#!/bin/env python27
from getwiki import GPTWiki, Peptide
import sys, urllib, string
import Bio.SeqIO
from util import peptide_mw, mod_mw
seen = set()
w = GPTWiki()
peps = []
for p in w.iterpages(include_categories=['Peptide']):
pep = w.get(p.name)
pepkey = Peptide.key(pep.get('sequence'), pep.get('glycan', []),
pep.get('mod', []))
if pepkey in seen:
print >> sys.stderr, p.name
w.delete(p.name)
seen.add(pepkey)
#!/bin/env python27
from getwiki import GPTWiki
import sys
w = GPTWiki()
for cat in sys.argv[1:]:
assert cat in ("Transition", "TransitionGroup", "Peptide", "Protein",
"Glycan")
w.deletemany(category=cat, verbose=True)
import json, urllib, re
from getwiki import GPTWiki
import numpy as np
import getwiki
from analysis.fisher import lod, fisher_exact_low, fisher_exact_high
from transitionspecificity import specscore
w = GPTWiki()
trspec = {}
labelspec = {}
glycanlabelspec = {}
smallwindow = 1
largewindow = 6
threshold = 50
nonspeccount = 0
alltrs = set()
for tg in w.itertgs(acqtype='DIA'):
pepid = tg.get('peptide')
pepage = w.get(pepid)
z1 = tg.get('z1')
spectra = tg.get('spectra')
if spectra.find('DIA') == -1:
continue
try:
glycan = re.search('\[H(.)*?\]', pepage.get('name')).group(0)[1:-1]
except:
continue
filename = pepid + '.' + str(z1) + '.50.json'
#!/bin/env python27
import sys
from getwiki import GPTWiki
w = GPTWiki()
if len(sys.argv) > 1:
if sys.argv[1] == "-":
for p in w.iterpages(exclude_categories=[
'Transition', 'Peptide', 'Protein', 'TransitionGroup', 'Glycan'
]):
print >> sys.stderr, p.name
w.refresh(p)
elif sys.argv[1] in ('Transition', 'Peptide', 'Protein', 'Glycan',
'TransitionGroup'):
for p in w.iterpages(include_categories=sys.argv[1:]):
print >> sys.stderr, p.name
w.refresh(p)
else:
for p in w.iterpages(regex=sys.argv[1]):
print >> sys.stderr, p.name
w.refresh(p)
else:
#!/bin/env python2
import sys
from collections import defaultdict
from getwiki import GPTWiki
w=GPTWiki()
tla = {'N': 'Asn'}
sampleids = set(sys.argv[1:])
prsites = defaultdict(dict)
for i,tg in enumerate(w.itertransgroups()):
pep = w.get(tg.get('peptide'))
# if not pep.get('nrt'):
# continue
glyid = pep.get('glycan')[0][0]
gly = w.get(glyid)
name = ""
for n in gly.get('name',[]):
if 'Fuc' in n:
continue
if 'HexNAc' in n:
name = n
break
cls = gly.get('class')
if len(cls) != 1:
continue
cls = cls[0]
#!/bin/env python27
from getwiki import GPTWiki, Protein
import sys, urllib, string, csv
import Bio.SeqIO
w = GPTWiki()
seen = set()
for praccfile in sys.argv[1:]:
for pracc in open(praccfile):
pracc = pracc.strip()
if pracc in seen:
continue
# print >>sys.stderr, pracc
seen.add(pracc)
data = urllib.urlopen('http://www.uniprot.org/uniprot/' + pracc +
'.xml')
for seq_record in Bio.SeqIO.parse(data, 'uniprot-xml'):
desc = seq_record.description
pracc1 = seq_record.id
seq = str(seq_record.seq)
gene = seq_record.annotations['gene_name_primary']
sys.stdout.write(seq_record.format('fasta'))
break
name = gene
seqlines = []
for i in range(0, len(seq), 60):
seqlines.append(seq[i:i + 60])
seq = "\n".join(seqlines)
std_dev, height, FWHM, area, '\n'
])))
if tgid not in updated:
tg.set('prt', adjrt)
updated.add(tgid)
if w.put(tg):
# print tgid
pass
json_file.close()
if len(sys.argv) < 2:
print 'please enter the spectra file name(s)'
exit(1)
spectrafiles = sys.argv[1:]
w = GPTWiki()
# outfile = open('../data/'+sys.argv[1][:5]+'.fitall.txt','w')
outfile = sys.stdout
outfile.write('\t'.join(
map(str, [
'TransGroup', 'Spectra', 'PeptideID', 'PrecZ', 'mmu', 'ExpRT', 'AdjRT',
'R_Value', 'Std_Dev', 'Height', 'FWHM', 'Area', '\n'
])))
for tg in w.itertransgroups():
tgid = tg.get('id')
pepid = tg.get('peptide')
z1 = tg.get('z1')
import matplotlib
# Force matplotlib to not use any Xwindows backend.
matplotlib.use('Agg')
from getwiki import GPTWiki
from collections import defaultdict
import matplotlib.pyplot as plt
import numpy as np
from scipy import stats
import sys
w = GPTWiki()
if len(sys.argv) < 2:
print 'please enter the spectra file name(s)'
exit(1)
spectrafiles = sys.argv[1:]
pepnrtpairs = defaultdict(list)
nrtobsgt0 = {}
for tgpage in w.itertransgroups():
spectra = tgpage.get('spectra')
if spectra not in spectrafiles:
continue
tgid = tgpage.get('id')
pepid = tgpage.get('peptide')
peppage = w.get(pepid)
pepnrt = peppage.get('nrt')
#!/bin/env python2
from getwiki import GPTWiki
import time, sys
w = GPTWiki()
for sp in w.iterspec(method=sys.argv[1]):
sp.set('inst', sys.argv[2])
sp.set('type', sys.argv[3])
if w.put(sp):
print sp.get('id')
#!/bin/env python2
from getwiki import GPTWiki, Peptide, ProteinSite
import sys
w = GPTWiki()
for pep in w.iterpep():
for al in pep.get('alignments', []):
pr = al.get('protein')
prsites = al.get('prsites', "").split('|')
for prs in prsites:
aa = prs[0]
pos = int(prs[1:])
ps = ProteinSite(protein=pr, aa=aa, position=pos)
if w.put(ps):
print ProteinSite.pagename(protein=pr, aa=aa, position=pos)
al.append('site', ps)
# al.delete('prsites')
if w.put(pep):
print pep.get('id')
#!/bin/env python27
from getwiki import GPTWiki, Peptide
import sys, urllib, string
import Bio.SeqIO
w = GPTWiki()
for pr in sorted(w.iterproteins(), key=lambda pr: pr.get('accession')):
acc = pr.get('accession')
desc = pr.get('description')
sequence = "".join(pr.get('sequence').split())
print ">%s %s" % (acc, desc)
for i in range(0, len(sequence), 60):
print sequence[i:i + 60]
#!/bin/env python27
from getwiki import GPTWiki
import sys
fromwiki = sys.argv[1].upper()
towiki = sys.argv[2].upper()
assert fromwiki in ("PROD", "DEV", "TEST")
assert towiki in ("PROD", "DEV", "TEST")
assert fromwiki != towiki
w1 = GPTWiki(smwenv=fromwiki, quiet=True)
print >> sys.stderr, "from: %s" % (w1.title(), )
w2 = GPTWiki(smwenv=towiki, quiet=True)
print >> sys.stderr, " to: %s" % (w2.title(), )
dummy = raw_input("Enter to proceed, <Ctrl-C> to abort:")
currentids = set()
for page in w1.iterpages(include_categories=('Transition', 'Peptide',
'TransitionGroup')):
id = page.name
currentids.add(id)
it = w1.get(id)
if w2.put(it):
print >> sys.stderr, "Pushing %s to %s" % (id, w2.title())
else:
print >> sys.stderr, "No change to %s in %s" % (id, w2.title())
for page in w2.iterpages(include_categories=('Transition', 'Peptide',
default=False,
help="Upload TG status and peptide nrt to GPTwiki. Default: False.")
opts, args = parser.parse_args()
if opts.cachefile and os.path.exists(opts.cachefile):
data = json.loads(open(opts.cachefile).read())
rows = data['rows']
tgs = data['tgs']
origpepnrt = data['pepnrt']
else:
monos = "NHFS"
tgs = dict()
origpepnrt = dict()
rows = []
w = GPTWiki(quiet=True)
for tg in w.itertransgroups():
pepid = tg.get('peptide')
p = w.get(pepid)
pepacc = p.get('id')
pepseq = p.get('sequence')
pepname = p.get('name')
pepnrt = p.get('nrt')
if not tg.has('nrt'):
continue
nrt = float(tg.get('nrt'))
glyacc = p.get('glycan')[0][0]
g = w.get(glyacc)
gsym = g.get('sym')
mcnt = {}
for mono in monos:
opts, args = parser.parse_args()
if opts.cachefile and os.path.exists(opts.cachefile):
data = json.loads(open(opts.cachefile).read())
tgrows = data['tgrows']
peprows = data['peprows']
tgs = data['tgs']
origpepnrt = data['pepnrt']
else:
monos = "NHFS"
tgs = dict()
origpepnrt = dict()
tgrows = []
peprows = []
pepseen = set()
w = GPTWiki(quiet=True)
for spec in w.iterspec(acqtype="DDA"):
print spec.get("name")
for tg in w.itertgs(spectra=spec.get("name")):
pepid = tg.get('peptide')
p = w.get(pepid)
pepacc = p.get('id')
pepseq = p.get('sequence')
pepname = p.get('name')
pepnrt = p.get('nrt')
pepnrtobs = int(p.get('nrtobs', 0))
if pepnrtobs == 0:
pepnrt = None
nrt = tg.get('nrt')
if nrt is None and pepnrt is None:
continue
#!/bin/env python2 from getwiki import GPTWiki import sys w = GPTWiki() w.loadsite(sys.argv[1])
#!/bin/env python27
from getwiki import GPTWiki, Peptide
import sys, urllib, string
import Bio.SeqIO
from collections import defaultdict
w = GPTWiki()
seenpeps = set()
sites = set()
prot2site = defaultdict(set)
samples = set()
glycans = set()
glysites = set()
site2gly = defaultdict(set)
for tg in w.itertransgroups():
tgid = tg.get('id')
if tg.get('peptide') in seenpeps:
continue
pep = w.get(tg.get('peptide'))
seenpeps.add(pep.get('id'))
gly = pep.get('glycan')[0][0]
glycans.add(gly)
for al in pep.get('alignments',[]):
site = al.get('prsites')
prot = al.get('protein')
print pep.get('id'),prot,site,gly
sites.add((prot,site))
prot2site[prot].add(site)
site2gly[(prot,site)].add(gly)
#!/bin/env python27
from getwiki import GPTWiki, Peptide
import sys
from collections import defaultdict
w = GPTWiki()
for sp in sys.argv[1:]:
for tg in w.iterspectgs(sp):
if not tg:
continue
print >> sys.stderr, "Delete transition group", tg.get('id')
w.delete(tg.get('id'))
print >> sys.stderr, "Delete spectra", sp
w.delete(sp)
m = re.search(r'\[(.*)\]', lab)
kvpairs = re.split(r'([A-Z])', m.group(1))
nmono = 0
for i in range(1, len(kvpairs), 2):
if kvpairs[i + 1] == "":
nmono += 1
else:
nmono += int(kvpairs[i + 1])
return nmono
def label2series(lab):
return lab[0].lower()
w = GPTWiki()
peps = defaultdict(lambda: defaultdict(dict))
for sp in w.iterspec(sample=opts.sample,
acqtype=opts.acqtype,
method=opts.method,
inst=opts.inst):
print >> sys.stderr, sp.get('name')
for i, tg in enumerate(w.itertgs(spectra=sp.get('name'))):
pep = w.get(tg.get('peptide'))
pepid = pep.get('id')
if pep.get('nrt') == None:
continue
z1 = tg.get('z1')
ntrans = len(tg.get('transitions', []))
from getwiki import GPTWiki, Glycan
import findpygly
from pygly.GlyTouCan import GlyTouCan
import os, sys, urllib, string
import Bio.SeqIO
gtc = GlyTouCan(usecache=True)
w = GPTWiki()
try:
os.mkdir('../glycoct')
except OSError:
pass
for gc in sorted(w.iterglycans(), key=lambda gc: gc.get('accession')):
acc = gc.get('accession')
topos = map(str.strip, map(str, gc.get('topo')))
for tacc in topos:
glycoct = gtc.getseq(tacc, 'glycoct')
if not glycoct:
gly = gtc.getGlycan(tacc)
glycoct = gly.glycoct()
f = open('../glycoct/' + acc + '.' + tacc + '.txt', 'w')
f.write(glycoct)
f.close()
print >> sys.stderr, "Dump GlycoCT to %s.%s.txt" % (acc, tacc)
#!/bin/env python27
from getwiki import GPTWiki, Peptide
import sys
from collections import defaultdict
w = GPTWiki()
for tgpage in w.iterpages(include_categories=['TransitionGroup']):
tg = w.get(tgpage.name)
if tg.get('spectra') in sys.argv[1:]:
print >> sys.stderr, "Delete transition group", tgpage.name
w.delete(tgpage.name)
for sp in sys.argv[1:]:
print >> sys.stderr, "Delete spectra", sp
w.delete(sp)
#!/bin/env python27
from getwiki import GPTWiki, Protein
import sys, urllib, string, csv, os.path
from collections import defaultdict
import Bio.SeqIO
from util import peptide_mw, mod_mw
def asscan(s):
t = s.rstrip(')').split('(')
return [int(t[0])] + t[1].split(',')
w = GPTWiki()
spectra2tg = defaultdict(set)
for tgpage in w.iterpages(include_categories=['TransitionGroup']):
tg = w.get(tgpage.name)
spectra = tg.get('spectra')
spectra2tg[spectra].add(tg.get('id'))
allspectra = set()
for transfile in sys.argv[1:]:
spectra, sample, method, index, extn = transfile.rsplit('.', 4)
spectra = os.path.split(spectra)[1]
allspectra.add(spectra)
w.addacquisition(name=spectra, method=method, sample=sample)
tgroup = defaultdict(dict)
#!/bin/env python27
from getwiki import GPTWiki, Protein
import sys, urllib, string
from collections import defaultdict
import Bio.SeqIO
w = GPTWiki()
alignfile = sys.argv[1]
alignments = defaultdict(list)
for l in open(alignfile):
sl = l.split()
st = int(sl[1]) + 1
ed = int(sl[2])
pep = sl[4]
laa = sl[3]
raa = sl[5]
pracc = sl[12][1:]
alignments[pep].append((pracc, st, ed))
for p in w.iterpeptides():
seq = p.get('sequence')
if seq in alignments:
p.update(alignment=alignments[seq])
if w.put(p):
print >> sys.stderr, p.get('id')
#!/bin/env python27
from getwiki import GPTWiki, Protein
import getwiki
import sys, urllib, string, csv, os.path, json, glob
from collections import defaultdict
import Bio.SeqIO
from util import peptide_mw, mod_mw
w = GPTWiki()
sample = sys.argv[1]
method = sys.argv[2]
if ":" in method:
method, anfrac = method.split(':')
else:
anfrac = None
tgs = defaultdict(set)
allspec = set()
lccal = defaultdict(dict)
for specfile in sys.argv[3:]:
dirname = specfile.rsplit('.', 2)[0]
if dirname.endswith('.centroid'):
dirname = dirname.rsplit('.', 1)[0]
spectra = os.path.split(dirname)[1]
allspec.add(spectra)
w.addacquisition(name=spectra,
method=method,
anfrac=anfrac,
#!/bin/env python2
from getwiki import GPTWiki, Protein
import sys, urllib, string, csv, os.path
from collections import defaultdict
import Bio.SeqIO
from util import peptide_mw, mod_mw
def asscan(s):
t = s.rstrip(')').split('(')
return [int(t[0])] + t[1].split(',')
w = GPTWiki()
allspectra = set()
spectra2tg = defaultdict(set)
for transfile in sys.argv[1:]:
spectra, sample, method, index, extn = transfile.rsplit('.', 4)
spectra = os.path.split(spectra)[1]
w.addacquisition(name=spectra, method=method, sample=sample)
allspectra.add(spectra)
for tg in w.itertgs(spectra=spectra, all=True):
spectra2tg[spectra].add(tg.get('id'))
for transfile in sys.argv[1:]:
spectra, sample, method, index, extn = transfile.rsplit('.', 4)
spectra = os.path.split(spectra)[1]
tgroup = defaultdict(dict)
#!/bin/env python2
from getwiki import GPTWiki, Alignment
import sys, urllib, string, csv
import Bio.SeqIO
from util import peptide_mw, mod_mw
from operator import itemgetter
w = GPTWiki()
gmw = dict()
gsym = dict()
seen = set()
for peptidefile in sys.argv[1:]:
rest, sample, method, index, extn = peptidefile.rsplit('.', 4)
for l in csv.DictReader(open(peptidefile), dialect='excel-tab'):
seq = l['PeptideSequence']
glyspec = l['Glycans']
modspec = l['Mods']
praccs = l['ProteinName']
pepid = l.get('PeptideID')
if (seq, glyspec, modspec) in seen:
continue
if '?' in glyspec:
continue
seen.add((seq, glyspec, modspec))
# print >>sys.stderr, seq,glyspec,modspec
#!/bin/env python27
from getwiki import GPTWiki
import re
w = GPTWiki()
monos = "NHSF"
for gly in w.iterglycans():
gsym = gly.get('sym')
mcnt = {}
for mono in monos:
mcnt[mono] = 0
m = re.search(mono + r'(\d+)', gsym)
if m:
mcnt[mono] = int(m.group(1))
elif mono in gsym:
mcnt[mono] = 1
gly.set('nneuac', mcnt['S'])
if w.put(gly):
print gly.get('id')
for pep in w.iterpeptides():
pepname = pep.get('name')
pep.set('nox', pepname.count('[Ox]'))
if w.put(pep):
print pep.get('id')
#!/bin/env python2
from getwiki import GPTWiki, Peptide
import sys, urllib, string
from collections import defaultdict
nrtonly = False
if len(sys.argv) > 1 and sys.argv[1] == "nrtonly":
nrtonly = True
w = GPTWiki()
seenpeps = set()
sites = set()
prot2site = defaultdict(set)
samples = set()
glycans = set()
glysites = set()
site2gly = defaultdict(set)
for sp in w.iterspec(type='DDA'):
for tg in w.itertgs(spectra=sp.get('name')):
tgid = tg.get('id')
if tg.get('peptide') in seenpeps:
continue
pep = w.get(tg.get('peptide'))
if nrtonly and pep.get('nrt') == None:
continue
seenpeps.add(pep.get('id'))
gly = pep.get('glycan')[0][0]
glycans.add(gly)
for al in pep.get('alignments', []):
#!/bin/env python2
from getwiki import GPTWiki
import sys, re
w = GPTWiki()
# if len(sys.argv) < 2:
# print 'please enter the spectra file name regex'
# exit(1)
for spectrapage in w.iterspec(acqtype="DDA"):
# if not re.search(sys.argv[1],spectrapage.get('name')):
# continue
print spectrapage.get('name')
nrtslope = spectrapage.get('nrtslope')
nrtintercept = spectrapage.get('nrtintercept')
if not nrtslope or not nrtintercept:
print "No NRT slope or intercept"
continue
for tgpage in w.itertgs(spectra=spectrapage.get('name')):
tgid = tgpage.get('id')
peakrt = tgpage.get('prt')
nrt = 0.0
if peakrt != None:
nrt = (peakrt - nrtintercept) / nrtslope
tgpage.set('nrt', nrt)
if w.put(tgpage):
print tgid
else:
tgpage.set('nrt', '')
#!/bin/env python27
from getwiki import GPTWiki
import sys
w = GPTWiki()
w.dumpsite(sys.argv[1],
exclude_categories=['Peptide', 'Transition', 'TransitionGroup'])
#!/bin/env python27
from getwiki import GPTWiki, Peptide
import sys, urllib, string
import Bio.SeqIO
print "\t".join(
map(str, [
"Spectra", "Accession", "Peptide", "Site", "Glycan", "TGAccession",
"Charge", "PrecursorMZ"
]))
seen = set()
w = GPTWiki()
for tgpage in w.iterpages(include_categories=['TransitionGroup']):
tg = w.get(tgpage.name)
pep = w.get(tg.get('peptide'))
pepid = pep.get('id')
z1 = tg.get('z1')
mz1 = tg.get('mz1')
spectra = tg.get('spectra')
if (spectra, pepid, z1) not in seen:
pepseq = list(pep.get('sequence'))
for deltastr, pos in pep.get('mod', []):
aa = pos[0]
pos = int(pos[1:]) - 1
if round(deltastr, 3) == 57.021:
pepseq[pos] += ":m"
elif round(deltastr, 3) in (15.995, 15.996):
pepseq[pos] += ":o"
pepseq = "".join(pepseq)
