Am getting a list index out of range error!!
but I cant add a -1 to the loop.can i??whats wrong with this??
but I cant add a -1 to the loop.can i??whats wrong with this??
Code:
from math import *
def parseArray(fn, dataset=1, key='PO', term='/'):
'''
Read a formatted data file in matrix format and
compile data into a dictionary
'''
f = open(fn)
# skip to required data set
for _ in range(dataset):
try:
line = f.next()
while not line.startswith(key):
line = f.next()
except StopIteration, e:
print 'We have reached the end of the file!'
f.close()
return False
headerList = line.strip().split()[1:]
lineList = []
line = f.next().strip()
while not line.startswith(term):
if line != '':
lineList.append(line.strip().split())
line = f.next().strip()
f.close()
# Key list
keys = [i[0] for i in lineList]
# Values list
values = [[float(s) for s in item] for item in [j[1:] for j in lineList]]
# Create a dictionary from keys and values
lineDict = dict(zip(keys, values))
dataDict = {}
for i, item in enumerate(headerList):
dataDict[item] = {}
for key in lineDict:
dataDict[item][key] = lineDict[key][i]
# Add 1.0 to every element in dataDict subdictionaries
for keyMain in dataDict:
for keySub in dataDict[keyMain]:
dataDict[keyMain][keySub] += 1.0
# Normalize original data (with 1 added) and update data
valueSums = [sum(item)+4 for item in values]
# print valueSums
for keyMain in dataDict:
for keySub in dataDict[keyMain]:
dataDict[keyMain][keySub] /= valueSums[int(keySub)-1]
return dataDict
def parseData(fn, dataset=1, key='>'):
'''
Read a formatted data file of sequences
Return a list of sequences
The first element in the list is the header
'''
# initialize output list
dataList = []
# open file for reading
f = open(fn)
# skip to required data set
for _ in range(dataset):
try:
s = f.next()
while not s.startswith(key):
s = f.next()
except StopIteration, e:
print 'We have reached the end of the file!'
f.close()
return False
# initialize output list
dataList = [s,]
for line in f:
if not line.startswith(key):
dataList.append(line.strip())
else:
break
f.close()
return dataList
if __name__ == '__main__':
arraySet = 4
#print arraySet
seqSet = 4
#print seqSet
value={"A":0.3,"T":0.3,"C":0.2,"G":0.2}
fnArray = r'all_redfly.transfac.txt'
fnSeq = r'redfly_sequence.fasta'
indxSeq=1
while True:
dataSeq=parseData(fnSeq,indxSeq)
if not dataSeq:
break
indxArray=1
while True:
dataArray = parseArray(fnArray, arraySet)
#dataSeq = parseData(fnSeq, seqSet)
if not dataArray:
break
# This is the complete sequence
seq = ''.join(dataSeq[1:])
# These are the subkeys of dataArray - '01', '02', '03',.............
subKeys = dataArray['A'].keys()
subKeys.sort()
# Calculate num/den for each slice of sequence
# Each sequence slice length = length of subKeys
# Example:
# seq = 'ATCGATA'
# subKeys length = 3
# 'ATC', 'TCG', 'CGA', 'GAT', 'ATA'
numList = []
denList = []
seqList = []
for i in xrange(len(seq) - len(subKeys) + 1):
subseq = seq[0:len(subKeys)]
seqList.append(subseq)
num, den = 1, 1
for j, s in enumerate(subseq):
num *= dataArray[s][subKeys[j]]
den *= value[s]
numList.append(num)
denList.append(den)
seq = seq[1:]
resultList = []
for i, num in enumerate(numList):
resultList.append(log10(num/denList[i]))
indxArray+=1
indxSeq +=1
outStr = '\n'.join(['Sequence = %s Calculation = %0.12f' % (seqList[i], res) for i, res in enumerate(resultList)])
print 'Array set # = %d\nSequence set # = %d' % (arraySet, seqSet)
print 'Sequence Header: %s' % dataSeq[0]
print outStr
Comment