_group_fn_list = [
_attr for _attr in dir(_group_fns)
if (not _attr.startswith('__') and not _attr.endswith('__')
and callable(getattr(_group_fns, _attr)))
]
@command.add_sub
@argument('-c', '--columns', nargs='+', help='column specs')
@argument('--no-header', '-H', dest='use_header', action='store_false')
@argument('--default-fn',
'-f',
default='first',
choices=_group_fn_list,
help='default group function')
@argument.exclusive(argument('-i', '--inputs', nargs='+', help='input files'),
argument('-l',
'--input-list',
help='list of input file names'),
required=True)
def summarize_row(args):
"""
-c {col1} {col2} ...
Availble specifiers :
col1:col2 --- concat(col1)
col1::first
col1:col1-sum:sum
col1::concat --- concat(col1) as col1
col1::length --- length(col1) as col1
0 --- default_fn(filelist) (1st column) as filelist
+n:sample --- (n+1)-th column of filelist
seq = cigar.hard_clip_seq(seq)
if qual is not None:
qual = cigar.hard_clip_seq(qual)
rec.query_sequence = seq # refill
rec.query_qualities = qual
out.write(rec)
@command.add_sub
@argument('bam')
@argument('-r', '--region', help='region of target bam file')
@argument('--max-nm', default=4, type=int)
@argument('--max-depth', default=8000, type=int)
@argument.exclusive(
argument('--summary', action='store_true'),
argument('--read-count', action='store_true'),
)
def bam_depth_with_nm(args):
"""
* unmapped is discarded
* both clipped is discarded
* end clipped is included
* multimap is included
* stratified with NM
default mode:
pos is 1-based
summary mode:
covered
'-0.301,0,-0.301,0,0,-0.301'
"""
het_gl = '0'
hom_gl = '{0:.3f}'.format(-np.log10(2))
gt_num = (alt_num + 1) * (alt_num + 2) // 2
gl = [het_gl] * gt_num
hom_idxs = get_gt_hom_idxs(alt_num)
for idx in hom_idxs:
gl[idx] = hom_gl
return ','.join(gl)
@command.add_sub
@argument('vcf', help='VCF or gzipped VCF')
@argument.exclusive(
argument('-s', '--samples', help='comma separated sample list'),
argument('-S', '--samples-file', help='sample list file'),
)
def vcf_reset_gl(args):
""" whitening format tag for specified samples
# TODO also reset PL
"""
vcffile = '/dev/stdin' if args.vcf == '-' else args.vcf
import pysam
reader = pysam.VariantFile(vcffile)
sample_flags = _get_sample_flags(reader, args)
print(reader.header, end='')
sample_offset = 9
# hom: log10 p**2 = 2 log10 p
"""
sam = pysam.Samfile(args.bamfile, 'rb')
totlen = sum(sam.lengths) # reference length (contains N)
cov = 1. * sam.mapped / totlen # (mapped may contains secondary or supplementary alignments)
print(cov)
@command.add_sub
@argument('bamfile')
@argument('-r', '--rsample', type=int, default=1000)
@argument('--pacbio',
action='store_true',
help='use suplementary alignemnt, use only aligned length')
@argument('--nbed', help='N bed regions')
@argument.exclusive(
argument('--chroms', nargs='+'),
argument('--autosomal', action='store_true'),
)
def bam_mean_depth(args):
""" Roughly estimate bam depth
- estimate mean read length by scanning top {rsample} reads
- divide the total length by total reference lengths
# TODO autosomal option
"""
sam = pysam.Samfile(args.bamfile, 'rb')
samm = SamMethods(sam)
if args.autosomal:
if 'chr1' in sam.references:
chroms = ['chr' + str(i + 1) for i in range(22)]
def test_subcommand_usage():
command = Command()
run_tracks = []
# create common argument
common1 = argument()
common1.add_arg('file', help='this is common option')
common1.add_arg(argument('--some-flag', action='store_true'))
# setup subcommand "main1" (basic style)
sub = command.add_sub()
sub.add_arg(common1)
sub.add_arg('-t', '--test', action='store_true', default=False)
@sub
def sub1(args):
""" This line is used as description
Write details (show in epilog).
"""
run_tracks.append({
'file': args.file,
'test': args.test,
'verbose': args.verbose,
'some_flag': args.some_flag,
})
# setup subcommand "sub2" (decorator style)
@command.add_sub
@argument(common1)
@argument('-t', '--times', action='count', default=0)
def sub2(args):
""" This line is used as description
Write details here (show in epilog).
"""
run_tracks.append({
'file': args.file,
'times': args.times,
'verbose': args.verbose,
'some_flag': args.some_flag,
})
# with group, exclusive
@command.add_sub
@argument('-a')
@argument.group(
'Counting options',
'Description of counting options',
argument('-c', '--counts', action='count', default=0),
argument('-t', '--times', action='count', default=0),
)
@argument.exclusive(
argument('--tsv', action='store_const', const='tsv', dest='filetype'),
argument('--csv', action='store_const', const='csv', dest='filetype'),
required=True,
)
def sub3(args):
""" This line is used as description
Write details here (show in epilog).
"""
run_tracks.append({
'a': args.a,
'counts': args.counts,
'times': args.times,
'filetype': args.filetype,
})
# root command option
#command.add_arg('--detail', help='this is root only option')
# run sub1
command.run(args=['sub1', 'foo.txt', '-t'])
eq_(run_tracks.pop(), {'file': 'foo.txt', 'test': True, 'verbose': 0, 'some_flag': False})
# run sub2
#command.run(args=['sub2', 'bar.txt', '-t', '--times', '-v'])
command.run(args=['sub2', 'bar.txt', '-t', '--times', '--some-flag'])
eq_(run_tracks.pop(), {'file': 'bar.txt', 'times': 2, 'verbose': 0, 'some_flag': True})
# run sub3
#command.run(args=['sub2', 'bar.txt', '-t', '--times', '-v'])
command.run(args=['sub3', '-t', '--times', '-cc', '--counts', '--csv'])
eq_(run_tracks.pop(), {'times': 2, 'counts': 3, 'a': None, 'filetype': 'csv'})
# run subcommand directly
sub1.run(args=['foo.txt', '-t', '-v', '--some-flag'])
eq_(run_tracks.pop(), {'file': 'foo.txt', 'test': True, 'verbose': 1, 'some_flag': True})
locus = '{0}:{1}-{2}'.format(reg.contig, left, right)
print ('<tr>')
print ('''<td><a href="{link}">igv_link</a></td>'''.format(link='http://localhost:{igv_port}/goto?locus={locus}'.format(igv_port=args.igv_port, locus=locus)))
for term in row: # TODO html escape
print ('<td>{0}</td>'.format(term))
print ('</tr>')
print ('</tbody>')
print ('</table>')
print ('''</body>''')
print ('''</html>''')
@command.add_sub
@argument('files', nargs='+', help='URL or file path')
@argument.exclusive(
argument('-l', '--loci', nargs='+'),
argument('-L', '--loci-file'),
)
@argument('-P', '--paths', nargs='+')
@argument('-g', '--genome')
@argument('-p', '--port', type=int)
@argument('-o', '--outdir')
@argument('-m', '--view-mode', choices=['expand', 'collapse', 'squished'])
@argument('--view-as-pairs', action='store_true')
@argument('--height', type=int)
@argument('--run-server', action='store_true', help='Run IGV server during snapshot')
@argument('--no-reset', dest='reset_on_end', action='store_false', help='Reset IGV server status on end')
def igv_snapshot(args):
""" Taking IGV snapshot
"""
if not args.loci and not args.loci_file:
def get_sample_name(fname):
name = os.path.basename(fname)
name = remove_suffix(name, '.sam')
name = remove_suffix(name, '.bam')
name = remove_suffix(name, '.sorted')
name = remove_suffix(name, '.sort')
return name
# TODO density or read depth
@command.add_sub
@argument('sam', nargs='+')
@argument.exclusive(
argument('-r', '--regions', nargs='+'),
argument('-R', '--region-file'),
required=True,
)
@argument('--sample', nargs='+')
@argument('--gtf', help='need tabix')
@argument('--show-clips', action='store_true')
@argument('-o', '--output', default='bam_bp_plot.pdf')
@argument('--sam-per-page', default=10, type=int)
@argument('--bin-size', default=1000, type=int)
@argument('--njobs', default=8, type=int)
@argument('--style', default='darkgrid')
@argument('--max-depth', type=int)
@argument('--xlab-rot', type=int)
@argument('--region-propto', action='store_true', help='set column width to that proportional to each region length')
#@argument('--skip-flag', type=lambda x: int(x, 16), default=0x904)
tokens = line.rstrip('\r\n').split(' ', 1)
name = tokens[0][1:]
rest = ''.join(tokens[1:])
if is_target(name):
print('>', name, ' ', rest, sep='')
emit = True
else:
emit = False
elif emit:
print(line, end='')
@command.add_sub
@argument('fasta')
@argument.exclusive(
argument('-n', '--names', nargs='*', help='list of fasta names to select'),
argument('-N', '--name-file', help='list of fasta names to select'),
argument('-r', '--regexp', help='match patterns for name'),
)
def fa_select(args):
""" Select sequences by names
O(n) but not required faidx
"""
if args.name_file:
names = [line.rstrip() for line in open(args.name_file)]
else:
names = args.names
_select_or_omit(args.fasta, names=names, regexp=args.regexp)
','.join(str(base_counts[b]) for b in cand_bases),
ref_base,
zygosity,
'|'.join(best_bases),
mean_depths and '|'.join('{0:.1f}'.format(d) for d in mean_depths),
um_depths and '|'.join('{0:.1f}'.format(d) for d in um_depths),
hap_prob,
sep='\t',
file=stdout)
@command.add_sub
@argument('bam')
@argument('-r', '--regions', nargs='*')
@argument.exclusive(
(argument('-c', '--copy-number', type=int, default=2)
.add_argument('--hap-depth', type=float, default=20.)),
argument('-t', '--table', help='contig, hap_depth, and copy_number are required')
)
@argument('-g', '--gref', required=True)
@argument('--no-phase', action='store_true')
@argument('-m', '--min-second-bases', type=int, default=2)
def mc_path_call6(args):
with open(args.gref) as fp:
fasta = Fasta(fp)
contigs = {contig.name: contig.seq.upper() for contig in fasta.contigs}
with Samfile(args.bam) as sam:
smb = SamModelBuilder2(sam, regions=args.regions, min_second_bases=args.min_second_bases, contigs=contigs)
if not args.table:
hap_depths = {ref.name: args.hap_depth for ref in smb.model.refs}
from __future__ import print_function
from argtools import command, argument
import logging
import pysam
from operator import attrgetter
from ..samutil import ReadCountGenerator, sam_intervals
from ..interval import Interval, parse_bed
@command.add_sub
@argument('sam')
@argument.exclusive(
argument(
'-r',
'--regions',
nargs='*',
help='region e.g. one based indexes chr1, chr1:1001, or chr1:1001-2000'
), argument('-b', '--bed', help='region defined bed file'))
@argument('-w', '--window', type=int, default=50, help='width of counter')
@argument('--offset',
type=int,
default=0,
help='offset of regions (or bed file)')
@argument('-H',
'--no-header',
dest='header',
action='store_false',
default=True,
help='add header')
@argument('--skip-flag', type=lambda x: int(x, 16), default=0x904)
@argument(