def split(args):
assert (args.min_len >= 2 * args.bin_size)
# We only need the bam to get the chromosome names and lengths.
in_bam = tk_bam.create_bam_infile(args.possorted_bam)
if args.targets is None:
target_regions = None
else:
with open(args.targets, 'r') as f:
target_regions = tk_io.get_target_regions(f)
primary_contigs = tk_reference.load_primary_contigs(args.reference_path)
all_loci = []
for (chrom_name, chrom_size) in zip(in_bam.references, in_bam.lengths):
if not chrom_name in primary_contigs:
continue
# The chunks will overlap by min_len. This will ensure that we don't
# miss any regions of low depth that span chunk boundaries.
new_loci = generate_chrom_loci(target_regions,
chrom_name,
chrom_size,
PARALLEL_LOCUS_SIZE / 2,
overlap=args.min_len)
all_loci.extend(new_loci)
in_bam.close()
# Group loci
locus_sets = pack_loci(all_loci)
chunk_defs = [{'loci': loci, '__mem_gb': 16} for loci in locus_sets]
return {'chunks': chunk_defs}
def split(args):
in_bam = tk_bam.create_bam_infile(args.possorted_bam)
if not args.reference_path is None and os.path.exists(
tk_reference.get_primary_contigs(args.reference_path)):
with open(tk_reference.get_primary_contigs(args.reference_path),
'r') as f:
primary_contigs = set([line.strip() for line in f.readlines()])
else:
# Default is to include all contigs
primary_contigs = set(in_bam.references)
all_loci = []
for (chrom_name, chrom_size) in zip(in_bam.references, in_bam.lengths):
if chrom_name in primary_contigs and not (
args.sex in ['f', 'female'] and chrom_name in ['Y', 'chrY']):
all_loci.extend(
generate_chrom_loci(None, chrom_name, chrom_size,
PARALLEL_LOCUS_SIZE))
in_bam.close()
locus_sets = pack_loci(all_loci)
chunk_defs = [{'loci': loci, '__mem_gb': 8} for loci in locus_sets]
return {'chunks': chunk_defs}
def split(args):
ref = contig_manager.contig_manager(args.reference_path)
contig_lengths = ref.get_contig_lengths()
target_regions = None
all_loci = []
for (chrom_name, chrom_size) in contig_lengths.iteritems():
all_loci.extend(
generate_chrom_loci(target_regions, chrom_name, chrom_size,
100000000))
locus_sets = pack_loci(all_loci)
chunk_defs = [{'loci': loci} for loci in locus_sets]
return {'chunks': chunk_defs}
def split(args):
ref = contig_manager.contig_manager(args.reference_path)
contig_lengths = ref.get_contig_lengths()
target_regions = None
all_loci = []
for (chrom_name, chrom_size) in contig_lengths.iteritems():
all_loci.extend(
generate_chrom_loci(target_regions, chrom_name, chrom_size,
tenkit.constants.PARALLEL_LOCUS_SIZE))
locus_sets = pack_loci(all_loci)
chunk_defs = [{'loci': loci, '__mem_gb': 12} for loci in locus_sets]
return {'chunks': chunk_defs, 'join': {'__mem_gb': 12}}
def split(args):
in_bam = tk_bam.create_bam_infile(args.possorted_bam)
# Load pull-down targets
if args.targets is None:
target_regions = None
else:
with open(args.targets, 'r') as f:
target_regions = tk_io.get_target_regions(f)
all_loci = []
for (chrom_name, chrom_size) in zip(in_bam.references, in_bam.lengths):
all_loci.extend(generate_chrom_loci(target_regions, chrom_name, chrom_size, PARALLEL_LOCUS_SIZE))
in_bam.close()
locus_sets = pack_loci(all_loci)
chunk_defs = [{'loci': loci, '__mem_gb':16} for loci in locus_sets]
return {'chunks': chunk_defs}