def main():
fastaCodes = helpers.getProtienCodesForFasta('E.Coli.txt')
GIFile = open('GI.txt', 'a+')
for fastaCode in fastaCodes:
keyCode = fastaCode[0:4].lower()
fastaURL = 'http://www.ncbi.nlm.nih.gov/protein/' + fastaCode + '?report=gilist&log$=seqview&format=text'
print fastaURL
codonFileName = 'protiens/' + keyCode + '/' + fastaCode + ".xml"
if not os.path.exists(codonFileName):
fastaRequest = urllib2.Request(fastaURL, None, headers={'User-Agent' : 'Mozilla/5.0'})
fastaResponse = urllib2.urlopen(fastaRequest)
GI = fastaResponse.read().split('<pre>')[1].split('</pre>')[0]
print GI
getCodon(keyCode, fastaCode, GI)
GIFile.write(GI)
GIFile.close()
CodonSeq = open('AA_CODONS.csv','r')
reader = csv.reader(CodonSeq)
for row in reader:
if(row[0] == aa1):
k=1
while(k<7):
if(row[k] == codon1):
CodonSeq.close()
return True
k+=1
CodonSeq.close()
return False
finally:
l=0
keyCodes = helpers.getProtienCodesForFasta('E.Coli.txt')
for keyCode in keyCodes:
tempKeyCode = keyCode[0:4].lower()
filename1 = 'protiens/' + tempKeyCode + '/' + tempKeyCode + '_*_AA_CODONS.txt'
filenames = glob.glob(filename1)
for filename in filenames:
print filename
CODON = open(filename, 'r')
AA = CODON.readline()
CS = next(CODON)
CS = CS.upper()
def driver():
print helpers.getProtienCodesForFasta('E.Coli.txt')
def main():
keycodes = helpers.getProtienCodesForFasta('E.Coli.txt')
for keycode in keycodes:
tempKeycode = keycode[0:4].lower()
path = "protiens/"+tempKeycode+"/"+tempKeycode+"_*_GROUP.csv"
filenames = glob.glob(path)
for filename in filenames:
infile = open(filename, 'r')
reader = csv.reader(infile)
d={}
allCodons = []
for codons in itertools.product('ACGT', repeat=9):
s1 = ''.join(codons)
s1 = s1[0]+s1[1]+s1[2]+'|'+s1[3]+s1[4]+s1[5]+'|'+s1[6]+s1[7]+s1[8]
allCodons.append(s1)
for structure in allStructures:
d[(s1,structure)] = 0
count = 0
for line in reader:
if(count==0):
count+=1
continue
if (line[2].rstrip(), line[1].rstrip()) in d:
d[(line[2].rstrip(), line[1].rstrip())] += 1
fin[(line[2].rstrip(), line[1].rstrip())] += 1
# print 'Incremented' + ' ' + line[2].rstrip() + ' ' + line[1].rstrip() + ' : ' + str(d[(line[2].rstrip(), line[1].rstrip())])
listStructure = ['']
for structure in allStructures:
listStructure.append(structure)
newfile = open('protiens/' + tempKeycode + '/' +'1kf6_'+filename[-13]+'_MATRIX.csv','w')
matrixcsv = csv.writer(newfile)
matrixcsv.writerow(listStructure)
for codons in allCodons:
listCodon=[]
listCodon.append(codons)
for structure in allStructures:
listCodon.append(d[(codons,structure)])
# print listCodon
matrixcsv.writerow(listCodon)
print filename
listStructure = ['']
for structure in allStructures:
listStructure.append(structure)
newfile = open('FINAL_MATRIX.csv','w')
matrixcsv = csv.writer(newfile)
matrixcsv.writerow(listStructure)
for codons in allCodons:
listCodon=[]
listCodon.append(codons)
for structure in allStructures:
listCodon.append(fin[(codons,structure)])
# print listCodon
matrixcsv.writerow(listCodon)
