import os, sys, glob
import utilities
inDirPath = sys.argv[1]
inFilePattern = sys.argv[2]
variablesFilePath = sys.argv[3]
dataValueIndex = int(sys.argv[4])
outPatientPrefix = sys.argv[5]
outFilePath = sys.argv[6]
patientIDs = utilities.getPatientIDs(inDirPath, inFilePattern)
variables = None
if variablesFilePath != "None":
variables = utilities.readVectorFromFile(variablesFilePath)
patientsKeyValuesDict = utilities.getPatientsKeyValuesDict(
inDirPath, patientIDs, inFilePattern, dataValueIndex, variables)
outFile = open(outFilePath, 'w')
outFile.write("\t".join(
["Key"] + [outPatientPrefix + patientID
for patientID in patientIDs]) + "\n")
if variables == None:
keys = sorted(patientsKeyValuesDict[patientIDs[0]].keys())
else:
keys = list(
set(variables) & set(patientsKeyValuesDict[patientIDs[0]].keys()))
for key in keys:
import os, sys, glob
import utilities
matrixFilePath = sys.argv[1]
samplesFilePath = sys.argv[2]
outDirPath = utilities.checkDirPath(sys.argv[3])
outDirFilePattern = sys.argv[4]
data = utilities.readMatrixFromFile(matrixFilePath)
dataPatientIDs = data.pop(0)
samplePatientIDs = [
x.replace(".", "-") for x in utilities.readVectorFromFile(samplesFilePath)
]
if len(dataPatientIDs) == len(data[0]): #check for description in first column
dataPatientIDs.pop(0)
variableNames = [x[0] for x in data]
patientValuesDict = {}
for samplePatientID in samplePatientIDs:
if not samplePatientID in dataPatientIDs:
continue
patientValues = [
x[dataPatientIDs.index(samplePatientID) + 1] for x in data
]
output = ""
import os, sys, glob
import utilities
inDirPath = sys.argv[1]
inFilePattern = sys.argv[2]
variablesFilePath = sys.argv[3]
dataValueIndex = int(sys.argv[4])
outPatientPrefix = sys.argv[5]
outFilePath = sys.argv[6]
patientIDs = utilities.getPatientIDs(inDirPath, inFilePattern)
variables = None
if variablesFilePath != "None":
variables = utilities.readVectorFromFile(variablesFilePath)
patientsKeyValuesDict = utilities.getPatientsKeyValuesDict(inDirPath, patientIDs, inFilePattern, dataValueIndex, variables)
outFile = open(outFilePath, 'w')
outFile.write("\t".join(["Key"] + [outPatientPrefix + patientID for patientID in patientIDs]) + "\n")
if variables == None:
keys = sorted(patientsKeyValuesDict[patientIDs[0]].keys())
else:
keys = list(set(variables) & set(patientsKeyValuesDict[patientIDs[0]].keys()))
for key in keys:
outFile.write("\t".join([key] + [patientsKeyValuesDict[patientID][key] for patientID in patientIDs]) + "\n")
outFile.close()
cel = MyCEL()
norm = Normalize()
if os.path.exists(outFilePath):
print "Already processed %s" % outFilePath
else:
print "Reading annotations"
probe2seq, coord2probe = getMetadata(probeSequenceTabFilePath, probeSequenceTabColIndices)
print "Reading " + celFilePath
probeIntensity = cel.read_cel(celFilePath, coord2probe)
modelProbes = None
if os.path.exists(modelProbesFilePath):
print "Reading model probes file"
modelProbes = utilities.readVectorFromFile(modelProbesFilePath)
else:
if modelProbesFilePath != "None":
print "No model probes file exists at " + modelProbesFilePath
print "Normalizing to " + outFilePath
normValues = norm.normalize(probeIntensity, probe2seq, modelProbes)
probes = sorted([str(x) for x in probe2seq.keys()])
exprValues = [normValues[probe][0] for probe in probes]
probValues = [normValues[probe][1] for probe in probes]
outFile = file(outFilePath, 'w')
for i in range(len(probes)):
outFile.write("%s\t%.9f\t%.9f\n" % (probes[i], exprValues[i], probValues[i]))
return utilities.calculateTrimmedMean(values)
patientID = sys.argv[1]
inFilePath = sys.argv[2]
dataColumnIndex = int(sys.argv[3])
keyProbeFilePath = sys.argv[4]
probeFilePath = sys.argv[5]
minNumProbesPer = int(sys.argv[6])
summarizeFunction = getattr(sys.modules[__name__], sys.argv[7])
outlierSamplesFilePath = sys.argv[8]
outFilePath = sys.argv[9]
outlierSamples = []
if os.path.exists(outlierSamplesFilePath):
outlierSamples = utilities.readVectorFromFile(outlierSamplesFilePath)
if patientID in outlierSamples:
print "%s is listed as an outlier, so it won't be summarized" % patientID
sys.exit(0)
keepProbes = set(utilities.readVectorFromFile(probeFilePath))
print "Getting key/probe dict from %s" % keyProbeFilePath
keyProbeDict = utilities.getKeyProbeDict(keyProbeFilePath)
print "Identifying probes to keep"
for key in keyProbeDict.keys():
keyProbeDict[key] = list(set(keyProbeDict[key]) & keepProbes)
print "Removing keys with few probes"
import os, sys, glob
import utilities
symbolsFilePath = sys.argv[1]
entrezGenesSymbolsFilePath = sys.argv[2]
entrezGenesSynonymsFilePath = sys.argv[3]
outFilePath = sys.argv[4]
symbols = utilities.readVectorFromFile(symbolsFilePath)
entrezGenesSymbolsData = utilities.readMatrixFromFile(
entrezGenesSymbolsFilePath)
entrezGenesSymbolsDict = {}
for row in entrezGenesSymbolsData:
entrezGenesSymbolsDict[row[1]] = row[0]
entrezGenesSynonymsData = utilities.readMatrixFromFile(
entrezGenesSynonymsFilePath)
entrezGenesSynonymsDict = {}
for row in entrezGenesSynonymsData:
for synonym in row[1].split("|"):
entrezGenesSynonymsDict[synonym] = entrezGenesSynonymsDict.setdefault(
synonym, []) + [row[0]]
outFile = open(outFilePath, 'w')
for symbol in symbols:
if entrezGenesSymbolsDict.has_key(symbol):
entrezID = entrezGenesSymbolsDict[symbol]
else:
if entrezGenesSynonymsDict.has_key(symbol):
entrezIDs = entrezGenesSynonymsDict[symbol]
import os, sys, glob
import utilities
symbolsFilePath = sys.argv[1]
entrezGenesSymbolsFilePath = sys.argv[2]
entrezGenesSynonymsFilePath = sys.argv[3]
outFilePath = sys.argv[4]
symbols = utilities.readVectorFromFile(symbolsFilePath)
entrezGenesSymbolsData = utilities.readMatrixFromFile(entrezGenesSymbolsFilePath)
entrezGenesSymbolsDict = {}
for row in entrezGenesSymbolsData:
entrezGenesSymbolsDict[row[1]] = row[0]
entrezGenesSynonymsData = utilities.readMatrixFromFile(entrezGenesSynonymsFilePath)
entrezGenesSynonymsDict = {}
for row in entrezGenesSynonymsData:
for synonym in row[1].split("|"):
entrezGenesSynonymsDict[synonym] = entrezGenesSynonymsDict.setdefault(synonym, []) + [row[0]]
outFile = open(outFilePath, 'w')
for symbol in symbols:
if entrezGenesSymbolsDict.has_key(symbol):
entrezID = entrezGenesSymbolsDict[symbol]
else:
if entrezGenesSynonymsDict.has_key(symbol):
entrezIDs = entrezGenesSynonymsDict[symbol]
if len(entrezIDs) == 1:
entrezID = entrezIDs[0]
norm = Normalize()
if os.path.exists(outFilePath):
print "Already processed %s" % outFilePath
else:
print "Reading annotations"
probe2seq, coord2probe = getMetadata(probeSequenceTabFilePath,
probeSequenceTabColIndices)
print "Reading " + celFilePath
probeIntensity = cel.read_cel(celFilePath, coord2probe)
modelProbes = None
if os.path.exists(modelProbesFilePath):
print "Reading model probes file"
modelProbes = utilities.readVectorFromFile(modelProbesFilePath)
else:
if modelProbesFilePath != "None":
print "No model probes file exists at " + modelProbesFilePath
print "Normalizing to " + outFilePath
normValues = norm.normalize(probeIntensity, probe2seq, modelProbes)
probes = sorted([str(x) for x in probe2seq.keys()])
exprValues = [normValues[probe][0] for probe in probes]
probValues = [normValues[probe][1] for probe in probes]
outFile = file(outFilePath, 'w')
for i in range(len(probes)):
outFile.write("%s\t%.9f\t%.9f\n" %
import os, sys, glob
import utilities
idFilePattern = sys.argv[1]
outFilePath = sys.argv[2]
outFile = open(outFilePath, 'w')
for idFilePath in glob.glob(idFilePattern):
name = os.path.basename(idFilePath).replace(".gene.ids", "")
name = name.replace(".txt", "")
ids = utilities.readVectorFromFile(idFilePath)
outFile.write("%s\t%s\t%s\n" % (name, name, "\t".join(ids)))
outFile.close()
return utilities.calculateTrimmedMean(values)
patientID = sys.argv[1]
inFilePath = sys.argv[2]
dataColumnIndex = int(sys.argv[3])
keyProbeFilePath = sys.argv[4]
probeFilePath = sys.argv[5]
minNumProbesPer = int(sys.argv[6])
summarizeFunction = getattr(sys.modules[__name__], sys.argv[7])
outlierSamplesFilePath = sys.argv[8]
outFilePath = sys.argv[9]
outlierSamples = []
if os.path.exists(outlierSamplesFilePath):
outlierSamples = utilities.readVectorFromFile(outlierSamplesFilePath)
if patientID in outlierSamples:
print "%s is listed as an outlier, so it won't be summarized" % patientID
sys.exit(0)
keepProbes = set(utilities.readVectorFromFile(probeFilePath))
print "Getting key/probe dict from %s" % keyProbeFilePath
keyProbeDict = utilities.getKeyProbeDict(keyProbeFilePath)
print "Identifying probes to keep"
for key in keyProbeDict.keys():
keyProbeDict[key] = list(set(keyProbeDict[key]) & keepProbes)
print "Removing keys with few probes"
import os, sys, glob
import utilities
matrixFilePath = sys.argv[1]
samplesFilePath = sys.argv[2]
outDirPath = utilities.checkDirPath(sys.argv[3])
outDirFilePattern = sys.argv[4]
data = utilities.readMatrixFromFile(matrixFilePath)
dataPatientIDs = data.pop(0)
samplePatientIDs = [x.replace(".", "-") for x in utilities.readVectorFromFile(samplesFilePath)]
if len(dataPatientIDs) == len(data[0]): #check for description in first column
dataPatientIDs.pop(0)
variableNames = [x[0] for x in data]
patientValuesDict = {}
for samplePatientID in samplePatientIDs:
if not samplePatientID in dataPatientIDs:
continue
patientValues = [x[dataPatientIDs.index(samplePatientID) + 1] for x in data]
output = ""
for i in range(len(variableNames)):
output += "\t".join([variableNames[i], patientValues[i]]) + "\n"
outFilePath = outDirPath + samplePatientID + outDirFilePattern