# parser.add_argument('--json', default="/dev/null")
parser.add_argument('summary', nargs='?', type=argparse.FileType('w'), default=sys.stdout)
args = parser.parse_args()
import json
from Bio import SeqIO
from postanalysis.variant import Variant
''' Load references '''
seqs = [(s.id,s) for s in SeqIO.parse(args.reffile,'fasta')]
sdict = dict(seqs)
''' '''
variants = {}
vlines = [l.strip('\n') for l in open(args.vcffile,'rU') if not l.startswith('#')]
for l in vlines:
v = Variant.from_vcf(l)
v.caller = 'gatk'
if v.chrom not in variants:
variants[v.chrom] = []
variants[v.chrom].append(v)
''' Output summary information '''
print >>args.summary, 'reference\tvariants'
for ref,seq in seqs:
if ref in variants:
print >>args.summary, '%s\t%d' % (ref,len(variants[ref]))
else:
print >>args.summary, '%s\t0' % ref
)
''' Load references '''
seqs = [(s.id, s) for s in SeqIO.parse(args.reffile, 'fasta')]
sdict = dict((ref, Reference(name=ref)) for ref, seq in seqs)
''' Summarize coverage data '''
covdata = parse_covdepth_samtools(args.covfile,
reflens=dict(
(s[0], len(s[1])) for s in seqs))
for ref, seq in seqs:
p, m = summarize_coverage(covdata[ref])
sdict[ref].pct_cov = p
sdict[ref].mean_cov = m
ncvars = find_nocov_variants(covdata[ref], chrom=ref, caller='samdepth')
if ncvars is not None: sdict[ref].dips.extend(ncvars)
''' Analyze variants '''
glines = [
l.strip('\n') for l in gzip.open(args.gfffile, 'rb')
if not l.startswith('#')
]
for l in glines:
v = Variant.from_gff(l)
v.caller = 'gencons'
sdict[v.chrom].variants.append(v)
''' Output summary information '''
print >> args.summary, 'ref\tpct_cov\tmean_cov\tnvars\tndips\tcall'
for ref, seq in seqs:
call = sdict[ref].make_call(seq)
print >> args.summary, '%s\t%s' % (sdict[ref].summary(), call)
return '%s\t%.1f\t%.1f\t%d\t%d' % (self.name,
self.pct_cov*100, self.mean_cov,
len(self.variants), len(self.dips),
)
''' Load references '''
seqs = [(s.id,s) for s in SeqIO.parse(args.reffile,'fasta')]
sdict = dict((ref,Reference(name=ref)) for ref,seq in seqs)
''' Summarize coverage data '''
covdata = parse_covdepth_samtools(args.covfile,reflens=dict((s[0],len(s[1])) for s in seqs))
for ref,seq in seqs:
p,m = summarize_coverage(covdata[ref])
sdict[ref].pct_cov = p
sdict[ref].mean_cov = m
ncvars = find_nocov_variants(covdata[ref],chrom=ref,caller='samdepth')
if ncvars is not None: sdict[ref].dips.extend(ncvars)
''' Analyze variants '''
glines = [l.strip('\n') for l in gzip.open(args.gfffile,'rb') if not l.startswith('#')]
for l in glines:
v = Variant.from_gff(l)
v.caller = 'gencons'
sdict[v.chrom].variants.append(v)
''' Output summary information '''
print >>args.summary, 'ref\tpct_cov\tmean_cov\tnvars\tndips\tcall'
for ref,seq in seqs:
call = sdict[ref].make_call(seq)
print >>args.summary, '%s\t%s' % (sdict[ref].summary(),call)