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
# 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():
raise RuntimeError("Required header: %s missing from SNV file %s" %
(h, filename))
for h in snvs.headers():
if h in snvheaders:
continue
# if h not in extrasnvheaders:
# extrasnvheaders.append(h)
m = re.search('^(\d+)-(\d+)$', fs)
if m:
f = map(lambda n: (n, opts.numberfmt % n),
range(int(m.group(1)),
int(m.group(2)) + 1))
else:
try:
f = [(fs, fs)]
f = [(int(fs), opts.numberfmt % int(fs))]
except ValueError:
pass
replicates.extend(f)
folders = []
from dataset import XLSXFileTable
rows = XLSXFileTable(args[0], sheet=opts.sheet)
for r in rows:
if not r.get("File Name"):
continue
if r.get("PCC", "") != opts.pcc:
continue
# print r
d = dict(Folder=r["Folder Name"])
d["114-Biospecimen"] = r["114-Biospecimen"]
d["115-Biospecimen"] = r["115-Biospecimen"]
d["116-Biospecimen"] = r["116-Biospecimen"]
d["117-Biospecimen"] = r["117-Biospecimen"]
# JHU filename inconsistencies...
# d["FilenameTemplate"] = re.sub(r'0?1\.raw$','%(fraction)s.raw',r["File Name"])
# BI/PNNL filenames...
# d["FilenameTemplate"] = r["File Name"].replace('_f01.raw','_f%s.raw')
from getwiki import GlycoMotifWiki, CCRCMotif
w = GlycoMotifWiki()
from pygly.GlyTouCan import GlyTouCan
gtc = GlyTouCan()
from gtccache import GlyTouCanCache
gtccache = GlyTouCanCache()
from dataset import XLSXFileTable
rows = XLSXFileTable(sys.argv[1])
current = set()
for r in rows:
try:
index = int(r['#'])
except ValueError:
traceback.print_exc()
continue
name = r['Trivial Name-Cummings']
if name:
name = name.strip()
if not name:
sys.argv.pop(1)
if len(sys.argv) < 5:
sys.exit(1)
d = sys.argv[1].rstrip(os.sep)
study = sys.argv[2]
subproteome = sys.argv[3]
site = sys.argv[4]
iniFile = sys.argv[0].rsplit('.', 1)[0] + '.ini'
config = ConfigParser()
config.read([iniFile])
from dataset import XLSXFileTable
prfile = glob.glob("%s/%s_Protocols.xlsx" % (d, d))[0]
mdfile = glob.glob("%s/%s_Metadata.xlsx" % (d, d))[0]
asp = XLSXFileTable(prfile, sheet='Analytical Sample Protocol')
chp = XLSXFileTable(prfile, sheet='Chromatography Protocol')
msp = XLSXFileTable(prfile, sheet='Mass Spectrometry Protocol')
metadatafile = XLSXFileTable(mdfile)
protocols = {}
for p, t in zip([asp, chp, msp], ["ASP", "CHP", "MSP"]):
headers = map(str.strip, p.headers())
for r in p:
field = str(r.get('Name')).strip()
for h in headers[1:]:
h = h.strip()
val = r.get(h)
if isinstance(val, basestring):
val = val.strip()
if not val:
