def ReadTSV(filename):
snvheaders = [_f for _f in """CHROM POS REF ALT""".split() if _f]
base, extn = filename.rsplit('.', 1)
extn = extn.lower()
if extn == 'csv':
snvs = CSVFileTable(filename=filename)
elif extn == 'tsv':
snvs = TSVFileTable(filename=filename)
elif extn == 'xls':
snvs = XLSFileTable(filename=filename)
elif extn == 'xlsx':
snvs = XLSXFileTable(filename=filename)
elif extn == 'txt':
snvs = TXTFileTable(filename=filename, headers=snvheaders)
else:
raise RuntimeError("Unexpected SNV file extension: %s" % filename)
for h in snvheaders:
if h not in snvs.headers():
raise RuntimeError("Required header: %s missing from SNV file %s" %
(h, filename))
assert (snvs.headers()[:4] == snvheaders)
chrom = set()
snvdata = []
for r in snvs:
ri = list(map(r.get, snvs.headers()))
chrom.add(ri[0])
snvdata.append(ri)
return ["\t".join(snvs.headers())], chrom, snvdata
progress.stage("Read SNV data", len(opt.snvs))
snvheaders = filter(None, """
CHROM POS REF ALT
""".split())
snvdata = {}
# extrasnvheaders = []
# usedsnvheaders = set()
snvchroms = defaultdict(set)
for filename in opt.snvs:
base, extn = filename.rsplit('.', 1)
extn = extn.lower()
if extn == 'csv':
snvs = CSVFileTable(filename=filename)
elif extn == 'vcf':
snvs = VCFFile(filename=filename)
elif extn == 'tsv':
snvs = TSVFileTable(filename=filename)
elif extn == 'xls':
snvs = XLSFileTable(filename=filename)
elif extn == 'xlsx':
snvs = XLSXFileTable(filename=filename)
elif extn == 'txt':
snvs = TXTFileTable(filename=filename, headers=snvheaders)
else:
raise RuntimeError("Unexpected SNV file extension: %s" % filename)
for h in snvheaders:
if h not in snvs.headers():
progress.stage("Read SNV data", len(opt.snvs))
snvheaders = filter(None, """
CHROM POS REF ALT
""".split())
snvdata = {}
# extrasnvheaders = []
# usedsnvheaders = set()
snvchroms = defaultdict(set)
for filename in opt.snvs:
base, extn = filename.rsplit('.', 1)
extn = extn.lower()
if extn == 'csv':
snvs = CSVFileTable(filename=filename)
elif extn == 'vcf':
snvs = VCFFile(filename=filename)
elif extn == 'tsv':
snvs = TSVFileTable(filename=filename)
elif extn == 'xls':
snvs = XLSFileTable(filename=filename)
elif extn == 'xlsx':
snvs = XLSXFileTable(filename=filename)
elif extn == 'txt':
snvs = TXTFileTable(filename=filename, headers=snvheaders)
else:
raise RuntimeError("Unexpected SNV file extension: %s" % filename)
for h in snvheaders:
if h not in snvs.headers():
from dataset import XLSFileTable, CSVFileTable, TSVFileTable, XLSXFileTable, TXTFileTable, BEDFile, VCFFile
progress.stage("Read SNV data", len(opt.snvs))
snvheaders = [_f for _f in """
CHROM POS REF ALT
""".split() if _f]
snvdata = {}
extrasnvheaders = []
usedsnvheaders = set()
for filename in opt.snvs:
base, extn = filename.rsplit('.', 1)
extn = extn.lower()
if extn == 'csv':
snvs = CSVFileTable(filename=filename)
elif extn == 'vcf':
snvs = VCFFile(filename=filename)
elif extn == 'tsv':
snvs = TSVFileTable(filename=filename)
elif extn == 'xls':
snvs = XLSFileTable(filename=filename)
elif extn == 'xlsx':
snvs = XLSXFileTable(filename=filename)
elif extn == 'txt':
snvs = TXTFileTable(filename=filename, headers=snvheaders)
else:
raise RuntimeError("Unexpected SNV file extension: %s" % filename)
for h in snvheaders:
if h not in snvs.headers():
sumkeys = [
_f for _f in map(
str.strip, """
SNPJuncIntronCount SNPJuncNoIntronCount NoSNPJuncIntronCount NoSNPJuncNoIntronCount SNPMateCount NoSNPMateCount SNPCount NoSNPCount MatesCount NotMatesCount IntronCount NoIntronCount SpanningReads RemovedDuplicateReads SNPLociReads"""
.split()) if _f
]
countdata = defaultdict(dict)
progress.stage("Read SNP/Junction counts")
from dataset import XLSFileTable, CSVFileTable, TSVFileTable, XLSXFileTable, TXTFileTable
countheaders = None
for filename in opt.counts:
base, extn = filename.rsplit('.', 1)
path, base = os.path.split(base)
extn = extn.lower()
if extn == 'csv':
counts = CSVFileTable(filename=filename)
elif extn == 'tsv':
counts = TSVFileTable(filename=filename)
elif extn == 'xls':
counts = XLSFileTable(filename=filename)
elif extn == 'xlsx':
counts = XLSXFileTable(filename=filename)
else:
raise RuntimeError("Unexpected count file extension: %s" % filename)
if countheaders == None:
countheaders = counts.headers()
else:
assert countheaders == counts.headers()
assert 'CHROM' in countheaders
assert 'POS' in countheaders
#!/bin/env python27
import sys, traceback, re
from collections import defaultdict
from getwiki import GlycoMotifWiki, GlyGenMotif
w = GlycoMotifWiki()
motif2gd = defaultdict(set)
from dataset import CSVFileTable
for r in CSVFileTable(sys.argv[1]):
entry = r['term (main_entry)'].strip()
xrefs = r['term_xref']
gdacc = r['glycan_dictionary_accession']
allmid = set()
for xr in filter(None, xrefs.split('|')):
try:
src, mid = xr.split(':', 1)
except ValueError:
continue
if src.lower() == "glycomotif":
if not re.search(r'^GGM\.\d{6}$', mid):
print "Bad motif id: %s (%s)" % (mid, entry)
continue
motif2gd[mid].add((gdacc, entry))
for mid in w.site.allpages(prefix='GGM.', generator=False):
# print mid
m = w.get(mid)
entries = motif2gd[mid]
from dataset import XLSFileTable, CSVFileTable, TSVFileTable, XLSXFileTable, TXTFileTable, BEDFile, VCFFile
progress.stage("Read SNV data", len(opt.snvs))
snvheaders = [_f for _f in """
CHROM POS REF ALT
""".split() if _f]
snvdata = {}
snvchroms = defaultdict(set)
for filename in opt.snvs:
base, extn = filename.rsplit('.', 1)
extn = extn.lower()
if extn == 'csv':
snvs = CSVFileTable(filename=filename)
elif extn == 'vcf':
snvs = VCFFile(filename=filename)
elif extn == 'tsv':
snvs = TSVFileTable(filename=filename)
elif extn == 'xls':
snvs = XLSFileTable(filename=filename)
elif extn == 'xlsx':
snvs = XLSXFileTable(filename=filename)
elif extn == 'txt':
snvs = TXTFileTable(filename=filename, headers=snvheaders)
else:
raise RuntimeError("Unexpected SNV file extension: %s" % filename)
for h in snvheaders:
if h not in snvs.headers():
if not opt.output:
opt.quiet = True
progress = ProgressText(quiet=opt.quiet)
sumkeys = filter(None, map(str.strip, """
SNPJuncIntronCount SNPJuncNoIntronCount NoSNPJuncIntronCount NoSNPJuncNoIntronCount SNPMateCount NoSNPMateCount SNPCount NoSNPCount MatesCount NotMatesCount IntronCount NoIntronCount SpanningReads RemovedDuplicateReads SNPLociReads""".split()))
countdata = defaultdict(dict)
progress.stage("Read SNP/Junction counts")
from dataset import XLSFileTable, CSVFileTable, TSVFileTable, XLSXFileTable, TXTFileTable
countheaders = None
for filename in opt.counts:
base, extn = filename.rsplit('.', 1)
path, base = os.path.split(base)
extn = extn.lower()
if extn == 'csv':
counts = CSVFileTable(filename=filename)
elif extn == 'tsv':
counts = TSVFileTable(filename=filename)
elif extn == 'xls':
counts = XLSFileTable(filename=filename)
elif extn == 'xlsx':
counts = XLSXFileTable(filename=filename)
else:
raise RuntimeError("Unexpected count file extension: %s" % filename)
if countheaders == None:
countheaders = counts.headers()
else:
assert countheaders == counts.headers()
assert 'CHROM' in countheaders
assert 'POS' in countheaders