import os, sys, glob, math
import utilities
from operator import itemgetter, attrgetter
inFilePath = sys.argv[1]
expression = sys.argv[2]
reverse = sys.argv[3] == "reverse"
numHeaderRows = int(sys.argv[4])
outFilePath = sys.argv[5]
data = utilities.readMatrixFromFile(inFilePath)
headerRows = []
for i in range(numHeaderRows):
headerRows.append(data.pop(0))
data = map(lambda x: eval("x + [" + expression + "]"), data)
data.sort(key=itemgetter(len(data[0])-1), reverse=reverse)
data = [x[:-1] for x in data]
utilities.writeMatrixToFile(headerRows + data, outFilePath)
numPlaces = sys.argv[4]
outFilePath = sys.argv[5]
numberFormatOption = "g"
if len(sys.argv) > 6:
numberFormatOption = sys.argv[6]
data = utilities.readMatrixFromFile(inFilePath)
def isNumber(x):
try:
float(x)
return True
except:
return False
for i in range(numHeaderRows, len(data)):
if isNumber(data[i][colIndex]):
modValue = ("%." + numPlaces + numberFormatOption) % float(
data[i][colIndex])
else:
modValue = data[i][colIndex]
if len(data[i][colIndex]) > int(numPlaces):
modValue = data[i][colIndex][:int(numPlaces)] + "..."
data[i][colIndex] = modValue
utilities.writeMatrixToFile(data, outFilePath)
import os, sys, glob, math
import utilities
from TransformFunctions import *
inFilePath = sys.argv[1]
hasHeaderRow = sys.argv[2] == "True"
transformFunction = getattr(sys.modules[__name__], sys.argv[3])
outFilePath = sys.argv[4]
data = utilities.readMatrixFromFile(inFilePath)
if hasHeaderRow:
headerRow = data.pop(0)
rowNames = [x[0] for x in data]
data = [x[1:] for x in data]
data = utilities.transposeMatrix(data)
data = [transformFunction([y for y in x]) for x in data]
data = utilities.transposeMatrix(data)
data = [[rowNames[i]] + data[i] for i in range(len(data))]
if hasHeaderRow:
data.insert(0, headerRow)
utilities.writeMatrixToFile(data, outFilePath)
import os, sys
import utilities
inFilePath = sys.argv[1]
outFilePath = sys.argv[2]
data = utilities.readMatrixFromFile(inFilePath)
if len(data) > 1 and len(data[0]) == len(data[1]) - 1:
data[0].insert(0, " ")
utilities.writeMatrixToFile(utilities.transposeMatrix(data), outFilePath)
import os, sys
import utilities
inFilePath = sys.argv[1]
outFilePath = sys.argv[2]
data = utilities.readMatrixFromFile(inFilePath)
if len(data[0]) == len(data[1]) - 1:
data[0].insert(0, " ")
utilities.writeMatrixToFile(utilities.transposeMatrix(data), outFilePath)
numNonMuts2 = int(dataDict2[descriptor][-3])
numMuts2 = int(dataDict2[descriptor][-2])
mutFreq2 = float(dataDict2[descriptor][-1])
if (numNonMuts1 == 0 and numNonMuts2 == 0) or (numMuts1 == 0
and numMuts2 == 0):
fisherP = "NaN"
else:
fisherP = calculateFisherExact(numNonMuts1, numMuts1, numNonMuts2,
numMuts2)
metaInfo1 = dataDict1[descriptor][1]
metaInfo2 = dataDict2[descriptor][1]
# meta = ""
# if len(set([metaInfo1] + [metaInfo2])) == 1:
# meta = ([metaInfo1] + [metaInfo2])[0]
# elif len(set([metaInfo1] + [metaInfo2])) > 1:
meta = ";".join(list([metaInfo1, metaInfo2]))
outData.append([
descriptor, meta, numNonMuts1, numMuts1, numNonMuts2, numMuts2,
mutFreq1, mutFreq2, fisherP
])
inFile2.close()
inFile1.close()
outData.sort(key=itemgetter(-1))
utilities.writeMatrixToFile(outHeader + outData, outFilePath)
for descriptor in (set(dataDict1.keys()) | set(dataDict2.keys())):
numNonMuts1 = int(dataDict1[descriptor][-3])
numMuts1 = int(dataDict1[descriptor][-2])
mutFreq1 = float(dataDict1[descriptor][-1])
numNonMuts2 = int(dataDict2[descriptor][-3])
numMuts2 = int(dataDict2[descriptor][-2])
mutFreq2 = float(dataDict2[descriptor][-1])
if (numNonMuts1== 0 and numNonMuts2 == 0) or (numMuts1 == 0 and numMuts2 == 0):
fisherP = "NaN"
else:
fisherP = calculateFisherExact(numNonMuts1, numMuts1, numNonMuts2, numMuts2)
metaInfo1 = dataDict1[descriptor][1]
metaInfo2 = dataDict2[descriptor][1]
# meta = ""
# if len(set([metaInfo1] + [metaInfo2])) == 1:
# meta = ([metaInfo1] + [metaInfo2])[0]
# elif len(set([metaInfo1] + [metaInfo2])) > 1:
meta = ";".join(list([metaInfo1, metaInfo2]))
outData.append([descriptor, meta, numNonMuts1, numMuts1, numNonMuts2, numMuts2, mutFreq1, mutFreq2, fisherP])
inFile2.close()
inFile1.close()
outData.sort(key=itemgetter(-1))
utilities.writeMatrixToFile(outHeader + outData, outFilePath)
import os, sys, glob, math
import utilities
from operator import itemgetter, attrgetter
inFilePath = sys.argv[1]
expression = sys.argv[2]
reverse = sys.argv[3] == "reverse"
numHeaderRows = int(sys.argv[4])
outFilePath = sys.argv[5]
data = utilities.readMatrixFromFile(inFilePath)
headerRows = []
for i in range(numHeaderRows):
headerRows.append(data.pop(0))
data = map(lambda x: eval("x + [" + expression + "]"), data)
data.sort(key=itemgetter(len(data[0]) - 1), reverse=reverse)
data = [x[:-1] for x in data]
utilities.writeMatrixToFile(headerRows + data, outFilePath)
outPositionsRow.append(geneInfoSingle[2])
outPositionsRow.append(geneInfoSingle[3])
outExonBedRows.append([chromosome, geneInfoSingle[2], geneInfoSingle[3], geneID])
else:
outPositionsRow.append(",".join([str(x[2]) for x in transcribedInfo]))
outPositionsRow.append(",".join([str(x[3]) for x in transcribedInfo]))
for i in range(len(transcribedInfo)):
outExonBedRows.append([chromosome, str(transcribedInfo[i][2]), str(transcribedInfo[i][3]), "%s_%i" % (geneID, i)])
# Add transcription start site
if len(cdsInfo) == 0:
if len(transcribedInfo) > 0:
outPositionsRow.append(",".join([str(x[2]) for x in transcribedInfo]))
outPositionsRow.append(",".join([str(x[3]) for x in transcribedInfo]))
else:
outPositionsRow.append(geneInfoSingle[2])
outPositionsRow.append(geneInfoSingle[3])
else:
outPositionsRow.append(",".join([str(x[2]) for x in cdsInfo]))
outPositionsRow.append(",".join([str(x[3]) for x in cdsInfo]))
utilities.writeMatrixToOpenFile([outPositionsRow], outPositionsFile)
utilities.writeMatrixToOpenFile([[geneID, geneInfoSingle[4]]], outStrandFile)
utilities.writeMatrixToFile(outExonBedRows, outExonBedFilePath)
outPositionsFile.close()
outStrandFile.close()
keys = set()
for line in file(inFilePath):
keys.add(line.rstrip().split("\t")[0])
summedDict = {}
for key in keys:
summedDict[key] = []
for line in file(inFilePath):
values = line.rstrip().split("\t")
key = values.pop(0)
summedDict[key].extend(values)
outLines = []
for key in summedDict.keys():
out = [key]
values = [x for x in summedDict[key] if x != ""]
if len(values) == 0:
out.append("NA")
elif len(values) == 1:
out.append(values[0])
else:
out.append(summarizeFunction(values)[0])
outLines.append(out)
utilities.writeMatrixToFile(outLines, outFilePath)