def main(argv):
bamfile = argv[0]
snp_gff = "/home/schudoma/projects/ngs/ped-0-snps-intergenic.gff"
snps = gff_helpers.read_snp_from_gff(open(snp_gff))
genome_path = "/home/schudoma/projects/ngs/tair10/TAIR10_chr%c.fas"
base_cmd = ["samtools", "mpileup", "-f"]
for snp in snps:
# (gffline[0], int(gffline[3]) + 1, int(gffline[4]), comments['refbase'], comments['mutation'])
genome_ref = genome_path % snp[0][-1]
cmd = base_cmd + [genome_ref, "-r", "%s:%i-%i" % (snp[0], snp[1] - 1, snp[1] + 1), bamfile]
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
output = p.communicate()[0].strip() # .split('\n')
if len(output) > 0:
sys.stdout.write("%s:%i-%i:%c%c\n" % (snp[0], snp[1] - 1, snp[1] + 1, snp[3], snp[4]))
sys.stdout.write("%s\n" % output)
sys.stdout.flush()
# if output[-1] != '<mpileup> Set max per-file depth to 8000':
# print output[2:]
# samtools mpileup -gf ~/projects/ngs/tair10/TAIR10_chr1.fas -r Chr1:10264-10265 2012-08-22/ped-N-shoot.all.sorted.bam
pass
def main(argv):
samfile = pysam.Samfile(argv[0], 'rb')
fo = sys.stdout
# fo = open('%s.covered_genes.csv' % argv[0].rstrip('.bam'), 'w')
# fo2 = open('%s.covered_genes_with_reads.csv' % argv[0].rstrip('.bam'), 'w')
fo2=sys.stdout
# fo.write('%s\n' % ','.join(COL_HEADERS))
"""
# tair10_genes.gff
intragenic_regions = gff_helpers.read_intragenic_regions(open(argv[1]))
intragenic_regions = sorted(intragenic_regions)
# print intragenic_regions[:10]
# ped-0-snps_no-indels.txt
snp_d = SNPDict(open(argv[2]))
# print snp_d.items()[:10]
snp_d = remove_intragenic_snps(snp_d, intragenic_regions)
"""
snps = gff_helpers.read_snp_from_gff(open(argv[1]))
count_snps = 0
print ';'.join(['contig', 'position', 'refbase_(Col)', 'mutation_(Ped)', 'total_reads',
'#support_Ped', 'fr_Ped', '#support_Col', 'fr_Col'])
# for snp_id, snpline in sorted(snp_d.items()):
reads_out = open('READS_CHECK.dat', 'wb')
for snp_id in snps:
# snp_id[1] - 1 because pysam pileup is 0-based
basecount = FIND_GENES.count_bases(samfile, snp_id[0], snp_id[1] - 1, reads_out)
refbase = basecount.get(snp_id[3], 0.0)
snpbase = basecount.get(snp_id[4], 0.0)
total_reads = sum(basecount.values()) - basecount['bad']
if total_reads > 0:
# line = str(snpline).split('\t')[1:5]
# snp = (gffline[0], int(gffline[3] + 1), int(gffline[4]), comments['refbase'], comments['mutation'])
line = [snp_id[0], snp_id[1], snp_id[3], snp_id[4]]
line.extend([total_reads,
snpbase, float(snpbase)/total_reads,
refbase, float(refbase)/total_reads])
print ';'.join(map(str, line))
# print snpline, 'x', total_reads, snpbase, float(snpbase)/total_reads,
# print refbase, float(refbase)/total_reads
count_snps += 1
reads_out.close()
#print '# Total SNPs: %i Covered: %i (%.3f)' % (len(snp_d), count_snps, float(count_snps)/len(snp_d))
print '# Total SNPs: %i Covered: %i (%.3f)' % (len(snps), count_snps, float(count_snps)/len(snps))
# tair10_genes.gff
# process_gff(open(argv[3]), polymorphs, snp_d, samfile, fo, fo2, min_reads=MIN_NREADS)
# fo2.close()
fo.close()
samfile.close()
return None
