def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
# setup command line parser
parser = U.OptionParser(version="%prog version: $Id$",
usage=usage,
description=globals()["__doc__"])
group = U.OptionGroup(parser, "dedup-specific options")
group.add_option("--output-stats",
dest="stats",
type="string",
default=False,
help="Specify location to output stats")
parser.add_option_group(group)
# add common options (-h/--help, ...) and parse command line
(options, args) = U.Start(parser, argv=argv)
U.validateSamOptions(options, group=False)
if options.random_seed:
np.random.seed(options.random_seed)
if options.stdin != sys.stdin:
in_name = options.stdin.name
options.stdin.close()
else:
raise ValueError("Input on standard in not currently supported")
if options.stdout != sys.stdout:
if options.no_sort_output:
out_name = options.stdout.name
else:
out_name = U.getTempFilename(dir=options.tmpdir)
sorted_out_name = options.stdout.name
options.stdout.close()
else:
if options.no_sort_output:
out_name = "-"
else:
out_name = U.getTempFilename(dir=options.tmpdir)
sorted_out_name = "-"
if not options.no_sort_output: # need to determine the output format for sort
if options.out_sam:
sort_format = "sam"
else:
sort_format = "bam"
if options.in_sam:
in_mode = "r"
else:
in_mode = "rb"
if options.out_sam:
out_mode = "wh"
else:
out_mode = "wb"
if options.stats and options.ignore_umi:
raise ValueError("'--output-stats' and '--ignore-umi' options"
" cannot be used together")
infile = pysam.Samfile(in_name, in_mode)
outfile = pysam.Samfile(out_name, out_mode, template=infile)
if options.paired:
outfile = sam_methods.TwoPassPairWriter(infile, outfile)
nInput, nOutput, input_reads, output_reads = 0, 0, 0, 0
if options.detection_method:
bam_features = detect_bam_features(infile.filename)
if not bam_features[options.detection_method]:
if sum(bam_features.values()) == 0:
raise ValueError(
"There are no bam tags available to detect multimapping. "
"Do not set --multimapping-detection-method")
else:
raise ValueError(
"The chosen method of detection for multimapping (%s) "
"will not work with this bam. Multimapping can be detected"
" for this bam using any of the following: %s" %
(options.detection_method, ",".join(
[x for x in bam_features if bam_features[x]])))
gene_tag = options.gene_tag
metacontig2contig = None
if options.chrom:
inreads = infile.fetch(reference=options.chrom)
else:
if options.per_contig and options.gene_transcript_map:
metacontig2contig = sam_methods.getMetaContig2contig(
infile, options.gene_transcript_map)
metatag = "MC"
inreads = sam_methods.metafetcher(infile, metacontig2contig,
metatag)
gene_tag = metatag
else:
inreads = infile.fetch()
# set up ReadCluster functor with methods specific to
# specified options.method
processor = network.ReadDeduplicator(options.method)
bundle_iterator = sam_methods.get_bundles(
options, metacontig_contig=metacontig2contig)
if options.stats:
# set up arrays to hold stats data
stats_pre_df_dict = {"UMI": [], "counts": []}
stats_post_df_dict = {"UMI": [], "counts": []}
pre_cluster_stats = []
post_cluster_stats = []
pre_cluster_stats_null = []
post_cluster_stats_null = []
topology_counts = collections.Counter()
node_counts = collections.Counter()
read_gn = umi_methods.random_read_generator(
infile.filename,
chrom=options.chrom,
barcode_getter=bundle_iterator.barcode_getter)
for bundle, key, status in bundle_iterator(inreads):
nInput += sum([bundle[umi]["count"] for umi in bundle])
while nOutput >= output_reads + 100000:
output_reads += 100000
U.info("Written out %i reads" % output_reads)
while nInput >= input_reads + 1000000:
input_reads += 1000000
U.info("Parsed %i input reads" % input_reads)
if options.stats:
# generate pre-dudep stats
average_distance = umi_methods.get_average_umi_distance(
bundle.keys())
pre_cluster_stats.append(average_distance)
cluster_size = len(bundle)
random_umis = read_gn.getUmis(cluster_size)
average_distance_null = umi_methods.get_average_umi_distance(
random_umis)
pre_cluster_stats_null.append(average_distance_null)
if options.ignore_umi:
for umi in bundle:
nOutput += 1
outfile.write(bundle[umi]["read"])
else:
# dedup using umis and write out deduped bam
reads, umis, umi_counts = processor(bundle=bundle,
threshold=options.threshold)
for read in reads:
outfile.write(read)
nOutput += 1
if options.stats:
# collect pre-dudupe stats
stats_pre_df_dict['UMI'].extend(bundle)
stats_pre_df_dict['counts'].extend(
[bundle[UMI]['count'] for UMI in bundle])
# collect post-dudupe stats
post_cluster_umis = [
bundle_iterator.barcode_getter(x)[0] for x in reads
]
stats_post_df_dict['UMI'].extend(umis)
stats_post_df_dict['counts'].extend(umi_counts)
average_distance = umi_methods.get_average_umi_distance(
post_cluster_umis)
post_cluster_stats.append(average_distance)
cluster_size = len(post_cluster_umis)
random_umis = read_gn.getUmis(cluster_size)
average_distance_null = umi_methods.get_average_umi_distance(
random_umis)
post_cluster_stats_null.append(average_distance_null)
outfile.close()
if not options.no_sort_output:
# sort the output
pysam.sort("-o", sorted_out_name, "-O", sort_format, out_name)
os.unlink(out_name) # delete the tempfile
if options.stats:
# generate the stats dataframe
stats_pre_df = pd.DataFrame(stats_pre_df_dict)
stats_post_df = pd.DataFrame(stats_post_df_dict)
# tally the counts per umi per position
pre_counts = collections.Counter(stats_pre_df["counts"])
post_counts = collections.Counter(stats_post_df["counts"])
counts_index = list(
set(pre_counts.keys()).union(set(post_counts.keys())))
counts_index.sort()
with U.openFile(options.stats + "_per_umi_per_position.tsv",
"w") as outf:
outf.write("counts\tinstances_pre\tinstances_post\n")
for count in counts_index:
values = (count, pre_counts[count], post_counts[count])
outf.write("\t".join(map(str, values)) + "\n")
# aggregate stats pre/post per UMI
agg_pre_df = aggregateStatsDF(stats_pre_df)
agg_post_df = aggregateStatsDF(stats_post_df)
agg_df = pd.merge(agg_pre_df,
agg_post_df,
how='left',
left_index=True,
right_index=True,
sort=True,
suffixes=["_pre", "_post"])
# TS - if count value not observed either pre/post-dedup,
# merge will leave an empty cell and the column will be cast as a float
# see http://pandas.pydata.org/pandas-docs/dev/missing_data.html
# --> Missing data casting rules and indexing
# so, back fill with zeros and convert back to int
agg_df = agg_df.fillna(0).astype(int)
agg_df.index = [x.decode() for x in agg_df.index]
agg_df.index.name = 'UMI'
agg_df.to_csv(options.stats + "_per_umi.tsv", sep="\t")
# bin distances into integer bins
max_ed = int(
max(
map(max, [
pre_cluster_stats, post_cluster_stats,
pre_cluster_stats_null, post_cluster_stats_null
])))
cluster_bins = range(-1, int(max_ed) + 2)
def bin_clusters(cluster_list, bins=cluster_bins):
''' take list of floats and return bins'''
return np.digitize(cluster_list, bins, right=True)
def tallyCounts(binned_cluster, max_edit_distance):
''' tally counts per bin '''
return np.bincount(binned_cluster, minlength=max_edit_distance + 3)
pre_cluster_binned = bin_clusters(pre_cluster_stats)
post_cluster_binned = bin_clusters(post_cluster_stats)
pre_cluster_null_binned = bin_clusters(pre_cluster_stats_null)
post_cluster_null_binned = bin_clusters(post_cluster_stats_null)
edit_distance_df = pd.DataFrame(
{
"unique":
tallyCounts(pre_cluster_binned, max_ed),
"unique_null":
tallyCounts(pre_cluster_null_binned, max_ed),
options.method:
tallyCounts(post_cluster_binned, max_ed),
"%s_null" % options.method:
tallyCounts(post_cluster_null_binned, max_ed),
"edit_distance":
cluster_bins
},
columns=[
"unique", "unique_null", options.method,
"%s_null" % options.method, "edit_distance"
])
# TS - set lowest bin (-1) to "Single_UMI"
edit_distance_df['edit_distance'][0] = "Single_UMI"
edit_distance_df.to_csv(options.stats + "_edit_distance.tsv",
index=False,
sep="\t")
# write footer and output benchmark information.
U.info("Reads: %s" % ", ".join([
"%s: %s" % (x[0], x[1])
for x in bundle_iterator.read_events.most_common()
]))
U.info("Number of reads out: %i" % nOutput)
if not options.ignore_umi: # otherwise processor has not been used
U.info("Total number of positions deduplicated: %i" %
processor.UMIClusterer.positions)
if processor.UMIClusterer.positions > 0:
U.info("Mean number of unique UMIs per position: %.2f" %
(float(processor.UMIClusterer.total_umis_per_position) /
processor.UMIClusterer.positions))
U.info("Max. number of unique UMIs per position: %i" %
processor.UMIClusterer.max_umis_per_position)
else:
U.warn("The BAM did not contain any valid "
"reads/read pairs for deduplication")
U.Stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
# setup command line parser
parser = U.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-i",
"--in-sam",
dest="in_sam",
action="store_true",
help="Input file is in sam format [default=%default]",
default=False)
parser.add_option(
"-o",
"--out-sam",
dest="out_sam",
action="store_true",
help="Output alignments in sam format [default=%default]",
default=False)
parser.add_option("--ignore-umi",
dest="ignore_umi",
action="store_true",
help="Ignore UMI and dedup"
" only on position",
default=False)
parser.add_option("--umi-separator",
dest="umi_sep",
type="string",
help="separator between read id and UMI",
default="_")
parser.add_option("--umi-tag",
dest="umi_tag",
type="string",
help="tag containing umi",
default='RX')
parser.add_option("--extract-umi-method",
dest="get_umi_method",
type="choice",
choices=("read_id", "tag"),
default="read_id",
help="where is the read UMI encoded? [default=%default]")
parser.add_option("--subset",
dest="subset",
type="float",
help="Use only a fraction of reads, specified by subset",
default=None)
parser.add_option("--spliced-is-unique",
dest="spliced",
action="store_true",
help="Treat a spliced read as different to an unspliced"
" one [default=%default]",
default=False)
parser.add_option("--soft-clip-threshold",
dest="soft",
type="float",
help="number of bases clipped from 5' end before"
"read is counted as spliced [default=%default]",
default=4)
parser.add_option("--edit-distance-threshold",
dest="threshold",
type="int",
default=1,
help="Edit distance theshold at which to join two UMIs"
"when clustering. [default=%default]")
parser.add_option("--chrom",
dest="chrom",
type="string",
help="Restrict to one chromosome",
default=None)
parser.add_option("--paired",
dest="paired",
action="store_true",
default=False,
help="paired BAM. [default=%default]")
parser.add_option("--method",
dest="method",
type="choice",
choices=("adjacency", "directional", "percentile",
"unique", "cluster"),
default="directional",
help="method to use for umi deduping [default=%default]")
parser.add_option("--output-stats",
dest="stats",
type="string",
default=False,
help="Specify location to output stats")
parser.add_option(
"--whole-contig",
dest="whole_contig",
action="store_true",
default=False,
help=
"Read whole contig before outputting bundles: guarantees that no reads"
"are missed, but increases memory usage")
parser.add_option("--multimapping-detection-method",
dest="detection_method",
type="choice",
choices=("NH", "X0", "XT"),
default=None,
help=("Some aligners identify multimapping using bam "
"tags. Setting this option to NH, X0 or XT will "
"use these tags when selecting the best read "
"amongst reads with the same position and umi "
"[default=%default]"))
parser.add_option("--mapping-quality",
dest="mapping_quality",
type="int",
help="Minimum mapping quality for a read to be retained"
" [default=%default]",
default=0)
parser.add_option(
"--read-length",
dest="read_length",
action="store_true",
default=False,
help=("use read length in addition to position and UMI"
"to identify possible duplicates [default=%default]"))
parser.add_option("--per-contig",
dest="per_contig",
action="store_true",
default=False,
help=("dedup per contig (field 3 in BAM; RNAME),"
" e.g for transcriptome where contig = gene"))
parser.add_option("--per-gene",
dest="per_gene",
action="store_true",
default=False,
help=("Deduplicate per gene,"
"e.g for transcriptome where contig = transcript"
"must also provide a transript to gene map with"
"--gene-transcript-map [default=%default]"))
parser.add_option("--gene-transcript-map",
dest="gene_transcript_map",
type="string",
help="file mapping transcripts to genes (tab separated)",
default=None)
parser.add_option("--gene-tag",
dest="gene_tag",
type="string",
help=("Deduplicate per gene where gene is"
"defined by this bam tag [default=%default]"),
default=None)
parser.add_option(
"--skip-tags-regex",
dest="skip_regex",
type="string",
help=("Used with --gene-tag. "
"Ignore reads where the gene-tag matches this regex"),
default="^[__|Unassigned]")
# add common options (-h/--help, ...) and parse command line
(options, args) = U.Start(parser, argv=argv)
if options.random_seed:
np.random.seed(options.random_seed)
if options.stdin != sys.stdin:
in_name = options.stdin.name
options.stdin.close()
else:
raise ValueError("Input on standard in not currently supported")
if options.stdout != sys.stdout:
out_name = options.stdout.name
options.stdout.close()
else:
out_name = "-"
if options.in_sam:
in_mode = "r"
else:
in_mode = "rb"
if options.out_sam:
out_mode = "wh"
else:
out_mode = "wb"
if options.stats:
if options.ignore_umi:
raise ValueError("'--output-stats' and '--ignore-umi' options"
" cannot be used together")
if options.per_gene:
if not options.gene_transcript_map and not options.gene_map:
raise ValueError(
"--per-gene option requires --gene-transcript-map "
"or --gene-tag")
try:
re.compile(options.skip_regex)
except re.error:
raise ValueError("skip-regex '%s' is not a "
"valid regex" % options.skip_regex)
infile = pysam.Samfile(in_name, in_mode)
outfile = pysam.Samfile(out_name, out_mode, template=infile)
if options.paired:
outfile = umi_methods.TwoPassPairWriter(infile, outfile)
nInput, nOutput = 0, 0
if options.detection_method:
bam_features = detect_bam_features(infile.filename)
if not bam_features[options.detection_method]:
if sum(bam_features.values()) == 0:
raise ValueError(
"There are no bam tags available to detect multimapping. "
"Do not set --multimapping-detection-method")
else:
raise ValueError(
"The chosen method of detection for multimapping (%s) "
"will not work with this bam. Multimapping can be detected"
" for this bam using any of the following: %s" %
(options.detection_method, ",".join(
[x for x in bam_features if bam_features[x]])))
# set the method with which to extract umis from reads
if options.get_umi_method == "read_id":
umi_getter = partial(umi_methods.get_umi_read_id, sep=options.umi_sep)
elif options.get_umi_method == "tag":
umi_getter = partial(umi_methods.get_umi_tag, tag=options.umi_tag)
else:
raise ValueError("Unknown umi extraction method")
if options.stats:
# set up arrays to hold stats data
stats_pre_df_dict = {"UMI": [], "counts": []}
stats_post_df_dict = {"UMI": [], "counts": []}
pre_cluster_stats = []
post_cluster_stats = []
pre_cluster_stats_null = []
post_cluster_stats_null = []
topology_counts = collections.Counter()
node_counts = collections.Counter()
read_gn = umi_methods.random_read_generator(infile.filename,
chrom=options.chrom,
umi_getter=umi_getter)
if options.chrom:
inreads = infile.fetch(reference=options.chrom)
else:
if options.per_gene and options.gene_transcript_map:
metacontig2contig = umi_methods.getMetaContig2contig(
infile, options.gene_transcript_map)
metatag = "MC"
inreads = umi_methods.metafetcher(infile, metacontig2contig,
metatag)
gene_tag = metatag
else:
inreads = infile.fetch()
gene_tag = options.gene_tag
for bundle, read_events, status in umi_methods.get_bundles(
inreads,
ignore_umi=options.ignore_umi,
subset=options.subset,
quality_threshold=options.mapping_quality,
paired=options.paired,
spliced=options.spliced,
soft_clip_threshold=options.soft,
per_contig=options.per_contig,
gene_tag=options.gene_tag,
skip_regex=options.skip_regex,
whole_contig=options.whole_contig,
read_length=options.read_length,
detection_method=options.detection_method,
umi_getter=umi_getter,
all_reads=False,
return_read2=False,
return_unmapped=False):
nInput += sum([bundle[umi]["count"] for umi in bundle])
if nOutput % 10000 == 0:
U.debug("Outputted %i" % nOutput)
if nInput % 1000000 == 0:
U.debug("Read %i input reads" % nInput)
if options.stats:
# generate pre-dudep stats
average_distance = umi_methods.get_average_umi_distance(
bundle.keys())
pre_cluster_stats.append(average_distance)
cluster_size = len(bundle)
random_umis = read_gn.getUmis(cluster_size)
average_distance_null = umi_methods.get_average_umi_distance(
random_umis)
pre_cluster_stats_null.append(average_distance_null)
if options.ignore_umi:
for umi in bundle:
nOutput += 1
outfile.write(bundle[umi]["read"])
else:
# set up ReadCluster functor with methods specific to
# specified options.method
processor = network.ReadDeduplicator(options.method)
# dedup using umis and write out deduped bam
reads, umis, umi_counts = processor(bundle=bundle,
threshold=options.threshold)
for read in reads:
outfile.write(read)
nOutput += 1
if options.stats:
# collect pre-dudupe stats
stats_pre_df_dict['UMI'].extend(bundle)
stats_pre_df_dict['counts'].extend(
[bundle[UMI]['count'] for UMI in bundle])
# collect post-dudupe stats
post_cluster_umis = [umi_getter(x) for x in reads]
stats_post_df_dict['UMI'].extend(umis)
stats_post_df_dict['counts'].extend(umi_counts)
average_distance = umi_methods.get_average_umi_distance(
post_cluster_umis)
post_cluster_stats.append(average_distance)
cluster_size = len(post_cluster_umis)
random_umis = read_gn.getUmis(cluster_size)
average_distance_null = umi_methods.get_average_umi_distance(
random_umis)
post_cluster_stats_null.append(average_distance_null)
outfile.close()
if options.stats:
# generate the stats dataframe
stats_pre_df = pd.DataFrame(stats_pre_df_dict)
stats_post_df = pd.DataFrame(stats_post_df_dict)
# tally the counts per umi per position
pre_counts = collections.Counter(stats_pre_df["counts"])
post_counts = collections.Counter(stats_post_df["counts"])
counts_index = list(
set(pre_counts.keys()).union(set(post_counts.keys())))
counts_index.sort()
with U.openFile(options.stats + "_per_umi_per_position.tsv",
"w") as outf:
outf.write("counts\tinstances_pre\tinstances_post\n")
for count in counts_index:
values = (count, pre_counts[count], post_counts[count])
outf.write("\t".join(map(str, values)) + "\n")
# aggregate stats pre/post per UMI
agg_pre_df = aggregateStatsDF(stats_pre_df)
agg_post_df = aggregateStatsDF(stats_post_df)
agg_df = pd.merge(agg_pre_df,
agg_post_df,
how='left',
left_index=True,
right_index=True,
sort=True,
suffixes=["_pre", "_post"])
# TS - if count value not observed either pre/post-dedup,
# merge will leave an empty cell and the column will be cast as a float
# see http://pandas.pydata.org/pandas-docs/dev/missing_data.html
# --> Missing data casting rules and indexing
# so, back fill with zeros and convert back to int
agg_df = agg_df.fillna(0).astype(int)
agg_df.index = [x.decode() for x in agg_df.index]
agg_df.index.name = 'UMI'
agg_df.to_csv(options.stats + "_per_umi.tsv", sep="\t")
# bin distances into integer bins
max_ed = int(
max(
map(max, [
pre_cluster_stats, post_cluster_stats,
pre_cluster_stats_null, post_cluster_stats_null
])))
cluster_bins = range(-1, int(max_ed) + 2)
def bin_clusters(cluster_list, bins=cluster_bins):
''' take list of floats and return bins'''
return np.digitize(cluster_list, bins, right=True)
def tallyCounts(binned_cluster, max_edit_distance):
''' tally counts per bin '''
return np.bincount(binned_cluster, minlength=max_edit_distance + 3)
pre_cluster_binned = bin_clusters(pre_cluster_stats)
post_cluster_binned = bin_clusters(post_cluster_stats)
pre_cluster_null_binned = bin_clusters(pre_cluster_stats_null)
post_cluster_null_binned = bin_clusters(post_cluster_stats_null)
edit_distance_df = pd.DataFrame({
"unique":
tallyCounts(pre_cluster_binned, max_ed),
"unique_null":
tallyCounts(pre_cluster_null_binned, max_ed),
options.method:
tallyCounts(post_cluster_binned, max_ed),
"%s_null" % options.method:
tallyCounts(post_cluster_null_binned, max_ed),
"edit_distance":
cluster_bins
})
# TS - set lowest bin (-1) to "Single_UMI"
edit_distance_df['edit_distance'][0] = "Single_UMI"
edit_distance_df.to_csv(options.stats + "_edit_distance.tsv",
index=False,
sep="\t")
# write footer and output benchmark information.
U.info(
"%s" %
", ".join(["%s: %s" % (x[0], x[1])
for x in read_events.most_common()]))
U.info("Number of reads out: %i" % nOutput)
U.Stop()