markdups',
axes=('read_group_id',),
ctx={'mem' : 48, 'num_retry' : 3, 'mem_retry_increment' : 16},
func=bam_tasks.mark_duplicates,
args=(
pypeliner.managed.TempInputFile('realigned_read_group_bam', 'read_group_id'),
pypeliner.managed.OutputFile(out_file),
),
kwargs={
'tmp_dir' : pypeliner.managed.TempSpace('markdup_temp', 'read_group_id')
}
)
return workflow
def create_tophat_transcriptome_index_workflow(
ref_genome_fasta_file,
transcript_gtf_file,
ref_genome_index_prefix,
transcriptome_index_prefix,
copy_ref_genome=False):
workflow = Workflow()
local_ref_genome_fasta_path = ref_genome_index_prefix + '.fa'
if copy_ref_genome:
workflow.commandline(
name='copy_genome',
ctx={'local': True},
args=(
'cp',
mgd.InputFile(ref_genome_fasta_file),
mgd.OutputFile(local_ref_genome_fasta_path),
),
)
else:
workflow.commandline(
name='link_genome',
ctx={'local': True},
args=(
'ln',
'-s',
mgd.InputFile(ref_genome_fasta_file),
mgd.OutputFile(local_ref_genome_fasta_path),
),
)
workflow.transform(
name='build_bowtie_index',
ctx={'mem': 8, 'num_retry': 3, 'mem_retry_increment': 8},
func=tasks.build_genome_index,
args=(
mgd.InputFile(local_ref_genome_fasta_path),
mgd.OutputFile(ref_genome_index_prefix),
)
)
workflow.transform(
name='build_tophat_index',
ctx={'mem': 8, 'num_retry': 3, 'mem_retry_increment': 8},
func=tasks.build_transcriptome_index,
args=(
mgd.InputFile(ref_genome_index_prefix),
mgd.InputFile(transcript_gtf_file),
mgd.OutputFile(transcriptome_index_prefix),
)
)
return workflow
def create_gc_wig_file(config, genome_file, out_file):
workflow = Workflow()
workflow.commandline(
name='create_gc',
ctx={'mem': 4},
args=(
'gcCounter',
'-w',
config['window_size'],
pypeliner.managed.InputFile(genome_file),
'>',
pypeliner.managed.OutputFile(out_file),
),
)
return workflow
def create_pvacseq_workflow(
vcf_file,
hla_type_file,
results_file,
config,
):
workflow = Workflow()
workflow.commandline(
name='vep',
ctx={'mem': 16},
args=(
'variant_effect_predictor.pl',
'--input_file', pypeliner.managed.InputFile(vcf_file),
'--format', 'vcf',
'--output_file', pypeliner.managed.TempOutputFile('vep_annotated.vcf'),
'--vcf', '--symbol', '--terms', 'SO',
'--plugin', 'Downstream',
'--plugin', 'Wildtype',
'--cache', '--offline', '--force_overwrite',
'--assembly', 'GRCh37',
'--dir', config['vep_dir'],
'--dir_plugins', os.path.join(config['vep_dir'], 'Plugins'),
),
)
workflow.transform(
name='run_pvacseq',
func=tasks.run_pvacseq,
args=(
pypeliner.managed.TempInputFile('vep_annotated.vcf'),
pypeliner.managed.InputFile(hla_type_file),
pypeliner.managed.OutputFile(results_file),
pypeliner.managed.TempSpace('pvacseq_temp'),
config,
),
)
return workflow
def create_titan_workflow(seqdata_files,
config,
out_file,
raw_data_dir,
somatic_breakpoint_file=None,
normal_id=None,
**kwargs):
if normal_id is None:
raise ValueError('Titan requires normal sample')
normal_seqdata_file = seqdata_files[normal_id]
tumour_seqdata_files = seqdata_files.copy()
del tumour_seqdata_files[normal_id]
results_files = os.path.join(raw_data_dir, 'results',
'sample_{sample_id}.h5')
utils.make_parent_directory(results_files)
workflow = Workflow()
workflow.setobj(
obj=pypeliner.managed.OutputChunks('sample_id'),
value=tumour_seqdata_files.keys(),
)
workflow.transform(
name='prepare_normal_data',
ctx={
'mem': 16,
'num_retry': 3,
'mem_retry_increment': 4
},
func=tasks.prepare_normal_data,
args=(
pypeliner.managed.InputFile(normal_seqdata_file),
pypeliner.managed.TempOutputFile('normal.wig'),
pypeliner.managed.TempOutputFile('het_positions.tsv'),
config,
),
)
workflow.transform(
name='prepare_tumour_data',
axes=('sample_id', ),
ctx={'mem': 20},
func=tasks.prepare_tumour_data,
args=(
pypeliner.managed.InputFile('tumour_seqdata',
'sample_id',
fnames=tumour_seqdata_files),
pypeliner.managed.TempInputFile('het_positions.tsv'),
pypeliner.managed.TempOutputFile('tumour.wig', 'sample_id'),
pypeliner.managed.TempOutputFile('tumour_alleles.tsv',
'sample_id'),
config,
),
)
workflow.transform(
name='create_intialization_parameters',
axes=('sample_id', ),
ctx={
'mem': 4,
'num_retry': 3,
'mem_retry_increment': 2
},
func=tasks.create_intialization_parameters,
ret=pypeliner.managed.TempOutputObj('init_params', 'sample_id',
'init_param_id'),
args=(config, ),
)
workflow.transform(
name='run_titan',
axes=('sample_id', 'init_param_id'),
ctx={
'mem': 16,
'num_retry': 3,
'mem_retry_increment': 4
},
func=tasks.run_titan,
args=(
pypeliner.managed.TempInputObj('init_params', 'sample_id',
'init_param_id'),
pypeliner.managed.TempInputFile('normal.wig'),
pypeliner.managed.TempInputFile('tumour.wig', 'sample_id'),
pypeliner.managed.TempInputFile('tumour_alleles.tsv', 'sample_id'),
pypeliner.managed.TempOutputFile('cn.tsv', 'sample_id',
'init_param_id'),
pypeliner.managed.TempOutputFile('params.tsv', 'sample_id',
'init_param_id'),
config,
),
)
if somatic_breakpoint_file is not None:
somatic_breakpoint_file = pypeliner.managed.InputFile(
somatic_breakpoint_file)
workflow.transform(
name='select_solution',
axes=('sample_id', ),
ctx={
'mem': 4,
'num_retry': 3,
'mem_retry_increment': 2
},
func=tasks.select_solution,
args=(
pypeliner.managed.TempInputObj('init_params', 'sample_id',
'init_param_id'),
pypeliner.managed.TempInputFile('cn.tsv', 'sample_id',
'init_param_id'),
pypeliner.managed.TempInputFile('params.tsv', 'sample_id',
'init_param_id'),
pypeliner.managed.OutputFile('results',
'sample_id',
template=results_files),
pypeliner.managed.OutputFile(
os.path.join(raw_data_dir, 'output',
'{sample_id}_cn_loci.tsv'), 'sample_id'),
pypeliner.managed.OutputFile(
os.path.join(raw_data_dir, 'output',
'{sample_id}_cn_segments.tsv'), 'sample_id'),
pypeliner.managed.OutputFile(
os.path.join(raw_data_dir, 'output', '{sample_id}_cn_igv.tsv'),
'sample_id'),
pypeliner.managed.OutputFile(
os.path.join(raw_data_dir, 'output', '{sample_id}_params.tsv'),
'sample_id'),
config,
pypeliner.managed.Template('{sample_id}', 'sample_id'),
),
kwargs={
'breakpoints_filename': somatic_breakpoint_file,
},
)
workflow.setobj(obj=pypeliner.managed.OutputChunks('sample_id',
'chromosome'),
value=config.get('chromosomes', default_chromosomes),
axes=('sample_id', ))
workflow.commandline(
name='plot_chromosome',
axes=('sample_id', 'chromosome'),
ctx={
'mem': 4,
'num_retry': 3,
'mem_retry_increment': 2
},
args=(
'plot_titan_chromosome.R',
pypeliner.managed.Instance('chromosome'),
pypeliner.managed.InputFile(
os.path.join(raw_data_dir, 'output',
'{sample_id}_cn_loci.tsv'), 'sample_id'),
pypeliner.managed.InputFile(
os.path.join(raw_data_dir, 'output', '{sample_id}_params.tsv'),
'sample_id'),
pypeliner.managed.OutputFile(
os.path.join(raw_data_dir, 'output',
'{sample_id}_chr_{chromosome}.png'), 'sample_id',
'chromosome'),
),
)
workflow.transform(
name='merge_results',
ctx={
'mem': 8,
'num_retry': 3,
'mem_retry_increment': 2
},
func=hdf5_tasks.merge_hdf5,
args=(
pypeliner.managed.InputFile('results',
'sample_id',
template=results_files),
pypeliner.managed.OutputFile(out_file),
),
kwargs={
'table_names': '/sample_{}',
},
)
return workflow
def create_ref_genome_download_and_index_workflow(config, out_file):
workflow = Workflow()
if config['url'].endswith('gz'):
workflow.subworkflow(
name='download',
func=download.create_download_workflow,
args=(
config['url'],
pypeliner.managed.TempOutputFile('ref.fasta.gz'),
)
)
workflow.commandline(
name='gunzip',
args=(
'gzip', '-cd',
pypeliner.managed.TempInputFile('ref.fasta.gz'),
'>',
pypeliner.managed.OutputFile(out_file)
),
)
else:
workflow.subworkflow(
name='download',
func=download.create_download_workflow,
args=(
config['url'],
pypeliner.managed.OutputFile(out_file)
)
)
workflow.commandline(
name='build_dict',
ctx={'mem': 6, 'num_retry': 3, 'mem_retry_increment': 2},
args=(
'samtools',
'dict',
pypeliner.managed.InputFile(out_file),
'>',
pypeliner.managed.OutputFile(out_file + '.build_dict.log'),
)
)
workflow.commandline(
name='build_fai',
ctx={'mem': 6, 'num_retry': 3, 'mem_retry_increment': 2},
args=(
'samtools',
'faidx',
pypeliner.managed.InputFile(out_file),
'>',
pypeliner.managed.OutputFile(out_file + '.build_fai.log'),
)
)
workflow.commandline(
name='build_bwa_index',
ctx={'mem': 6, 'num_retry': 3, 'mem_retry_increment': 2},
args=(
'bwa',
'index',
pypeliner.managed.InputFile(out_file),
'>',
pypeliner.managed.OutputFile(out_file + '.build_bwa_index.log'),
)
)
return workflow
def create_setup_reference_dbs_workflow(config):
workflow = Workflow()
if 'cosmic' in config:
workflow.transform(
name='cosmic',
func=tasks.download_cosmic,
args=(
config['cosmic'],
pypeliner.managed.OutputFile(config['cosmic']['local_path']),
pypeliner.managed.TempSpace('cosmic_work', cleanup=None)
)
)
if 'dbsnp' in config:
workflow.subworkflow(
name='dbsnp',
func=create_dbsnp_download_workflow,
args=(
config['dbsnp'],
pypeliner.managed.OutputFile(config['dbsnp']['local_path']),
)
)
if 'mappability' in config:
workflow.subworkflow(
name='mappability',
func=download.create_download_workflow,
args=(
config['mappability']['url'],
pypeliner.managed.OutputFile(config['mappability']['local_path']),
)
)
if 'ref_genome' in config and 'url' in config['ref_genome']:
workflow.subworkflow(
name='ref_genome',
func=create_ref_genome_download_and_index_workflow,
args=(
config['ref_genome'],
pypeliner.managed.OutputFile(config['ref_genome']['local_path']),
)
)
if 'snpeff' in config:
workflow.commandline(
name='snpeff',
args=(
'snpEff',
'download',
config['snpeff']['db']
)
)
if 'chrom_info' in config:
workflow.subworkflow(
name='chrom_info',
func=download.create_download_workflow,
args=(
config['chrom_info']['url'],
pypeliner.managed.OutputFile(config['chrom_info']['local_path']),
)
)
return workflow
