#open and read in as list our file containing our genes of interest
genesofinterest = open('diffexpressedgenes.txt', 'r')
genelist = genesofinterest.readlines()
genesofinterest.close()

#edit each gene name to change to appropriate format
goodnamelist = []
for gene in genelist:
    newname = gene.rstrip('\n')
    withcarot = '>' + newname
    goodnamelist.append(withcarot)

#read in file containing gene ID terms and GO terms and save it as a list 
allgoterms = {}
allgos = open('contigs_GO.txt', 'r')
golist = allgos.readlines()

goodgolist = []
for item in golist: 
    newname2 = item.rstrip('\n')
    goodgolist.append(newname2)

#convert list of gene ID and GO terms to dictionary
#gene ID is key and associated GO terms are the values
allgodict = {}
i = 0
while i < len(goodgolist): 
    allgodict.update({goodgolist[i]: goodgolist[i+1]})
    i += 2

#create dictionary of gene IDs and GO terms only for our genes of interest
diffexpressdict = {}
for name in goodnamelist: 
    if name[0] == '>': 
        for term in goodgolist:
            if name == term: 
                diffexpressdict.update({name: allgodict[name]})

#write our genes of interest and associated GO terms to a text file
output = open('genes_with_GOterms.txt', 'w')
output2 = open('genes_lacking_GOterms.txt', 'w')
for contig in diffexpressdict: 
    output.write(contig + '; ' + diffexpressdict[contig] + '\n')
for genename in goodnamelist: 
    if genename in diffexpressdict.keys(): 
        print genename + ' in dictionary'
    else: 
        output2.write(genename + '\n')
output.close()
output2.close()