Save each object using cPickle.""" import csv import math import cPickle from sequence import Sequence from geneBank import GeneBank fileList = ["wt1.csv", "wt2.csv", "rny1.csv", "rny2.csv"] for fileName in fileList: geneFile = open('Spy49_allGenes.csv', 'rU') genes = csv.reader(geneFile) with open(fileName, 'rU') as readsFile: reads = csv.reader(readsFile, delimiter='\t') readsList = [] for row in reads: readsList.append(float(row[2])) geneBank = GeneBank() for row in genes: name = row[0] start = int(row[1]) end = int(row[2]) orientation = row[3] seq = Sequence(readsList, (start, end), name, orientation) geneBank.add(seq) geneBankName = "geneBank_" + fileName[0:-4] + ".txt" geneBank.save(geneBankName) geneFile.close()
"""Find all operon after-gaps that occur in the four operonBanks. """ geneBankFiles = ["geneBank_wt1.txt", "geneBank_wt2.txt", \ "geneBank_rny1.txt", "geneBank_rny2.txt"] readsFiles = ["wt1.csv", "wt2.csv", "rny1.csv", "rny2.csv"] operonBankFiles = [OperonBank("operonBank_wt1.txt"), \ OperonBank("operonBank_wt2.txt"), \ OperonBank("operonBank_rny1.txt"), \ OperonBank("operonBank_rny2.txt")] gapList = [] n = 0 for i in xrange(4): operonBank = operonBankFiles[i] geneBank = GeneBank(geneBankFiles[i]) for operon in operonBank: gene = operon[-1] gap = geneBank.getIndex(gene.getName()) if gap not in gapList: gapList.append(gap) n += 1 print "The number of after-gaps is: ", n gapList.sort() """Group genes into operons based on the gap information """ for i in xrange(len(geneBankFiles)): geneBank = GeneBank(geneBankFiles[i])