#!/bin/env python2
import sys, time, re
from collections import defaultdict
import csv
from getwiki import GlycanData, Glycan
w = GlycanData()
allsources = set()
gtc2taxid = defaultdict(lambda: defaultdict(set))
for f in sys.argv[1:]:
for l in open(f):
sl = l.split()
gtc = sl[0]
taxid = int(sl[1])
source = sl[2]
if len(sl) > 3:
sourceid = sl[3]
else:
sourceid = None
gtc2taxid[gtc][(source, sourceid)].add(taxid)
allsources.add(source)
for m in w.iterglycan():
start = time.time()
acc = m.get('accession')
for source in allsources:
m.delete_annotations(source=source,
#!/bin/env python2
import re, sys
from getwiki import GlycanData
from collections import defaultdict
headers = """
accession Hex HexNAc dHex NeuAc NeuGc HexA HexN S P aldi Xxx X Count
""".split()
w = GlycanData()
print "\t".join(headers)
for acc in w.iterglycanid():
g = w.get(acc)
row = defaultdict(lambda: [0, False])
row['accession'] = (acc, False)
for ann in g.annotations(type="MonosaccharideCount", source="EdwardsLab"):
try:
value = [int(ann.get('value')), False]
except ValueError:
value = [int(ann.get('value')[:-1]), True]
prop = ann.get('property')
if prop.endswith('Count'):
prop = prop[:-5]
row[prop] = value
# print row
row['Count'] = row['Monosaccharide']
if 'Xxx' not in row:
row['Xxx'] = [0, False]
for k in row:
#!/bin/env python27
import re, sys
from getwiki import GlycanData
w = GlycanData()
for g in w.iterglycanid():
print g
#!/bin/env python27 from getwiki import GlycanData import sys w = GlycanData() w.loadsite(sys.argv[1])
#!/bin/env python2
import re, sys
from getwiki import GlycanData
w = GlycanData()
for l in sys.stdin:
print l.strip()
try:
w.delete(l.strip())
except OSError:
pass
#!/bin/env python2
from getwiki import GlycanData
import sys
w = GlycanData()
if sys.argv[1] == "--all":
sys.argv.pop(1)
w.dumpsite(sys.argv[1])
else:
w.dumpsite(sys.argv[1], exclude_categories=['Glycan', 'Annotation'])
#!/bin/env python27
import sys, time, traceback
from collections import defaultdict
from getwiki import GlycanData, Glycan
w = GlycanData()
import findpygly
from pygly.GlycanResource import GlyTouCan
def accessions(args):
if len(args) == 0:
for it in sys.stdin:
yield it.strip()
else:
for fn in args:
for it in open(fn):
yield it.strip()
gtc = GlyTouCan()
allmotifs = dict()
for acc, label, redend in gtc.allmotifs():
allmotifs[acc] = dict(label=label, redend=redend)
current = set()
for gtcacc in accessions(sys.argv[1:]):
start = time.time()
#!/bin/env python2
import sys
from getwiki import GlycanData
w = GlycanData()
if len(sys.argv) >= 2:
database = sys.argv[1]
else:
database = "glycandatadev"
head = """<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE rdf:RDF[
<!ENTITY rdf 'http://www.w3.org/1999/02/22-rdf-syntax-ns#'>
<!ENTITY rdfs 'http://www.w3.org/2000/01/rdf-schema#'>
<!ENTITY swivt 'http://semantic-mediawiki.org/swivt/1.0#'>
<!ENTITY glycandata 'http://glyomics.org/glycandata#'>
]>
<rdf:RDF
xmlns:rdf="&rdf;"
xmlns:rdfs="&rdfs;"
xmlns:swivt="&swivt;"
xmlns:glycandata="&glycandata;"
xmlns:skos="http://www.w3.org/2004/02/skos/core#">
"""
tail = """
</rdf:RDF>
"""
glycantmpl = """
#!/bin/env python27
import sys, time, traceback
from getwiki import GlycanData
w = GlycanData()
def accessions():
if len(sys.argv) > 1:
for arg in sys.argv[1:]:
g = w.get(arg.strip())
if g:
yield g
else:
for g in w.iterglycan():
yield g
for g in accessions():
start = time.time()
glycan = g.getGlycan()
if not glycan:
continue
if not g.has_annotations(
property='GlycoCT', type='Sequence', source='GlyTouCan'):
if not g.has_annotations(
property='GlycoCT', type='Sequence', source='EdwardsLab'):
#!/bin/env python2
import sys
from getwiki import GlycanData
w = GlycanData()
def accessions(args):
if len(args) == 0:
for it in sys.stdin:
yield it.strip()
else:
for fn in args:
for it in open(fn):
yield it.strip()
current_glygen = set(accessions(sys.argv[1:]))
for acc in w.iterglycanid():
m = w.get(acc)
if acc in current_glygen:
m.set_annotation(value=acc,property="GlyGen",source="EdwardsLab",type="CrossReference")
else:
m.delete_annotations(property="GlyGen",source="EdwardsLab",type="CrossReference")
if w.put(m):
print acc,"updated"
else:
print acc,"checked"
#!/bin/env python2
import sys
from getwiki import GlycanData
w = GlycanData()
if len(sys.argv) > 1:
if sys.argv[1] == "-":
for p in w.iterpages(exclude_categories=['Glycan']):
print >> sys.stderr, p.name
w.refresh(p)
elif sys.argv[1] == "stdin":
for p in map(str.strip, sys.stdin):
print >> sys.stderr, p
w.refresh(p)
else:
for p in w.iterpages(regex=sys.argv[1]):
print >> sys.stderr, p.name
w.refresh(p)
else:
for p in w.iterpages(include_categories=['Glycan']):
print >> sys.stderr, p.name
#!/bin/env python27
import sys
from collections import defaultdict
from getwiki import GlycanData, Glycan
from pygly.GlycanFormatter import GlycoCTFormat
w = GlycanData()
glycoctformat = GlycoCTFormat()
monosdb = {}
f = open(sys.argv[1], 'r')
for line in f:
k, v = line.split()
monosdb[k] = v
for g in w.iterglycan():
acc = g.get('accession')
monodbids = set()
glycan = g.getGlycan()
if not glycan:
continue
for m in glycan.all_nodes():
try:
glycoctsym = glycoctformat.mtoStr(m)
except KeyError:
continue
try:
monodbids.add(monosdb[glycoctsym])
except KeyError:
#!/bin/env python2
import sys
from operator import itemgetter
from collections import defaultdict
from getwiki import GlycanData, Glycan
w = GlycanData()
from pygly.GNOme import SubsumptionGraph
gnome = SubsumptionGraph()
gnome.loaddata(sys.argv[1])
sys.argv.pop(1)
def iterglycan():
if len(sys.argv) > 1:
seen = set()
for acc in sys.argv[1:]:
if acc in seen:
continue
m = w.get(acc)
if m:
seen.add(acc)
yield m
for desc in gnome.descendants(acc):
if desc in seen:
continue
m = w.get(desc)
if m:
#!/bin/env python27 import sys from operator import itemgetter from getwiki import GlycanData, Glycan from pygly.GlyNLinkedFilter import GlyNLinkedFilter mnlc = GlyNLinkedFilter(None).test1 w = GlycanData() motif_rules_data = """ G00026MO N-linked G00028MO N-linked high mannose G00029MO N-linked hybrid G00030MO N-linked complex G00031MO O-linked core 1 G00032MO O-linked core 1 G00033MO O-linked core 2 G00034MO O-linked core 2 G00035MO O-linked core 3 G00036MO O-linked core 3 G00037MO O-linked core 4 G00038MO O-linked core 4 G00039MO O-linked core 5 G00040MO O-linked core 5 G00041MO O-linked core 6 G00042MO O-linked core 6 G00043MO O-linked core 7 G00044MO O-linked core 7
class GlycosphingolipidLacto(MotifClassifier):
_class = ("Glycosphingolipid","lacto series")
_motifs = ["GGM.001106"]
class GlycosphingolipidNeolacto(MotifClassifier):
_class = ("Glycosphingolipid","neo-lacto series")
_motifs = ["GGM.001107"]
class GlycosphingolipidGanglio(MotifClassifier):
_class = ("Glycosphingolipid","ganglio series")
_motifs = ["GGM.001108"]
class GlycosphingolipidGlobo(MotifClassifier):
_class = ("Glycosphingolipid","globo series")
_motifs = ["GGM.001109"]
class GPIAnchor(MotifClassifier):
_class = ("GPI anchor","")
_motifs = ["GGM.001030"]
if __name__ == "__main__":
from getwiki import GlycanData, Glycan
w = GlycanData()
classifier = ClassifierEngine()
for acc in sys.argv[1:]:
g = w.get(acc)
for asn in classifier.assign(g):
print g.get('accession'),asn[0],asn[1]
#!/bin/env python2
import sys, time, traceback
from collections import defaultdict
from getwiki import GlycanData, Glycan
w = GlycanData()
import findpygly
from pygly.GlycanResource import GlyTouCan
from pygly.GlycanResource import GlyCosmos
def accessions(args):
if len(args) == 0:
for it in sys.stdin:
yield it.strip()
else:
for fn in args:
for it in open(fn):
yield it.strip()
gtc = GlyTouCan(verbose=False, usecache=False)
gco = GlyCosmos(verbose=False, usecache=False)
allgco = set(gco.allaccessions())
# allmotifs = dict()
# for acc,label,redend in gtc.allmotifs():
# allmotifs[acc] = dict(label=label,redend=redend)