def preprocessWrapper(file_and_location, args):
starttime = time.time()
filename, location_str = file_and_location
if args["bcf"]:
int_suffix = "bcf"
else:
int_suffix = "vcf.gz"
tf = tempfile.NamedTemporaryFile(delete=False,
prefix="input.%s" % location_str,
suffix=".prep." + int_suffix)
tf.close()
to_run = "preprocess %s:* %s-o %s -V %i -L %i -r %s" % \
(pipes.quote(filename),
("-l %s " % pipes.quote(location_str)) if location_str else "",
tf.name,
args["decompose"],
args["leftshift"],
pipes.quote(args["reference"]))
if args["haploid_x"]:
to_run += " --haploid-x 1"
tfe = tempfile.NamedTemporaryFile(delete=False,
prefix="stderr",
suffix=".log")
tfo = tempfile.NamedTemporaryFile(delete=False,
prefix="stdout",
suffix=".log")
finished = False
try:
logging.info("Running '%s'" % to_run)
subprocess.check_call(to_run, shell=True, stdout=tfo, stderr=tfe)
finished = True
finally:
if finished:
tfo.close()
tfe.close()
with open(tfo.name) as f:
for l in f:
logging.info(l.replace("\n", ""))
os.unlink(tfo.name)
with open(tfe.name) as f:
for l in f:
logging.warn(l.replace("\n", ""))
os.unlink(tfe.name)
else:
logging.error("Preprocess command %s failed. Outputs are here %s / %s" % (to_run, tfo.name, tfe.name))
with open(tfo.name) as f:
for l in f:
logging.error(l.replace("\n", ""))
with open(tfe.name) as f:
for l in f:
logging.error(l.replace("\n", ""))
elapsed = time.time() - starttime
logging.info("preprocess for %s -- time taken %.2f" % (location_str, elapsed))
runBcftools("index", tf.name)
return tf.name
def preprocessWrapper(file_and_location, args):
starttime = time.time()
filename, location_str = file_and_location
if args["bcf"]:
int_suffix = "bcf"
else:
int_suffix = "vcf.gz"
tf = tempfile.NamedTemporaryFile(delete=False, prefix="input.%s" % location_str, suffix=".prep." + int_suffix)
tf.close()
to_run = "preprocess %s:* %s-o %s -V %i -L %i -r %s" % (
filename.replace(" ", "\\ "),
("-l %s " % location_str) if location_str else "",
tf.name,
args["decompose"],
args["leftshift"],
args["reference"],
)
tfe = tempfile.NamedTemporaryFile(delete=False, prefix="stderr", suffix=".log")
tfo = tempfile.NamedTemporaryFile(delete=False, prefix="stdout", suffix=".log")
try:
logging.info("Running '%s'" % to_run)
subprocess.check_call(to_run, shell=True, stdout=tfo, stderr=tfe)
finally:
tfo.close()
tfe.close()
with open(tfo.name) as f:
for l in f:
logging.info(l.replace("\n", ""))
os.unlink(tfo.name)
with open(tfe.name) as f:
for l in f:
logging.warn(l.replace("\n", ""))
os.unlink(tfe.name)
elapsed = time.time() - starttime
logging.info("preprocess for %s -- time taken %.2f" % (location_str, elapsed))
runBcftools("index", tf.name)
return tf.name
def runSCmp(vcf1, vcf2, target, args):
""" Runs scmp, which outputs a file quantify can produce counts on
vcf1 and vcf2 must be indexed and only contain a single sample column.
"""
try:
if args.engine == "scmp-distance":
cmode = "distance"
else:
cmode = "alleles"
tf = tempfile.NamedTemporaryFile(delete=False)
tf.close()
try:
# change GTs so we can compare them
vargs = ["merge", "--force-samples", vcf1, vcf2,
"-o", tf.name]
runBcftools(*vargs)
vargs = ["view", tf.name,
"|",
"scmp",
"-M", cmode,
"-", "-r", args.ref,
"--threads", str(args.threads),
"-o", target]
if args.roc:
vargs += ["--q", args.roc]
vargs += ["--distance-maxdist", str(args.engine_scmp_distance)]
runBcftools(*vargs)
finally:
os.remove(tf.name)
if target.endswith(".vcf.gz"):
runBcftools("index", "-t", target)
return [target, target + ".tbi"]
else:
runBcftools("index", target)
return [target, target + ".csi"]
except Exception as e:
logging.error("Exception when running scmp: %s" % str(e))
logging.error('-'*60)
traceback.print_exc(file=LoggingWriter(logging.ERROR))
logging.error('-'*60)
raise
except BaseException as e:
logging.error("Exception when running scmp: %s" % str(e))
logging.error('-'*60)
traceback.print_exc(file=LoggingWriter(logging.ERROR))
logging.error('-'*60)
raise
def runSCmp(vcf1, vcf2, target, args):
""" Runs scmp, which outputs a file quantify can produce counts on
vcf1 and vcf2 must be indexed and only contain a single sample column.
"""
try:
if args.engine == "scmp-distance":
cmode = "distance"
else:
cmode = "alleles"
tf = tempfile.NamedTemporaryFile(delete=False)
tf.close()
try:
# change GTs so we can compare them
vargs = ["merge", "--force-samples", vcf1, vcf2, "-o", tf.name]
runBcftools(*vargs)
vargs = [
"view", tf.name, "|", "scmp", "-M", cmode, "-", "-r", args.ref,
"--threads",
str(args.threads), "-o", target
]
if args.roc:
vargs += ["--q", args.roc]
vargs += ["--distance-maxdist", str(args.engine_scmp_distance)]
runBcftools(*vargs)
finally:
os.remove(tf.name)
if target.endswith(".vcf.gz"):
runBcftools("index", "-t", target)
return [target, target + ".tbi"]
else:
runBcftools("index", target)
return [target, target + ".csi"]
except Exception as e:
logging.error("Exception when running scmp: %s" % str(e))
logging.error('-' * 60)
traceback.print_exc(file=LoggingWriter(logging.ERROR))
logging.error('-' * 60)
raise
except BaseException as e:
logging.error("Exception when running scmp: %s" % str(e))
logging.error('-' * 60)
traceback.print_exc(file=LoggingWriter(logging.ERROR))
logging.error('-' * 60)
raise
def runSCmp(vcf1, vcf2, target, args):
""" Runs scmp, which outputs a file quantify can produce counts on
vcf1 and vcf2 must be indexed and only contain a single sample column.
"""
try:
# change GTs so we can compare them
vargs = [
"merge", "--force-samples", vcf1, vcf2, "|", "scmp", "-", "-r",
args.ref, "--threads",
str(args.threads), "-o", target
]
if args.roc:
vargs += ["--q", args.roc]
runBcftools(*vargs)
if target.endswith(".vcf.gz"):
runBcftools("index", "-t", target)
return [target, target + ".tbi"]
else:
runBcftools("index", target)
return [target, target + ".csi"]
except Exception as e:
logging.error("Exception when running scmp: %s" % str(e))
logging.error('-' * 60)
traceback.print_exc(file=LoggingWriter(logging.ERROR))
logging.error('-' * 60)
raise
except BaseException as e:
logging.error("Exception when running scmp: %s" % str(e))
logging.error('-' * 60)
traceback.print_exc(file=LoggingWriter(logging.ERROR))
logging.error('-' * 60)
raise
def main():
parser = argparse.ArgumentParser("Somatic VCF Feature Extraction")
parser.add_argument("input", help="Input VCF file")
parser.add_argument("-o",
"--output",
dest="output",
required=True,
help="Output file name. Output will be in CSV format")
parser.add_argument("-l",
"--location",
dest="location",
default="",
help="Location for bcftools view (e.g. chr1)")
parser.add_argument(
"-R",
"--restrict-regions",
dest="regions_bedfile",
default=None,
type=str,
help=
"Restrict analysis to given (sparse) regions (using -R in bcftools).")
parser.add_argument(
"-T",
"--target-regions",
dest="targets_bedfile",
default=None,
type=str,
help=
"Restrict analysis to given (dense) regions (using -T in bcftools).")
parser.add_argument("-P",
"--include-nonpass",
dest="inc_nonpass",
action="store_true",
default=False,
help="Use to include failing variants in comparison.")
parser.add_argument(
"--feature-table",
dest="features",
default="generic",
help="Select a feature table to output. Options are: %s" %
str(Somatic.FeatureSet.sets.keys()))
parser.add_argument(
"--feature-label",
dest="label",
default=None,
help=
"We will output a lable column, this value will go in there -- default is "
"the input filename.")
parser.add_argument(
"--bam",
dest="bams",
default=[],
action="append",
help="pass one or more BAM files for feature table extraction")
parser.add_argument("-r",
"--reference",
dest="ref",
default=Tools.defaultReference(),
help="Specify a reference file for normalization.")
parser.add_argument(
"--normalize",
dest="normalize",
default=False,
action="store_true",
help="Enable running of bcftools norm on the input file.")
parser.add_argument(
"--fix-chr",
dest="fixchr",
default=False,
action="store_true",
help="Replace numeric chromosome names in the query by chr*-type names"
)
args = parser.parse_args()
scratch = tempfile.mkdtemp()
try:
logging.info("Scratch path is %s" % scratch)
if not args.label:
args.label = os.path.basename(args.input)
bams = []
md = None
for x in args.bams:
bams.append(bamStats(x))
if bams:
bres = pandas.concat(bams).groupby("CHROM").mean()
md = {}
for x in bres.index:
logging.info("Mean coverage on %s is %f" %
(x, bres.loc[x]["COVERAGE"]))
md[x] = float(bres.loc[x]["COVERAGE"]) * 3.0
nqpath = os.path.join(scratch, "normalized_query.vcf.gz")
logging.info("Preprocessing input...")
preprocessVCF(
args.input,
nqpath,
args.location,
not args.inc_nonpass, # pass_only
args.fixchr, # chrprefix
args.normalize, # norm,
args.regions_bedfile,
args.targets_bedfile,
args.ref)
runBcftools("index", nqpath)
logging.info("Extracting features...")
fset = Somatic.FeatureSet.make(args.features)
fset.setChrDepths(md)
featuretable = fset.collect(nqpath, args.label)
if not args.output.endswith(".csv"):
args.output += ".csv"
logging.info("Saving feature table %s..." % args.output)
featuretable.to_csv(args.output)
finally:
logging.info("Deleting scratch folder %s " % scratch)
shutil.rmtree(scratch)
def partialCredit(vcfname,
outputname,
reference,
locations,
threads=1,
window=10000,
leftshift=True,
decompose=True,
haploid_x=False):
""" Partial-credit-process a VCF file according to our args """
pool = getPool(int(threads))
if threads > 1:
logging.info("Partial credit processing uses %i parallel processes." % threads)
if not locations:
h = extractHeadersJSON(vcfname)
if not h["tabix"]["chromosomes"]:
logging.warn("Empty input or not tabix indexed")
if outputname.endswith(".bcf"):
runBcftools("view", "-O", "b", "-o", outputname, vcfname)
runBcftools("index", outputname)
else:
runBcftools("view", "-O", "z", "-o", outputname, vcfname)
runBcftools("index", "-t", outputname)
# just return the same file
return
locations = h["tabix"]["chromosomes"]
elif type(locations) is str or type(locations) is unicode:
locations = locations.split(",")
# use blocksplit to subdivide input
res = runParallel(pool,
blocksplitWrapper,
locations,
{"vcf": vcfname,
"dist": window,
"pieces": min(40, threads*4)})
if None in res:
raise Exception("One of the blocksplit processes failed.")
locations = list(itertools.chain.from_iterable(res))
if not len(locations):
logging.warn("Blocksplit returned no blocks. This can happen when "
"an input contains no valid variants.")
locations = [""]
else:
locations = [""]
res = []
try:
res = runParallel(pool,
preprocessWrapper,
itertools.izip(itertools.repeat(vcfname), locations),
{"reference": reference,
"decompose": decompose,
"leftshift": leftshift,
"haploid_x": haploid_x,
"bcf": outputname.endswith(".bcf")})
if None in res:
raise Exception("One of the preprocess jobs failed")
if not res:
raise Exception("No blocks were processed. List of locations: %s" % str(list(locations)))
concatenateParts(outputname, *res)
if outputname.endswith(".vcf.gz"):
runBcftools("index", "-f", "-t", outputname)
else: # use bcf
runBcftools("index", "-f", outputname)
finally:
for r in res:
try:
os.unlink(r)
except:
pass
try:
os.unlink(r + ".tbi")
except:
pass
try:
os.unlink(r + ".csi")
except:
pass
def main():
parser = argparse.ArgumentParser("Haplotype Comparison")
# input
parser.add_argument("-v",
"--version",
dest="version",
action="store_true",
help="Show version number and exit.")
parser.add_argument("-r",
"--reference",
dest="ref",
default=None,
help="Specify a reference file.")
# output
parser.add_argument("-o",
"--report-prefix",
dest="reports_prefix",
default=None,
help="Filename prefix for report output.")
parser.add_argument("--scratch-prefix",
dest="scratch_prefix",
default=None,
help="Directory for scratch files.")
parser.add_argument("--keep-scratch",
dest="delete_scratch",
default=True,
action="store_false",
help="Filename prefix for scratch report output.")
# add quantification args
qfy.updateArgs(parser)
# control preprocessing
pre.updateArgs(parser)
parser.add_argument(
'--convert-gvcf-truth',
dest='convert_gvcf_truth',
action="store_true",
default=False,
help=
'Convert the truth set from genome VCF format to a VCF before processing.'
)
parser.add_argument(
'--convert-gvcf-query',
dest='convert_gvcf_query',
action="store_true",
default=False,
help=
'Convert the query set from genome VCF format to a VCF before processing.'
)
parser.add_argument(
"--preprocess-truth",
dest="preprocessing_truth",
action="store_true",
default=False,
help=
"Preprocess truth file with same settings as query (default is to accept truth in original format)."
)
parser.add_argument(
"--usefiltered-truth",
dest="usefiltered_truth",
action="store_true",
default=False,
help=
"Use filtered variant calls in truth file (by default, only PASS calls in the truth file are used)"
)
parser.add_argument(
"--preprocessing-window-size",
dest="preprocess_window",
default=10000,
type=int,
help=
"Preprocessing window size (variants further apart than that size are not expected to interfere)."
)
parser.add_argument(
"--adjust-conf-regions",
dest="preprocessing_truth_confregions",
action="store_true",
default=True,
help=
"Adjust confident regions to include variant locations. Note this will only include variants "
"that are included in the CONF regions already when viewing with bcftools; this option only "
"makes sure insertions are padded correctly in the CONF regions (to capture these, both the "
"base before and after must be contained in the bed file).")
parser.add_argument("--no-adjust-conf-regions",
dest="preprocessing_truth_confregions",
action="store_false",
help="Do not adjust confident regions for insertions.")
# detailed control of comparison
parser.add_argument(
"--unhappy",
"--no-haplotype-comparison",
dest="no_hc",
action="store_true",
default=False,
help=
"Disable haplotype comparison (only count direct GT matches as TP).")
parser.add_argument(
"-w",
"--window-size",
dest="window",
default=50,
type=int,
help=
"Minimum distance between variants such that they fall into the same superlocus."
)
# xcmp-specific stuff
parser.add_argument(
"--xcmp-enumeration-threshold",
dest="max_enum",
default=16768,
type=int,
help=
"Enumeration threshold / maximum number of sequences to enumerate per block."
)
parser.add_argument(
"--xcmp-expand-hapblocks",
dest="hb_expand",
default=30,
type=int,
help="Expand haplotype blocks by this many basepairs left and right.")
parser.add_argument("--threads",
dest="threads",
default=multiprocessing.cpu_count(),
type=int,
help="Number of threads to use.")
parser.add_argument(
"--engine",
dest="engine",
default="xcmp",
choices=["xcmp", "vcfeval", "scmp-somatic", "scmp-distance"],
help="Comparison engine to use.")
parser.add_argument(
"--engine-vcfeval-path",
dest="engine_vcfeval",
required=False,
default=Haplo.vcfeval.findVCFEval(),
help="This parameter should give the path to the \"rtg\" executable. "
"The default is %s" % Haplo.vcfeval.findVCFEval())
parser.add_argument(
"--engine-vcfeval-template",
dest="engine_vcfeval_template",
required=False,
help=
"Vcfeval needs the reference sequence formatted in its own file format "
"(SDF -- run rtg format -o ref.SDF ref.fa). You can specify this here "
"to save time when running hap.py with vcfeval. If no SDF folder is "
"specified, hap.py will create a temporary one.")
parser.add_argument(
"--scmp-distance",
dest="engine_scmp_distance",
required=False,
default=30,
type=int,
help=
"For distance-based matching (vcfeval and scmp), this is the distance between variants to use."
)
parser.add_argument(
"--lose-match-distance",
dest="engine_scmp_distance",
required=False,
type=int,
help=
"For distance-based matching (vcfeval and scmp), this is the distance between variants to use."
)
if Tools.has_sge:
parser.add_argument(
"--force-interactive",
dest="force_interactive",
default=False,
action="store_true",
help=
"Force running interactively (i.e. when JOB_ID is not in the environment)"
)
parser.add_argument("_vcfs", help="Two VCF files.", default=[], nargs="*")
parser.add_argument(
"--logfile",
dest="logfile",
default=None,
help="Write logging information into file rather than to stderr")
verbosity_options = parser.add_mutually_exclusive_group(required=False)
verbosity_options.add_argument(
"--verbose",
dest="verbose",
default=False,
action="store_true",
help="Raise logging level from warning to info.")
verbosity_options.add_argument(
"--quiet",
dest="quiet",
default=False,
action="store_true",
help="Set logging level to output errors only.")
args, unknown_args = parser.parse_known_args()
if not Tools.has_sge:
args.force_interactive = True
if args.verbose:
loglevel = logging.INFO
elif args.quiet:
loglevel = logging.ERROR
else:
loglevel = logging.WARNING
# reinitialize logging
for handler in logging.root.handlers[:]:
logging.root.removeHandler(handler)
logging.basicConfig(filename=args.logfile,
format='%(asctime)s %(levelname)-8s %(message)s',
level=loglevel)
# remove some safe unknown args
unknown_args = [
x for x in unknown_args if x not in ["--force-interactive"]
]
if len(sys.argv) < 2 or len(unknown_args) > 0:
if unknown_args:
logging.error("Unknown arguments specified : %s " %
str(unknown_args))
parser.print_help()
exit(1)
print "Hap.py %s" % Tools.version
if args.version:
exit(0)
if args.roc:
args.write_vcf = True
# sanity-check regions bed file (HAP-57)
if args.regions_bedfile:
logging.info("Checking input regions.")
if bedOverlapCheck(args.regions_bedfile):
raise Exception(
"The regions bed file (specified using -R) has overlaps, this will not work with xcmp."
" You can either use -T, or run the file through bedtools merge"
)
if args.fp_bedfile and not os.path.exists(args.fp_bedfile):
raise Exception("FP/confident call region bed file does not exist.")
if not args.force_interactive and "JOB_ID" not in os.environ:
parser.print_help()
raise Exception(
"Please qsub me so I get approximately 1 GB of RAM per thread.")
if not args.ref:
args.ref = Tools.defaultReference()
if not args.ref or not os.path.exists(args.ref):
raise Exception("Please specify a valid reference path using -r.")
if not args.reports_prefix:
raise Exception("Please specify an output prefix using -o ")
if not os.path.exists(os.path.dirname(os.path.abspath(
args.reports_prefix))):
raise Exception(
"The output path does not exist. Please specify a valid output path and prefix using -o"
)
if os.path.basename(args.reports_prefix) == "" or os.path.isdir(
args.reports_prefix):
raise Exception(
"The output path should specify a file name prefix. Please specify a valid output path "
"and prefix using -o. For example, -o /tmp/test will create files named /tmp/test* ."
)
# noinspection PyProtectedMember
if not args._vcfs or len(args._vcfs) != 2:
raise Exception("Please specify exactly two input VCFs.")
# noinspection PyProtectedMember
args.vcf1 = args._vcfs[0]
# noinspection PyProtectedMember
args.vcf2 = args._vcfs[1]
if not os.path.exists(args.vcf1):
raise Exception("Input file %s does not exist." % args.vcf1)
if not os.path.exists(args.vcf2):
raise Exception("Input file %s does not exist." % args.vcf2)
tempfiles = []
# turn on allele conversion
if (args.engine == "scmp-somatic" or args.engine == "scmp-distance") \
and not args.somatic_allele_conversion:
args.somatic_allele_conversion = True
if args.engine == "scmp-distance":
args.somatic_allele_conversion = "first"
# somatic allele conversion should also switch off decomposition
if args.somatic_allele_conversion and ("-D" not in sys.argv
and "--decompose" not in sys.argv):
args.preprocessing_decompose = False
# xcmp/scmp support bcf; others don't
if args.engine in ["xcmp", "scmp-somatic", "scmp-distance"] \
and (args.bcf or (args.vcf1.endswith(".bcf") and args.vcf2.endswith(".bcf"))):
internal_format_suffix = ".bcf"
else:
internal_format_suffix = ".vcf.gz"
# write session info and args file
session = sessionInfo()
session["final_args"] = args.__dict__
with open(args.reports_prefix + ".runinfo.json", "w") as sessionfile:
json.dump(session, sessionfile)
try:
logging.info("Comparing %s and %s" % (args.vcf1, args.vcf2))
logging.info("Preprocessing truth: %s" % args.vcf1)
starttime = time.time()
ttf = tempfile.NamedTemporaryFile(delete=False,
dir=args.scratch_prefix,
prefix="truth.pp",
suffix=internal_format_suffix)
ttf.close()
if args.engine.endswith("somatic") and \
args.preprocessing_truth and \
(args.preprocessing_leftshift or args.preprocessing_norm or args.preprocessing_decompose):
args.preprocessing_truth = False
logging.info(
"Turning off pre.py preprocessing for somatic comparisons")
if args.preprocessing_truth:
if args.filter_nonref:
logging.info(
"Filtering out any variants genotyped as <NON_REF>")
## Only converting truth gvcf to vcf if both arguments are true
convert_gvcf_truth = False
if args.convert_gvcf_truth or args.convert_gvcf_to_vcf:
logging.info("Converting genome VCF to VCF")
convert_gvcf_truth = True
tempfiles.append(ttf.name)
tempfiles.append(ttf.name + ".csi")
tempfiles.append(ttf.name + ".tbi")
args.gender = pre.preprocess(
args.vcf1,
ttf.name,
args.ref,
args.locations,
None if args.usefiltered_truth else "*", # filters
args.fixchr,
args.regions_bedfile,
args.targets_bedfile,
args.preprocessing_leftshift
if args.preprocessing_truth else False,
args.preprocessing_decompose
if args.preprocessing_truth else False,
args.preprocessing_norm if args.preprocessing_truth else False,
args.preprocess_window,
args.threads,
args.gender,
args.somatic_allele_conversion,
"TRUTH",
filter_nonref=args.filter_nonref
if args.preprocessing_truth else False,
convert_gvcf_to_vcf=convert_gvcf_truth)
args.vcf1 = ttf.name
if args.fp_bedfile and args.preprocessing_truth_confregions:
conf_temp = Haplo.gvcf2bed.gvcf2bed(args.vcf1, args.ref,
args.fp_bedfile,
args.scratch_prefix)
tempfiles.append(conf_temp)
args.strat_regions.append("CONF_VARS:" + conf_temp)
h1 = vcfextract.extractHeadersJSON(args.vcf1)
elapsed = time.time() - starttime
logging.info("preprocess for %s -- time taken %.2f" %
(args.vcf1, elapsed))
# once we have preprocessed the truth file we can resolve the locations
# doing this here improves the time for query preprocessing below
reference_contigs = set(fastaContigLengths(args.ref).keys())
if not args.locations:
# default set of locations is the overlap between truth and reference
args.locations = list(reference_contigs
& set(h1["tabix"]["chromosomes"]))
if not args.locations:
raise Exception(
"Truth and reference have no chromosomes in common!")
elif type(args.locations) is not list:
args.locations = args.locations.split(",")
args.locations = sorted(args.locations)
logging.info("Preprocessing query: %s" % args.vcf2)
if args.filter_nonref:
logging.info("Filtering out any variants genotyped as <NON_REF>")
## Only converting truth gvcf to vcf if both arguments are true
convert_gvcf_query = False
if args.convert_gvcf_query or args.convert_gvcf_to_vcf:
logging.info("Converting genome VCF to VCF")
convert_gvcf_query = True
starttime = time.time()
if args.pass_only:
filtering = "*"
else:
filtering = args.filters_only
qtf = tempfile.NamedTemporaryFile(delete=False,
dir=args.scratch_prefix,
prefix="query.pp",
suffix=internal_format_suffix)
qtf.close()
tempfiles.append(qtf.name)
tempfiles.append(qtf.name + ".csi")
tempfiles.append(qtf.name + ".tbi")
if args.engine.endswith("somatic") and \
(args.preprocessing_leftshift or args.preprocessing_norm or args.preprocessing_decompose):
args.preprocessing_leftshift = False
args.preprocessing_norm = False
args.preprocessing_decompose = False
logging.info(
"Turning off pre.py preprocessing (query) for somatic comparisons"
)
pre.preprocess(
args.vcf2,
qtf.name,
args.ref,
str(",".join(args.locations)),
filtering,
args.fixchr,
args.regions_bedfile,
args.targets_bedfile,
args.preprocessing_leftshift,
args.preprocessing_decompose,
args.preprocessing_norm,
args.preprocess_window,
args.threads,
args.gender, # same gender as truth above
args.somatic_allele_conversion,
"QUERY",
filter_nonref=args.filter_nonref,
convert_gvcf_to_vcf=convert_gvcf_query)
args.vcf2 = qtf.name
h2 = vcfextract.extractHeadersJSON(args.vcf2)
elapsed = time.time() - starttime
logging.info("preprocess for %s -- time taken %.2f" %
(args.vcf2, elapsed))
if not h1["tabix"]:
raise Exception("Truth file is not indexed after preprocesing.")
if not h2["tabix"]:
raise Exception("Query file is not indexed after preprocessing.")
for _xc in args.locations:
if _xc not in h2["tabix"]["chromosomes"]:
logging.warn("No calls for location %s in query!" % _xc)
pool = getPool(args.threads)
if args.threads > 1 and args.engine == "xcmp":
logging.info("Running using %i parallel processes." % args.threads)
# find balanced pieces
# cap parallelism at 64 since otherwise bcftools concat below might run out
# of file handles
args.pieces = min(args.threads, 64)
res = runParallel(pool, Haplo.blocksplit.blocksplitWrapper,
args.locations, args)
if None in res:
raise Exception("One of the blocksplit processes failed.")
tempfiles += res
args.locations = []
for f in res:
with open(f) as fp:
for l in fp:
ll = l.strip().split("\t", 3)
if len(ll) < 3:
continue
xchr = ll[0]
start = int(ll[1]) + 1
end = int(ll[2])
args.locations.append("%s:%i-%i" % (xchr, start, end))
# count variants before normalisation
if "samples" not in h1 or not h1["samples"]:
raise Exception("Cannot read sample names from truth VCF file")
if "samples" not in h2 or not h2["samples"]:
raise Exception("Cannot read sample names from query VCF file")
tf = tempfile.NamedTemporaryFile(delete=False,
dir=args.scratch_prefix,
prefix="hap.py.result.",
suffix=internal_format_suffix)
tf.close()
tempfiles.append(tf.name)
tempfiles.append(tf.name + ".tbi")
tempfiles.append(tf.name + ".csi")
output_name = tf.name
if args.engine == "xcmp":
# do xcmp
logging.info("Using xcmp for comparison")
res = runParallel(pool, Haplo.xcmp.xcmpWrapper, args.locations,
args)
tempfiles += [x for x in res if x is not None] # VCFs
if None in res:
raise Exception("One of the xcmp jobs failed.")
if len(res) == 0:
raise Exception(
"Input files/regions do not contain variants (0 haplotype blocks were processed)."
)
# concatenate + index
logging.info("Concatenating variants...")
runme_list = [x for x in res if x is not None]
if len(runme_list) == 0:
raise Exception("No outputs to concatenate!")
logging.info("Concatenating...")
bcftools.concatenateParts(output_name, *runme_list)
logging.info("Indexing...")
bcftools.runBcftools("index", output_name)
# passed to quantify
args.type = "xcmp"
# xcmp extracts whichever field we're using into the QQ info field
args.roc_header = args.roc
args.roc = "IQQ"
elif args.engine == "vcfeval":
tempfiles += Haplo.vcfeval.runVCFEval(args.vcf1, args.vcf2,
output_name, args)
# passed to quantify
args.type = "ga4gh"
elif args.engine.startswith("scmp"):
tempfiles += Haplo.scmp.runSCmp(args.vcf1, args.vcf2, output_name,
args)
# passed to quantify
args.type = "ga4gh"
else:
raise Exception("Unknown comparison engine: %s" % args.engine)
if args.preserve_info and args.engine == "vcfeval":
# if we use vcfeval we need to merge the INFO fields back in.
tf = tempfile.NamedTemporaryFile(suffix=".txt", delete=False)
tempfiles.append(tf)
print >> tf, "TRUTH_IN"
print >> tf, "QUERY_IN"
tf.close()
info_file = tempfile.NamedTemporaryFile(suffix=".vcf.gz",
delete=False)
tempfiles.append(info_file.name)
info_file.close()
bcftools.runBcftools("merge", args.vcf1, args.vcf2,
"--force-samples", "-m", "all", "|",
"bcftools", "reheader", "-s", tf.name, "|",
"bcftools", "view", "-o", info_file.name,
"-O", "z")
bcftools.runBcftools("index", info_file.name)
merged_info_file = tempfile.NamedTemporaryFile(suffix=".vcf.gz",
delete=False)
tempfiles.append(merged_info_file.name)
merged_info_file.close()
bcftools.runBcftools("merge", output_vcf, info_file.name, "-m",
"all", "|", "bcftools", "view", "-s",
"^TRUTH_IN,QUERY_IN", "-X", "-U", "-o",
merged_info_file.name, "-O", "z")
output_name = merged_info_file.name
args.in_vcf = [output_name]
args.runner = "hap.py"
qfy.quantify(args)
finally:
if args.delete_scratch:
for x in tempfiles:
try:
os.remove(x)
except:
pass
else:
logging.info("Scratch files kept : %s" % (str(tempfiles)))
def run_quantify(filename,
output_file=None,
write_vcf=False,
regions=None,
reference=Tools.defaultReference(),
locations=None,
threads=1,
output_vtc=False,
output_rocs=False,
qtype=None,
roc_file=None,
roc_val=None,
roc_header=None,
roc_filter=None,
roc_delta=None,
roc_regions=None,
clean_info=True,
strat_fixchr=False):
"""Run quantify and return parsed JSON
:param filename: the VCF file name
:param output_file: output file name (if None, will use a temp file)
:param write_vcf: write annotated VCF (give filename)
:type write_vcf: str
:param regions: dictionary of stratification region names and file names
:param reference: reference fasta path
:param locations: a location to use
:param output_vtc: enable / disable the VTC field
:param output_rocs: enable / disable output of ROCs by QQ level
:param roc_file: filename for a TSV file with ROC observations
:param roc_val: field to use for ROC QQ
:param roc_header: name of ROC value for tables
:param roc_filter: ROC filtering settings
:param roc_delta: ROC minimum spacing between levels
:param roc_regions: List of regions to output full ROCs for
:param clean_info: remove unused INFO fields
:param strat_fixchr: fix chr naming in stratification regions
:returns: parsed counts JSON
"""
if not output_file:
output_file = tempfile.NamedTemporaryFile().name
run_str = "quantify %s -o %s" % (pipes.quote(filename),
pipes.quote(output_file))
run_str += " -r %s" % pipes.quote(reference)
run_str += " --threads %i" % threads
if output_vtc:
run_str += " --output-vtc 1"
else:
run_str += " --output-vtc 0"
if output_rocs:
run_str += " --output-rocs 1"
else:
run_str += " --output-rocs 0"
if qtype:
run_str += " --type %s" % qtype
if roc_file:
run_str += " --output-roc %s" % pipes.quote(roc_file)
if roc_val:
run_str += " --qq %s" % pipes.quote(roc_val)
if roc_header != roc_val:
# for xcmp, we extract the QQ value into the IQQ INFO field
# we pass the original name along here
run_str += " --qq-header %s" % pipes.quote(roc_header)
if roc_filter:
run_str += " --roc-filter '%s'" % pipes.quote(roc_filter)
if roc_delta:
run_str += " --roc-delta %f" % roc_delta
if clean_info:
run_str += " --clean-info 1"
else:
run_str += " --clean-info 0"
if strat_fixchr:
run_str += " --fix-chr-regions 1"
else:
run_str += " --fix-chr-regions 0"
if write_vcf:
if not write_vcf.endswith(".vcf.gz") and not write_vcf.endswith(
".bcf"):
write_vcf += ".vcf.gz"
run_str += " -v %s" % pipes.quote(write_vcf)
if regions:
for k, v in regions.iteritems():
run_str += " -R '%s:%s'" % (k, v)
if roc_regions:
for r in roc_regions:
run_str += " --roc-regions '%s'" % r
location_file = None
if locations:
location_file = _locations_tmp_bed_file(locations)
run_str += " --only '%s'" % location_file
tfe = tempfile.NamedTemporaryFile(delete=False,
prefix="stderr",
suffix=".log")
tfo = tempfile.NamedTemporaryFile(delete=False,
prefix="stdout",
suffix=".log")
logging.info("Running '%s'" % run_str)
try:
subprocess.check_call(run_str, shell=True, stdout=tfo, stderr=tfe)
except:
tfo.close()
tfe.close()
with open(tfo.name) as f:
for l in f:
logging.error("[stdout] " + l.replace("\n", ""))
os.unlink(tfo.name)
with open(tfe.name) as f:
for l in f:
logging.error("[stderr] " + l.replace("\n", ""))
os.unlink(tfe.name)
if location_file:
os.unlink(location_file)
raise
tfo.close()
tfe.close()
with open(tfo.name) as f:
for l in f:
logging.info("[stdout] " + l.replace("\n", ""))
os.unlink(tfo.name)
with open(tfe.name) as f:
for l in f:
logging.info("[stderr] " + l.replace("\n", ""))
os.unlink(tfe.name)
if location_file:
os.unlink(location_file)
if write_vcf and write_vcf.endswith(".bcf"):
runBcftools("index", write_vcf)
elif write_vcf:
to_run = "tabix -p vcf %s" % pipes.quote(write_vcf)
logging.info("Running '%s'" % to_run)
subprocess.check_call(to_run, shell=True)
def main():
parser = argparse.ArgumentParser("Somatic Comparison")
parser.add_argument("truth", help="Truth VCF file")
parser.add_argument("query", help="Query VCF file")
parser.add_argument("-o", "--output", dest="output", required=True,
help="Output file prefix for statistics and feature table (when selected)")
parser.add_argument("-l", "--location", dest="location", default="",
help="Location for bcftools view (e.g. chr1)")
parser.add_argument("-R", "--restrict-regions", dest="regions_bedfile",
default=None, type=str,
help="Restrict analysis to given (sparse) regions (using -R in bcftools).")
parser.add_argument("-T", "--target-regions", dest="targets_bedfile",
default=None, type=str,
help="Restrict analysis to given (dense) regions (using -T in bcftools).")
parser.add_argument("-f", "--false-positives", dest="FP",
help="False-positive region bed file to distinguish UNK from FP")
parser.add_argument("-a", "--ambiguous", dest="ambi", action='append',
help="Ambiguous region bed file(s) to distinguish from FP (e.g. variant only observed "
"in some replicates)")
parser.add_argument("--ambi-fp", dest="ambi_fp", action='store_true', default=False,
help="Use FP calls from ambiguous region files also.")
parser.add_argument("--no-ambi-fp", dest="ambi_fp", action='store_false',
help="Do not use FP calls from ambiguous region files also.")
parser.add_argument("--count-unk", dest="count_unk", action='store_true', default=False,
help="Assume the truth set covers the whole genome and only count FPs in regions "
"specified by the truth VCF or ambiguous/false-positive regions.")
parser.add_argument("--no-count-unk", dest="count_unk", action='store_false',
help="Do not use FP calls from ambiguous region files also.")
parser.add_argument("-e", "--explain_ambiguous", dest="explain_ambiguous", required=False,
default=False, action="store_true",
help="print a table giving the number of ambiguous events per category")
parser.add_argument("-r", "--reference", dest="ref", default=Tools.defaultReference(),
help="Specify a reference file.")
parser.add_argument("--scratch-prefix", dest="scratch_prefix",
default=None,
help="Filename prefix for scratch report output.")
parser.add_argument("--keep-scratch", dest="delete_scratch",
default=True, action="store_false",
help="Filename prefix for scratch report output.")
parser.add_argument("--continue", dest="cont", default=False, action="store_true",
help="Continue from scratch space (i.e. use VCFs in there if they already exist).")
parser.add_argument("-P", "--include-nonpass", dest="inc_nonpass", action="store_true", default=False,
help="Use to include failing variants in comparison.")
parser.add_argument("--feature-table", dest="features", default=False, choices=Somatic.FeatureSet.sets.keys(),
help="Select a feature table to output.")
parser.add_argument("--bam", dest="bams", default=[], action="append",
help="pass one or more BAM files for feature table extraction")
parser.add_argument("--normalize-truth", dest="normalize_truth", default=False, action="store_true",
help="Enable running of bcftools norm on the truth file.")
parser.add_argument("--normalize-query", dest="normalize_query", default=False, action="store_true",
help="Enable running of bcftools norm on the query file.")
parser.add_argument("-N", "--normalize-all", dest="normalize_all", default=False, action="store_true",
help="Enable running of bcftools norm on both truth and query file.")
parser.add_argument("--fixchr-truth", dest="fixchr_truth", action="store_true", default=True,
help="Add chr prefix to truth file (default: true).")
parser.add_argument("--fixchr-query", dest="fixchr_query", action="store_true", default=True,
help="Add chr prefix to query file (default: true).")
parser.add_argument("--fix-chr-truth", dest="fixchr_truth", action="store_true", default=None,
help="Same as --fixchr-truth.")
parser.add_argument("--fix-chr-query", dest="fixchr_query", action="store_true", default=None,
help="Same as --fixchr-query.")
parser.add_argument("--no-fixchr-truth", dest="fixchr_truth", action="store_false", default=False,
help="Disable chr replacement for truth (default: false).")
parser.add_argument("--no-fixchr-query", dest="fixchr_query", action="store_false", default=False,
help="Add chr prefix to query file (default: false).")
parser.add_argument("--no-order-check", dest="disable_order_check", default=False, action="store_true",
help="Disable checking the order of TP features (dev feature).")
parser.add_argument("--roc", dest="roc", default=None, choices=ROC.list(),
help="Create a ROC-style table. This is caller specific "
" - this will override the --feature-table switch!")
parser.add_argument("--bin-afs", dest="af_strat", default=None, action="store_true",
help="Stratify into different AF buckets. This needs to have features available"
"for getting the AF both in truth and query variants.")
parser.add_argument("--af-binsize", dest="af_strat_binsize", default=0.2,
help="Bin size for AF binning (should be < 1). Multiple bin sizes can be specified using a comma, "
"e.g. 0.1,0.2,0.5,0.2 will split at 0.1, 0.3, 0.8 and 1.0.")
parser.add_argument("--af-truth", dest="af_strat_truth", default="I.T_ALT_RATE",
help="Feature name to use for retrieving AF for truth variants (TP and FN)")
parser.add_argument("--af-query", dest="af_strat_query", default="T_AF",
help="Feature name to use for retrieving AF for query variants (FP/UNK/AMBI)")
parser.add_argument("-FN", "--count-filtered-fn", dest="count_filtered_fn", action="store_true",
help="Count filtered vs. absent FN numbers. This requires the -P switch (to use all "
"variants) and either the --feature-table or --roc switch.")
parser.add_argument("--fp-region-size", dest="fpr_size",
help="How to obtain the normalisation constant for FP rate. By default, this will use the FP region bed file size when using"
" --count-unk and the size of all reference contigs that overlap with the location specified in -l otherwise."
" This can be overridden with: 1) a number of nucleotides, or 2) \"auto\" to use the lengths of all contigs that have calls."
" The resulting value is used as fp.region.size.")
parser.add_argument("--ci-level", dest="ci_level", default=0.95, type = float,
help="Confidence level for precision/recall confidence intervals (default: 0.95)")
parser.add_argument("--logfile", dest="logfile", default=None,
help="Write logging information into file rather than to stderr")
verbosity_options = parser.add_mutually_exclusive_group(required=False)
verbosity_options.add_argument("--verbose", dest="verbose", default=False, action="store_true",
help="Raise logging level from warning to info.")
verbosity_options.add_argument("--quiet", dest="quiet", default=False, action="store_true",
help="Set logging level to output errors only.")
args = parser.parse_args()
if args.verbose:
loglevel = logging.INFO
elif args.quiet:
loglevel = logging.ERROR
else:
loglevel = logging.WARNING
try:
if type(args.af_strat_binsize) is str:
args.af_strat_binsize = map(float, args.af_strat_binsize.split(","))
else:
args.af_strat_binsize = map(float, [args.af_strat_binsize])
if not args.af_strat_binsize:
raise Exception("Bin size list is empty")
except:
logging.error("Failed to parse stratification bin size: %s" % str(args.af_strat_binsize))
exit(1)
# reinitialize logging
for handler in logging.root.handlers[:]:
logging.root.removeHandler(handler)
logging.basicConfig(filename=args.logfile,
format='%(asctime)s %(levelname)-8s %(message)s',
level=loglevel)
if args.normalize_all:
args.normalize_truth = True
args.normalize_query = True
if args.roc:
args.roc = ROC.make(args.roc)
args.features = args.roc.ftname
if not args.inc_nonpass:
logging.warn("When creating ROCs without the -P switch, the ROC data points will only "
"include filtered variants (i.e. they will normally end at the caller's "
"quality threshold).")
if not (args.ci_level > 0.0 and args.ci_level < 1.0):
raise Exception("Confidence interval level must be > 0.0 and < 1.0.")
if args.af_strat and not args.features:
raise Exception("To stratify by AFs, a feature table must be selected -- use this switch together "
"with --feature-table or --roc")
if args.count_filtered_fn and (not args.inc_nonpass or not args.features):
raise Exception("Counting filtered / unfiltered FNs only works when a feature table is selected, "
"and when using unfiltered variants. Specify -P --feature-table <...> or use "
"--roc to select a ROC type.")
if args.scratch_prefix:
scratch = os.path.abspath(args.scratch_prefix)
args.delete_scratch = False
Tools.mkdir_p(scratch)
else:
scratch = tempfile.mkdtemp()
logging.info("Scratch path is %s" % scratch)
try:
bams = []
md = None
for x in args.bams:
bams.append(bamStats(x))
if bams:
bres = pandas.concat(bams).groupby("CHROM").mean()
md = {}
for x in bres.index:
logging.info("Mean coverage on %s is %f" % (x, bres.loc[x]["COVERAGE"]))
md[x] = float(bres.loc[x]["COVERAGE"]) * 3.0
logging.info("Normalizing/reading inputs")
ntpath = os.path.join(scratch, "normalized_truth.vcf.gz")
if not (args.cont and os.path.exists(ntpath)):
preprocessVCF(args.truth, ntpath, args.location,
True, # pass_only
args.fixchr_truth, # chrprefix
args.normalize_truth, # norm,
args.regions_bedfile,
args.targets_bedfile,
args.ref)
else:
logging.info("Continuing from %s" % ntpath)
if not (args.cont and os.path.exists(ntpath + ".csi")):
runBcftools("index", ntpath)
nqpath = os.path.join(scratch, "normalized_query.vcf.gz")
if not (args.cont and os.path.exists(nqpath)):
preprocessVCF(args.query, nqpath, args.location,
not args.inc_nonpass, # pass_only
args.fixchr_query, # chrprefix
args.normalize_query, # norm,
args.regions_bedfile,
args.targets_bedfile,
args.ref)
else:
logging.info("Continuing from %s" % nqpath)
if not (args.cont and os.path.exists(nqpath + ".csi")):
runBcftools("index", nqpath)
logging.info("Intersecting")
tpfn_files = all([os.path.exists(os.path.join(scratch, "tpfn", "0000.vcf.gz")),
os.path.exists(os.path.join(scratch, "tpfn", "0001.vcf.gz")),
os.path.exists(os.path.join(scratch, "tpfn", "0002.vcf.gz"))])
tpfn_r_files = all([os.path.exists(os.path.join(scratch, "tpfn", "0000.vcf.gz")),
os.path.exists(os.path.join(scratch, "tpfn", "0001.vcf.gz")),
os.path.exists(os.path.join(scratch, "tpfn", "0002.vcf.gz"))])
if not (args.cont and tpfn_files):
runBcftools("isec", ntpath, nqpath, "-p", os.path.join(scratch, "tpfn"), "-O", "z")
else:
logging.info("Continuing from %s" % os.path.join(scratch, "tpfn"))
if args.features and not (args.cont and tpfn_r_files):
# only need to do this for getting the feature table
runBcftools("isec", nqpath, ntpath, "-p", os.path.join(scratch, "tpfn_r"), "-O", "z")
logging.info("Getting FPs / Ambi / Unk")
fppath = os.path.join(scratch, "fp.vcf.gz")
unkpath = os.path.join(scratch, "unk.vcf.gz")
ambipath = os.path.join(scratch, "ambi.vcf.gz")
# get header to print to unk and ambi VCFs
rununiquepath = os.path.join(scratch, "tpfn", "0001.vcf.gz")
header = runBcftools("view", rununiquepath, "--header-only")
fp = Tools.BGZipFile(fppath, True)
fp.write(header)
unk = Tools.BGZipFile(unkpath, True)
unk.write(header)
ambi = Tools.BGZipFile(ambipath, True)
ambi.write(header)
ambiClasses = Counter()
ambiReasons = Counter()
fpclasses = BedIntervalTree()
if args.ambi:
# can have multiple ambiguous BED files
for aBED in args.ambi:
# auto-label from first value after chr start end
# new ambi files have the label in position 4
# old ones will look weird here.
fpclasses.addFromBed(aBED, lambda xe: xe[4], args.fixchr_truth)
if args.FP:
fpclasses.addFromBed(args.FP, "FP", args.fixchr_truth)
# split VCF into FP, UNK and AMBI
toProcess = gzip.open(rununiquepath, "rb")
for entry in toProcess:
if entry[0] == '#':
continue
fields = entry.strip().split("\t")
chrom = fields[0]
start = int(fields[1])
stop = int(fields[1]) + len(fields[3])
overlap = fpclasses.intersect(chrom, start, stop)
is_fp = False
is_ambi = False
classes_this_pos = set()
for o in overlap:
reason = o.value[0]
if reason == "fp" and args.ambi_fp:
reason = "FP"
elif reason == "fp":
reason = "ambi-fp"
elif reason == "unk":
reason = "ambi-unk"
classes_this_pos.add(reason)
try:
ambiReasons["%s: rep. count %s" % (reason, o.value[1])] += 1
except IndexError:
ambiReasons["%s: rep. count *" % reason] += 1
for x in o.value[3:]:
ambiReasons["%s: %s" % (reason, x)] += 1
if reason == "FP":
is_fp = True
else:
is_ambi = True
for reason in classes_this_pos:
ambiClasses[reason] += 1
if is_fp:
fp.write(entry)
elif is_ambi:
ambi.write(entry)
elif not args.count_unk:
# when we don't have FP regions, unk stuff becomes FP
fp.write(entry)
else:
unk.write(entry)
toProcess.close()
# since 0001.vcf.gz should already be sorted, we can just convert to bgzipped vcf
# and create index
fp.close()
ambi.close()
unk.close()
runBcftools("index", "--tbi", fppath)
runBcftools("index", "--tbi", unkpath)
runBcftools("index", "--tbi", ambipath)
logging.info("Counting variants...")
truthcounts = parseStats(runBcftools("stats", ntpath), "total.truth")
querycounts = parseStats(runBcftools("stats", nqpath), "total.query")
tpcounts = parseStats(runBcftools("stats", os.path.join(scratch, "tpfn", "0002.vcf.gz")), "tp")
fncounts = parseStats(runBcftools("stats", os.path.join(scratch, "tpfn", "0000.vcf.gz")), "fn")
fpcounts = parseStats(runBcftools("stats", fppath), "fp")
ambicounts = parseStats(runBcftools("stats", ambipath), "ambi")
unkcounts = parseStats(runBcftools("stats", unkpath), "unk")
res = pandas.merge(truthcounts, querycounts, on="type")
res = pandas.merge(res, tpcounts, on="type")
res = pandas.merge(res, fpcounts, on="type")
res = pandas.merge(res, fncounts, on="type")
res = pandas.merge(res, unkcounts, on="type")
res = pandas.merge(res, ambicounts, on="type")
# no explicit guarantee that total.query is equal to unk + ambi + fp + tp
# testSum = res["fp"] + res["tp"] + res["unk"] + res["ambi"]
# filter and relabel
res = res[res["type"] != "samples"]
res = res[res["type"] != "multiallelic SNP sites"]
res = res[res["type"] != "multiallelic sites"]
res.loc[res["type"] == "SNPs", "type"] = "SNVs"
metrics_output = makeMetricsObject("som.py.comparison")
if args.ambi and args.explain_ambiguous:
ac = list(ambiClasses.iteritems())
if ac:
ambie = pandas.DataFrame(ac, columns=["class", "count"])
ambie.sort(["class"], inplace=True)
pandas.set_option("display.max_rows", 1000)
pandas.set_option("display.max_columns", 1000)
pandas.set_option("display.width", 1000)
pandas.set_option("display.height", 1100)
logging.info("FP/ambiguity classes with info (multiple classes can "
"overlap):\n" + ambie.to_string(index=False))
# in default mode, print result summary to stdout
if not args.quiet and not args.verbose:
print "FP/ambiguity classes with info (multiple classes can " \
"overlap):\n" + ambie.to_string(index=False)
ambie.to_csv(args.output + ".ambiclasses.csv")
metrics_output["metrics"].append(dataframeToMetricsTable("ambiclasses", ambie))
else:
logging.info("No ambiguous variants.")
ar = list(ambiReasons.iteritems())
if ar:
ambie = pandas.DataFrame(ar, columns=["reason", "count"])
ambie.sort(["reason"], inplace=True)
pandas.set_option("display.max_rows", 1000)
pandas.set_option("display.max_columns", 1000)
pandas.set_option("display.width", 1000)
pandas.set_option("display.height", 1100)
logging.info("Reasons for defining as ambiguous (multiple reasons can overlap):\n" + ambie.to_string(
formatters={'reason': '{{:<{}s}}'.format(ambie['reason'].str.len().max()).format}, index=False))
# in default mode, print result summary to stdout
if not args.quiet and not args.verbose:
print "Reasons for defining as ambiguous (multiple reasons can overlap):\n" + ambie.to_string(
formatters={'reason': '{{:<{}s}}'.format(ambie['reason'].str.len().max()).format}, index=False)
ambie.to_csv(args.output + ".ambireasons.csv")
metrics_output["metrics"].append(dataframeToMetricsTable("ambireasons", ambie))
else:
logging.info("No ambiguous variants.")
if args.features:
logging.info("Extracting features...")
fset = Somatic.FeatureSet.make(args.features)
fset.setChrDepths(md)
logging.info("Collecting TP info (1)...")
tps = fset.collect(os.path.join(scratch, "tpfn", "0002.vcf.gz"), "TP")
# TP_r is a hint for fset, they are both TPs
logging.info("Collecting TP info (2)...")
tps2 = fset.collect(os.path.join(scratch, "tpfn_r", "0002.vcf.gz"), "TP_r")
# this is slow because it tries to sort
# ... which we don't need to do since tps1 and tps2 have the same ordering
logging.info("Sorting...")
tps.sort(["CHROM", "POS"], inplace=True)
tps2.sort(["CHROM", "POS"], inplace=True)
tps = tps.reset_index(drop=True)
tps2 = tps2.reset_index(drop=True)
logging.info("Merging TP info...")
columns_tps = list(tps)
columns_tps2 = list(tps2)
len1 = tps.shape[0]
len2 = tps2.shape[0]
if len1 != len2:
raise Exception("Cannot read TP features, lists have different lengths : %i != %i" % (len1, len2))
if not args.disable_order_check:
logging.info("Checking order %i / %i" % (len1, len2))
for x in xrange(0, len1):
for a in ["CHROM", "POS"]:
if tps.loc[x][a] != tps2.loc[x][a]:
raise Exception("Cannot merge TP features, inputs are out of order at %s / %s" % (
str(tps[x:x + 1]), str(tps2[x:x + 1])))
logging.info("Merging...")
cdata = {
"CHROM": tps["CHROM"],
"POS": tps["POS"],
"tag": tps["tag"]
}
tpc = pandas.DataFrame(cdata, columns=["CHROM", "POS", "tag"])
all_columns = list(set(columns_tps + columns_tps2))
for a in all_columns:
if a in columns_tps and a not in columns_tps2:
tpc[a] = tps[a]
elif a not in columns_tps and a in columns_tps2:
tpc[a] = tps2[a]
elif a not in ["CHROM", "POS", "tag"]:
tpc[a] = tps2[a]
tpc[a + ".truth"] = tps[a]
logging.info("Collecting FP info...")
fps = fset.collect(fppath, "FP")
ambs = fset.collect(ambipath, "AMBI")
logging.info("Collecting FN info...")
fns = fset.collect(os.path.join(scratch, "tpfn", "0000.vcf.gz"), "FN")
renamed = {}
tp_cols = list(tpc)
for col in list(fns):
if col + ".truth" in tp_cols:
renamed[col] = col + ".truth"
fns.rename(columns=renamed, inplace=True)
featurelist = [tpc, fps, fns, ambs]
if unkpath is not None:
logging.info("Collecting UNK info...")
unk = fset.collect(unkpath, "UNK")
featurelist.append(unk)
logging.info("Making feature table...")
featuretable = pandas.concat(featurelist)
# reorder to make more legible
first_columns = ["CHROM", "POS", "tag"]
# noinspection PyTypeChecker
all_columns = list(featuretable)
if "REF" in all_columns:
first_columns.append("REF")
if "REF.truth" in all_columns:
first_columns.append("REF.truth")
if "ALT" in all_columns:
first_columns.append("ALT")
if "ALT.truth" in all_columns:
first_columns.append("ALT.truth")
ordered_columns = first_columns + sorted([x for x in all_columns if x not in first_columns])
featuretable = featuretable[ordered_columns]
# make sure positions are integers
featuretable["POS"] = featuretable["POS"].astype(int)
logging.info("Saving feature table...")
featuretable.to_csv(args.output + ".features.csv", float_format='%.8f')
if args.roc is not None:
roc_table = args.roc.from_table(featuretable)
roc_table.to_csv(args.output + ".roc.csv", float_format='%.8f')
featuretable["FILTER"].fillna("", inplace=True)
featuretable.ix[featuretable["REF"].str.len() < 1, "absent"] = True
featuretable.ix[featuretable["tag"] == "FN", "REF"] = featuretable.ix[featuretable["tag"] == "FN",
"REF.truth"]
featuretable.ix[featuretable["tag"] == "FN", "ALT"] = featuretable.ix[featuretable["tag"] == "FN",
"ALT.truth"]
af_t_feature = args.af_strat_truth
af_q_feature = args.af_strat_query
for vtype in ["records", "SNVs", "indels"]:
if vtype == "SNVs":
featuretable_this_type = featuretable[(featuretable["REF"].str.len() > 0) &
(featuretable["ALT"].str.len() ==
featuretable["REF"].str.len())]
elif vtype == "indels":
featuretable_this_type = featuretable[(featuretable["REF"].str.len() != 1) |
(featuretable["ALT"].str.len() != 1)]
else:
featuretable_this_type = featuretable
if args.count_filtered_fn:
res.ix[res["type"] == vtype, "fp.filtered"] = featuretable_this_type[
(featuretable_this_type["tag"] == "FP") & (featuretable_this_type["FILTER"] != "")].shape[0]
res.ix[res["type"] == vtype, "tp.filtered"] = featuretable_this_type[
(featuretable_this_type["tag"] == "TP") & (featuretable_this_type["FILTER"] != "")].shape[0]
res.ix[res["type"] == vtype, "unk.filtered"] = featuretable_this_type[
(featuretable_this_type["tag"] == "UNK") & (featuretable_this_type["FILTER"] != "")].shape[0]
res.ix[res["type"] == vtype, "ambi.filtered"] = featuretable_this_type[
(featuretable_this_type["tag"] == "AMBI") & (featuretable_this_type["FILTER"] != "")].shape[0]
if args.af_strat:
start = 0.0
current_binsize = args.af_strat_binsize[0]
next_binsize = 0
while start < 1.0:
# include 1 in last interval
end = min(1.000000001, start + current_binsize)
n_tp = featuretable_this_type[(featuretable_this_type["tag"] == "TP") &
(featuretable_this_type[af_t_feature] >= start) &
(featuretable_this_type[af_t_feature] < end)]
n_fn = featuretable_this_type[(featuretable_this_type["tag"] == "FN") &
(featuretable_this_type[af_t_feature] >= start) &
(featuretable_this_type[af_t_feature] < end)]
n_fp = featuretable_this_type[(featuretable_this_type["tag"] == "FP") &
(featuretable_this_type[af_q_feature] >= start) &
(featuretable_this_type[af_q_feature] < end)]
n_ambi = featuretable_this_type[(featuretable_this_type["tag"] == "AMBI") &
(featuretable_this_type[af_q_feature] >= start) &
(featuretable_this_type[af_q_feature] < end)]
n_unk = featuretable_this_type[(featuretable_this_type["tag"] == "UNK") &
(featuretable_this_type[af_q_feature] >= start) &
(featuretable_this_type[af_q_feature] < end)]
r = {"type": "%s.%f-%f" % (vtype, start, end),
"total.truth": n_tp.shape[0] + n_fn.shape[0],
"total.query": n_tp.shape[0] + n_fp.shape[0] + n_ambi.shape[0] + n_unk.shape[0],
"tp": n_tp.shape[0],
"fp": n_fp.shape[0],
"fn": n_fn.shape[0],
"unk": n_unk.shape[0],
"ambi": n_ambi.shape[0], }
if args.count_filtered_fn:
r["fp.filtered"] = n_fp[n_fp["FILTER"] != ""].shape[0]
r["tp.filtered"] = n_tp[n_tp["FILTER"] != ""].shape[0]
r["unk.filtered"] = n_unk[n_unk["FILTER"] != ""].shape[0]
r["ambi.filtered"] = n_ambi[n_ambi["FILTER"] != ""].shape[0]
res = pandas.concat([res, pandas.DataFrame([r])])
if args.roc is not None and (n_tp.shape[0] + n_fn.shape[0] + n_fp.shape[0]) > 0:
roc_table_strat = args.roc.from_table(pandas.concat([n_tp, n_fp, n_fn]))
rtname = "%s.%s.%f-%f.roc.csv" % (args.output, vtype, start, end)
roc_table_strat.to_csv(rtname, float_format='%.8f')
start += current_binsize
next_binsize += 1
if next_binsize >= len(args.af_strat_binsize):
next_binsize = 0
current_binsize = args.af_strat_binsize[next_binsize]
# remove things where we haven't seen any variants in truth and query
res = res[(res["total.truth"] > 0) & (res["total.query"] > 0)]
# summary metrics with confidence intervals
ci_alpha = 1.0 - args.ci_level
recall = binomialCI(res["tp"], res["tp"]+res["fn"], ci_alpha)
precision = binomialCI(res["tp"], res["tp"]+res["fp"], ci_alpha)
res["recall"], res["recall_lower"], res["recall_upper"] = recall
res["recall2"] = res["tp"] / (res["total.truth"])
res["precision"], res["precision_lower"], res["precision_upper"] = precision
res["na"] = res["unk"] / (res["total.query"])
res["ambiguous"] = res["ambi"] / res["total.query"]
any_fp = fpclasses.countbases(label="FP")
fp_region_count = 0
auto_size = True
if args.fpr_size:
try:
fp_region_count = int(args.fpr_size)
auto_size = False
except:
pass
if auto_size:
if any_fp:
if args.location:
chrom, _, rest = args.location.partition(":")
if rest:
start, _, end = rest.partition("_")
if start:
start = int(start)
if end:
end = int(end)
else:
fp_region_count += fpclasses.countbases(chrom, label="FP")
else:
fp_region_count = any_fp
else:
cs = fastaContigLengths(args.ref)
if args.location:
fp_region_count = calculateLength(cs, args.location)
else:
# use all locations we saw calls on
h1 = Tools.vcfextract.extractHeadersJSON(ntpath)
h1_chrs = h1["tabix"]["chromosomes"]
if not h1_chrs:
logging.warn("ntpath is empty")
h1_chrs = []
h2 = Tools.vcfextract.extractHeadersJSON(nqpath)
h2_chrs = h2["tabix"]["chromosomes"]
if not h2_chrs:
logging.warn("nqpath is empty")
h2_chrs = []
combined_chrs = list(set(h1_chrs + h2_chrs))
if len(combined_chrs) > 0:
qlocations = " ".join(combined_chrs)
fp_region_count = calculateLength(cs, qlocations)
else:
fp_region_count = 0
res["fp.region.size"] = fp_region_count
res["fp.rate"] = 1e6 * res["fp"] / res["fp.region.size"]
if args.count_filtered_fn:
res["recall.filtered"] = (res["tp"] - res["tp.filtered"]) / (res["tp"] + res["fn"])
res["precision.filtered"] = (res["tp"] - res["tp.filtered"]) / (res["tp"] - res["tp.filtered"] +
res["fp"] - res["fp.filtered"])
res["fp.rate.filtered"] = 1e6 * (res["fp"] - res["fp.filtered"]) / res["fp.region.size"]
res["na.filtered"] = (res["unk"] - res["unk.filtered"]) / (res["total.query"])
res["ambiguous.filtered"] = (res["ambi"] - res["ambi.filtered"]) / res["total.query"]
# HAP-162 remove inf values
res.replace([np.inf, -np.inf], 0)
metrics_output["metrics"].append(dataframeToMetricsTable("result", res))
vstring = "som.py-%s" % Tools.version
logging.info("\n" + res.to_string())
# in default mode, print result summary to stdout
if not args.quiet and not args.verbose:
print "\n" + res.to_string()
res["sompyversion"] = vstring
vstring = " ".join(sys.argv)
res["sompycmd"] = vstring
res.to_csv(args.output + ".stats.csv")
with open(args.output + ".metrics.json", "w") as fp:
json.dump(metrics_output, fp)
finally:
if args.delete_scratch:
shutil.rmtree(scratch)
else:
logging.info("Scratch kept at %s" % scratch)
def run_quantify(
filename,
output_file=None,
write_vcf=False,
regions=None,
reference=Tools.defaultReference(),
locations=None,
threads=1,
output_vtc=False,
output_rocs=False,
qtype=None,
roc_file=None,
roc_val=None,
roc_filter=None,
roc_delta=None,
clean_info=True,
strat_fixchr=False,
):
"""Run quantify and return parsed JSON
:param filename: the VCF file name
:param output_file: output file name (if None, will use a temp file)
:param write_vcf: write annotated VCF (give filename)
:type write_vcf: str
:param regions: dictionary of stratification region names and file names
:param reference: reference fasta path
:param locations: a location to use
:param output_vtc: enable / disable the VTC field
:param output_rocs: enable / disable output of ROCs by QQ level
:param roc_file: filename for a TSV file with ROC observations
:param roc_val: field to use for ROC QQ
:param roc_filter: ROC filtering settings
:param roc_delta: ROC minimum spacing between levels
:param clean_info: remove unused INFO fields
:param strat_fixchr: fix chr naming in stratification regions
:returns: parsed counts JSON
"""
if not output_file:
output_file = tempfile.NamedTemporaryFile().name
run_str = "quantify '%s' -o '%s'" % (filename.replace(" ", "\\ "), output_file)
run_str += " -r '%s'" % reference.replace(" ", "\\ ")
run_str += " --threads %i" % threads
if output_vtc:
run_str += " --output-vtc 1"
else:
run_str += " --output-vtc 0"
if output_rocs:
run_str += " --output-rocs 1"
else:
run_str += " --output-rocs 0"
if qtype:
run_str += " --type %s" % qtype
if roc_file:
run_str += " --output-roc %s" % roc_file
if roc_val:
run_str += " --qq %s" % roc_val
if roc_filter:
run_str += " --roc-filter '%s'" % roc_filter
if roc_delta:
run_str += " --roc-delta %f" % roc_delta
if clean_info:
run_str += " --clean-info 1"
else:
run_str += " --clean-info 0"
if strat_fixchr:
run_str += " --fix-chr-regions 1"
else:
run_str += " --fix-chr-regions 0"
if write_vcf:
if not write_vcf.endswith(".vcf.gz") and not write_vcf.endswith(".bcf"):
write_vcf += ".vcf.gz"
run_str += " -v '%s'" % write_vcf
if regions:
for k, v in regions.iteritems():
run_str += " -R '%s:%s'" % (k, v)
location_file = None
if locations:
location_file = _locations_tmp_bed_file(locations)
run_str += " --only '%s'" % location_file
tfe = tempfile.NamedTemporaryFile(delete=False, prefix="stderr", suffix=".log")
tfo = tempfile.NamedTemporaryFile(delete=False, prefix="stdout", suffix=".log")
logging.info("Running '%s'" % run_str)
try:
subprocess.check_call(run_str, shell=True, stdout=tfo, stderr=tfe)
except:
tfo.close()
tfe.close()
with open(tfo.name) as f:
for l in f:
logging.error("[stdout] " + l.replace("\n", ""))
os.unlink(tfo.name)
with open(tfe.name) as f:
for l in f:
logging.error("[stderr] " + l.replace("\n", ""))
os.unlink(tfe.name)
if location_file:
os.unlink(location_file)
raise
tfo.close()
tfe.close()
with open(tfo.name) as f:
for l in f:
logging.info("[stdout] " + l.replace("\n", ""))
os.unlink(tfo.name)
with open(tfe.name) as f:
for l in f:
logging.info("[stderr] " + l.replace("\n", ""))
os.unlink(tfe.name)
if location_file:
os.unlink(location_file)
if write_vcf and write_vcf.endswith(".bcf"):
runBcftools("index", write_vcf)
else:
to_run = "tabix -p vcf '%s'" % write_vcf
logging.info("Running '%s'" % to_run)
subprocess.check_call(to_run, shell=True)
def main():
parser = argparse.ArgumentParser("Somatic Comparison")
parser.add_argument("truth", help="Truth VCF file")
parser.add_argument("query", help="Query VCF file")
parser.add_argument(
"-o",
"--output",
dest="output",
required=True,
help="Output file prefix for statistics and feature table (when selected)",
)
parser.add_argument("-l", "--location", dest="location", default="", help="Location for bcftools view (e.g. chr1)")
parser.add_argument(
"-R",
"--restrict-regions",
dest="regions_bedfile",
default=None,
type=str,
help="Restrict analysis to given (sparse) regions (using -R in bcftools).",
)
parser.add_argument(
"-T",
"--target-regions",
dest="targets_bedfile",
default=None,
type=str,
help="Restrict analysis to given (dense) regions (using -T in bcftools).",
)
parser.add_argument(
"-f", "--false-positives", dest="FP", help="False-positive region bed file to distinguish UNK from FP"
)
parser.add_argument(
"-a",
"--ambiguous",
dest="ambi",
action="append",
help="Ambiguous region bed file(s) to distinguish from FP (e.g. variant only observed " "in some replicates)",
)
parser.add_argument(
"--ambiguous-fp",
dest="ambi_fp",
action="store_true",
default=False,
help="Use FP calls from ambiguous region files also.",
)
parser.add_argument(
"-e",
"--explain_ambiguous",
dest="explain_ambiguous",
required=False,
default=False,
action="store_true",
help="print a table giving the number of ambiguous events per category",
)
parser.add_argument(
"-r", "--reference", dest="ref", default=Tools.defaultReference(), help="Specify a reference file."
)
parser.add_argument(
"--scratch-prefix", dest="scratch_prefix", default=None, help="Filename prefix for scratch report output."
)
parser.add_argument(
"--keep-scratch",
dest="delete_scratch",
default=True,
action="store_false",
help="Filename prefix for scratch report output.",
)
parser.add_argument(
"--continue",
dest="cont",
default=False,
action="store_true",
help="Continue from scratch space (i.e. use VCFs in there if they already exist).",
)
parser.add_argument(
"-P",
"--include-nonpass",
dest="inc_nonpass",
action="store_true",
default=False,
help="Use to include failing variants in comparison.",
)
parser.add_argument(
"--feature-table",
dest="features",
default=False,
choices=Somatic.FeatureSet.sets.keys(),
help="Select a feature table to output.",
)
parser.add_argument(
"--bam",
dest="bams",
default=[],
action="append",
help="pass one or more BAM files for feature table extraction",
)
parser.add_argument(
"--normalize-truth",
dest="normalize_truth",
default=False,
action="store_true",
help="Enable running of bcftools norm on the truth file.",
)
parser.add_argument(
"--normalize-query",
dest="normalize_query",
default=False,
action="store_true",
help="Enable running of bcftools norm on the query file.",
)
parser.add_argument(
"-N",
"--normalize-all",
dest="normalize_all",
default=False,
action="store_true",
help="Enable running of bcftools norm on both truth and query file.",
)
parser.add_argument(
"--fix-chr-query",
dest="fixchr_query",
default=False,
action="store_true",
help="Replace numeric chromosome names in the query by chr*-type names",
)
parser.add_argument(
"--fix-chr-truth",
dest="fixchr_truth",
default=False,
action="store_true",
help="Replace numeric chromosome names in the truth by chr*-type names",
)
parser.add_argument(
"--no-order-check",
dest="disable_order_check",
default=False,
action="store_true",
help="Disable checking the order of TP features (dev feature).",
)
parser.add_argument(
"--roc",
dest="roc",
default=None,
choices=ROC.list(),
help="Create a ROC-style table. This is caller specific " " - this will override the --feature-table switch!",
)
parser.add_argument(
"--logfile", dest="logfile", default=None, help="Write logging information into file rather than to stderr"
)
verbosity_options = parser.add_mutually_exclusive_group(required=False)
verbosity_options.add_argument(
"--verbose",
dest="verbose",
default=False,
action="store_true",
help="Raise logging level from warning to info.",
)
verbosity_options.add_argument(
"--quiet", dest="quiet", default=False, action="store_true", help="Set logging level to output errors only."
)
args = parser.parse_args()
if args.verbose:
loglevel = logging.INFO
elif args.quiet:
loglevel = logging.ERROR
else:
loglevel = logging.WARNING
# reinitialize logging
for handler in logging.root.handlers[:]:
logging.root.removeHandler(handler)
logging.basicConfig(filename=args.logfile, format="%(asctime)s %(levelname)-8s %(message)s", level=loglevel)
if args.normalize_all:
args.normalize_truth = True
args.normalize_query = True
if args.roc:
args.roc = ROC.make(args.roc)
args.features = args.roc.ftname
if args.scratch_prefix:
scratch = os.path.abspath(args.scratch_prefix)
args.delete_scratch = False
Tools.mkdir_p(scratch)
else:
scratch = tempfile.mkdtemp()
logging.info("Scratch path is %s" % scratch)
try:
bams = []
md = None
for x in args.bams:
bams.append(bamStats(x))
if bams:
bres = pandas.concat(bams).groupby("CHROM").mean()
md = {}
for x in bres.index:
logging.info("Mean coverage on %s is %f" % (x, bres.loc[x]["COVERAGE"]))
md[x] = float(bres.loc[x]["COVERAGE"]) * 3.0
logging.info("Normalizing/reading inputs")
ntpath = os.path.join(scratch, "normalized_truth.vcf.gz")
if not (args.cont and os.path.exists(ntpath)):
preprocessVCF(
args.truth,
ntpath,
args.location,
True, # pass_only
args.fixchr_truth, # chrprefix
args.normalize_truth, # norm,
args.regions_bedfile,
args.targets_bedfile,
args.ref,
)
else:
logging.info("Continuing from %s" % ntpath)
if not (args.cont and os.path.exists(ntpath + ".csi")):
runBcftools("index", ntpath)
nqpath = os.path.join(scratch, "normalized_query.vcf.gz")
if not (args.cont and os.path.exists(nqpath)):
preprocessVCF(
args.query,
nqpath,
args.location,
not args.inc_nonpass, # pass_only
args.fixchr_query, # chrprefix
args.normalize_query, # norm,
args.regions_bedfile,
args.targets_bedfile,
args.ref,
)
else:
logging.info("Continuing from %s" % nqpath)
if not (args.cont and os.path.exists(nqpath + ".csi")):
runBcftools("index", nqpath)
logging.info("Intersecting")
tpfn_files = all(
[
os.path.exists(os.path.join(scratch, "tpfn", "0000.vcf.gz")),
os.path.exists(os.path.join(scratch, "tpfn", "0001.vcf.gz")),
os.path.exists(os.path.join(scratch, "tpfn", "0002.vcf.gz")),
]
)
tpfn_r_files = all(
[
os.path.exists(os.path.join(scratch, "tpfn", "0000.vcf.gz")),
os.path.exists(os.path.join(scratch, "tpfn", "0001.vcf.gz")),
os.path.exists(os.path.join(scratch, "tpfn", "0002.vcf.gz")),
]
)
if not (args.cont and tpfn_files):
runBcftools("isec", ntpath, nqpath, "-p", os.path.join(scratch, "tpfn"), "-O", "z")
else:
logging.info("Continuing from %s" % os.path.join(scratch, "tpfn"))
if args.features and not (args.cont and tpfn_r_files):
# only need to do this for getting the feature table
runBcftools("isec", nqpath, ntpath, "-p", os.path.join(scratch, "tpfn_r"), "-O", "z")
logging.info("Getting FPs / Ambi / Unk")
fppath = os.path.join(scratch, "fp.vcf.gz")
unkpath = os.path.join(scratch, "unk.vcf.gz")
ambipath = os.path.join(scratch, "ambi.vcf.gz")
# get header to print to unk and ambi VCFs
rununiquepath = os.path.join(scratch, "tpfn", "0001.vcf.gz")
header = runBcftools("view", rununiquepath, "--header-only")
fp = Tools.BGZipFile(fppath, True)
fp.write(header)
unk = Tools.BGZipFile(unkpath, True)
unk.write(header)
ambi = Tools.BGZipFile(ambipath, True)
ambi.write(header)
ambiClasses = Counter()
ambiReasons = Counter()
fpclasses = BedIntervalTree()
if args.ambi:
# can have multiple ambiguous BED files
for aBED in args.ambi:
# auto-label from first value after chr start end
# new ambi files have the label in position 4
# old ones will look weird here.
fpclasses.addFromBed(aBED, lambda xe: xe[4])
if args.FP:
fpclasses.addFromBed(args.FP, "FP")
has_fp = (fpclasses.count("FP") > 0) or (fpclasses.count("fp") > 0 and args.ambi_fp)
# split VCF into FP, UNK and AMBI
toProcess = gzip.open(rununiquepath, "rb")
for entry in toProcess:
if entry[0] == "#":
continue
fields = entry.strip().split("\t")
chrom = fields[0]
start = int(fields[1])
stop = int(fields[1]) + len(fields[3])
overlap = fpclasses.intersect(chrom, start, stop)
is_fp = False
is_ambi = False
classes_this_pos = set()
for o in overlap:
reason = o.value[0]
if reason == "fp" and args.ambi_fp:
reason = "FP"
elif reason == "fp":
reason = "ambi-fp"
elif reason == "unk":
reason = "ambi-unk"
classes_this_pos.add(reason)
try:
ambiReasons["%s: rep. count %s" % (reason, o.value[1])] += 1
except IndexError:
ambiReasons["%s: rep. count *" % reason] += 1
for x in o.value[3:]:
ambiReasons["%s: %s" % (reason, x)] += 1
if reason == "FP":
is_fp = True
else:
is_ambi = True
for reason in classes_this_pos:
ambiClasses[reason] += 1
if is_fp:
fp.write(entry)
elif is_ambi:
ambi.write(entry)
elif not has_fp:
# when we don't have FP regions, unk stuff becomes FP
fp.write(entry)
else:
unk.write(entry)
toProcess.close()
# since 0001.vcf.gz should already be sorted, we can just convert to bgzipped vcf
# and create index
fp.close()
ambi.close()
unk.close()
runBcftools("index", "--tbi", fppath)
runBcftools("index", "--tbi", unkpath)
runBcftools("index", "--tbi", ambipath)
logging.info("Counting variants...")
truthcounts = parseStats(runBcftools("stats", ntpath), "total.truth")
querycounts = parseStats(runBcftools("stats", nqpath), "total.query")
tpcounts = parseStats(runBcftools("stats", os.path.join(scratch, "tpfn", "0002.vcf.gz")), "tp")
fncounts = parseStats(runBcftools("stats", os.path.join(scratch, "tpfn", "0000.vcf.gz")), "fn")
fpcounts = parseStats(runBcftools("stats", fppath), "fp")
ambicounts = parseStats(runBcftools("stats", ambipath), "ambi")
unkcounts = parseStats(runBcftools("stats", unkpath), "unk")
res = pandas.merge(truthcounts, querycounts, on="type")
res = pandas.merge(res, tpcounts, on="type")
res = pandas.merge(res, fpcounts, on="type")
res = pandas.merge(res, fncounts, on="type")
res = pandas.merge(res, unkcounts, on="type")
res = pandas.merge(res, ambicounts, on="type")
# no explicit guarantee that total.query is equal to unk + ambi + fp + tp
# testSum = res["fp"] + res["tp"] + res["unk"] + res["ambi"]
# filter and relabel
res = res[res["type"] != "samples"]
res = res[res["type"] != "multiallelic SNP sites"]
res = res[res["type"] != "multiallelic sites"]
res.loc[res["type"] == "SNPs", "type"] = "SNVs"
res = res[(res["total.truth"] > 0) | (res["total.query"] > 0)]
# use this to use plain row counts rather than stratified bcftools counts
# truthcounts = countVCFRows(ntpath) # , "total.truth")
# querycounts = countVCFRows(nqpath) # , "total.query")
#
# tpcounts = countVCFRows(os.path.join(scratch, "tpfn", "0002.vcf.gz")) #, "tp")
# fncounts = countVCFRows(os.path.join(scratch, "tpfn", "0000.vcf.gz")) #, "fn")
# fpcounts = countVCFRows(fppath) #, "fp")
# ambicounts = countVCFRows(ambipath) #, "ambi")
# unkcounts = countVCFRows(unkpath) #, "unk")
#
# res = pandas.DataFrame({
# "total.truth" : [ truthcounts ],
# "total.query" : [ querycounts ],
# "tp" : [ tpcounts ],
# "fn" : [ fncounts ],
# "fp" : [ fpcounts ],
# "ambi" : [ ambicounts ],
# "unk" : [ unkcounts ]
# })
#
# res["type"] = "records"
# summary metrics
res["recall"] = res["tp"] / (res["tp"] + res["fn"])
res["recall2"] = res["tp"] / (res["total.truth"])
res["precision"] = res["tp"] / (res["tp"] + res["fp"])
res["na"] = res["unk"] / (res["total.query"])
res["ambiguous"] = res["ambi"] / res["total.query"]
metrics_output = makeMetricsObject("som.py.comparison")
metrics_output["metrics"].append(dataframeToMetricsTable("result", res))
vstring = "som.py-%s" % Tools.version
logging.info("\n" + res.to_string())
# in default mode, print result summary to stdout
if not args.quiet and not args.verbose:
print "\n" + res.to_string()
res["sompyversion"] = vstring
vstring = " ".join(sys.argv)
res["sompycmd"] = vstring
if args.ambi and args.explain_ambiguous:
ac = list(ambiClasses.iteritems())
if ac:
ambie = pandas.DataFrame(ac, columns=["class", "count"])
ambie.sort(["class"], inplace=True)
pandas.set_option("display.max_rows", 1000)
pandas.set_option("display.max_columns", 1000)
pandas.set_option("display.width", 1000)
pandas.set_option("display.height", 1100)
logging.info(
"FP/ambiguity classes with info (multiple classes can " "overlap):\n" + ambie.to_string(index=False)
)
# in default mode, print result summary to stdout
if not args.quiet and not args.verbose:
print "FP/ambiguity classes with info (multiple classes can " "overlap):\n" + ambie.to_string(
index=False
)
ambie.to_csv(args.output + ".ambiclasses.csv")
metrics_output["metrics"].append(dataframeToMetricsTable("ambiclasses", ambie))
else:
logging.info("No ambiguous variants.")
ar = list(ambiReasons.iteritems())
if ar:
ambie = pandas.DataFrame(ar, columns=["reason", "count"])
ambie.sort(["reason"], inplace=True)
pandas.set_option("display.max_rows", 1000)
pandas.set_option("display.max_columns", 1000)
pandas.set_option("display.width", 1000)
pandas.set_option("display.height", 1100)
logging.info(
"Reasons for defining as ambiguous (multiple reasons can overlap):\n"
+ ambie.to_string(
formatters={"reason": "{{:<{}s}}".format(ambie["reason"].str.len().max()).format}, index=False
)
)
# in default mode, print result summary to stdout
if not args.quiet and not args.verbose:
print "Reasons for defining as ambiguous (multiple reasons can overlap):\n" + ambie.to_string(
formatters={"reason": "{{:<{}s}}".format(ambie["reason"].str.len().max()).format}, index=False
)
ambie.to_csv(args.output + ".ambireasons.csv")
metrics_output["metrics"].append(dataframeToMetricsTable("ambireasons", ambie))
else:
logging.info("No ambiguous variants.")
res.to_csv(args.output + ".stats.csv")
with open(args.output + ".metrics.json", "w") as fp:
json.dump(metrics_output, fp)
if args.features:
logging.info("Extracting features...")
fset = Somatic.FeatureSet.make(args.features)
fset.setChrDepths(md)
logging.info("Collecting TP info (1)...")
tps = fset.collect(os.path.join(scratch, "tpfn", "0002.vcf.gz"), "TP")
# TP_r is a hint for fset, they are both TPs
logging.info("Collecting TP info (2)...")
tps2 = fset.collect(os.path.join(scratch, "tpfn_r", "0002.vcf.gz"), "TP_r")
# this is slow because it tries to sort
# ... which we don't need to do since tps1 and tps2 have the same ordering
logging.info("Sorting...")
tps.sort(["CHROM", "POS"], inplace=True)
tps2.sort(["CHROM", "POS"], inplace=True)
tps = tps.reset_index(drop=True)
tps2 = tps2.reset_index(drop=True)
logging.info("Merging TP info...")
columns_tps = list(tps)
columns_tps2 = list(tps2)
len1 = tps.shape[0]
len2 = tps.shape[0]
if len1 != len2:
raise Exception("Cannot read TP features, lists have different lengths : %i != %i" % (len1, len2))
if not args.disable_order_check:
logging.info("Checking order %i / %i" % (len1, len2))
for x in xrange(0, len1):
for a in ["CHROM", "POS"]:
if tps.loc[x][a] != tps2.loc[x][a]:
raise Exception(
"Cannot merge TP features, inputs are out of order at %s / %s"
% (str(tps[x : x + 1]), str(tps2[x : x + 1]))
)
logging.info("Merging...")
cdata = {"CHROM": tps["CHROM"], "POS": tps["POS"], "tag": tps["tag"]}
tpc = pandas.DataFrame(cdata, columns=["CHROM", "POS", "tag"])
all_columns = list(set(columns_tps + columns_tps2))
for a in all_columns:
if a in columns_tps and not a in columns_tps2:
tpc[a] = tps[a]
elif not a in columns_tps and a in columns_tps2:
tpc[a] = tps2[a]
elif a not in ["CHROM", "POS", "tag"]:
tpc[a] = tps2[a]
tpc[a + ".truth"] = tps[a]
logging.info("Collecting FP info...")
fps = fset.collect(fppath, "FP")
ambs = fset.collect(fppath, "AMBI")
unks = fset.collect(fppath, "UNK")
logging.info("Collecting FN info...")
fns = fset.collect(os.path.join(scratch, "tpfn", "0000.vcf.gz"), "FN")
renamed = {}
tp_cols = list(tpc)
for col in list(fns):
if col + ".truth" in tp_cols:
renamed[col] = col + ".truth"
fns.rename(columns=renamed, inplace=True)
featurelist = [tpc, fps, fns, ambs, unks]
if unkpath is not None:
logging.info("Collecting UNK info...")
unk = fset.collect(unkpath, "UNK")
featurelist.append(unk)
logging.info("Making feature table...")
featuretable = pandas.concat(featurelist)
# reorder to make more legible
first_columns = ["CHROM", "POS", "tag"]
all_columns = list(featuretable)
if "REF" in all_columns:
first_columns.append("REF")
if "REF.truth" in all_columns:
first_columns.append("REF.truth")
if "ALT" in all_columns:
first_columns.append("ALT")
if "ALT.truth" in all_columns:
first_columns.append("ALT.truth")
ordered_columns = first_columns + sorted([x for x in all_columns if x not in first_columns])
featuretable = featuretable[ordered_columns]
# make sure positions are integers
featuretable["POS"] = featuretable["POS"].astype(int)
logging.info("Saving feature table...")
featuretable.to_csv(args.output + ".features.csv", float_format="%.8f")
if args.roc is not None:
roc_table = args.roc.from_table(featuretable)
roc_table.to_csv(args.output + ".roc.csv", float_format="%.8f")
finally:
if args.delete_scratch:
shutil.rmtree(scratch)
else:
logging.info("Scratch kept at %s" % scratch)
def main():
parser = argparse.ArgumentParser("Haplotype Comparison")
# input
parser.add_argument("-v", "--version", dest="version", action="store_true",
help="Show version number and exit.")
parser.add_argument("-r", "--reference", dest="ref", default=None, help="Specify a reference file.")
# output
parser.add_argument("-o", "--report-prefix", dest="reports_prefix",
default=None,
help="Filename prefix for report output.")
parser.add_argument("--scratch-prefix", dest="scratch_prefix",
default=None,
help="Directory for scratch files.")
parser.add_argument("--keep-scratch", dest="delete_scratch",
default=True, action="store_false",
help="Filename prefix for scratch report output.")
# add quantification args
qfy.updateArgs(parser)
# control preprocessing
pre.updateArgs(parser)
parser.add_argument("--preprocess-truth", dest="preprocessing_truth", action="store_true", default=False,
help="Preprocess truth file with same settings as query (default is to accept truth in original format).")
parser.add_argument("--usefiltered-truth", dest="usefiltered_truth", action="store_true", default=False,
help="Preprocess truth file with same settings as query (default is to accept truth in original format).")
parser.add_argument("--preprocessing-window-size", dest="preprocess_window",
default=10000, type=int,
help="Preprocessing window size (variants further apart than that size are not expected to interfere).")
# detailed control of comparison
parser.add_argument("--unhappy", "--no-haplotype-comparison", dest="no_hc", action="store_true", default=False,
help="Disable haplotype comparison (only count direct GT matches as TP).")
parser.add_argument("-w", "--window-size", dest="window",
default=50, type=int,
help="Minimum distance between variants such that they fall into the same superlocus.")
# xcmp-specific stuff
parser.add_argument("--xcmp-enumeration-threshold", dest="max_enum",
default=16768, type=int,
help="Enumeration threshold / maximum number of sequences to enumerate per block.")
parser.add_argument("--xcmp-expand-hapblocks", dest="hb_expand",
default=30, type=int,
help="Expand haplotype blocks by this many basepairs left and right.")
parser.add_argument("--threads", dest="threads",
default=multiprocessing.cpu_count(), type=int,
help="Number of threads to use.")
parser.add_argument("--engine", dest="engine",
default="xcmp", choices=["xcmp", "vcfeval"],
help="Comparison engine to use.")
parser.add_argument("--engine-vcfeval-path", dest="engine_vcfeval", required=False,
default=Haplo.vcfeval.findVCFEval(),
help="This parameter should give the path to the \"rtg\" executable. "
"The default is %s" % Haplo.vcfeval.findVCFEval())
parser.add_argument("--engine-vcfeval-template", dest="engine_vcfeval_template", required=False,
help="Vcfeval needs the reference sequence formatted in its own file format "
"(SDF -- run rtg format -o ref.SDF ref.fa). You can specify this here "
"to save time when running hap.py with vcfeval. If no SDF folder is "
"specified, hap.py will create a temporary one.")
if Tools.has_sge:
parser.add_argument("--force-interactive", dest="force_interactive",
default=False, action="store_true",
help="Force running interactively (i.e. when JOB_ID is not in the environment)")
parser.add_argument("_vcfs", help="Two VCF files.", default=[], nargs="*")
parser.add_argument("--logfile", dest="logfile", default=None,
help="Write logging information into file rather than to stderr")
verbosity_options = parser.add_mutually_exclusive_group(required=False)
verbosity_options.add_argument("--verbose", dest="verbose", default=False, action="store_true",
help="Raise logging level from warning to info.")
verbosity_options.add_argument("--quiet", dest="quiet", default=False, action="store_true",
help="Set logging level to output errors only.")
args, unknown_args = parser.parse_known_args()
if not Tools.has_sge:
args.force_interactive = True
if args.verbose:
loglevel = logging.INFO
elif args.quiet:
loglevel = logging.ERROR
else:
loglevel = logging.WARNING
# reinitialize logging
for handler in logging.root.handlers[:]:
logging.root.removeHandler(handler)
logging.basicConfig(filename=args.logfile,
format='%(asctime)s %(levelname)-8s %(message)s',
level=loglevel)
# remove some safe unknown args
unknown_args = [x for x in unknown_args if x not in ["--force-interactive"]]
if len(sys.argv) < 2 or len(unknown_args) > 0:
if unknown_args:
logging.error("Unknown arguments specified : %s " % str(unknown_args))
parser.print_help()
exit(1)
if args.version:
print "Hap.py %s" % Tools.version
exit(0)
if args.roc:
args.write_vcf = True
# sanity-check regions bed file (HAP-57)
if args.regions_bedfile:
logging.info("Checking input regions.")
if bedOverlapCheck(args.regions_bedfile):
raise Exception("The regions bed file (specified using -R) has overlaps, this will not work with xcmp."
" You can either use -T, or run the file through bedtools merge")
if args.fp_bedfile and not os.path.exists(args.fp_bedfile):
raise Exception("FP/confident call region bed file does not exist.")
if not args.force_interactive and "JOB_ID" not in os.environ:
parser.print_help()
raise Exception("Please qsub me so I get approximately 1 GB of RAM per thread.")
if not args.ref:
args.ref = Tools.defaultReference()
if not os.path.exists(args.ref):
raise Exception("Please specify a valid reference path using -r.")
if not args.reports_prefix:
raise Exception("Please specify an output prefix using -o ")
if not os.path.exists(os.path.dirname(os.path.abspath(args.reports_prefix))):
raise Exception("The output path does not exist. Please specify a valid output path and prefix using -o")
if os.path.basename(args.reports_prefix) == "" or os.path.isdir(args.reports_prefix):
raise Exception("The output path should specify a file name prefix. Please specify a valid output path "
"and prefix using -o. For example, -o /tmp/test will create files named /tmp/test* .")
# noinspection PyProtectedMember
if not args._vcfs or len(args._vcfs) != 2:
raise Exception("Please specify exactly two input VCFs.")
# noinspection PyProtectedMember
args.vcf1 = args._vcfs[0]
# noinspection PyProtectedMember
args.vcf2 = args._vcfs[1]
if not os.path.exists(args.vcf1):
raise Exception("Input file %s does not exist." % args.vcf1)
if not os.path.exists(args.vcf2):
raise Exception("Input file %s does not exist." % args.vcf2)
tempfiles = []
# xcmp supports bcf; others don't
if args.engine == "xcmp" and (args.bcf or (args.vcf1.endswith(".bcf") and args.vcf2.endswith(".bcf"))):
internal_format_suffix = ".bcf"
else:
internal_format_suffix = ".vcf.gz"
try:
logging.info("Comparing %s and %s" % (args.vcf1, args.vcf2))
logging.info("Preprocessing truth: %s" % args.vcf1)
starttime = time.time()
ttf = tempfile.NamedTemporaryFile(delete=False,
dir=args.scratch_prefix,
prefix="truth.pp",
suffix=internal_format_suffix)
ttf.close()
tempfiles.append(ttf.name)
tempfiles.append(ttf.name + ".csi")
tempfiles.append(ttf.name + ".tbi")
pre.preprocess(args.vcf1,
ttf.name,
args.ref,
args.locations,
None if args.usefiltered_truth else "*", # filters
args.fixchr,
args.regions_bedfile,
args.targets_bedfile,
args.preprocessing_leftshift if args.preprocessing_truth else False,
args.preprocessing_decompose if args.preprocessing_truth else False,
args.preprocessing_norm if args.preprocessing_truth else False,
args.preprocess_window,
args.threads)
args.vcf1 = ttf.name
h1 = vcfextract.extractHeadersJSON(args.vcf1)
elapsed = time.time() - starttime
logging.info("preprocess for %s -- time taken %.2f" % (args.vcf1, elapsed))
# once we have preprocessed the truth file we can resolve the locations
# doing this here improves the time for query preprocessing below
reference_contigs = set(fastaContigLengths(args.ref).keys())
if not args.locations:
# default set of locations is the overlap between truth and reference
args.locations = list(reference_contigs & set(h1["tabix"]["chromosomes"]))
if not args.locations:
raise Exception("Truth and reference have no chromosomes in common!")
elif type(args.locations) is not list:
args.locations = [args.locations]
args.locations = sorted(args.locations)
logging.info("Preprocessing query: %s" % args.vcf2)
starttime = time.time()
if args.pass_only:
filtering = "*"
else:
filtering = args.filters_only
qtf = tempfile.NamedTemporaryFile(delete=False,
dir=args.scratch_prefix,
prefix="query.pp",
suffix=internal_format_suffix)
qtf.close()
tempfiles.append(qtf.name)
tempfiles.append(qtf.name + ".csi")
tempfiles.append(qtf.name + ".tbi")
pre.preprocess(args.vcf2,
qtf.name,
args.ref,
str(",".join(args.locations)),
filtering,
args.fixchr,
args.regions_bedfile,
args.targets_bedfile,
args.preprocessing_leftshift,
args.preprocessing_decompose,
args.preprocessing_norm,
args.preprocess_window,
args.threads)
args.vcf2 = qtf.name
h2 = vcfextract.extractHeadersJSON(args.vcf2)
elapsed = time.time() - starttime
logging.info("preprocess for %s -- time taken %.2f" % (args.vcf2, elapsed))
if not h1["tabix"]:
raise Exception("Truth file is not indexed after preprocesing.")
if not h2["tabix"]:
raise Exception("Query file is not indexed after preprocessing.")
for _xc in args.locations:
if _xc not in h2["tabix"]["chromosomes"]:
logging.warn("No calls for location %s in query!" % _xc)
pool = getPool(args.threads)
if args.threads > 1 and args.engine == "xcmp":
logging.info("Running using %i parallel processes." % args.threads)
# find balanced pieces
# cap parallelism at 64 since otherwise bcftools concat below might run out
# of file handles
args.pieces = min(args.threads, 64)
res = runParallel(pool, Haplo.blocksplit.blocksplitWrapper, args.locations, args)
if None in res:
raise Exception("One of the blocksplit processes failed.")
tempfiles += res
args.locations = []
for f in res:
with open(f) as fp:
for l in fp:
ll = l.strip().split("\t", 3)
if len(ll) < 3:
continue
xchr = ll[0]
start = int(ll[1]) + 1
end = int(ll[2])
args.locations.append("%s:%i-%i" % (xchr, start, end))
# count variants before normalisation
if "samples" not in h1 or not h1["samples"]:
raise Exception("Cannot read sample names from truth VCF file")
if "samples" not in h2 or not h2["samples"]:
raise Exception("Cannot read sample names from query VCF file")
tf = tempfile.NamedTemporaryFile(delete=False,
dir=args.scratch_prefix,
prefix="hap.py.result.",
suffix=internal_format_suffix)
tf.close()
tempfiles.append(tf.name)
tempfiles.append(tf.name + ".tbi")
tempfiles.append(tf.name + ".csi")
output_name = tf.name
if args.engine == "xcmp":
# do xcmp
logging.info("Using xcmp for comparison")
res = runParallel(pool, Haplo.xcmp.xcmpWrapper, args.locations, args)
tempfiles += [x for x in res if x is not None] # VCFs
if None in res:
raise Exception("One of the xcmp jobs failed.")
if len(res) == 0:
raise Exception("Input files/regions do not contain variants (0 haplotype blocks were processed).")
# concatenate + index
logging.info("Concatenating variants...")
runme_list = [x for x in res if x is not None]
if len(runme_list) == 0:
raise Exception("No outputs to concatenate!")
logging.info("Concatenating...")
bcftools.concatenateParts(output_name, *runme_list)
logging.info("Indexing...")
bcftools.runBcftools("index", output_name)
# passed to quantify
args.type = "xcmp"
# xcmp extracts whichever field we're using into the QQ info field
args.roc = "IQQ"
elif args.engine == "vcfeval":
tempfiles += Haplo.vcfeval.runVCFEval(args.vcf1, args.vcf2, output_name, args)
# passed to quantify
args.type = "ga4gh"
else:
raise Exception("Unknown comparison engine: %s" % args.engine)
args.in_vcf = [output_name]
args.runner = "hap.py"
qfy.quantify(args)
finally:
if args.delete_scratch:
for x in tempfiles:
try:
os.remove(x)
except:
pass
else:
logging.info("Scratch files kept : %s" % (str(tempfiles)))
def main():
args = parse_args()
if args.scratch_prefix:
scratch = os.path.abspath(args.scratch_prefix)
args.delete_scratch = False
Tools.mkdir_p(scratch)
else:
scratch = tempfile.mkdtemp()
logging.info("Scratch path is %s" % scratch)
try:
bams = []
md = None
for x in args.bams:
bams.append(bamStats(x))
if bams:
bres = pandas.concat(bams).groupby("CHROM").mean()
md = {}
for x in bres.index:
logging.info("Mean coverage on %s is %f" %
(x, bres.loc[x]["COVERAGE"]))
md[x] = float(bres.loc[x]["COVERAGE"]) * 3.0
logging.info("Normalizing/reading inputs")
ntpath = os.path.join(scratch, "normalized_truth.vcf.gz")
if not (args.cont and os.path.exists(ntpath)):
preprocessVCF(
args.truth,
ntpath,
args.location,
True, # pass_only
args.fixchr_truth, # chrprefix
args.normalize_truth, # norm,
args.regions_bedfile,
args.targets_bedfile,
args.ref)
else:
logging.info("Continuing from %s" % ntpath)
if not (args.cont and os.path.exists(ntpath + ".csi")):
runBcftools("index", ntpath)
nqpath = os.path.join(scratch, "normalized_query.vcf.gz")
if not (args.cont and os.path.exists(nqpath)):
preprocessVCF(
args.query,
nqpath,
args.location,
not args.inc_nonpass, # pass_only
args.fixchr_query, # chrprefix
args.normalize_query, # norm,
args.regions_bedfile,
args.targets_bedfile,
args.ref)
else:
logging.info("Continuing from %s" % nqpath)
if not (args.cont and os.path.exists(nqpath + ".csi")):
runBcftools("index", nqpath)
logging.info("Intersecting")
tpfn_files = all([
os.path.exists(os.path.join(scratch, "tpfn", "0000.vcf.gz")),
os.path.exists(os.path.join(scratch, "tpfn", "0001.vcf.gz")),
os.path.exists(os.path.join(scratch, "tpfn", "0002.vcf.gz"))
])
tpfn_r_files = all([
os.path.exists(os.path.join(scratch, "tpfn", "0000.vcf.gz")),
os.path.exists(os.path.join(scratch, "tpfn", "0001.vcf.gz")),
os.path.exists(os.path.join(scratch, "tpfn", "0002.vcf.gz"))
])
if not (args.cont and tpfn_files):
runBcftools("isec", ntpath, nqpath, "-p",
os.path.join(scratch, "tpfn"), "-O", "z")
else:
logging.info("Continuing from %s" % os.path.join(scratch, "tpfn"))
if args.features and not (args.cont and tpfn_r_files):
# only need to do this for getting the feature table
runBcftools("isec", nqpath, ntpath, "-p",
os.path.join(scratch, "tpfn_r"), "-O", "z")
logging.info("Getting FPs / Ambi / Unk")
fppath = os.path.join(scratch, "fp.vcf.gz")
unkpath = os.path.join(scratch, "unk.vcf.gz")
ambipath = os.path.join(scratch, "ambi.vcf.gz")
# get header to print to unk and ambi VCFs
rununiquepath = os.path.join(scratch, "tpfn", "0001.vcf.gz")
header = runBcftools("view", rununiquepath, "--header-only")
fp = Tools.BGZipFile(fppath, True)
fp.write(header)
unk = Tools.BGZipFile(unkpath, True)
unk.write(header)
ambi = Tools.BGZipFile(ambipath, True)
ambi.write(header)
ambiClasses = Counter()
ambiReasons = Counter()
fpclasses = BedIntervalTree()
if args.ambi:
# can have multiple ambiguous BED files
for aBED in args.ambi:
# auto-label from first value after chr start end
# new ambi files have the label in position 4
# old ones will look weird here.
fpclasses.addFromBed(aBED, lambda xe: xe[4], args.fixchr_truth)
if args.FP:
fpclasses.addFromBed(args.FP, "FP", args.fixchr_truth)
# split VCF into FP, UNK and AMBI
toProcess = gzip.open(rununiquepath, "rb")
for entry in toProcess:
if entry[0] == '#':
continue
fields = entry.strip().split("\t")
chrom = fields[0]
start = int(fields[1])
stop = int(fields[1]) + len(fields[3])
overlap = fpclasses.intersect(chrom, start, stop)
is_fp = False
is_ambi = False
classes_this_pos = set()
for o in overlap:
reason = o.value[0]
if reason == "fp" and args.ambi_fp:
reason = "FP"
elif reason == "fp":
reason = "ambi-fp"
elif reason == "unk":
reason = "ambi-unk"
classes_this_pos.add(reason)
try:
ambiReasons["%s: rep. count %s" %
(reason, o.value[1])] += 1
except IndexError:
ambiReasons["%s: rep. count *" % reason] += 1
for x in o.value[3:]:
ambiReasons["%s: %s" % (reason, x)] += 1
if reason == "FP":
is_fp = True
else:
is_ambi = True
for reason in classes_this_pos:
ambiClasses[reason] += 1
if is_fp:
fp.write(entry)
elif is_ambi:
ambi.write(entry)
elif not args.count_unk:
# when we don't have FP regions, unk stuff becomes FP
fp.write(entry)
else:
unk.write(entry)
toProcess.close()
# since 0001.vcf.gz should already be sorted, we can just convert to bgzipped vcf
# and create index
fp.close()
ambi.close()
unk.close()
runBcftools("index", "--tbi", fppath)
runBcftools("index", "--tbi", unkpath)
runBcftools("index", "--tbi", ambipath)
logging.info("Counting variants...")
truthcounts = parseStats(runBcftools("stats", ntpath), "total.truth")
querycounts = parseStats(runBcftools("stats", nqpath), "total.query")
tpcounts = parseStats(
runBcftools("stats", os.path.join(scratch, "tpfn", "0002.vcf.gz")),
"tp")
fncounts = parseStats(
runBcftools("stats", os.path.join(scratch, "tpfn", "0000.vcf.gz")),
"fn")
fpcounts = parseStats(runBcftools("stats", fppath), "fp")
ambicounts = parseStats(runBcftools("stats", ambipath), "ambi")
unkcounts = parseStats(runBcftools("stats", unkpath), "unk")
res = pandas.merge(truthcounts, querycounts, on="type")
res = pandas.merge(res, tpcounts, on="type")
res = pandas.merge(res, fpcounts, on="type")
res = pandas.merge(res, fncounts, on="type")
res = pandas.merge(res, unkcounts, on="type")
res = pandas.merge(res, ambicounts, on="type")
# no explicit guarantee that total.query is equal to unk + ambi + fp + tp
# testSum = res["fp"] + res["tp"] + res["unk"] + res["ambi"]
# filter and relabel
res = res[res["type"] != "samples"]
res = res[res["type"] != "multiallelic SNP sites"]
res = res[res["type"] != "multiallelic sites"]
res.loc[res["type"] == "SNPs", "type"] = "SNVs"
metrics_output = makeMetricsObject("som.py.comparison")
if args.ambi and args.explain_ambiguous:
ac = list(ambiClasses.iteritems())
if ac:
ambie = pandas.DataFrame(ac, columns=["class", "count"])
ambie.sort_values(["class"], inplace=True)
pandas.set_option("display.max_rows", 1000)
pandas.set_option("display.max_columns", 1000)
pandas.set_option("display.width", 1000)
pandas.set_option("display.height", 1100)
logging.info(
"FP/ambiguity classes with info (multiple classes can "
"overlap):\n" + ambie.to_string(index=False))
# in default mode, print result summary to stdout
if not args.quiet and not args.verbose:
print "FP/ambiguity classes with info (multiple classes can " \
"overlap):\n" + ambie.to_string(index=False)
ambie.to_csv(args.output + ".ambiclasses.csv")
metrics_output["metrics"].append(
dataframeToMetricsTable("ambiclasses", ambie))
else:
logging.info("No ambiguous variants.")
ar = list(ambiReasons.iteritems())
if ar:
ambie = pandas.DataFrame(ar, columns=["reason", "count"])
ambie.sort_values(["reason"], inplace=True)
pandas.set_option("display.max_rows", 1000)
pandas.set_option("display.max_columns", 1000)
pandas.set_option("display.width", 1000)
pandas.set_option("display.height", 1100)
logging.info(
"Reasons for defining as ambiguous (multiple reasons can overlap):\n"
+ ambie.to_string(formatters={
'reason':
'{{:<{}s}}'.format(
ambie['reason'].str.len().max()).format
},
index=False))
# in default mode, print result summary to stdout
if not args.quiet and not args.verbose:
print "Reasons for defining as ambiguous (multiple reasons can overlap):\n" + ambie.to_string(
formatters={
'reason':
'{{:<{}s}}'.format(
ambie['reason'].str.len().max()).format
},
index=False)
ambie.to_csv(args.output + ".ambireasons.csv")
metrics_output["metrics"].append(
dataframeToMetricsTable("ambireasons", ambie))
else:
logging.info("No ambiguous variants.")
if args.features:
logging.info("Extracting features...")
fset = Somatic.FeatureSet.make(args.features)
fset.setChrDepths(md)
logging.info("Collecting TP info (1)...")
tps = fset.collect(os.path.join(scratch, "tpfn", "0002.vcf.gz"),
"TP")
# TP_r is a hint for fset, they are both TPs
logging.info("Collecting TP info (2)...")
tps2 = fset.collect(os.path.join(scratch, "tpfn_r", "0002.vcf.gz"),
"TP_r")
# this is slow because it tries to sort
# ... which we don't need to do since tps1 and tps2 have the same ordering
logging.info("Sorting...")
tps.sort_values(["CHROM", "POS"], inplace=True)
tps2.sort_values(["CHROM", "POS"], inplace=True)
tps = tps.reset_index(drop=True)
tps2 = tps2.reset_index(drop=True)
logging.info("Merging TP info...")
columns_tps = list(tps)
columns_tps2 = list(tps2)
len1 = tps.shape[0]
len2 = tps2.shape[0]
if len1 != len2:
raise Exception(
"Cannot read TP features, lists have different lengths : %i != %i"
% (len1, len2))
if not args.disable_order_check:
logging.info("Checking order %i / %i" % (len1, len2))
for x in xrange(0, len1):
for a in ["CHROM", "POS"]:
if tps.loc[x][a] != tps2.loc[x][a]:
raise Exception(
"Cannot merge TP features, inputs are out of order at %s / %s"
% (str(tps[x:x + 1]), str(tps2[x:x + 1])))
logging.info("Merging...")
cdata = {
"CHROM": tps["CHROM"],
"POS": tps["POS"],
"tag": tps["tag"]
}
tpc = pandas.DataFrame(cdata, columns=["CHROM", "POS", "tag"])
all_columns = list(set(columns_tps + columns_tps2))
for a in all_columns:
if a in columns_tps and a not in columns_tps2:
tpc[a] = tps[a]
elif a not in columns_tps and a in columns_tps2:
tpc[a] = tps2[a]
elif a not in ["CHROM", "POS", "tag"]:
tpc[a] = tps2[a]
tpc[a + ".truth"] = tps[a]
logging.info("Collecting FP info...")
fps = fset.collect(fppath, "FP")
ambs = fset.collect(ambipath, "AMBI")
logging.info("Collecting FN info...")
fns = fset.collect(os.path.join(scratch, "tpfn", "0000.vcf.gz"),
"FN")
renamed = {}
tp_cols = list(tpc)
for col in list(fns):
if col + ".truth" in tp_cols:
renamed[col] = col + ".truth"
fns.rename(columns=renamed, inplace=True)
featurelist = [tpc, fps, fns, ambs]
if unkpath is not None:
logging.info("Collecting UNK info...")
unk = fset.collect(unkpath, "UNK")
featurelist.append(unk)
logging.info("Making feature table...")
featuretable = pandas.concat(featurelist)
# reorder to make more legible
first_columns = ["CHROM", "POS", "tag"]
# noinspection PyTypeChecker
all_columns = list(featuretable)
if "REF" in all_columns:
first_columns.append("REF")
if "REF.truth" in all_columns:
first_columns.append("REF.truth")
if "ALT" in all_columns:
first_columns.append("ALT")
if "ALT.truth" in all_columns:
first_columns.append("ALT.truth")
ordered_columns = first_columns + sorted(
[x for x in all_columns if x not in first_columns])
featuretable = featuretable[ordered_columns]
# make sure positions are integers
featuretable["POS"] = featuretable["POS"].astype(int)
logging.info("Saving feature table...")
featuretable.to_csv(args.output + ".features.csv",
float_format='%.8f')
if args.roc is not None:
roc_table = args.roc.from_table(featuretable)
roc_table.to_csv(args.output + ".roc.csv", float_format='%.8f')
featuretable["FILTER"].fillna("", inplace=True)
featuretable.ix[featuretable["REF"].str.len() < 1, "absent"] = True
featuretable.ix[featuretable["tag"] == "FN",
"REF"] = featuretable.ix[featuretable["tag"] ==
"FN", "REF.truth"]
featuretable.ix[featuretable["tag"] == "FN",
"ALT"] = featuretable.ix[featuretable["tag"] ==
"FN", "ALT.truth"]
af_t_feature = args.af_strat_truth
af_q_feature = args.af_strat_query
for vtype in ["records", "SNVs", "indels"]:
featuretable["vtype"] = resolve_vtype(args)
featuretable_this_type = featuretable
if args.count_filtered_fn:
res.ix[res["type"] == vtype,
"fp.filtered"] = featuretable_this_type[
(featuretable_this_type["tag"] == "FP")
& (featuretable_this_type["FILTER"] != ""
)].shape[0]
res.ix[res["type"] == vtype,
"tp.filtered"] = featuretable_this_type[
(featuretable_this_type["tag"] == "TP")
& (featuretable_this_type["FILTER"] != ""
)].shape[0]
res.ix[res["type"] == vtype,
"unk.filtered"] = featuretable_this_type[
(featuretable_this_type["tag"] == "UNK")
& (featuretable_this_type["FILTER"] != ""
)].shape[0]
res.ix[res["type"] == vtype,
"ambi.filtered"] = featuretable_this_type[
(featuretable_this_type["tag"] == "AMBI")
& (featuretable_this_type["FILTER"] != ""
)].shape[0]
if args.af_strat:
start = 0.0
end = 1.0
current_binsize = args.af_strat_binsize[0]
next_binsize = 0
while start < 1.0:
# include 1 in last interval
end = start + current_binsize
if end >= 1:
end = 1.00000001
if start >= end:
break
n_tp = featuretable_this_type[
(featuretable_this_type["tag"] == "TP")
& (featuretable_this_type[af_t_feature] >= start) &
(featuretable_this_type[af_t_feature] < end)]
n_fn = featuretable_this_type[
(featuretable_this_type["tag"] == "FN")
& (featuretable_this_type[af_t_feature] >= start) &
(featuretable_this_type[af_t_feature] < end)]
n_fp = featuretable_this_type[
(featuretable_this_type["tag"] == "FP")
& (featuretable_this_type[af_q_feature] >= start) &
(featuretable_this_type[af_q_feature] < end)]
n_ambi = featuretable_this_type[
(featuretable_this_type["tag"] == "AMBI")
& (featuretable_this_type[af_q_feature] >= start) &
(featuretable_this_type[af_q_feature] < end)]
n_unk = featuretable_this_type[
(featuretable_this_type["tag"] == "UNK")
& (featuretable_this_type[af_q_feature] >= start) &
(featuretable_this_type[af_q_feature] < end)]
r = {
"type":
"%s.%f-%f" % (vtype, start, end),
"total.truth":
n_tp.shape[0] + n_fn.shape[0],
"total.query":
n_tp.shape[0] + n_fp.shape[0] + n_ambi.shape[0] +
n_unk.shape[0],
"tp":
n_tp.shape[0],
"fp":
n_fp.shape[0],
"fn":
n_fn.shape[0],
"unk":
n_unk.shape[0],
"ambi":
n_ambi.shape[0]
}
if args.count_filtered_fn:
r["fp.filtered"] = n_fp[
n_fp["FILTER"] != ""].shape[0]
r["tp.filtered"] = n_tp[
n_tp["FILTER"] != ""].shape[0]
r["unk.filtered"] = n_unk[
n_unk["FILTER"] != ""].shape[0]
r["ambi.filtered"] = n_ambi[
n_ambi["FILTER"] != ""].shape[0]
res = pandas.concat([res, pandas.DataFrame([r])])
if args.roc is not None and (n_tp.shape[0] +
n_fn.shape[0] +
n_fp.shape[0]) > 0:
roc_table_strat = args.roc.from_table(
pandas.concat([n_tp, n_fp, n_fn]))
rtname = "%s.%s.%f-%f.roc.csv" % (
args.output, vtype, start, end)
roc_table_strat.to_csv(rtname, float_format='%.8f')
start = end
next_binsize += 1
if next_binsize >= len(args.af_strat_binsize):
next_binsize = 0
current_binsize = args.af_strat_binsize[next_binsize]
if not args.af_strat:
res = res[(res["total.truth"] > 0)]
# summary metrics with confidence intervals
ci_alpha = 1.0 - args.ci_level
recall = binomialCI(res["tp"], res["tp"] + res["fn"], ci_alpha)
precision = binomialCI(res["tp"], res["tp"] + res["fp"], ci_alpha)
res["recall"], res["recall_lower"], res["recall_upper"] = recall
res["recall2"] = res["tp"] / (res["total.truth"])
res["precision"], res["precision_lower"], res[
"precision_upper"] = precision
res["na"] = res["unk"] / (res["total.query"])
res["ambiguous"] = res["ambi"] / res["total.query"]
any_fp = fpclasses.countbases(label="FP")
fp_region_count = 0
auto_size = True
if args.fpr_size:
try:
fp_region_count = int(args.fpr_size)
auto_size = False
except:
pass
if auto_size:
if any_fp:
if args.location:
chrom, _, rest = args.location.partition(":")
if rest:
start, _, end = rest.partition("_")
if start:
start = int(start)
if end:
end = int(end)
else:
fp_region_count += fpclasses.countbases(chrom,
label="FP")
else:
fp_region_count = any_fp
else:
cs = fastaContigLengths(args.ref)
if args.location:
fp_region_count = calculateLength(cs, args.location)
else:
# use all locations we saw calls on
h1 = Tools.vcfextract.extractHeadersJSON(ntpath)
h1_chrs = h1["tabix"]["chromosomes"]
if not h1_chrs:
logging.warn("No contigs in truth file")
h1_chrs = []
if len(h1_chrs) > 0:
qlocations = " ".join(h1_chrs)
fp_region_count = calculateLength(cs, qlocations)
else:
fp_region_count = 0
res["fp.region.size"] = fp_region_count
res["fp.rate"] = 1e6 * res["fp"] / res["fp.region.size"]
if args.count_filtered_fn:
res["recall.filtered"] = (res["tp"] - res["tp.filtered"]) / (
res["tp"] + res["fn"])
res["precision.filtered"] = (res["tp"] - res["tp.filtered"]) / (
res["tp"] - res["tp.filtered"] + res["fp"] -
res["fp.filtered"])
res["fp.rate.filtered"] = 1e6 * (
res["fp"] - res["fp.filtered"]) / res["fp.region.size"]
res["na.filtered"] = (res["unk"] -
res["unk.filtered"]) / (res["total.query"])
res["ambiguous.filtered"] = (
res["ambi"] - res["ambi.filtered"]) / res["total.query"]
# HAP-162 remove inf values
res.replace([np.inf, -np.inf], 0)
metrics_output["metrics"].append(dataframeToMetricsTable(
"result", res))
vstring = "som.py-%s" % Tools.version
logging.info("\n" + res.to_string())
# in default mode, print result summary to stdout
if not args.quiet and not args.verbose:
print "\n" + res.to_string()
res["sompyversion"] = vstring
vstring = " ".join(sys.argv)
res["sompycmd"] = vstring
# save results
res.to_csv(args.output + ".stats.csv")
with open(args.output + ".metrics.json", "w") as fp:
json.dump(metrics_output, fp)
if args.happy_stats:
# parse saved feature table as the one in memory has been updated
featuretable = pandas.read_csv(args.output + ".features.csv",
low_memory=False,
dtype={"FILTER": str})
# hap.py summary.csv
summary = summary_from_featuretable(featuretable, args)
summary.to_csv(args.output + ".summary.csv")
# hap.py extended.csv
if args.af_strat:
extended = extended_from_featuretable(featuretable, args)
extended.to_csv(args.output + ".extended.csv",
index=False,
na_rep="NA")
finally:
if args.delete_scratch:
shutil.rmtree(scratch)
else:
logging.info("Scratch kept at %s" % scratch)
def main():
parser = argparse.ArgumentParser("Somatic Comparison")
parser.add_argument("truth", help="Truth VCF file")
parser.add_argument("query", help="Query VCF file")
parser.add_argument("-o", "--output", dest="output", required=True,
help="Output file prefix for statistics and feature table (when selected)")
parser.add_argument("-l", "--location", dest="location", default="",
help="Location for bcftools view (e.g. chr1)")
parser.add_argument("-R", "--restrict-regions", dest="regions_bedfile",
default=None, type=str,
help="Restrict analysis to given (sparse) regions (using -R in bcftools).")
parser.add_argument("-T", "--target-regions", dest="targets_bedfile",
default=None, type=str,
help="Restrict analysis to given (dense) regions (using -T in bcftools).")
parser.add_argument("-f", "--false-positives", dest="FP",
help="False-positive region bed file to distinguish UNK from FP")
parser.add_argument("-a", "--ambiguous", dest="ambi", action='append',
help="Ambiguous region bed file(s) to distinguish from FP (e.g. variant only observed "
"in some replicates)")
parser.add_argument("--ambi-fp", dest="ambi_fp", action='store_true', default=False,
help="Use FP calls from ambiguous region files also.")
parser.add_argument("--no-ambi-fp", dest="ambi_fp", action='store_false',
help="Do not use FP calls from ambiguous region files also.")
parser.add_argument("--count-unk", dest="count_unk", action='store_true', default=False,
help="Assume the truth set covers the whole genome and only count FPs in regions "
"specified by the truth VCF or ambiguous/false-positive regions.")
parser.add_argument("--no-count-unk", dest="count_unk", action='store_false',
help="Do not use FP calls from ambiguous region files also.")
parser.add_argument("-e", "--explain_ambiguous", dest="explain_ambiguous", required=False,
default=False, action="store_true",
help="print a table giving the number of ambiguous events per category")
parser.add_argument("-r", "--reference", dest="ref", default=Tools.defaultReference(),
help="Specify a reference file.")
parser.add_argument("--scratch-prefix", dest="scratch_prefix",
default=None,
help="Filename prefix for scratch report output.")
parser.add_argument("--keep-scratch", dest="delete_scratch",
default=True, action="store_false",
help="Filename prefix for scratch report output.")
parser.add_argument("--continue", dest="cont", default=False, action="store_true",
help="Continue from scratch space (i.e. use VCFs in there if they already exist).")
parser.add_argument("-P", "--include-nonpass", dest="inc_nonpass", action="store_true", default=False,
help="Use to include failing variants in comparison.")
parser.add_argument("--feature-table", dest="features", default=False, choices=Somatic.FeatureSet.sets.keys(),
help="Select a feature table to output.")
parser.add_argument("--bam", dest="bams", default=[], action="append",
help="pass one or more BAM files for feature table extraction")
parser.add_argument("--normalize-truth", dest="normalize_truth", default=False, action="store_true",
help="Enable running of bcftools norm on the truth file.")
parser.add_argument("--normalize-query", dest="normalize_query", default=False, action="store_true",
help="Enable running of bcftools norm on the query file.")
parser.add_argument("-N", "--normalize-all", dest="normalize_all", default=False, action="store_true",
help="Enable running of bcftools norm on both truth and query file.")
parser.add_argument("--fixchr-truth", dest="fixchr_truth", action="store_true", default=True,
help="Add chr prefix to truth file (default: true).")
parser.add_argument("--fixchr-query", dest="fixchr_query", action="store_true", default=True,
help="Add chr prefix to query file (default: true).")
parser.add_argument("--fix-chr-truth", dest="fixchr_truth", action="store_true", default=None,
help="Same as --fixchr-truth.")
parser.add_argument("--fix-chr-query", dest="fixchr_query", action="store_true", default=None,
help="Same as --fixchr-query.")
parser.add_argument("--no-fixchr-truth", dest="fixchr_truth", action="store_false", default=False,
help="Disable chr replacement for truth (default: false).")
parser.add_argument("--no-fixchr-query", dest="fixchr_query", action="store_false", default=False,
help="Add chr prefix to query file (default: false).")
parser.add_argument("--no-order-check", dest="disable_order_check", default=False, action="store_true",
help="Disable checking the order of TP features (dev feature).")
parser.add_argument("--roc", dest="roc", default=None, choices=ROC.list(),
help="Create a ROC-style table. This is caller specific "
" - this will override the --feature-table switch!")
parser.add_argument("--bin-afs", dest="af_strat", default=None, action="store_true",
help="Stratify into different AF buckets. This needs to have features available"
"for getting the AF both in truth and query variants.")
parser.add_argument("--af-binsize", dest="af_strat_binsize", default=0.2,
help="Bin size for AF binning (should be < 1). Multiple bin sizes can be specified using a comma, "
"e.g. 0.1,0.2,0.5,0.2 will split at 0.1, 0.3, 0.8 and 1.0.")
parser.add_argument("--af-truth", dest="af_strat_truth", default="I.T_ALT_RATE",
help="Feature name to use for retrieving AF for truth variants (TP and FN)")
parser.add_argument("--af-query", dest="af_strat_query", default="T_AF",
help="Feature name to use for retrieving AF for query variants (FP/UNK/AMBI)")
parser.add_argument("-FN", "--count-filtered-fn", dest="count_filtered_fn", action="store_true",
help="Count filtered vs. absent FN numbers. This requires the -P switch (to use all "
"variants) and either the --feature-table or --roc switch.")
parser.add_argument("--fp-region-size", dest="fpr_size",
help="How to obtain the normalisation constant for FP rate. By default, this will use the FP region bed file size when using"
" --count-unk and the size of all reference contigs that overlap with the location specified in -l otherwise."
" This can be overridden with: 1) a number of nucleotides, or 2) \"auto\" to use the lengths of all contigs that have calls."
" The resulting value is used as fp.region.size.")
parser.add_argument("--logfile", dest="logfile", default=None,
help="Write logging information into file rather than to stderr")
verbosity_options = parser.add_mutually_exclusive_group(required=False)
verbosity_options.add_argument("--verbose", dest="verbose", default=False, action="store_true",
help="Raise logging level from warning to info.")
verbosity_options.add_argument("--quiet", dest="quiet", default=False, action="store_true",
help="Set logging level to output errors only.")
args = parser.parse_args()
if args.verbose:
loglevel = logging.INFO
elif args.quiet:
loglevel = logging.ERROR
else:
loglevel = logging.WARNING
try:
if type(args.af_strat_binsize) is str:
args.af_strat_binsize = map(float, args.af_strat_binsize.split(","))
else:
args.af_strat_binsize = map(float, [args.af_strat_binsize])
if not args.af_strat_binsize:
raise Exception("Bin size list is empty")
except:
logging.error("Failed to parse stratification bin size: %s" % str(args.af_strat_binsize))
exit(1)
# reinitialize logging
for handler in logging.root.handlers[:]:
logging.root.removeHandler(handler)
logging.basicConfig(filename=args.logfile,
format='%(asctime)s %(levelname)-8s %(message)s',
level=loglevel)
if args.normalize_all:
args.normalize_truth = True
args.normalize_query = True
if args.roc:
args.roc = ROC.make(args.roc)
args.features = args.roc.ftname
if not args.inc_nonpass:
logging.warn("When creating ROCs without the -P switch, the ROC data points will only "
"include filtered variants (i.e. they will normally end at the caller's "
"quality threshold).")
if args.af_strat and not args.features:
raise Exception("To stratify by AFs, a feature table must be selected -- use this switch together "
"with --feature-table or --roc")
if args.count_filtered_fn and (not args.inc_nonpass or not args.features):
raise Exception("Counting filtered / unfiltered FNs only works when a feature table is selected, "
"and when using unfiltered variants. Specify -P --feature-table <...> or use "
"--roc to select a ROC type.")
if args.scratch_prefix:
scratch = os.path.abspath(args.scratch_prefix)
args.delete_scratch = False
Tools.mkdir_p(scratch)
else:
scratch = tempfile.mkdtemp()
logging.info("Scratch path is %s" % scratch)
try:
bams = []
md = None
for x in args.bams:
bams.append(bamStats(x))
if bams:
bres = pandas.concat(bams).groupby("CHROM").mean()
md = {}
for x in bres.index:
logging.info("Mean coverage on %s is %f" % (x, bres.loc[x]["COVERAGE"]))
md[x] = float(bres.loc[x]["COVERAGE"]) * 3.0
logging.info("Normalizing/reading inputs")
ntpath = os.path.join(scratch, "normalized_truth.vcf.gz")
if not (args.cont and os.path.exists(ntpath)):
preprocessVCF(args.truth, ntpath, args.location,
True, # pass_only
args.fixchr_truth, # chrprefix
args.normalize_truth, # norm,
args.regions_bedfile,
args.targets_bedfile,
args.ref)
else:
logging.info("Continuing from %s" % ntpath)
if not (args.cont and os.path.exists(ntpath + ".csi")):
runBcftools("index", ntpath)
nqpath = os.path.join(scratch, "normalized_query.vcf.gz")
if not (args.cont and os.path.exists(nqpath)):
preprocessVCF(args.query, nqpath, args.location,
not args.inc_nonpass, # pass_only
args.fixchr_query, # chrprefix
args.normalize_query, # norm,
args.regions_bedfile,
args.targets_bedfile,
args.ref)
else:
logging.info("Continuing from %s" % nqpath)
if not (args.cont and os.path.exists(nqpath + ".csi")):
runBcftools("index", nqpath)
logging.info("Intersecting")
tpfn_files = all([os.path.exists(os.path.join(scratch, "tpfn", "0000.vcf.gz")),
os.path.exists(os.path.join(scratch, "tpfn", "0001.vcf.gz")),
os.path.exists(os.path.join(scratch, "tpfn", "0002.vcf.gz"))])
tpfn_r_files = all([os.path.exists(os.path.join(scratch, "tpfn", "0000.vcf.gz")),
os.path.exists(os.path.join(scratch, "tpfn", "0001.vcf.gz")),
os.path.exists(os.path.join(scratch, "tpfn", "0002.vcf.gz"))])
if not (args.cont and tpfn_files):
runBcftools("isec", ntpath, nqpath, "-p", os.path.join(scratch, "tpfn"), "-O", "z")
else:
logging.info("Continuing from %s" % os.path.join(scratch, "tpfn"))
if args.features and not (args.cont and tpfn_r_files):
# only need to do this for getting the feature table
runBcftools("isec", nqpath, ntpath, "-p", os.path.join(scratch, "tpfn_r"), "-O", "z")
logging.info("Getting FPs / Ambi / Unk")
fppath = os.path.join(scratch, "fp.vcf.gz")
unkpath = os.path.join(scratch, "unk.vcf.gz")
ambipath = os.path.join(scratch, "ambi.vcf.gz")
# get header to print to unk and ambi VCFs
rununiquepath = os.path.join(scratch, "tpfn", "0001.vcf.gz")
header = runBcftools("view", rununiquepath, "--header-only")
fp = Tools.BGZipFile(fppath, True)
fp.write(header)
unk = Tools.BGZipFile(unkpath, True)
unk.write(header)
ambi = Tools.BGZipFile(ambipath, True)
ambi.write(header)
ambiClasses = Counter()
ambiReasons = Counter()
fpclasses = BedIntervalTree()
if args.ambi:
# can have multiple ambiguous BED files
for aBED in args.ambi:
# auto-label from first value after chr start end
# new ambi files have the label in position 4
# old ones will look weird here.
fpclasses.addFromBed(aBED, lambda xe: xe[4], args.fixchr_truth)
if args.FP:
fpclasses.addFromBed(args.FP, "FP", args.fixchr_truth)
# split VCF into FP, UNK and AMBI
toProcess = gzip.open(rununiquepath, "rb")
for entry in toProcess:
if entry[0] == '#':
continue
fields = entry.strip().split("\t")
chrom = fields[0]
start = int(fields[1])
stop = int(fields[1]) + len(fields[3])
overlap = fpclasses.intersect(chrom, start, stop)
is_fp = False
is_ambi = False
classes_this_pos = set()
for o in overlap:
reason = o.value[0]
if reason == "fp" and args.ambi_fp:
reason = "FP"
elif reason == "fp":
reason = "ambi-fp"
elif reason == "unk":
reason = "ambi-unk"
classes_this_pos.add(reason)
try:
ambiReasons["%s: rep. count %s" % (reason, o.value[1])] += 1
except IndexError:
ambiReasons["%s: rep. count *" % reason] += 1
for x in o.value[3:]:
ambiReasons["%s: %s" % (reason, x)] += 1
if reason == "FP":
is_fp = True
else:
is_ambi = True
for reason in classes_this_pos:
ambiClasses[reason] += 1
if is_fp:
fp.write(entry)
elif is_ambi:
ambi.write(entry)
elif not args.count_unk:
# when we don't have FP regions, unk stuff becomes FP
fp.write(entry)
else:
unk.write(entry)
toProcess.close()
# since 0001.vcf.gz should already be sorted, we can just convert to bgzipped vcf
# and create index
fp.close()
ambi.close()
unk.close()
runBcftools("index", "--tbi", fppath)
runBcftools("index", "--tbi", unkpath)
runBcftools("index", "--tbi", ambipath)
logging.info("Counting variants...")
truthcounts = parseStats(runBcftools("stats", ntpath), "total.truth")
querycounts = parseStats(runBcftools("stats", nqpath), "total.query")
tpcounts = parseStats(runBcftools("stats", os.path.join(scratch, "tpfn", "0002.vcf.gz")), "tp")
fncounts = parseStats(runBcftools("stats", os.path.join(scratch, "tpfn", "0000.vcf.gz")), "fn")
fpcounts = parseStats(runBcftools("stats", fppath), "fp")
ambicounts = parseStats(runBcftools("stats", ambipath), "ambi")
unkcounts = parseStats(runBcftools("stats", unkpath), "unk")
res = pandas.merge(truthcounts, querycounts, on="type")
res = pandas.merge(res, tpcounts, on="type")
res = pandas.merge(res, fpcounts, on="type")
res = pandas.merge(res, fncounts, on="type")
res = pandas.merge(res, unkcounts, on="type")
res = pandas.merge(res, ambicounts, on="type")
# no explicit guarantee that total.query is equal to unk + ambi + fp + tp
# testSum = res["fp"] + res["tp"] + res["unk"] + res["ambi"]
# filter and relabel
res = res[res["type"] != "samples"]
res = res[res["type"] != "multiallelic SNP sites"]
res = res[res["type"] != "multiallelic sites"]
res.loc[res["type"] == "SNPs", "type"] = "SNVs"
metrics_output = makeMetricsObject("som.py.comparison")
if args.ambi and args.explain_ambiguous:
ac = list(ambiClasses.iteritems())
if ac:
ambie = pandas.DataFrame(ac, columns=["class", "count"])
ambie.sort(["class"], inplace=True)
pandas.set_option("display.max_rows", 1000)
pandas.set_option("display.max_columns", 1000)
pandas.set_option("display.width", 1000)
pandas.set_option("display.height", 1100)
logging.info("FP/ambiguity classes with info (multiple classes can "
"overlap):\n" + ambie.to_string(index=False))
# in default mode, print result summary to stdout
if not args.quiet and not args.verbose:
print "FP/ambiguity classes with info (multiple classes can " \
"overlap):\n" + ambie.to_string(index=False)
ambie.to_csv(args.output + ".ambiclasses.csv")
metrics_output["metrics"].append(dataframeToMetricsTable("ambiclasses", ambie))
else:
logging.info("No ambiguous variants.")
ar = list(ambiReasons.iteritems())
if ar:
ambie = pandas.DataFrame(ar, columns=["reason", "count"])
ambie.sort(["reason"], inplace=True)
pandas.set_option("display.max_rows", 1000)
pandas.set_option("display.max_columns", 1000)
pandas.set_option("display.width", 1000)
pandas.set_option("display.height", 1100)
logging.info("Reasons for defining as ambiguous (multiple reasons can overlap):\n" + ambie.to_string(
formatters={'reason': '{{:<{}s}}'.format(ambie['reason'].str.len().max()).format}, index=False))
# in default mode, print result summary to stdout
if not args.quiet and not args.verbose:
print "Reasons for defining as ambiguous (multiple reasons can overlap):\n" + ambie.to_string(
formatters={'reason': '{{:<{}s}}'.format(ambie['reason'].str.len().max()).format}, index=False)
ambie.to_csv(args.output + ".ambireasons.csv")
metrics_output["metrics"].append(dataframeToMetricsTable("ambireasons", ambie))
else:
logging.info("No ambiguous variants.")
if args.features:
logging.info("Extracting features...")
fset = Somatic.FeatureSet.make(args.features)
fset.setChrDepths(md)
logging.info("Collecting TP info (1)...")
tps = fset.collect(os.path.join(scratch, "tpfn", "0002.vcf.gz"), "TP")
# TP_r is a hint for fset, they are both TPs
logging.info("Collecting TP info (2)...")
tps2 = fset.collect(os.path.join(scratch, "tpfn_r", "0002.vcf.gz"), "TP_r")
# this is slow because it tries to sort
# ... which we don't need to do since tps1 and tps2 have the same ordering
logging.info("Sorting...")
tps.sort(["CHROM", "POS"], inplace=True)
tps2.sort(["CHROM", "POS"], inplace=True)
tps = tps.reset_index(drop=True)
tps2 = tps2.reset_index(drop=True)
logging.info("Merging TP info...")
columns_tps = list(tps)
columns_tps2 = list(tps2)
len1 = tps.shape[0]
len2 = tps2.shape[0]
if len1 != len2:
raise Exception("Cannot read TP features, lists have different lengths : %i != %i" % (len1, len2))
if not args.disable_order_check:
logging.info("Checking order %i / %i" % (len1, len2))
for x in xrange(0, len1):
for a in ["CHROM", "POS"]:
if tps.loc[x][a] != tps2.loc[x][a]:
raise Exception("Cannot merge TP features, inputs are out of order at %s / %s" % (
str(tps[x:x + 1]), str(tps2[x:x + 1])))
logging.info("Merging...")
cdata = {
"CHROM": tps["CHROM"],
"POS": tps["POS"],
"tag": tps["tag"]
}
tpc = pandas.DataFrame(cdata, columns=["CHROM", "POS", "tag"])
all_columns = list(set(columns_tps + columns_tps2))
for a in all_columns:
if a in columns_tps and a not in columns_tps2:
tpc[a] = tps[a]
elif a not in columns_tps and a in columns_tps2:
tpc[a] = tps2[a]
elif a not in ["CHROM", "POS", "tag"]:
tpc[a] = tps2[a]
tpc[a + ".truth"] = tps[a]
logging.info("Collecting FP info...")
fps = fset.collect(fppath, "FP")
ambs = fset.collect(ambipath, "AMBI")
logging.info("Collecting FN info...")
fns = fset.collect(os.path.join(scratch, "tpfn", "0000.vcf.gz"), "FN")
renamed = {}
tp_cols = list(tpc)
for col in list(fns):
if col + ".truth" in tp_cols:
renamed[col] = col + ".truth"
fns.rename(columns=renamed, inplace=True)
featurelist = [tpc, fps, fns, ambs]
if unkpath is not None:
logging.info("Collecting UNK info...")
unk = fset.collect(unkpath, "UNK")
featurelist.append(unk)
logging.info("Making feature table...")
featuretable = pandas.concat(featurelist)
# reorder to make more legible
first_columns = ["CHROM", "POS", "tag"]
# noinspection PyTypeChecker
all_columns = list(featuretable)
if "REF" in all_columns:
first_columns.append("REF")
if "REF.truth" in all_columns:
first_columns.append("REF.truth")
if "ALT" in all_columns:
first_columns.append("ALT")
if "ALT.truth" in all_columns:
first_columns.append("ALT.truth")
ordered_columns = first_columns + sorted([x for x in all_columns if x not in first_columns])
featuretable = featuretable[ordered_columns]
# make sure positions are integers
featuretable["POS"] = featuretable["POS"].astype(int)
logging.info("Saving feature table...")
featuretable.to_csv(args.output + ".features.csv", float_format='%.8f')
if args.roc is not None:
roc_table = args.roc.from_table(featuretable)
roc_table.to_csv(args.output + ".roc.csv", float_format='%.8f')
featuretable["FILTER"].fillna("", inplace=True)
featuretable.ix[featuretable["REF"].str.len() < 1, "absent"] = True
featuretable.ix[featuretable["tag"] == "FN", "REF"] = featuretable.ix[featuretable["tag"] == "FN",
"REF.truth"]
featuretable.ix[featuretable["tag"] == "FN", "ALT"] = featuretable.ix[featuretable["tag"] == "FN",
"ALT.truth"]
af_t_feature = args.af_strat_truth
af_q_feature = args.af_strat_query
for vtype in ["records", "SNVs", "indels"]:
if vtype == "SNVs":
featuretable_this_type = featuretable[(featuretable["REF"].str.len() > 0) &
(featuretable["ALT"].str.len() ==
featuretable["REF"].str.len())]
elif vtype == "indels":
featuretable_this_type = featuretable[(featuretable["REF"].str.len() != 1) |
(featuretable["ALT"].str.len() != 1)]
else:
featuretable_this_type = featuretable
if args.count_filtered_fn:
res.ix[res["type"] == vtype, "fp.filtered"] = featuretable_this_type[
(featuretable_this_type["tag"] == "FP") & (featuretable_this_type["FILTER"] != "")].shape[0]
res.ix[res["type"] == vtype, "tp.filtered"] = featuretable_this_type[
(featuretable_this_type["tag"] == "TP") & (featuretable_this_type["FILTER"] != "")].shape[0]
res.ix[res["type"] == vtype, "unk.filtered"] = featuretable_this_type[
(featuretable_this_type["tag"] == "UNK") & (featuretable_this_type["FILTER"] != "")].shape[0]
res.ix[res["type"] == vtype, "ambi.filtered"] = featuretable_this_type[
(featuretable_this_type["tag"] == "AMBI") & (featuretable_this_type["FILTER"] != "")].shape[0]
if args.af_strat:
start = 0.0
current_binsize = args.af_strat_binsize[0]
next_binsize = 0
while start < 1.0:
# include 1 in last interval
end = min(1.000000001, start + current_binsize)
n_tp = featuretable_this_type[(featuretable_this_type["tag"] == "TP") &
(featuretable_this_type[af_t_feature] >= start) &
(featuretable_this_type[af_t_feature] < end)]
n_fn = featuretable_this_type[(featuretable_this_type["tag"] == "FN") &
(featuretable_this_type[af_t_feature] >= start) &
(featuretable_this_type[af_t_feature] < end)]
n_fp = featuretable_this_type[(featuretable_this_type["tag"] == "FP") &
(featuretable_this_type[af_q_feature] >= start) &
(featuretable_this_type[af_q_feature] < end)]
n_ambi = featuretable_this_type[(featuretable_this_type["tag"] == "AMBI") &
(featuretable_this_type[af_q_feature] >= start) &
(featuretable_this_type[af_q_feature] < end)]
n_unk = featuretable_this_type[(featuretable_this_type["tag"] == "UNK") &
(featuretable_this_type[af_q_feature] >= start) &
(featuretable_this_type[af_q_feature] < end)]
r = {"type": "%s.%f-%f" % (vtype, start, end),
"total.truth": n_tp.shape[0] + n_fn.shape[0],
"total.query": n_tp.shape[0] + n_fp.shape[0] + n_ambi.shape[0] + n_unk.shape[0],
"tp": n_tp.shape[0],
"fp": n_fp.shape[0],
"fn": n_fn.shape[0],
"unk": n_unk.shape[0],
"ambi": n_ambi.shape[0], }
if args.count_filtered_fn:
r["fp.filtered"] = n_fp[n_fp["FILTER"] != ""].shape[0]
r["tp.filtered"] = n_tp[n_tp["FILTER"] != ""].shape[0]
r["unk.filtered"] = n_unk[n_unk["FILTER"] != ""].shape[0]
r["ambi.filtered"] = n_ambi[n_ambi["FILTER"] != ""].shape[0]
res = pandas.concat([res, pandas.DataFrame([r])])
if args.roc is not None and (n_tp.shape[0] + n_fn.shape[0] + n_fp.shape[0]) > 0:
roc_table_strat = args.roc.from_table(pandas.concat([n_tp, n_fp, n_fn]))
rtname = "%s.%s.%f-%f.roc.csv" % (args.output, vtype, start, end)
roc_table_strat.to_csv(rtname, float_format='%.8f')
start += current_binsize
next_binsize += 1
if next_binsize >= len(args.af_strat_binsize):
next_binsize = 0
current_binsize = args.af_strat_binsize[next_binsize]
# remove things where we haven't seen any variants in truth and query
res = res[(res["total.truth"] > 0) & (res["total.query"] > 0)]
# summary metrics
res["recall"] = res["tp"] / (res["tp"] + res["fn"])
res["recall2"] = res["tp"] / (res["total.truth"])
res["precision"] = res["tp"] / (res["tp"] + res["fp"])
res["na"] = res["unk"] / (res["total.query"])
res["ambiguous"] = res["ambi"] / res["total.query"]
any_fp = fpclasses.countbases(label="FP")
fp_region_count = 0
auto_size = True
if args.fpr_size:
try:
fp_region_count = int(args.fpr_size)
auto_size = False
except:
pass
if auto_size:
if any_fp:
if args.location:
chrom, _, rest = args.location.partition(":")
if rest:
start, _, end = rest.partition("_")
if start:
start = int(start)
if end:
end = int(end)
else:
fp_region_count += fpclasses.countbases(chrom, label="FP")
else:
fp_region_count = any_fp
else:
cs = fastaContigLengths(args.ref)
if args.location:
fp_region_count = calculateLength(cs, args.location)
else:
# use all locations we saw calls on
h1 = Tools.vcfextract.extractHeadersJSON(ntpath)
h1_chrs = h1["tabix"]["chromosomes"]
if not h1_chrs:
logging.warn("ntpath is empty")
h1_chrs = []
h2 = Tools.vcfextract.extractHeadersJSON(nqpath)
h2_chrs = h2["tabix"]["chromosomes"]
if not h2_chrs:
logging.warn("nqpath is empty")
h2_chrs = []
combined_chrs = list(set(h1_chrs + h2_chrs))
if len(combined_chrs) > 0:
qlocations = " ".join(combined_chrs)
fp_region_count = calculateLength(cs, qlocations)
else:
fp_region_count = 0
res["fp.region.size"] = fp_region_count
res["fp.rate"] = 1e6 * res["fp"] / res["fp.region.size"]
if args.count_filtered_fn:
res["recall.filtered"] = (res["tp"] - res["tp.filtered"]) / (res["tp"] + res["fn"])
res["precision.filtered"] = (res["tp"] - res["tp.filtered"]) / (res["tp"] - res["tp.filtered"] +
res["fp"] - res["fp.filtered"])
res["fp.rate.filtered"] = 1e6 * (res["fp"] - res["fp.filtered"]) / res["fp.region.size"]
res["na.filtered"] = (res["unk"] - res["unk.filtered"]) / (res["total.query"])
res["ambiguous.filtered"] = (res["ambi"] - res["ambi.filtered"]) / res["total.query"]
# HAP-162 remove inf values
res.replace([np.inf, -np.inf], 0)
metrics_output["metrics"].append(dataframeToMetricsTable("result", res))
vstring = "som.py-%s" % Tools.version
logging.info("\n" + res.to_string())
# in default mode, print result summary to stdout
if not args.quiet and not args.verbose:
print "\n" + res.to_string()
res["sompyversion"] = vstring
vstring = " ".join(sys.argv)
res["sompycmd"] = vstring
res.to_csv(args.output + ".stats.csv")
with open(args.output + ".metrics.json", "w") as fp:
json.dump(metrics_output, fp)
finally:
if args.delete_scratch:
shutil.rmtree(scratch)
else:
logging.info("Scratch kept at %s" % scratch)
def preprocess(vcf_input,
vcf_output,
reference,
locations=None,
filters=None,
fixchr=None,
regions=None,
targets=None,
leftshift=True,
decompose=True,
bcftools_norm=False,
windowsize=10000,
threads=1,
gender=None,
somatic_allele_conversion=False,
sample="SAMPLE"):
""" Preprocess a single VCF file
:param vcf_input: input file name
:param vcf_output: output file name
:param reference: reference fasta name
:param locations: list of locations or None
:param filters: list of filters to apply ("*" to only allow PASS)
:param fixchr: None for auto, or True/False -- fix chr prefix to match reference
:param regions: regions bed file
:param targets: targets bed file
:param leftshift: left-shift variants
:param decompose: decompose variants
:param bcftools_norm: use bcftools_norm
:param windowsize: normalisation window size
:param threads: number of threads to for preprcessing
:param gender: the gender of the sample ("male" / "female" / "auto" / None)
:param somatic_allele_conversion: convert somatic alleles -- False / half / het / hemi / hom
:param sample: when using somatic_allele_conversion, name of the output sample
:return: the gender if auto-determined (otherwise the same value as gender parameter)
"""
tempfiles = []
try:
# If the input is in BCF format, we can continue to
# process it in bcf
# if it is in .vcf.gz, don't try to convert it to
# bcf because there are a range of things that can
# go wrong there (e.g. undefined contigs and bcftools
# segfaults)
if vcf_input.endswith(".bcf") or vcf_output.endswith(".bcf"):
int_suffix = ".bcf"
int_format = "b"
if not vcf_input.endswith(".bcf") and vcf_output.endswith(".bcf"):
logging.warn(
"Turning vcf into bcf can cause problems when headers are not consistent with all "
"records in the file. I will run vcfcheck to see if we will run into trouble. "
"To save time in the future, consider converting your files into bcf using bcftools before"
" running pre.py.")
else:
int_suffix = ".vcf.gz"
int_format = "z"
# HAP-317 always check for BCF errors since preprocessing tools now require valid headers
mf = subprocess.check_output("vcfcheck %s --check-bcf-errors 1" %
pipes.quote(vcf_input),
shell=True)
if gender == "auto":
logging.info(mf)
if "female" in mf:
gender = "female"
else:
gender = "male"
h = vcfextract.extractHeadersJSON(vcf_input)
reference_contigs = set(fastaContigLengths(reference).keys())
reference_has_chr_prefix = hasChrPrefix(reference_contigs)
allfilters = []
for f in h["fields"]:
try:
if f["key"] == "FILTER":
allfilters.append(f["values"]["ID"])
except:
logging.warn("ignoring header: %s" % str(f))
required_filters = None
if filters:
fts = filters.split(",")
required_filters = ",".join(
list(
set(["PASS", "."] +
[x for x in allfilters if x not in fts])))
if fixchr is None:
try:
if not h["tabix"]:
logging.warn(
"input file is not tabix indexed, consider doing this in advance for performance reasons"
)
vtf = tempfile.NamedTemporaryFile(delete=False,
suffix=int_suffix)
vtf.close()
tempfiles.append(vtf.name)
runBcftools("view", "-o", vtf.name, "-O", int_format,
vcf_input)
runBcftools("index", vtf.name)
h2 = vcfextract.extractHeadersJSON(vcf_input)
chrlist = h2["tabix"]["chromosomes"]
else:
chrlist = h["tabix"]["chromosomes"]
vcf_has_chr_prefix = hasChrPrefix(chrlist)
if reference_has_chr_prefix and not vcf_has_chr_prefix:
fixchr = True
except:
logging.warn("Guessing the chr prefix in %s has failed." %
vcf_input)
# all these require preprocessing
vtf = vcf_input
if leftshift or decompose:
vtf = tempfile.NamedTemporaryFile(delete=False, suffix=int_suffix)
vtf.close()
tempfiles.append(vtf.name)
vtf = vtf.name
else:
vtf = vcf_output
preprocessVCF(vcf_input,
vtf,
locations,
filters == "*",
fixchr,
bcftools_norm,
regions,
targets,
reference,
required_filters,
somatic_allele_conversion=somatic_allele_conversion,
sample=sample)
if leftshift or decompose or gender == "male":
Haplo.partialcredit.partialCredit(vtf,
vcf_output,
reference,
locations,
threads=threads,
window=windowsize,
leftshift=leftshift,
decompose=decompose,
haploid_x=gender == "male")
finally:
for t in tempfiles:
try:
os.unlink(t)
except:
pass
return gender
def main():
parser = argparse.ArgumentParser("Somatic VCF Feature Extraction")
parser.add_argument("input", help="Input VCF file")
parser.add_argument("-o", "--output", dest="output", required=True,
help="Output file name. Output will be in CSV format")
parser.add_argument("-l", "--location", dest="location", default="",
help="Location for bcftools view (e.g. chr1)")
parser.add_argument("-R", "--restrict-regions", dest="regions_bedfile",
default=None, type=str,
help="Restrict analysis to given (sparse) regions (using -R in bcftools).")
parser.add_argument("-T", "--target-regions", dest="targets_bedfile",
default=None, type=str,
help="Restrict analysis to given (dense) regions (using -T in bcftools).")
parser.add_argument("-P", "--include-nonpass", dest="inc_nonpass", action="store_true", default=False,
help="Use to include failing variants in comparison.")
parser.add_argument("--feature-table", dest="features", default="generic",
help="Select a feature table to output. Options are: %s" % str(Somatic.FeatureSet.sets.keys()))
parser.add_argument("--feature-label", dest="label", default=None,
help="We will output a lable column, this value will go in there -- default is "
"the input filename.")
parser.add_argument("--bam", dest="bams", default=[], action="append",
help="pass one or more BAM files for feature table extraction")
parser.add_argument("-r", "--reference", dest="ref", default=Tools.defaultReference(),
help="Specify a reference file for normalization.")
parser.add_argument("--normalize", dest="normalize", default=False, action="store_true",
help="Enable running of bcftools norm on the input file.")
parser.add_argument("--fix-chr", dest="fixchr", default=False, action="store_true",
help="Replace numeric chromosome names in the query by chr*-type names")
args = parser.parse_args()
scratch = tempfile.mkdtemp()
try:
logging.info("Scratch path is %s" % scratch)
if not args.label:
args.label = os.path.basename(args.input)
bams = []
md = None
for x in args.bams:
bams.append(bamStats(x))
if bams:
bres = pandas.concat(bams).groupby("CHROM").mean()
md = {}
for x in bres.index:
logging.info("Mean coverage on %s is %f" % (x, bres.loc[x]["COVERAGE"]))
md[x] = float(bres.loc[x]["COVERAGE"])*3.0
nqpath = os.path.join(scratch, "normalized_query.vcf.gz")
logging.info("Preprocessing input...")
preprocessVCF(args.input, nqpath, args.location,
not args.inc_nonpass, # pass_only
args.fixchr, # chrprefix
args.normalize, # norm,
args.regions_bedfile,
args.targets_bedfile,
args.ref)
runBcftools("index", nqpath)
logging.info("Extracting features...")
fset = Somatic.FeatureSet.make(args.features)
fset.setChrDepths(md)
featuretable = fset.collect(nqpath, args.label)
if not args.output.endswith(".csv"):
args.output += ".csv"
logging.info("Saving feature table %s..." % args.output)
featuretable.to_csv(args.output)
finally:
logging.info("Deleting scratch folder %s " % scratch)
shutil.rmtree(scratch)
def partialCredit(vcfname, outputname, reference, locations, threads=1, window=10000, leftshift=True, decompose=True):
""" Partial-credit-process a VCF file according to our args """
pool = getPool(int(threads))
if threads > 1:
logging.info("Partial credit processing uses %i parallel processes." % threads)
if not locations:
h = extractHeadersJSON(vcfname)
if not h["tabix"]["chromosomes"]:
logging.warn("Empty input or not tabix indexed")
if outputname.endswith(".bcf"):
runBcftools("view", "-O", "b", "-o", outputname, vcfname)
runBcftools("index", outputname)
else:
runBcftools("view", "-O", "z", "-o", outputname, vcfname)
runBcftools("index", "-t", outputname)
# just return the same file
return
locations = h["tabix"]["chromosomes"]
elif type(locations) is str or type(locations) is unicode:
locations = locations.split(",")
# use blocksplit to subdivide input
res = runParallel(
pool, blocksplitWrapper, locations, {"vcf": vcfname, "dist": window, "pieces": min(40, threads * 4)}
)
if None in res:
raise Exception("One of the blocksplit processes failed.")
locations = list(itertools.chain.from_iterable(res))
if not len(locations):
logging.warn("Blocksplit returned no blocks. This can happen when " "an input contains no valid variants.")
locations = [""]
else:
locations = [""]
res = []
try:
res = runParallel(
pool,
preprocessWrapper,
itertools.izip(itertools.repeat(vcfname), locations),
{
"reference": reference,
"decompose": decompose,
"leftshift": leftshift,
"bcf": outputname.endswith(".bcf"),
},
)
if None in res:
raise Exception("One of the preprocess jobs failed")
if not res:
raise Exception("No blocks were processed. List of locations: %s" % str(list(locations)))
concatenateParts(outputname, *res)
if outputname.endswith(".vcf.gz"):
runBcftools("index", "-t", outputname)
else: # use bcf
runBcftools("index", outputname)
finally:
for r in res:
try:
os.unlink(r)
except:
pass
try:
os.unlink(r + ".tbi")
except:
pass
try:
os.unlink(r + ".csi")
except:
pass