def _get_target_access_files(cov_interval, data, work_dir):
"""Retrieve target and access files based on the type of data to process.
pick targets, anti-targets and access files based on analysis type
http://cnvkit.readthedocs.org/en/latest/nonhybrid.html
"""
base_regions = regions.get_sv_bed(data)
# if we don't have a configured BED or regions to use for SV caling
if not base_regions:
# For genome calls, subset to regions within 10kb of genes
if cov_interval == "genome":
base_regions = regions.get_sv_bed(data, "transcripts1e4", work_dir)
if base_regions:
base_regions = shared.remove_exclude_regions(
base_regions, base_regions, [data])
# Finally, default to the defined variant regions
if not base_regions:
base_regions = dd.get_variant_regions(data)
target_bed = bedutils.merge_overlaps(base_regions, data, out_dir=work_dir)
if cov_interval == "amplicon":
return target_bed, target_bed
elif cov_interval == "genome":
return target_bed, target_bed
else:
access_file = _create_access_file(dd.get_ref_file(data),
_sv_workdir(data), data)
return target_bed, access_file
def _get_target_access_files(cov_interval, data, work_dir):
"""Retrieve target and access files based on the type of data to process.
pick targets, anti-targets and access files based on analysis type
http://cnvkit.readthedocs.org/en/latest/nonhybrid.html
"""
base_regions = regions.get_sv_bed(data)
# if we don't have a configured BED or regions to use for SV caling
if not base_regions:
# For genome calls, subset to regions within 10kb of genes
if cov_interval == "genome":
base_regions = regions.get_sv_bed(data, "transcripts1e4", work_dir)
if base_regions:
base_regions = shared.remove_exclude_regions(base_regions, base_regions, [data])
# Finally, default to the defined variant regions
if not base_regions:
base_regions = dd.get_variant_regions(data)
target_bed = bedutils.merge_overlaps(base_regions, data, out_dir=work_dir)
if cov_interval == "amplicon":
return target_bed, target_bed
elif cov_interval == "genome":
return target_bed, target_bed
else:
access_file = _create_access_file(dd.get_ref_file(data), _sv_workdir(data), data)
return target_bed, access_file
def clean_inputs(data):
"""Clean BED input files to avoid overlapping segments that cause downstream issues.
Per-merges inputs to avoid needing to call multiple times during later parallel steps.
"""
if not utils.get_in(data, ("config", "algorithm", "variant_regions_orig")):
data["config"]["algorithm"]["variant_regions_orig"] = dd.get_variant_regions(data)
clean_vr = clean_file(dd.get_variant_regions(data), data, prefix="cleaned-")
merged_vr = merge_overlaps(clean_vr, data)
data["config"]["algorithm"]["variant_regions"] = clean_vr
data["config"]["algorithm"]["variant_regions_merged"] = merged_vr
if dd.get_coverage(data):
if not utils.get_in(data, ("config", "algorithm", "coverage_orig")):
data["config"]["algorithm"]["coverage_orig"] = dd.get_coverage(data)
clean_cov_bed = clean_file(dd.get_coverage(data), data, prefix="cov-", simple=True)
merged_cov_bed = merge_overlaps(clean_cov_bed, data)
data["config"]["algorithm"]["coverage"] = clean_cov_bed
data["config"]["algorithm"]["coverage_merged"] = merged_cov_bed
if 'seq2c' in get_svcallers(data):
seq2c_ready_bed = prep_seq2c_bed(data)
if not seq2c_ready_bed:
logger.warning("Can't run Seq2C without a svregions or variant_regions BED file")
else:
data["config"]["algorithm"]["seq2c_bed_ready"] = seq2c_ready_bed
elif regions.get_sv_bed(data):
dd.set_sv_regions(data, clean_file(regions.get_sv_bed(data), data, prefix="svregions-"))
return data
def clean_inputs(data):
"""Clean BED input files to avoid overlapping segments that cause downstream issues.
Per-merges inputs to avoid needing to call multiple times during later parallel steps.
"""
if not utils.get_in(data, ("config", "algorithm", "variant_regions_orig")):
data["config"]["algorithm"]["variant_regions_orig"] = dd.get_variant_regions(data)
clean_vr = clean_file(dd.get_variant_regions(data), data, prefix="cleaned-")
merged_vr = merge_overlaps(clean_vr, data)
data["config"]["algorithm"]["variant_regions"] = clean_vr
data["config"]["algorithm"]["variant_regions_merged"] = merged_vr
if dd.get_coverage(data):
if not utils.get_in(data, ("config", "algorithm", "coverage_orig")):
data["config"]["algorithm"]["coverage_orig"] = dd.get_coverage(data)
clean_cov_bed = clean_file(dd.get_coverage(data), data, prefix="cov-", simple=True)
merged_cov_bed = merge_overlaps(clean_cov_bed, data)
data["config"]["algorithm"]["coverage"] = clean_cov_bed
data["config"]["algorithm"]["coverage_merged"] = merged_cov_bed
if 'seq2c' in get_svcallers(data):
seq2c_ready_bed = prep_seq2c_bed(data)
if not seq2c_ready_bed:
logger.warning("Can't run Seq2C without a svregions or variant_regions BED file")
else:
data["config"]["algorithm"]["seq2c_bed_ready"] = seq2c_ready_bed
elif regions.get_sv_bed(data):
dd.set_sv_regions(data, clean_file(regions.get_sv_bed(data), data, prefix="svregions-"))
return data
def _create_subset_file(in_file, work_dir, data):
"""Subset the VCF to a set of smaller regions, matching what was used for CNV calling.
"""
out_file = os.path.join(work_dir, "%s-orig.bcf" % utils.splitext_plus(os.path.basename(in_file))[0])
if not utils.file_uptodate(out_file, in_file):
with file_transaction(data, out_file) as tx_out_file:
region_bed = regions.get_sv_bed(data)
if not region_bed:
region_bed = regions.get_sv_bed(data, "transcripts1e4", work_dir)
cmd = "bcftools view -R {region_bed} -o {tx_out_file} -O b {in_file}"
do.run(cmd.format(**locals()), "Extract SV only regions for BubbleTree")
return out_file
def calculate(bam_file, data):
"""Calculate coverage in parallel using mosdepth.
Removes duplicates and secondary reads from the counts:
if ( b->core.flag & (BAM_FUNMAP | BAM_FSECONDARY | BAM_FQCFAIL | BAM_FDUP) ) continue;
"""
params = {"min": dd.get_coverage_depth_min(data)}
variant_regions = dd.get_variant_regions_merged(data)
if not variant_regions:
variant_regions = _create_genome_regions(data)
# Back compatible with previous pre-mosdepth callable files
callable_file = os.path.join(utils.safe_makedir(os.path.join(dd.get_work_dir(data), "align",
dd.get_sample_name(data))),
"%s-coverage.callable.bed" % (dd.get_sample_name(data)))
if not utils.file_uptodate(callable_file, bam_file):
vr_quantize = ("0:1:%s:" % (params["min"]), ["NO_COVERAGE", "LOW_COVERAGE", "CALLABLE"])
to_calculate = [("variant_regions", variant_regions, vr_quantize, None),
("sv_regions", regions.get_sv_bed(data), None, None),
("coverage", dd.get_coverage(data), None, DEPTH_THRESHOLDS)]
depth_files = {}
for target_name, region_bed, quantize, thresholds in to_calculate:
if region_bed:
cur_depth = {}
depth_info = run_mosdepth(data, target_name, region_bed, quantize=quantize, thresholds=thresholds)
for attr in ("dist", "regions", "thresholds"):
val = getattr(depth_info, attr, None)
if val:
cur_depth[attr] = val
depth_files[target_name] = cur_depth
if target_name == "variant_regions":
callable_file = depth_info.quantize
else:
depth_files = {}
final_callable = _subset_to_variant_regions(callable_file, variant_regions, data)
return final_callable, depth_files
def add_genes(in_file, data, max_distance=10000):
"""Add gene annotations to a BED file from pre-prepared RNA-seq data.
max_distance -- only keep annotations within this distance of event
"""
gene_file = regions.get_sv_bed(data, "exons", out_dir=os.path.dirname(in_file))
if gene_file and utils.file_exists(in_file):
out_file = "%s-annotated.bed" % utils.splitext_plus(in_file)[0]
if not utils.file_uptodate(out_file, in_file):
input_rec = iter(pybedtools.BedTool(in_file)).next()
# keep everything after standard chrom/start/end, 1-based
extra_fields = range(4, len(input_rec.fields) + 1)
# keep the new gene annotation
gene_index = len(input_rec.fields) + 4
extra_fields.append(gene_index)
columns = ",".join([str(x) for x in extra_fields])
max_column = max(extra_fields) + 1
ops = ",".join(["distinct"] * len(extra_fields))
with file_transaction(data, out_file) as tx_out_file:
# swap over gene name to '.' if beyond maximum distance
# cut removes the last distance column which can cause issues
# with bedtools merge: 'ERROR: illegal character '.' found in integer conversion of string'
distance_filter = (r"""awk -F$'\t' -v OFS='\t' '{if ($NF > %s) $%s = "."} {print}'""" %
(max_distance, gene_index))
cmd = ("sort -k1,1 -k2,2n {in_file} | "
"bedtools closest -d -t all -a - -b {gene_file} | "
"{distance_filter} | cut -f 1-{max_column} | "
"bedtools merge -i - -c {columns} -o {ops} -delim ',' > {tx_out_file}")
do.run(cmd.format(**locals()), "Annotate BED file with gene info")
return out_file
else:
return in_file
def process_intervals(data):
"""Prepare intervals file"""
bed_file = regions.get_sv_bed(data)
if not bed_file:
bed_file = bedutils.clean_file(dd.get_variant_regions(data), data)
if not bed_file:
return None
basename = os.path.splitext(bed_file)[0]
ready_file = basename + ".txt"
if os.path.exists(ready_file):
return ready_file
optimized_bed = basename + ".optimized.bed"
rscript = utils.Rscript_cmd("r36")
interval_file_r = utils.R_package_script("r36", "PureCN", "extdata/IntervalFile.R")
ref_file = dd.get_ref_file(data)
mappability_resource = dd.get_variation_resources(data)["purecn_mappability"]
genome = dd.get_genome_build(data)
cmd = [rscript, interval_file_r, "--infile", bed_file,
"--fasta", ref_file,
"--outfile", ready_file,
"--offtarget",
"--genome", genome,
"--export", optimized_bed,
"--mappability", mappability_resource]
try:
cmd_line = "export R_LIBS_USER=%s && %s && %s" % (utils.R_sitelib(env = "r36"),
utils.get_R_exports(env = "r36"),
" ".join([str(x) for x in cmd]))
do.run(cmd_line, "PureCN intervals")
except subprocess.CalledProcessError as msg:
logger.info("PureCN failed to prepare intervals")
logger.debug("Saved PureCN interval file into " + ready_file)
return ready_file
def calculate(bam_file, data):
"""Calculate coverage in parallel using mosdepth.
Removes duplicates and secondary reads from the counts:
if ( b->core.flag & (BAM_FUNMAP | BAM_FSECONDARY | BAM_FQCFAIL | BAM_FDUP) ) continue;
"""
params = {"min": dd.get_coverage_depth_min(data)}
variant_regions = dd.get_variant_regions_merged(data)
if not variant_regions:
variant_regions = _create_genome_regions(data)
# Back compatible with previous pre-mosdepth callable files
callable_file = os.path.join(utils.safe_makedir(os.path.join(dd.get_work_dir(data), "align",
dd.get_sample_name(data))),
"%s-coverage.callable.bed" % (dd.get_sample_name(data)))
if not utils.file_uptodate(callable_file, bam_file):
vr_quantize = ("0:1:%s:" % (params["min"]), ["NO_COVERAGE", "LOW_COVERAGE", "CALLABLE"])
to_calculate = [("variant_regions", variant_regions, vr_quantize, None),
("sv_regions", bedutils.clean_file(regions.get_sv_bed(data), data), None, None),
("coverage", bedutils.clean_file(dd.get_coverage(data), data), None, DEPTH_THRESHOLDS)]
depth_files = {}
for target_name, region_bed, quantize, thresholds in to_calculate:
if region_bed:
cur_depth = {}
depth_info = run_mosdepth(data, target_name, region_bed, quantize=quantize, thresholds=thresholds)
for attr in ("dist", "regions", "thresholds"):
val = getattr(depth_info, attr, None)
if val:
cur_depth[attr] = val
depth_files[target_name] = cur_depth
if target_name == "variant_regions":
callable_file = depth_info.quantize
else:
depth_files = {}
final_callable = _subset_to_variant_regions(callable_file, variant_regions, data)
return final_callable, depth_files
def _prioritize_vcf(caller, vcf_file, prioritize_by, post_prior_fn, work_dir, data):
"""Provide prioritized tab delimited output for a single caller.
"""
sample = dd.get_sample_name(data)
out_file = os.path.join(work_dir, "%s-%s-prioritize.tsv" % (sample, caller))
if not utils.file_exists(out_file):
priority_vcf = "%s.vcf.gz" % utils.splitext_plus(out_file)[0]
if not utils.file_exists(priority_vcf):
with file_transaction(data, priority_vcf) as tx_out_file:
cmd = ("bcbio-prioritize known -i {vcf_file} -o {tx_out_file} -k {prioritize_by}")
do.run(cmd.format(**locals()), "Prioritize: select in known regions of interest")
if post_prior_fn:
priority_vcf = post_prior_fn(priority_vcf, work_dir, data)
simple_vcf = "%s-simple.vcf.gz" % utils.splitext_plus(priority_vcf)[0]
if not utils.file_exists(simple_vcf):
with file_transaction(data, simple_vcf) as tx_out_file:
transcript_file = regions.get_sv_bed(data, "transcripts1000", work_dir)
if transcript_file:
transcript_file = vcfutils.bgzip_and_index(transcript_file, data["config"])
ann_opt = "--gene_bed %s" % transcript_file
else:
ann_opt = ""
cmd = "simple_sv_annotation.py {ann_opt} -o - {priority_vcf} | bgzip -c > {tx_out_file}"
do.run(cmd.format(**locals()), "Prioritize: simplified annotation output")
simple_vcf = vcfutils.bgzip_and_index(vcfutils.sort_by_ref(simple_vcf, data), data["config"])
with file_transaction(data, out_file) as tx_out_file:
cmd = ("zcat {simple_vcf} | vawk -v SNAME={sample} -v CALLER={caller} "
"""'{{if (($7 == "PASS" || $7 == ".") && (S${sample}$GT != "0/0")) """
"print CALLER,SNAME,$1,$2,I$END,"
"""I$SVTYPE=="BND" ? I$SVTYPE":"$3":"I$MATEID : I$SVTYPE,"""
"I$KNOWN,I$END_GENE,I$LOF,I$SIMPLE_ANN,"
"S${sample}$SR,S${sample}$PE}}' > {tx_out_file}")
do.run(cmd.format(**locals()), "Prioritize: convert to tab delimited")
return out_file
def _prep_bed(data, work_dir):
"""Selecting the bed file, cleaning, and properly annotating for Seq2C
"""
bed_file = regions.get_sv_bed(data)
if bed_file:
bed_file = clean_file(bed_file, data, prefix="svregions-")
else:
bed_file = clean_file(dd.get_variant_regions(data), data)
col_num = bt.BedTool(bed_file).field_count()
if col_num < 4:
annotated_file = annotate.add_genes(bed_file, data, max_distance=0)
if annotated_file == bed_file:
raise ValueError("BED file for Seq2C must be annotated with gene names, "
"however the input BED is 3-columns and we have no transcript "
"data to annotate with " + bed_file)
annotated_file = annotate.gene_one_per_line(annotated_file, data)
else:
annotated_file = bed_file
ready_file = "%s-seq2cclean.bed" % (utils.splitext_plus(annotated_file)[0])
if not utils.file_uptodate(ready_file, annotated_file):
bed = bt.BedTool(annotated_file)
if col_num > 4 and col_num != 8:
bed = bed.cut(range(4))
bed = bed.filter(lambda x: x.name not in ["", ".", "-"])
with file_transaction(data, ready_file) as tx_out_file:
bed.saveas(tx_out_file)
logger.debug("Saved Seq2C clean annotated ready input BED into " + ready_file)
return ready_file
def sample_callable_bed(bam_file, ref_file, data):
"""Retrieve callable regions for a sample subset by defined analysis regions.
"""
from bcbio.heterogeneity import chromhacks
CovInfo = collections.namedtuple("CovInfo",
"callable, raw_callable, depth_files")
noalt_calling = "noalt_calling" in dd.get_tools_on(
data) or "altcontigs" in dd.get_exclude_regions(data)
def callable_chrom_filter(r):
"""Filter to callable region, potentially limiting by chromosomes.
"""
return r.name == "CALLABLE" and (not noalt_calling
or chromhacks.is_nonalt(r.chrom))
out_file = "%s-callable_sample.bed" % os.path.splitext(bam_file)[0]
with shared.bedtools_tmpdir(data):
sv_bed = regions.get_sv_bed(data)
callable_bed, depth_files = coverage.calculate(bam_file, data, sv_bed)
input_regions_bed = dd.get_variant_regions(data)
if not utils.file_uptodate(out_file, callable_bed):
with file_transaction(data, out_file) as tx_out_file:
callable_regions = pybedtools.BedTool(callable_bed)
filter_regions = callable_regions.filter(callable_chrom_filter)
if input_regions_bed:
if not utils.file_uptodate(out_file, input_regions_bed):
input_regions = pybedtools.BedTool(input_regions_bed)
filter_regions.intersect(
input_regions,
nonamecheck=True).saveas(tx_out_file)
else:
filter_regions.saveas(tx_out_file)
return CovInfo(out_file, callable_bed, depth_files)
def sample_callable_bed(bam_file, ref_file, data):
"""Retrieve callable regions for a sample subset by defined analysis regions.
"""
from bcbio.heterogeneity import chromhacks
CovInfo = collections.namedtuple("CovInfo", "callable, raw_callable, depth_files")
noalt_calling = "noalt_calling" in dd.get_tools_on(data) or "altcontigs" in dd.get_exclude_regions(data)
def callable_chrom_filter(r):
"""Filter to callable region, potentially limiting by chromosomes.
"""
return r.name == "CALLABLE" and (not noalt_calling or chromhacks.is_nonalt(r.chrom))
out_file = "%s-callable_sample.bed" % os.path.splitext(bam_file)[0]
with shared.bedtools_tmpdir(data):
sv_bed = regions.get_sv_bed(data)
callable_bed, depth_files = coverage.calculate(bam_file, data, sv_bed)
input_regions_bed = dd.get_variant_regions(data)
if not utils.file_uptodate(out_file, callable_bed):
with file_transaction(data, out_file) as tx_out_file:
callable_regions = pybedtools.BedTool(callable_bed)
filter_regions = callable_regions.filter(callable_chrom_filter)
if input_regions_bed:
if not utils.file_uptodate(out_file, input_regions_bed):
input_regions = pybedtools.BedTool(input_regions_bed)
filter_regions.intersect(input_regions, nonamecheck=True).saveas(tx_out_file)
else:
filter_regions.saveas(tx_out_file)
return CovInfo(out_file, callable_bed, depth_files)
def add_genes(in_file, data, max_distance=10000):
"""Add gene annotations to a BED file from pre-prepared RNA-seq data.
max_distance -- only keep annotations within this distance of event
"""
gene_file = regions.get_sv_bed(data, "exons", out_dir=os.path.dirname(in_file))
if gene_file and utils.file_exists(in_file):
out_file = "%s-annotated.bed" % utils.splitext_plus(in_file)[0]
if not utils.file_uptodate(out_file, in_file):
input_rec = iter(pybedtools.BedTool(in_file)).next()
# keep everything after standard chrom/start/end, 1-based
extra_fields = range(4, len(input_rec.fields) + 1)
# keep the new gene annotation
gene_index = len(input_rec.fields) + 4
extra_fields.append(gene_index)
columns = ",".join([str(x) for x in extra_fields])
max_column = max(extra_fields) + 1
ops = ",".join(["distinct"] * len(extra_fields))
fai_file = ref.fasta_idx(dd.get_ref_file(data))
with file_transaction(data, out_file) as tx_out_file:
# swap over gene name to '.' if beyond maximum distance
# cut removes the last distance column which can cause issues
# with bedtools merge: 'ERROR: illegal character '.' found in integer conversion of string'
distance_filter = (r"""awk -F$'\t' -v OFS='\t' '{if ($NF > %s) $%s = "."} {print}'""" %
(max_distance, gene_index))
sort_cmd = bedutils.get_sort_cmd()
cmd = ("{sort_cmd} -k1,1 -k2,2n {in_file} | "
"bedtools closest -g <(cut -f1,2 {fai_file} | {sort_cmd} -k1,1 -k2,2n) "
"-d -t all -a - -b <({sort_cmd} -k1,1 -k2,2n {gene_file}) | "
"{distance_filter} | cut -f 1-{max_column} | "
"bedtools merge -i - -c {columns} -o {ops} -delim ',' > {tx_out_file}")
do.run(cmd.format(**locals()), "Annotate BED file with gene info")
return out_file
else:
return in_file
def _create_subset_file(in_file, work_dir, data):
"""Subset the VCF to a set of smaller regions, matching what was used for CNV calling.
"""
out_file = os.path.join(
work_dir,
"%s-orig.bcf" % utils.splitext_plus(os.path.basename(in_file))[0])
if not utils.file_uptodate(out_file, in_file):
with file_transaction(data, out_file) as tx_out_file:
region_bed = regions.get_sv_bed(data)
if not region_bed:
region_bed = regions.get_sv_bed(data, "transcripts1e4",
work_dir)
cmd = "bcftools view -R {region_bed} -o {tx_out_file} -O b {in_file}"
do.run(cmd.format(**locals()),
"Extract SV only regions for BubbleTree")
return out_file
def get_base_cnv_regions(data, work_dir):
"""Retrieve set of target regions for CNV analysis.
Subsets to extended transcript regions for WGS experiments to avoid
long runtimes.
"""
cov_interval = dd.get_coverage_interval(data)
base_regions = regions.get_sv_bed(data)
# if we don't have a configured BED or regions to use for SV caling
if not base_regions:
# For genome calls, subset to regions within 10kb of genes
if cov_interval == "genome":
base_regions = regions.get_sv_bed(data, "transcripts1e4", work_dir)
if base_regions:
base_regions = remove_exclude_regions(base_regions, base_regions, [data])
# Finally, default to the defined variant regions
if not base_regions:
base_regions = dd.get_variant_regions(data)
return base_regions
def _prioritize_vcf(caller, vcf_file, prioritize_by, post_prior_fn, work_dir,
data):
"""Provide prioritized tab delimited output for a single caller.
"""
sample = dd.get_sample_name(data)
out_file = os.path.join(work_dir,
"%s-%s-prioritize.tsv" % (sample, caller))
if not utils.file_exists(out_file):
priority_vcf = "%s.vcf.gz" % utils.splitext_plus(out_file)[0]
if not utils.file_exists(priority_vcf):
with file_transaction(data, priority_vcf) as tx_out_file:
resources = config_utils.get_resources("bcbio_prioritize",
data["config"])
jvm_opts = " ".join(
resources.get("jvm_opts", ["-Xms1g", "-Xmx4g"]))
cmd = (
"bcbio-prioritize {jvm_opts} known -i {vcf_file} -o {tx_out_file} -k {prioritize_by}"
)
do.run(cmd.format(**locals()),
"Prioritize: select in known regions of interest")
if post_prior_fn:
priority_vcf = post_prior_fn(priority_vcf, work_dir, data)
simple_vcf = "%s-simple.vcf.gz" % utils.splitext_plus(priority_vcf)[0]
if not utils.file_exists(simple_vcf):
with file_transaction(data, simple_vcf) as tx_out_file:
transcript_file = regions.get_sv_bed(data, "transcripts1000",
work_dir)
if transcript_file:
transcript_file = vcfutils.bgzip_and_index(
transcript_file, data["config"])
ann_opt = "--gene_bed %s" % transcript_file
else:
ann_opt = ""
cmd = "simple_sv_annotation.py {ann_opt} -o - {priority_vcf} | bgzip -c > {tx_out_file}"
do.run(cmd.format(**locals()),
"Prioritize: simplified annotation output")
simple_vcf = vcfutils.bgzip_and_index(
vcfutils.sort_by_ref(simple_vcf, data), data["config"])
with file_transaction(data, out_file) as tx_out_file:
cmd = (
"zcat {simple_vcf} | vawk -v SNAME={sample} -v CALLER={caller} "
"""'{{if (($7 == "PASS" || $7 == ".") && (S${sample}$GT != "0/0")) """
"print CALLER,SNAME,$1,$2,I$END,"
"""I$SVTYPE=="BND" ? I$SVTYPE":"$3":"I$MATEID : I$SVTYPE,"""
"I$KNOWN,I$END_GENE,I$LOF,I$SIMPLE_ANN,"
"S${sample}$SR,S${sample}$PE}}' > {tx_out_file}")
do.run(cmd.format(**locals()),
"Prioritize: convert to tab delimited")
return out_file
def subset_by_genes(in_file, data, out_dir, pad):
"""Subset BED file of regions to only those within pad of the final output.
"""
gene_file = regions.get_sv_bed(data, "exons", out_dir=os.path.dirname(in_file))
fai_file = ref.fasta_idx(dd.get_ref_file(data))
if not gene_file or not utils.file_exists(in_file):
return in_file
else:
out_file = os.path.join(out_dir, "%s-geneonly.bed" % utils.splitext_plus(os.path.basename(in_file))[0])
if not utils.file_uptodate(out_file, in_file):
with file_transaction(data, out_file) as tx_out_file:
want_region_file = "%s-targetregions%s" % utils.splitext_plus(out_file)
pybedtools.BedTool(gene_file).slop(g=fai_file, b=pad).merge().saveas(want_region_file)
pybedtools.BedTool(in_file).intersect(b=want_region_file).sort().saveas(tx_out_file)
return out_file
def add_genes(in_file, data, max_distance=10000, work_dir=None):
"""Add gene annotations to a BED file from pre-prepared RNA-seq data.
max_distance -- only keep annotations within this distance of event
"""
gene_file = regions.get_sv_bed(data, "exons", out_dir=os.path.dirname(in_file))
if gene_file and utils.file_exists(in_file):
out_file = "%s-annotated.bed" % utils.splitext_plus(in_file)[0]
if work_dir:
out_file = os.path.join(work_dir, os.path.basename(out_file))
if not utils.file_uptodate(out_file, in_file):
fai_file = ref.fasta_idx(dd.get_ref_file(data))
with file_transaction(data, out_file) as tx_out_file:
_add_genes_to_bed(in_file, gene_file, fai_file, tx_out_file, data, max_distance)
return out_file
else:
return in_file
def add_genes(in_file, data, max_distance=10000, work_dir=None):
"""Add gene annotations to a BED file from pre-prepared RNA-seq data.
max_distance -- only keep annotations within this distance of event
"""
gene_file = regions.get_sv_bed(data, "exons", out_dir=os.path.dirname(in_file))
if gene_file and utils.file_exists(in_file):
out_file = "%s-annotated.bed" % utils.splitext_plus(in_file)[0]
if work_dir:
out_file = os.path.join(work_dir, os.path.basename(out_file))
if not utils.file_uptodate(out_file, in_file):
fai_file = ref.fasta_idx(dd.get_ref_file(data))
with file_transaction(data, out_file) as tx_out_file:
_add_genes_to_bed(in_file, gene_file, fai_file, tx_out_file, data, max_distance)
return out_file
else:
return in_file
def _setup_variant_regions(data, out_dir):
"""Ensure we have variant regions for calling, using transcript if not present.
Respects noalt_calling by removing additional contigs to improve
speeds.
"""
vr_file = dd.get_variant_regions(data)
if not vr_file:
vr_file = regions.get_sv_bed(data, "transcripts", out_dir=out_dir)
contigs = set([c.name for c in ref.file_contigs(dd.get_ref_file(data))])
out_file = os.path.join(utils.safe_makedir(os.path.join(dd.get_work_dir(data), "bedprep")),
"%s-rnaseq_clean.bed" % utils.splitext_plus(os.path.basename(vr_file))[0])
if not utils.file_uptodate(out_file, vr_file):
with file_transaction(data, out_file) as tx_out_file:
with open(tx_out_file, "w") as out_handle:
with shared.bedtools_tmpdir(data):
for r in pybedtools.BedTool(vr_file):
if r.chrom in contigs:
if chromhacks.is_nonalt(r.chrom):
out_handle.write(str(r))
data = dd.set_variant_regions(data, out_file)
return data
def _setup_variant_regions(data, out_dir):
"""Ensure we have variant regions for calling, using transcript if not present.
Respects noalt_calling by removing additional contigs to improve
speeds.
"""
vr_file = dd.get_variant_regions(data)
if not vr_file:
vr_file = regions.get_sv_bed(data, "transcripts", out_dir=out_dir)
contigs = set([c.name for c in ref.file_contigs(dd.get_ref_file(data))])
out_file = os.path.join(utils.safe_makedir(os.path.join(dd.get_work_dir(data), "bedprep")),
"%s-rnaseq_clean.bed" % utils.splitext_plus(os.path.basename(vr_file))[0])
if not utils.file_uptodate(out_file, vr_file):
with file_transaction(data, out_file) as tx_out_file:
with open(tx_out_file, "w") as out_handle:
with shared.bedtools_tmpdir(data):
for r in pybedtools.BedTool(vr_file):
if r.chrom in contigs:
if chromhacks.is_nonalt(r.chrom):
out_handle.write(str(r))
data = dd.set_variant_regions(data, out_file)
return data
def precall(items):
"""Perform initial pre-calling steps -- coverage calcuation by sample.
Use sambamba to call average region coverage in regions, and convert into a correct format.
"""
items = [utils.to_single_data(x) for x in items]
assert len(items) == 1, "Expect one item to Seq2C coverage calculation"
data = utils.to_single_data(items)
assert dd.get_coverage_interval(data) != "genome", "Seq2C only for amplicon and exome sequencing"
work_dir = _sv_workdir(data)
bed_file = regions.get_sv_bed(data) or dd.get_variant_regions(data)
bed_file = _prep_bed(data, bed_file, work_dir)
bam_file = dd.get_align_bam(data)
sample_name = dd.get_sample_name(data)
cov_file = _calculate_coverage(data, work_dir, bed_file, bam_file, sample_name)
if "sv" not in data:
data["sv"] = []
data["sv"].append({"variantcaller": "seq2c",
"coverage": cov_file})
return [data]
def precall(items):
"""Perform initial pre-calling steps -- coverage calcuation by sample.
Use sambamba to call average region coverage in regions, and convert into a correct format.
"""
items = [utils.to_single_data(x) for x in items]
assert len(items) == 1, "Expect one item to Seq2C coverage calculation"
data = utils.to_single_data(items)
assert dd.get_coverage_interval(
data) != "genome", "Seq2C only for amplicon and exome sequencing"
work_dir = _sv_workdir(data)
bed_file = regions.get_sv_bed(data) or dd.get_variant_regions(data)
bed_file = _prep_bed(data, bed_file, work_dir)
bam_file = dd.get_align_bam(data)
sample_name = dd.get_sample_name(data)
cov_file = _calculate_coverage(data, work_dir, bed_file, bam_file,
sample_name)
if "sv" not in data:
data["sv"] = []
data["sv"].append({"variantcaller": "seq2c", "coverage": cov_file})
return [data]