#!/bin/env python27
from getwiki import GlycoMotifWiki
import sys
w = GlycoMotifWiki()
if len(sys.argv) > 1:
w.deletemany(regex=sys.argv[1],verbose=True)
else:
w.deletemany(category='Motif')
#!/bin/env python2
import findpygly
from getwiki import GlycoMotifWiki
# we must instantiate early, before any use of the command-line.
w = GlycoMotifWiki()
#print w._prefix
import sys, os, os.path
dir = sys.argv[1]
try:
os.makedirs(dir)
except OSError:
pass
format = sys.argv[2]
assert format in ('wurcs', 'glycoct')
seen = set()
for m in w.itermotif():
glytoucan = m.get('glytoucan')
if glytoucan in seen:
continue
seen.add(glytoucan)
seq = m.get(format)
if not seq:
continue
print glytoucan
fn = os.path.join(dir, glytoucan + '.txt')
wh = open(fn, 'w')
wh.write(seq.strip() + "\n")
#!/bin/env python2
from collections import defaultdict
from getwiki import GlycoMotifWiki
import findpygly
from pygly.GlycanResource import GlyTouCan
import sys
w = GlycoMotifWiki()
gtc = None
def accs():
global gtc
if len(sys.argv) > 1:
gtc = GlyTouCan(prefetch=False, usecache=False)
for acc in sys.argv[1:]:
yield acc
else:
gtc = GlyTouCan(prefetch=True, usecache=False)
for m in w.itermotif():
yield m.get('id')
for acc in accs():
m = w.get(acc)
gtcacc = m.get('glytoucan')
wurcs = gtc.getseq(gtcacc, 'wurcs')
#!/bin/env python27
import sys,traceback
from getwiki import GlycoMotifWiki, GlycoEpitopeMotif
w = GlycoMotifWiki()
import csv
from gtccache import GlyTouCanCache
gtccache = GlyTouCanCache()
current = set()
for r in csv.DictReader(open(sys.argv[1]),dialect='excel-tab'):
if not r['glytoucan']:
continue
redend = None
aglycon = None
if r['sequence'].endswith('Cer'):
redend = True
aglycon = 'Cer'
elif r['sequence'].endswith('Ser/Thr'):
redend = True
aglycon = 'Ser/Thr'
elif r['sequence'].endswith('-R'):
redend = False
aglycon = 'R'
wurcs=gtccache.gtc2wurcs(r['glytoucan'])
glycoct=gtccache.gtc2glycoct(r['glytoucan'])
motif = GlycoEpitopeMotif(accession=r['acc'],name=r['name'],glytoucan=r['glytoucan'],redend=redend,aglycon=aglycon,wurcs=wurcs,glycoct=glycoct)
if w.update(motif):
print >>sys.stderr, r['acc']
#!/bin/env python2
import sys
from getwiki import GlycoMotifWiki, GlyTouCanMotif
w = GlycoMotifWiki()
if len(sys.argv) > 1:
if sys.argv[1] == "-":
for p in w.iterpages(exclude_categories=['Motif', 'Collection']):
print >> sys.stderr, p.name
w.refresh(p)
elif sys.argv[1] == "Publications":
for p in w.iterpages(include_categories=['Publication']):
print >> sys.stderr, p.name
w.refresh(p)
elif sys.argv[1] == "Collections":
for p in w.iterpages(include_categories=['Collection']):
print >> sys.stderr, p.name
w.refresh(p)
else:
for p in w.iterpages(regex=sys.argv[1]):
print >> sys.stderr, p.name
#!/bin/env python2 from getwiki import GlycoMotifWiki import sys w = GlycoMotifWiki() w.dumpsite(sys.argv[1], exclude_regex='^GM\.')
#!/bin/env python27
from getwiki import GlycoMotifWiki
import sys
w = GlycoMotifWiki()
m = w.get(sys.argv[1])
if m:
coll,acc = sys.argv[2].split('.')
m.delete('sameas')
m.set('accession',acc)
m.set('collection',coll)
m.set('id',sys.argv[2])
if w.put(m):
print "Copied:",sys.argv[1],"to",m.get('id')
#!/bin/env python2
import sys, traceback, time
from getwiki import GlycoMotifWiki, Publication
w = GlycoMotifWiki()
refs = []
if len(sys.argv) > 1:
h = open(sys.argv[1])
else:
h = sys.stdin
for l in h:
sl = l.split()
try:
refid = int(sl[0])
except:
refid = sl[0]
if refid == "-":
refid = None
pmid = sl[1]
refs.append((refid, pmid))
currentpmids = set()
for pub in w.iterpages(include_categories=['Publication']):
pmid = w.get(pub.name).get('pmid')
if pmid != None:
currentpmids.add(pmid)
from Bio import Entrez
#!/bin/env python27
from getwiki import GlycoMotifWiki
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 = GlycoMotifWiki(smwenv=fromwiki, quiet=True)
print >> sys.stderr, "from: %s" % (w1.title(), )
w2 = GlycoMotifWiki(smwenv=towiki, quiet=True)
print >> sys.stderr, " to: %s" % (w2.title(), )
dummy = raw_input("Enter to proceed, <Ctrl-C> to abort:")
currentcoll = set()
for c1 in w1.itercollection():
id = c1.get('id')
assert (id)
currentcoll.add(id)
if w2.put(c1):
print >> sys.stderr, "Pushing %s to %s" % (id, w2.title())
else:
print >> sys.stderr, "No change to %s in %s" % (id, w2.title())
currentmotif = set()
for m1 in w1.itermotif():
#!/bin/env python27
from getwiki import GlycoMotifWiki, GlyTouCanMotif
w = GlycoMotifWiki()
for m in w.itermotif(collection='GGM'):
print m
# print m.get('collection'), m.get('accession'), m.get('id')
#!/bin/env python27
import sys, traceback
from getwiki import GlycoMotifWiki, UniCarbMotif
w = GlycoMotifWiki()
from pygly.GlyTouCan import GlyTouCan
gtc = GlyTouCan()
from gtccache import GlyTouCanCache
gtccache = GlyTouCanCache()
from pygly.GlycanFormatter import GlycoCTFormat, IUPACParserExtended1
gparser = GlycoCTFormat()
imparser = IUPACParserExtended1()
from dataset import XLSXFileTable
rows = XLSXFileTable(sys.argv[1])
possibleaglycon = ["Cer", "R", "Ser/Thr"]
reaglycon = ["Ser/Thr", "Cer", "Other"]
current = set()
for r in rows:
id = r["ID"]
name = r["Name"]
iupacseq = r["IUPAC"]
accession = "%06d" % id
if not iupacseq:
continue
#!/bin/env python27 from getwiki import GlycoMotifWiki import sys w = GlycoMotifWiki() w.dumpsite(sys.argv[1], exclude_categories=['Motif', 'Collection'])
#!/bin/env python27
from getwiki import GlycoMotifWiki, Collection, GlyTouCanMotif, CCRCMotif, GlycoEpitopeMotif, AllMotif, GlyGenMotif
from getwiki import GlydinMotif, GlydinCummingsMotif, GlydinHayesMotif, GlydinCermavMotif, GlydinSugarbindMotif, GlydinBioligoMotif
from getwiki import UniCarbMotif
import sys
w = GlycoMotifWiki()
current = set()
w.put(
Collection(id=GlyTouCanMotif.id,
name="GlyTouCan Motifs",
contact="Kiyoko Aoki-Kinoshita",
email="*****@*****.**",
url="https://glytoucan.org/Motifs/listAll"))
current.add(GlyTouCanMotif.id)
w.put(
Collection(
id=CCRCMotif.id,
name="CCRC Motifs",
contact="Rene Ranzinger",
email="*****@*****.**",
url=
"https://github.com/glygen-glycan-data/PyGly/raw/master/smw/glycomotif/data/MotifsMP2.xlsx"
))
current.add(CCRCMotif.id)
w.put(
Collection(id=GlycoEpitopeMotif.id,
name="GlycoEpitope Epitopes",
contact="Toshisuke Kawasaki",
email="*****@*****.**",
#!/bin/env python27
from getwiki import GlycoMotifWiki
import sys, re
w = GlycoMotifWiki()
for m in w.itermotif(collection="GGM"):
match = False
if re.search(sys.argv[2], m.get('accession')):
match = True
if not match:
for name in m.get('name', []):
if re.search(sys.argv[2], name):
match = True
break
if match:
keywords = m.get("keyword", set())
keywords.add(sys.argv[1])
m.set("keyword", keywords)
if w.put(m):
print >> sys.stderr, m.get('id'), sys.argv[1]
#!/bin/env python27 from getwiki import GlycoMotifWiki, GlyTouCanMotif w = GlycoMotifWiki()
#!/bin/env python27 from getwiki import GlycoMotifWiki import sys w = GlycoMotifWiki() w.loadsite(sys.argv[1])
#!/bin/env python2
from collections import defaultdict
from getwiki import GlycoMotifWiki
w = GlycoMotifWiki()
gtc2motif = defaultdict(list)
for m in w.itermotif():
gtc = m.get('glytoucan')
if gtc:
gtc2motif[gtc].append(m)
for gtc, motiflist in sorted(gtc2motif.iteritems()):
print gtc
for m in motiflist:
sameas = sorted(map(lambda m1: m1.get('id'), motiflist))
sameas.remove(m.get('id'))
m.set('sameas', sameas)
w.update(m)
#!/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]
#!/bin/env python27
from collections import defaultdict
import sys
from getwiki import GlycoMotifWiki, AllMotif
w = GlycoMotifWiki()
gtc2motif = defaultdict(list)
for m in w.itermotif():
if m.get('collection') != AllMotif.id:
gtc = m.get('glytoucan')
gtc2motif[gtc].append(m)
current = set()
for gtc, motiflist in sorted(gtc2motif.iteritems()):
names = []
redend = set()
aglycon = set()
for m in motiflist:
if m.has('name'):
for n in m.get('name'):
if n not in names:
names.append(n)
if m.has('redend'):
redend.update(m.get('redend', []))
if m.has('aglycon'):
aglycon.update(m.get('aglycon', []))
if len(redend) == 0:
redend = None
if len(aglycon) == 0:
#!/bin/env python27
import sys, traceback, os, csv
from getwiki import GlycoMotifWiki
from getwiki import GlydinMotif, GlydinCummingsMotif, GlydinHayesMotif, GlydinCermavMotif, GlydinSugarbindMotif, GlydinBioligoMotif
w = GlycoMotifWiki()
from dataset import XLSXFileTable
rows = XLSXFileTable(sys.argv[1])
from pygly.GlyTouCan import GlyTouCan
gtc = GlyTouCan()
from gtccache import GlyTouCanCache
gtccache = GlyTouCanCache()
"""
[x]collection structure
key: id (not row number)
value: {"aglycon":"String"/None, "name":""/None, "gtcid":""}
"""
ccollection = {}
hcollection = {}
vcollection = {}
sbcollection = {}
bcollection = {}
collections = {
"c": ccollection,
"h": hcollection,