reactionParse.py

import os,csv

#parser for CSV download of https://spreadsheets1.google.com/ccc?key=toMz3Kp3T2EAUDF3MSGCquw&hl=en#gid=0
# extract pairwise combinations of compounds in the same ReactionID
# use this combinations to define edges in a graph viewable in Gephi

#recent versions of py include this as itertools.combinations()
def combinations(iterable, r):
    # combinations('ABCD', 2) --> AB AC AD BC BD CD
    # combinations(range(4), 3) --> 012 013 023 123
    pool = tuple(iterable)
    n = len(pool)
    if r > n:
        return
    indices = range(r)
    yield tuple(pool[i] for i in indices)
    while True:
        for i in reversed(range(r)):
            if indices[i] != i + n - r:
                break
        else:
            return
        indices[i] += 1
        for j in range(i+1, r):
            indices[j] = indices[j-1] + 1
        yield tuple(pool[i] for i in indices)

fr3=open('csid2csid.gdf','w')

anon={}
reactionCompounds={}
reactions=csv.reader(open('ReactionAttempts.csv'))

fr3.write("nodedef> name VARCHAR,label VARCHAR, type VARCHAR, labbook VARCHAR\n")

unique=[]
firstrow=True
for r in reactions:
  if firstrow is False:
    ReactionID,hyperlink,CompoundName,CSID,SMILES,Role,Type,SolventPredict=r
    if ReactionID not in unique:
      reactionCompounds[ReactionID]=[]
      unique.append(ReactionID)
    if CSID not in unique:
      unique.append(CSID)
      if CompoundName !='':
        name=CompoundName
      else:
        name=CSID
      fr3.write('"'+CSID+'","'+CompoundName+'","Compound","'+hyperlink+'"\n')
    if hyperlink not in unique:
      unique.append(hyperlink)
    reactionCompounds[ReactionID].append(CSID)
  else:
    firstrow=False

fr3.write("edgedef> node1 VARCHAR,node2 VARCHAR, reaction VARCHAR\n")

for r in reactionCompounds:
  pairs=combinations(reactionCompounds[r],2)
  for p in pairs:
    fr3.write('"'+p[0]+'","'+p[1]+'","'+r+'"\n')
    
fr3.close()