def main(options, programName, programVersion):
## REGION: DEFAULT VALUES AND VARIABLE ACQUISITION
# basic default info
logFile = ""
tagFile = ""
analysisName = ""
analysisFolder = ""
defaultAnalysisName = programName.lower()
verbose = False
separator = "_"
# default extensions
# begin: jmrc
# defaultTableExtension = ".xls"
defaultTextExtension = ".txt"
# defaultTextExtension = ".tsv"
# end: jmrc
# default file names
defaultLogFile = "logFile"
defaultNewRelsFile = "newRels"
defaultNewDataFile = "newData"
newRelsFile = ""
newDataFile = ""
# basic log file
logList = [[programName + " " + programVersion], ["Start: " + strftime("%Y-%m-%d %H:%M:%S")]]
# parsing arguments from commandline
options.add_argument("-a", "--analysis", type = str, default = "", required = True, help = "Use a prefix for the output files.")
options.add_argument("-p", "--place", type = str, default = "", required = True, help = "To use a different common folder for the output files. If this is not provided, the the folder used will be the same as the FASTA file folder.")
options.add_argument("-L", "--logfile", type = str, default = "", required = False, help = "To use a non-default name for the log file.")
options.add_argument("-t", "--tagfile", type = str, default = "", required = True, help = "The file containing the tags used for the different experiments to be joined.")
options.add_argument("-d", "--datafile", type = str, default = "", required = False, help = "To use a non-default merged data file name.")
options.add_argument("-r", "--relfile", type = str, default = "", required = False, help = "To use a non-default merged relations file name.")
options.add_argument("-s", "--separator", type = str, default = "_", required = False, help = """To use a non-default suffix separator (default is "_").""")
options.add_argument("-v", "--verbose", action = "store_true", help = "To write down extra information about operations performed.")
# *-*-* add easter egg
arguments = options.parse_args()
# copying parsed arguments
# copy any arguments used
if len(arguments.analysis) > 0: analysisName = arguments.analysis
if len(arguments.place) > 0: analysisFolder = arguments.place
if len(arguments.logfile) > 0: logFile = arguments.logfile
if len(arguments.tagfile) > 0: tagFile = arguments.tagfile
if len(arguments.datafile) > 0: newDataFile = arguments.datafile
if len(arguments.relfile) > 0: newRelsFile = arguments.relfile
if len(arguments.separator) > 0: separator = arguments.separator
verbose = arguments.verbose
## END REGION: DEFAULT VALUES AND VARIABLE ACQUISITION
## **********************************************************
## REGION: FILE NAMES SETUP
if len(analysisName) == 0:
if len(tagFile) > 0:
analysisName = os.path.splitext(os.path.basename(tagFile))[0]
else:
analysisName = defaultAnalysisName
if len(os.path.dirname(analysisName)) > 0:
analysisNameFirstPart = os.path.dirname(analysisName)
analysisName = os.path.basename(analysisName)
if len(analysisFolder) == 0:
analysisFolder = analysisNameFirstPart
# input
if len(os.path.dirname(tagFile)) == 0:
tagFile = os.path.join(analysisFolder, tagFile)
# output
if len(logFile) == 0:
logFile = os.path.join(analysisFolder, analysisName + "_" + defaultLogFile + defaultTextExtension)
if len(os.path.dirname(logFile)) == 0 and len(os.path.basename(logFile)) > 0:
logFile = os.path.join(analysisFolder, logFile)
if len(newRelsFile) == 0:
newRelsFile = os.path.join(analysisFolder, analysisName + "_" + defaultNewRelsFile + defaultTextExtension)
if len(os.path.dirname(newRelsFile)) == 0 and len(os.path.basename(newRelsFile)) > 0:
newRelsFile = os.path.join(analysisFolder, newRelsFile)
if len(newDataFile) == 0:
newDataFile = os.path.join(analysisFolder, analysisName + "_" + defaultNewDataFile + defaultTextExtension)
if len(os.path.dirname(newDataFile)) == 0 and len(os.path.basename(newDataFile)) > 0:
newDataFile = os.path.join(analysisFolder, newDataFile)
logList.append([""])
logList.append(["Input tags file: " + tagFile])
logList.append(["Output new data file: " + newDataFile])
logList.append(["Output new relations file: " + newRelsFile])
logList.append(["Output log file: " + logFile])
logList.append([""])
## END REGION: FILE NAMES SETUP
## **********************************************************
## REGION: PROGRAM BASIC STRUCTURE
tagList, dataFileList = readTagFile(tagFile, defaultFolder = analysisFolder)
processMessage = processFiles(tagList,
dataFileList,
verbose = verbose,
separator = separator,
dataFile = newDataFile,
relsFile = newRelsFile)
logList.extend(processMessage)
## END REGION: PROGRAM BASIC STRUCTURE
## **********************************************************
## REGION: SAVING FILES
## exceptionally, due to memory errors, the data are read and written in processFiles
# try:
# # operations here
# logList.append(["Saving new data file..."])
# stats.saveFile(newDataFile, newDataList, "idinf\tX'inf\tVinf")
# except Exception:
# logList.append(["Error."])
# stats.saveFile(logFile, logList, "LOG FILE")
# sys.exit(2)
# try:
# # operations here
# logList.append(["Saving new relations file..."])
# stats.saveFile(newRelsFile, newRelsList, "idsup\tidinf")
# except Exception:
# stats.saveFile(logFile, logList, "LOG FILE")
# logList.append(["Error."])
# sys.exit(2)
try:
# operations here
logList.append(["Looks like everything went fine."])
except Exception:
logList.append(["Error."])
stats.saveFile(logFile, logList, "LOG FILE")
sys.exit(2)
stats.saveFile(logFile, logList, "LOG FILE")
def showGraphTool(inputRawData,
inputRelations,
k,
variance,
alpha,
medianSide,
verbose=False,
showRank=False,
graphFile=None,
graphData=None,
dpi=None,
showGraph=True):
plt.clf()
inputRawData.sort()
inputRelations.sort()
windowWidth = medianSide * 2 + 1
if len(inputRawData) < windowWidth:
print('Error: window for median is bigger than total input size')
sys.exit(1)
# output = makeStats(k, variance, input = input)
nextIdXData = getNextIdX_klibrate(inputRawData,
inputRelations,
k,
variance,
alpha,
giveMergedData=True)
nextIdX = nextIdXData[0]
mergedData = nextIdXData[1]
MADdistrOut, weights = getMADDistribution(nextIdX, mergedData, k, variance,
alpha, medianSide)
invOfFitOut = getInverseOfFit(mergedData, k, variance, alpha)
MADdistrOut = MADdistrOut[medianSide:len(MADdistrOut) - medianSide + 1]
invOfFitOut = invOfFitOut[medianSide:len(invOfFitOut) - medianSide + 1]
weights = weights[medianSide:len(weights) - medianSide + 1]
# folderToSave = "D:\\DATUMARO\\trabajo\\programas_repositorio\\BioSistemas SanXoT\\MicroArrays\\intento5 CvsCs usando var robusta por partes\\"
# stats.saveFile(folderToSave + "MADdistrOut.txt", MADdistrOut)
# stats.saveFile(folderToSave + "invOfFitOut.txt", invOfFitOut)
# stats.saveFile(folderToSave + "weights.txt", weights)
if showRank:
plt.plot(list(range(len(MADdistrOut))),
MADdistrOut,
'g.',
list(range(len(invOfFitOut))),
invOfFitOut,
'r',
linewidth=1.0,
markersize=2.0,
markeredgewidth=0.0)
plt.xlabel('rank($V_s$)')
plt.ylabel('1 / MSD')
# to save data
# *** use a better filename
dataToSave = []
for i in range(len(MADdistrOut)):
dataToSave.append([i, weights[i], MADdistrOut[i], invOfFitOut[i]])
if graphData:
stats.saveFile(graphData, dataToSave,
"rank(Vs)\tweight\tMAD\t1/fit")
else:
# uncomment to graph MSD instead of 1 / MSD
#
# for i in xrange(len(invOfFitOut)):
# invOfFitOut[i] = 1 / invOfFitOut[i]
# for i in xrange(len(MADdistrOut)):
# MADdistrOut[i] = 1 / MADdistrOut[i]
plt.plot(weights,
MADdistrOut,
'g.',
weights,
invOfFitOut,
'r',
linewidth=1.0,
markersize=2.0,
markeredgewidth=0.0)
plt.xlabel('($V_s$)')
plt.ylabel('1 / MSD')
plt.grid(True)
plt.title('k = %g, $\sigma^2$ = %g, alpha = %g' % (k, variance, alpha))
if graphFile:
plt.savefig(graphFile, dpi=dpi)
if showGraph:
plt.show()
def main(argv):
version = "v1.19"
verbose = True
showGraph = True
graphDPI = 100 # default of Matplotlib's savefig method
showSteps = True
forceParameters = False
kSeed = 1.0
varianceSeed = 0.001
alphaSeed = 1.0
useCooperativity = False
medianSide = 100
maxIterations = 0
dataFile = ""
relationsFile = ""
outputCalibrated = ""
infoFile = ""
kFile = ""
kSeedProvided = False
varFile = ""
varianceSeedProvided = False
graphFileVRank = ""
graphFileVValue = ""
graphDataFile = ""
showRank = False
analysisName = ""
defaultAnalysisName = "klibrate"
analysisFolder = ""
logList = [["Klibrate " + version],
["Start: " + strftime("%Y-%m-%d %H:%M:%S")]]
defaultDataFile = "data"
defaultRelationsFile = "rels"
defaultOutputInfo = "infoFile"
defaultOutputGraphVRank = "outGraph_VRank"
defaultOutputGraphVValue = "outGraph_VValue"
defaultGraphDataFile = "outGraph_Data"
defaultOutputCalibrated = "calibrated"
defaultTableExtension = ".tsv"
defaultTextExtension = ".txt"
defaultGraphExtension = ".png"
try:
opts, args = getopt.getopt(
argv, "a:p:k:v:c:d:r:o:w:m:L:G:D:R:K:V:bgsfh", [
"analysis=", "folder=", "kseed=", "varianceseed=",
"alphaseed=", "datafile=", "relfile=", "outputfile=",
"window=", "maxiterations=", "infofile=", "outgraphvrank=",
"outgraphvvalue=", "outgraphdata=", "kfile=", "varfile=",
"no-verbose", "no-showgraph", "no-showsteps",
"forceparameters", "showrank", "help", "egg", "easteregg"
])
except getopt.GetoptError:
message = "Error while getting parameters."
print(message)
logList.append([message])
# stats.saveFile(infoFile, logList, "INFO FILE")
sys.exit(2)
if len(opts) == 0:
printHelp(version)
sys.exit()
for opt, arg in opts:
if opt in ("-a", "--analysis"):
analysisName = arg
if opt in ("-p", "--place", "--folder"):
analysisFolder = arg
if opt in ("-k", "--kseed"):
kSeed = float(arg)
kSeedProvided = True
elif opt in ("-v", "--var", "--varianceseed"):
varianceSeed = float(arg)
varianceSeedProvided = True
elif opt in ("-c", "--alphaseed"):
useCooperativity = True
alphaSeed = float(arg)
elif opt in ("-d", "--datafile"):
dataFile = arg
elif opt in ("-r", "--relfile", "--relationsfile"):
relationsFile = arg
elif opt in ("-o", "--outputfile"):
outputCalibrated = arg
elif opt in ("-w", "--window"):
windowWidth = round(float(arg))
if windowWidth % 2 == 0:
windowWidth += 1
medianSide = int((windowWidth - 1) / 2)
elif opt in ("-b", "--no-verbose"):
verbose = False
elif opt in ("-g", "--no-showgraph"):
showGraph = False
elif opt in ("-s", "--no-showsteps"):
showSteps = False
elif opt in ("-m", "--maxiterations"):
maxIterations = int(arg)
elif opt in ("-L", "--infofile"):
infoFile = arg
elif opt in ("-G", "--outgraphvvalue"):
graphFileVValue = arg
elif opt in ("-D", "--outgraphdata"):
graphDataFile = arg
elif opt in ("-K", "--kfile"):
kFile = arg
elif opt in ("-V", "--varfile"):
varFile = arg
elif opt in ("-f", "--forceparameters"):
forceParameters = True
elif opt in ("-R", "--outgraphvrank"):
graphFileVRank = arg
elif opt in ("-h", "--help"):
printHelp(version)
sys.exit()
elif opt in ("--egg", "--easteregg"):
easterEgg()
sys.exit()
verbose = verbose or showSteps
# REGION: FILE NAMES SETUP
if len(analysisName) == 0:
if len(dataFile) > 0:
analysisName = os.path.splitext(os.path.basename(dataFile))[0]
else:
analysisName = defaultAnalysisName
if len(os.path.dirname(analysisName)) > 0:
analysisNameFirstPart = os.path.dirname(analysisName)
analysisName = os.path.basename(analysisName)
if len(analysisFolder) == 0:
analysisFolder = analysisNameFirstPart
if len(dataFile) > 0 and len(analysisFolder) == 0:
if len(os.path.dirname(dataFile)) > 0:
analysisFolder = os.path.dirname(dataFile)
# input
if len(dataFile) == 0:
dataFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultDataFile + defaultTableExtension)
if len(os.path.dirname(dataFile)) == 0 and len(analysisFolder) > 0:
dataFile = os.path.join(analysisFolder, dataFile)
if len(relationsFile) == 0:
relationsFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultRelationsFile + defaultTableExtension)
if len(os.path.dirname(relationsFile)) == 0:
relationsFile = os.path.join(analysisFolder, relationsFile)
if len(os.path.dirname(varFile)) == 0 and len(
os.path.basename(varFile)) > 0:
varFile = os.path.join(analysisFolder, varFile)
if len(varFile) > 0 and not varianceSeedProvided:
varianceSeed, varianceOk = stats.extractVarianceFromVarFile(
varFile, verbose=verbose, defaultSeed=varianceSeed)
if not varianceOk:
logList.append(["Variance not found in text file"])
stats.saveFile(infoFile, logList, "INFO FILE")
sys.exit()
if len(os.path.dirname(kFile)) == 0 and len(os.path.basename(kFile)) > 0:
kFile = os.path.join(analysisFolder, kFile)
if len(kFile) > 0 and not kSeedProvided:
kSeed, KOk = stats.extractKFromKFile(kFile,
verbose=verbose,
defaultSeed=kSeed)
if not KOk:
logList.append(["K not found in text file."])
stats.saveFile(infoFile, logList, "INFO FILE")
sys.exit()
# output
if len(outputCalibrated) == 0:
outputCalibrated = os.path.join(
analysisFolder, analysisName + "_" + defaultOutputCalibrated +
defaultTableExtension)
else:
if len(os.path.dirname(outputCalibrated)) == 0:
outputCalibrated = os.path.join(analysisFolder, outputCalibrated)
if len(graphFileVRank) == 0:
graphFileVRank = os.path.join(
analysisFolder, analysisName + "_" + defaultOutputGraphVRank +
defaultGraphExtension)
if len(graphFileVValue) == 0:
graphFileVValue = os.path.join(
analysisFolder, analysisName + "_" + defaultOutputGraphVValue +
defaultGraphExtension)
if len(graphDataFile) == 0:
graphDataFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultGraphDataFile + defaultTableExtension)
if len(infoFile) == 0:
infoFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultOutputInfo + defaultTextExtension)
logList.append(["Variance seed = " + str(varianceSeed)])
logList.append(["K seed = " + str(kSeed)])
if useCooperativity: logList.append(["Alpha seed = " + str(alphaSeed)])
logList.append(["Input data file: " + dataFile])
logList.append(["Input relations file: " + relationsFile])
logList.append(["Output calibrated file: " + outputCalibrated])
logList.append(["Output info file: " + infoFile])
logList.append(["Output V rank graph file: " + graphFileVRank])
logList.append(["Output V graph file: " + graphFileVValue])
logList.append(["Output data file for graph: " + graphDataFile])
logList.append(["Parameters forced: " + str(forceParameters)])
logList.append(["Max iterations: " + str(maxIterations)])
# END REGION: FILE NAMES SETUP
calibratedData, variance, k, alpha, extraLog = calibrate(
rawDataFile=dataFile,
relationsFile=relationsFile,
kSeed=kSeed,
varianceSeed=varianceSeed,
medianSide=medianSide,
maxIterations=maxIterations,
verbose=showSteps,
showGraph=showGraph,
forceParameters=forceParameters,
alphaSeed=alphaSeed,
showRank=showRank,
useCooperativity=useCooperativity,
graphFileVRank=graphFileVRank,
graphFileVValue=graphFileVValue,
graphDataFile=graphDataFile,
graphDPI=graphDPI)
logList.extend(extraLog)
if not calibratedData:
if len(infoFile) > 0:
stats.saveFile(infoFile, logList, "INFO FILE")
sys.exit()
if len(outputCalibrated) > 0:
stats.saveFile(outputCalibrated, calibratedData, "id\tX\tVcal")
logList.append([])
logList.append(["K = " + str(k)])
logList.append(["Variance = " + str(variance)])
if useCooperativity: logList.append(["Alpha = " + str(alpha)])
if len(infoFile) > 0:
stats.saveFile(infoFile, logList, "INFO FILE")
if verbose:
print()
print("*** results ***")
print("k = " + str(k))
print("variance = " + str(variance))
if useCooperativity: print("alpha = " + str(alpha))
print()
print("Output calibrated file in: " + outputCalibrated)
print("Graph with rank of V in: " + graphFileVRank)
print("Graph with value of V in: " + graphFileVValue)
print("Info file in: " + infoFile)
def main(argv):
version = "v1.18"
verbose = True
showGraph = True
graphDPI = 100 # default of Matplotlib's savefig method
showSteps = True
forceParameters = False
kSeed = 1.0
varianceSeed = 0.001
alphaSeed = 1.0
useCooperativity = False
medianSide = 100
maxIterations = 0
dataFile = ""
relationsFile = ""
outputCalibrated = ""
infoFile = ""
kFile = ""
kSeedProvided = False
varFile = ""
varianceSeedProvided = False
graphFileVRank = ""
graphFileVValue = ""
graphDataFile = ""
showRank = False
analysisName = ""
defaultAnalysisName = "klibrate"
analysisFolder = ""
logList = [["Klibrate " + version], ["Start: " + strftime("%Y-%m-%d %H:%M:%S")]]
defaultDataFile = "data"
defaultRelationsFile = "rels"
defaultOutputInfo = "infoFile"
defaultOutputGraphVRank = "outGraph_VRank"
defaultOutputGraphVValue = "outGraph_VValue"
defaultGraphDataFile = "outGraph_Data"
defaultOutputCalibrated = "calibrated"
defaultTableExtension = ".tsv"
defaultTextExtension = ".txt"
defaultGraphExtension = ".png"
try:
opts, args = getopt.getopt(argv, "a:p:k:v:c:d:r:o:w:m:L:G:D:R:K:V:bgsfh", ["analysis=", "folder=", "kseed=", "varianceseed=", "alphaseed=", "datafile=", "relfile=", "outputfile=", "window=", "maxiterations=", "infofile=", "outgraphvrank=", "outgraphvvalue=", "outgraphdata=", "kfile=", "varfile=", "no-verbose", "no-showgraph", "no-showsteps", "forceparameters", "showrank", "help", "egg", "easteregg"])
except getopt.GetoptError:
message = "Error while getting parameters."
print(message)
logList.append([message])
# stats.saveFile(infoFile, logList, "INFO FILE")
sys.exit(2)
if len(opts) == 0:
printHelp(version)
sys.exit()
for opt, arg in opts:
if opt in ("-a", "--analysis"):
analysisName = arg
if opt in ("-p", "--place", "--folder"):
analysisFolder = arg
if opt in ("-k", "--kseed"):
kSeed = float(arg)
kSeedProvided = True
elif opt in ("-v", "--var", "--varianceseed"):
varianceSeed = float(arg)
varianceSeedProvided = True
elif opt in ("-c", "--alphaseed"):
useCooperativity = True
alphaSeed = float(arg)
elif opt in ("-d", "--datafile"):
dataFile = arg
elif opt in ("-r", "--relfile", "--relationsfile"):
relationsFile = arg
elif opt in ("-o", "--outputfile"):
outputCalibrated = arg
elif opt in ("-w", "--window"):
windowWidth = round(float(arg))
if windowWidth % 2 == 0:
windowWidth += 1
medianSide = int((windowWidth - 1) / 2)
elif opt in ("-b", "--no-verbose"):
verbose = False
elif opt in ("-g", "--no-showgraph"):
showGraph = False
elif opt in ("-s", "--no-showsteps"):
showSteps = False
elif opt in ("-m", "--maxiterations"):
maxIterations = int(arg)
elif opt in ("-L", "--infofile"):
infoFile = arg
elif opt in ("-G", "--outgraphvvalue"):
graphFileVValue = arg
elif opt in ("-D", "--outgraphdata"):
graphDataFile = arg
elif opt in ("-K", "--kfile"):
kFile = arg
elif opt in ("-V", "--varfile"):
varFile = arg
elif opt in ("-f", "--forceparameters"):
forceParameters = True
elif opt in ("-R", "--outgraphvrank"):
graphFileVRank = arg
elif opt in ("-h", "--help"):
printHelp(version)
sys.exit()
elif opt in ("--egg", "--easteregg"):
easterEgg()
sys.exit()
verbose = verbose or showSteps
# REGION: FILE NAMES SETUP
if len(analysisName) == 0:
if len(dataFile) > 0:
analysisName = os.path.splitext(os.path.basename(dataFile))[0]
else:
analysisName = defaultAnalysisName
if len(os.path.dirname(analysisName)) > 0:
analysisNameFirstPart = os.path.dirname(analysisName)
analysisName = os.path.basename(analysisName)
if len(analysisFolder) == 0:
analysisFolder = analysisNameFirstPart
if len(dataFile) > 0 and len(analysisFolder) == 0:
if len(os.path.dirname(dataFile)) > 0:
analysisFolder = os.path.dirname(dataFile)
# input
if len(dataFile) == 0:
dataFile = os.path.join(analysisFolder, analysisName + "_" + defaultDataFile + defaultTableExtension)
if len(os.path.dirname(dataFile)) == 0 and len(analysisFolder) > 0:
dataFile = os.path.join(analysisFolder, dataFile)
if len(relationsFile) == 0:
relationsFile = os.path.join(analysisFolder, analysisName + "_" + defaultRelationsFile + defaultTableExtension)
if len(os.path.dirname(relationsFile)) == 0:
relationsFile = os.path.join(analysisFolder, relationsFile)
if len(os.path.dirname(varFile)) == 0 and len(os.path.basename(varFile)) > 0:
varFile = os.path.join(analysisFolder, varFile)
if len(varFile) > 0 and not varianceSeedProvided:
varianceSeed, varianceOk = stats.extractVarianceFromVarFile(varFile, verbose = verbose, defaultSeed = varianceSeed)
if not varianceOk:
logList.append(["Variance not found in text file"])
stats.saveFile(infoFile, logList, "INFO FILE")
sys.exit()
if len(os.path.dirname(kFile)) == 0 and len(os.path.basename(kFile)) > 0:
kFile = os.path.join(analysisFolder, kFile)
if len(kFile) > 0 and not kSeedProvided:
kSeed, KOk = stats.extractKFromKFile(kFile, verbose = verbose, defaultSeed = kSeed)
if not KOk:
logList.append(["K not found in text file."])
stats.saveFile(infoFile, logList, "INFO FILE")
sys.exit()
# output
if len(outputCalibrated) == 0:
outputCalibrated = os.path.join(analysisFolder, analysisName + "_" + defaultOutputCalibrated + defaultTableExtension)
else:
if len(os.path.dirname(outputCalibrated)) == 0:
outputCalibrated = os.path.join(analysisFolder, outputCalibrated)
if len(graphFileVRank) == 0:
graphFileVRank = os.path.join(analysisFolder, analysisName + "_" + defaultOutputGraphVRank + defaultGraphExtension)
if len(graphFileVValue) == 0:
graphFileVValue = os.path.join(analysisFolder, analysisName + "_" + defaultOutputGraphVValue + defaultGraphExtension)
if len(graphDataFile) == 0:
graphDataFile = os.path.join(analysisFolder, analysisName + "_" + defaultGraphDataFile + defaultTableExtension)
if len(infoFile) == 0:
infoFile = os.path.join(analysisFolder, analysisName + "_" + defaultOutputInfo + defaultTextExtension)
logList.append(["Variance seed = " + str(varianceSeed)])
logList.append(["K seed = " + str(kSeed)])
if useCooperativity: logList.append(["Alpha seed = " + str(alphaSeed)])
logList.append(["Input data file: " + dataFile])
logList.append(["Input relations file: " + relationsFile])
logList.append(["Output calibrated file: " + outputCalibrated])
logList.append(["Output info file: " + infoFile])
logList.append(["Output V rank graph file: " + graphFileVRank])
logList.append(["Output V graph file: " + graphFileVValue])
logList.append(["Output data file for graph: " + graphDataFile])
logList.append(["Parameters forced: " + str(forceParameters)])
logList.append(["Max iterations: " + str(maxIterations)])
# END REGION: FILE NAMES SETUP
calibratedData, variance, k, alpha, extraLog = calibrate(rawDataFile = dataFile,
relationsFile = relationsFile, kSeed = kSeed, varianceSeed = varianceSeed,
medianSide = medianSide, maxIterations = maxIterations, verbose = showSteps,
showGraph = showGraph, forceParameters = forceParameters, alphaSeed = alphaSeed,
showRank = showRank, useCooperativity = useCooperativity, graphFileVRank = graphFileVRank, graphFileVValue = graphFileVValue, graphDataFile = graphDataFile, graphDPI = graphDPI)
logList.extend(extraLog)
if not calibratedData:
if len(infoFile) > 0:
stats.saveFile(infoFile, logList, "INFO FILE")
sys.exit()
if len(outputCalibrated) > 0:
stats.saveFile(outputCalibrated, calibratedData, "id\tX\tVcal")
logList.append([])
logList.append(["K = " + str(k)])
logList.append(["Variance = " + str(variance)])
if useCooperativity: logList.append(["Alpha = " + str(alpha)])
if len(infoFile) > 0:
stats.saveFile(infoFile, logList, "INFO FILE")
if verbose:
print()
print("*** results ***")
print("k = " + str(k))
print("variance = " + str(variance))
if useCooperativity: print("alpha = " + str(alpha))
print()
print("Output calibrated file in: " + outputCalibrated)
print("Graph with rank of V in: " + graphFileVRank)
print("Graph with value of V in: " + graphFileVValue)
print("Info file in: " + infoFile)
def main(argv):
version = "v1.06"
verbose = False
showGraph = True
showLegend = True
analysisName = ""
graphLimits = 6.0
defaultAnalysisName = "arbor"
analysisFolder = ""
# input files
inStats = ""
useSubStats = False # True if inStats (-z) and relationsFile (-r) are provided
bigListFile = ""
defaultStatsFile = "stats"
defaultRelationsFile = "rels"
defaultTableExtension = ".tsv"
defaultTextExtension = ".txt"
defaultGVFileExtension = ".gv"
relationsFile = ""
listOfCategoriesFile = ""
# output files
defaultListOfCategoriesFile = "ulst"
defaultBigListFile = "table_allPaths.tsv"
defaultOutputFile = "outNodes"
defaultOutputGraphFile = "outTree"
defaultLogFile = "logFile"
logFile = ""
outputFile = ""
graphFile = ""
similarityMatrixFile = ""
graphFileFormat = "png"
altMax = 5
selectedNodeColour = "#ff9090"
defaultNodeColour = "#ffff80"
errorNodeColour = "#8080ff"
minColour = "#00ff00"
middleColour = "#ffffff"
maxColour = "#ff0000"
logList = [["SanXoTGauss " + version],
["Start: " + strftime("%Y-%m-%d %H:%M:%S")]]
try:
opts, args = getopt.getopt(argv, "a:p:z:c:d:l:L:b:G:r:g:N:h", [
"analysis=", "folder=", "place=", "statsfile=", "list=",
"dotfile=", "graphlimits=", "logfile=", "biglist=", "graphfile=",
"relfile=", "relationsfile=", "graphformat=", "altmax=",
"selectednodecolour=", "selectednodecolor=", "defaultnodecolour=",
"defaultnodecolor=", "errornodecolour=", "errornodecolor=",
"mincolour=", "mincolor=", "middlecolour=", "middlecolor=",
"maxcolour=", "maxcolor=", "help", "egg", "easteregg"
])
except getopt.GetoptError:
message = "Error while getting parameters."
print message
logList.append([message])
sys.exit(2)
if len(opts) == 0:
printHelp(version)
sys.exit()
for opt, arg in opts:
if opt in ("-a", "--analysis"):
analysisName = arg
elif opt in ("-p", "--place", "--folder"):
analysisFolder = arg
elif opt in ("-z", "--statsfile"):
inStats = arg
elif opt in ("-c", "--list"): # outList from SanXoTSqueezer
listOfCategoriesFile = arg
elif opt in ("-d", "--dotfile"):
dotFile = float(arg)
elif opt in ("-l", "--graphlimits"):
graphLimits = float(arg)
elif opt in ("-L", "--logfile"):
logFile = arg
elif opt in ("-d", "--dotfile"):
outputFile = arg
elif opt in ("-G", "--graphfile"):
graphFile = arg
elif opt in ("-b", "--biglist"): # table_allPaths.xls from GOconnect
bigListFile = arg
elif opt in ("-r", "--relfile", "--relationsfile"):
relationsFile = arg
elif opt in ("-N", "--altmax"):
altMax = int(arg)
elif opt in ("-g", "--graphformat"):
graphFileFormat = arg.lower().strip()
if graphFileFormat == "jpeg": graphFileFormat = "jpg"
if graphFileFormat != "png" and \
graphFileFormat != "svg" and \
graphFileFormat != "jpg" and \
graphFileFormat != "gif":
print
print "Warning: graph format \"%s\" is not supported,\npng will be used instead." % graphFileFormat
print
graphFileFormat = "png"
elif opt in ("--selectednodecolour", "--selectednodecolor"):
selectedNodeColour = arg
elif opt in ("--defaultnodecolour", "--defaultnodecolor"):
defaultNodeColour = arg
elif opt in ("--errornodecolour", "--errornodecolor"):
errorNodeColour = arg
elif opt in ("--mincolour", "--mincolor"):
minColour = arg
elif opt in ("--middlecolour", "--middlecolor"):
middleColour = arg
elif opt in ("--maxcolour", "--maxcolor"):
maxColour = arg
elif opt in ("-h", "--help"):
printHelp(version)
sys.exit()
elif opt in ("--egg", "--easteregg"):
easterEgg()
sys.exit()
if len(inStats) > 0 and len(relationsFile) > 0:
useSubStats = True
# REGION: FILE NAMES SETUP
defaultGraphExtension = "." + graphFileFormat
if len(analysisName) == 0:
if len(inStats) > 0:
analysisName = os.path.splitext(os.path.basename(inStats))[0]
else:
analysisName = defaultAnalysisName
if len(os.path.dirname(analysisName)) > 0:
analysisNameFirstPart = os.path.dirname(analysisName)
analysisName = os.path.basename(analysisName)
if len(analysisFolder) == 0:
analysisFolder = analysisNameFirstPart
if len(inStats) > 0 and len(analysisFolder) == 0:
if len(os.path.dirname(inStats)) > 0:
analysisFolder = os.path.dirname(inStats)
# input
if len(inStats) == 0:
inStats = os.path.join(
analysisFolder,
analysisName + "_" + defaultStatsFile + defaultTableExtension)
if len(os.path.dirname(inStats)) == 0 and len(analysisFolder) > 0:
inStats = os.path.join(analysisFolder, inStats)
if len(os.path.dirname(relationsFile)) == 0 and len(analysisFolder) > 0:
relationsFile = os.path.join(analysisFolder, relationsFile)
if len(listOfCategoriesFile) == 0:
listOfCategoriesFile = os.path.join(
analysisFolder, analysisName + "_" + defaultListOfCategoriesFile +
defaultTextExtension)
if len(os.path.dirname(listOfCategoriesFile)) == 0 and len(
os.path.basename(listOfCategoriesFile)) > 0:
listOfCategoriesFile = os.path.join(analysisFolder,
listOfCategoriesFile)
if len(bigListFile) == 0:
bigListFile = defaultBigListFile
if len(os.path.dirname(bigListFile)) == 0 and len(
os.path.basename(bigListFile)) > 0:
bigListFile = os.path.join(analysisFolder, bigListFile)
# output
if len(outputFile) == 0:
outputFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultOutputFile + defaultGVFileExtension)
if len(graphFile) == 0:
graphFile = os.path.join(
analysisFolder, analysisName + "_" + defaultOutputGraphFile +
defaultGraphExtension)
if len(logFile) == 0:
logFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultLogFile + defaultTextExtension)
if len(os.path.dirname(outputFile)) == 0 and len(
os.path.basename(outputFile)) > 0:
outputFile = os.path.join(analysisFolder, outputFile)
if len(os.path.dirname(graphFile)) == 0 and len(
os.path.basename(graphFile)) > 0:
graphFile = os.path.join(analysisFolder, graphFile)
if len(os.path.dirname(logFile)) == 0 and len(
os.path.basename(logFile)) > 0:
logFile = os.path.join(analysisFolder, logFile)
logList.append([""])
logList.append(["Input stats file: " + inStats])
logList.append(["File with categories to check: " + listOfCategoriesFile])
logList.append(["Output GV table: " + outputFile])
logList.append(["Output graph table: " + graphFile])
logList.append(["Output log file: " + logFile])
logList.append([""])
# pp.pprint(logList)
# sys.exit()
# END REGION: FILE NAMES SETUP
bigList = stats.load2stringList(bigListFile, removeCommas=True)
higherElements = stats.load2stringList(listOfCategoriesFile,
removeCommas=True)
if higherElements[0] == ['id', 'Z', 'n'
] or higherElements[0] == ['id', 'n', 'Z', 'FDR']:
# this means the list comes from SanXoTSqueezer
# so the header and the extra columns have to be removed
higherElements = stats.extractColumns(higherElements[1:], 0)
else:
# only removing extra columns and converting list into text
higherElements = stats.extractColumns(higherElements, 0)
if useSubStats:
# añadir salida para log ***
subData = stats.arrangeSubData(inStats=inStats,
higherElements=higherElements,
relFile=relationsFile,
ignoreNaNsInFDR=False)
else:
subData = None
GVFileText = createGVFileTree(bigList,
higherElements,
subData=subData,
ZLimit=graphLimits,
altMax=altMax,
defaultNodeColour=defaultNodeColour,
errorNodeColour=errorNodeColour,
minColour=minColour,
middleColour=middleColour,
maxColour=maxColour)
stats.saveTextFile(outputFile, GVFileText)
createDOTTree(
outputFile,
graphFile,
imageFormat=graphFileFormat,
)
stats.saveFile(logFile, logList, "LOG FILE")
def main(argv):
version = "v0.17"
analysisName = ""
analysisFolder = ""
varianceSeed = 0.001
FDRLimit = 0.01
varianceSeedProvided = False
removeDuplicateUpper = False
tags = "!out"
outlierTag = "out"
logicOperatorsAsWords = False
dataFile = ""
relationsFile = ""
newRelFile = ""
removedRelFile = ""
defaultDataFile = "data"
defaultRelationsFile = "rels"
defaultTaggedRelFile = "tagged"
defaultNewRelFile = "cleaned"
defaultRemovedRelFile = "outliers"
defaultOutputInfo = "infoFile"
infoFile = ""
varFile = ""
defaultTableExtension = ".tsv"
defaultTextExtension = ".txt"
defaultGraphExtension = ".png"
verbose = True
oldWay = False # instead of tagging outliers, separating relations files, the old way
modeUsed = mode.onePerHigher
logList = [["SanXoTSieve " + version], ["Start: " + strftime("%Y-%m-%d %H:%M:%S")]]
try:
opts, args = getopt.getopt(argv, "a:p:v:d:r:n:L:V:f:ubDhH", ["analysis=", "folder=", "varianceseed=", "datafile=", "relfile=", "newrelfile=", "outlierrelfile=", "infofile=", "varfile=", "fdrlimit=", "one-to-one", "no-verbose", "randomise", "removeduplicateupper", "help", "advanced-help", "tags=", "outliertag=", "oldway", "word-operators"])
except getopt.GetoptError:
logList.append(["Error while getting parameters."])
stats.saveFile(infoFile, logList, "INFO FILE")
sys.exit(2)
if len(opts) == 0:
printHelp(version)
sys.exit()
for opt, arg in opts:
if opt in ("-a", "--analysis"):
analysisName = arg
if opt in ("-p", "--place", "--folder"):
analysisFolder = arg
if opt in ("-v", "--var", "--varianceseed"):
varianceSeed = float(arg)
varianceSeedProvided = True
elif opt in ("-d", "--datafile"):
dataFile = arg
elif opt in ("-r", "--relfile", "--relationsfile"):
relationsFile = arg
elif opt in ("-n", "--newrelfile"):
removedRelFile = arg
elif opt in ("-L", "--infofile"):
infoFile = arg
elif opt in ("-V", "--varfile"):
varFile = arg
elif opt in ("-u", "--one-to-one"):
modeUsed = mode.onlyOne
elif opt in ("-b", "--no-verbose"):
verbose = False
elif opt in ("--oldway"):
oldWay = True
elif opt in ("-f", "--fdrlimit"):
FDRLimit = float(arg)
elif opt in ("-D", "--removeduplicateupper"):
removeDuplicateUpper = True
elif opt in ("--tags"):
if arg.strip().lower() != "!out":
tags = "!out&(" + arg + ")"
elif opt in ("--word-operators"):
logicOperatorsAsWords = True
elif opt in ("--outliertag"):
outlierTag = "out"
elif opt in ("-h", "--help"):
printHelp(version)
sys.exit()
elif opt in ("-H", "--advanced-help"):
printHelp(version, advanced = True)
sys.exit()
# REGION: FILE NAMES SETUP
if len(analysisName) == 0:
if len(dataFile) > 0:
analysisName = os.path.splitext(os.path.basename(dataFile))[0]
else:
analysisName = defaultAnalysisName
if len(os.path.dirname(analysisName)) > 0:
analysisNameFirstPart = os.path.dirname(analysisName)
analysisName = os.path.basename(analysisName)
if len(analysisFolder) == 0:
analysisFolder = analysisNameFirstPart
if len(dataFile) > 0 and len(analysisFolder) == 0:
if len(os.path.dirname(dataFile)) > 0:
analysisFolder = os.path.dirname(dataFile)
# input
if len(dataFile) == 0:
dataFile = os.path.join(analysisFolder, analysisName + "_" + defaultDataFile + defaultTableExtension)
if len(os.path.dirname(dataFile)) == 0 and len(analysisFolder) > 0:
dataFile = os.path.join(analysisFolder, dataFile)
if len(os.path.dirname(varFile)) == 0 and len(os.path.basename(varFile)) > 0:
varFile = os.path.join(analysisFolder, varFile)
if len(varFile) > 0 and not varianceSeedProvided:
varianceSeed, varianceOk = stats.extractVarianceFromVarFile(varFile, verbose = verbose, defaultSeed = varianceSeed)
if not varianceOk:
logList.append(["Variance not found in text file."])
stats.saveFile(infoFile, logList, "INFO FILE")
sys.exit()
if len(relationsFile) == 0:
relationsFile = os.path.join(analysisFolder, analysisName + "_" + defaultRelationsFile + defaultTableExtension)
if len(os.path.dirname(relationsFile)) == 0:
relationsFile = os.path.join(analysisFolder, relationsFile)
# output
if len(newRelFile) == 0:
if oldWay: # suffix: "cleaned"
newRelFile = os.path.join(analysisFolder, analysisName + "_" + defaultNewRelFile + defaultTableExtension)
else: # suffix: "tagged"
newRelFile = os.path.join(analysisFolder, analysisName + "_" + defaultTaggedRelFile + defaultTableExtension)
if len(removedRelFile) == 0:
removedRelFile = os.path.join(analysisFolder, analysisName + "_" + defaultRemovedRelFile + defaultTableExtension)
if len(os.path.dirname(newRelFile)) == 0:
newRelFile = os.path.join(analysisFolder, newRelFile)
if len(os.path.dirname(removedRelFile)) == 0:
removedRelFile = os.path.join(analysisFolder, removedRelFile)
if len(infoFile) == 0:
infoFile = os.path.join(analysisFolder, analysisName + "_" + defaultOutputInfo + defaultTextExtension)
logList.append(["Variance seed = " + str(varianceSeed)])
logList.append(["Input data file: " + dataFile])
logList.append(["Input relations file: " + relationsFile])
if oldWay:
logList.append(["Output relations file without outliers: " + newRelFile])
logList.append(["Output relations file with outliers only: " + removedRelFile])
logList.append(["Removing duplicate higher level elements: " + str(removeDuplicateUpper)])
logList.append(["OldWay option activated: outliers are removed instead of tagged"])
else:
logList.append(["Relations file tagging outliers: " + newRelFile])
logList.append(["Tags to filter relations: " + tags])
logList.append(["Tag used for outliers: " + outlierTag])
# pp.pprint(logList)
# sys.exit()
# END REGION: FILE NAMES SETUP
relations = stats.loadRelationsFile(relationsFile)
data = stats.loadInputDataFile(dataFile)
if oldWay:
# only for backward compatibility. Note that tags are not supported
newRelations, removedRelations, logResults = \
getRelationsWithoutOutliers(data,
relations,
varianceSeed,
FDRLimit = FDRLimit,
modeUsed = modeUsed,
removeDuplicateUpper = removeDuplicateUpper)
else:
newRelations, removedRelations, logResults = \
tagRelationsWithoutOutliers(data,
relations,
varianceSeed,
FDRLimit = FDRLimit,
modeUsed = modeUsed,
removeDuplicateUpper = removeDuplicateUpper,
tags = tags,
outlierTag = outlierTag,
logicOperatorsAsWords = logicOperatorsAsWords)
if oldWay:
stats.saveFile(newRelFile, newRelations, "idsup\tidinf")
else:
stats.saveFile(newRelFile, newRelations, "idsup\tidinf\ttags")
stats.saveFile(infoFile, logList, "INFO FILE")
if oldWay:
stats.saveFile(removedRelFile, removedRelations, "idsup\tidinf")
def main(argv):
version = "v0.14"
verbose = False
analysisName = ""
defaultAnalysisName = "squeeze"
analysisFolder = ""
# parametres
minimumElements = 2
maximumElements = 1e6
maximumFDR = 0.05
minimumZ = 0.0 # take all by default
filterByFDR = True # if false, then it filters by abs(Z)
# input files
lowerStats = ""
higherStats = ""
defaultLowerStatsFile = "lower"
defaultHigherStatsFile = "upper"
defaultTableExtension = ".tsv"
defaultTextExtension = ".txt"
defaultGraphExtension = ".png"
defaultOutputFile = "outList"
defaultLogFile = "logFile"
# output files
logFile = ""
outputFile = ""
logList = [["SanXoTSqueezer " + version],
["Start: " + strftime("%Y-%m-%d %H:%M:%S")]]
try:
opts, args = getopt.getopt(argv, "a:l:L:o:p:u:n:N:f:z:h", [
"analysis=", "lowerstats=", "logfile=", "outputfile=", "place=",
"minelements=", "maxelements=", "fdr=", "sigmas=", "help"
])
except getopt.GetoptError:
logList.append(["Error while getting parameters."])
sys.exit(2)
if len(opts) == 0:
printHelp(version)
sys.exit()
for opt, arg in opts:
if opt in ("-a", "--analysis"):
analysisName = arg
if opt in ("-p", "--place", "--folder"):
analysisFolder = arg
if opt in ("-l", "--lowerstats"):
lowerStats = arg
if opt in ("-u", "--upperstats"):
higherStats = arg
elif opt in ("-L", "--logfile"):
logFile = arg
elif opt in ("-o", "--outputfile"):
outputFile = arg
elif opt in ("-n", "--minelements"):
minimumElements = int(arg)
elif opt in ("-N", "--maxelements"):
maximumElements = int(arg)
elif opt in ("-f", "--fdr"):
maximumFDR = float(arg)
elif opt in ("-z", "--sigmas"):
filterByFDR = False
minimumZ = float(arg)
elif opt in ("-h", "--help"):
printHelp(version)
sys.exit()
# REGION: FILE NAMES SETUP
if len(analysisName) == 0:
if len(lowerStats) > 0:
analysisName = os.path.splitext(os.path.basename(lowerStats))[0]
else:
analysisName = defaultAnalysisName
if len(os.path.dirname(analysisName)) > 0:
analysisNameFirstPart = os.path.dirname(analysisName)
analysisName = os.path.basename(analysisName)
if len(analysisFolder) == 0:
analysisFolder = analysisNameFirstPart
if len(lowerStats) > 0 and len(analysisFolder) == 0:
if len(os.path.dirname(lowerStats)) > 0:
analysisFolder = os.path.dirname(lowerStats)
# input
if len(lowerStats) == 0:
lowerStats = os.path.join(
analysisFolder,
analysisName + "_" + defaultLowerStatsFile + defaultTableExtension)
if len(higherStats) == 0:
higherStats = os.path.join(
analysisFolder, analysisName + "_" + defaultHigherStatsFile +
defaultTableExtension)
if len(os.path.dirname(lowerStats)) == 0 and len(analysisFolder) > 0:
lowerStats = os.path.join(analysisFolder, lowerStats)
if len(os.path.dirname(higherStats)) == 0 and len(analysisFolder) > 0:
higherStats = os.path.join(analysisFolder, higherStats)
# output
if len(outputFile) == 0:
outputFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultOutputFile + defaultTableExtension)
if len(logFile) == 0:
logFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultLogFile + defaultTextExtension)
if len(os.path.dirname(outputFile)) == 0 and len(
os.path.basename(outputFile)) > 0:
outputFile = os.path.join(analysisFolder, outputFile)
if len(os.path.dirname(logFile)) == 0 and len(
os.path.basename(logFile)) > 0:
logFile = os.path.join(analysisFolder, logFile)
logList.append([""])
logList.append(["Lower input stats file: " + lowerStats])
logList.append(["Higher input stats file: " + higherStats])
logList.append(["Output list: " + outputFile])
logList.append(["Output log file: " + logFile])
logList.append(
["Minimum elements in higher category: " + str(minimumElements)])
logList.append(
["Maximum elements in higher category: " + str(maximumElements)])
logList.append(["Minimum z: " + str(minimumZ)])
logList.append([""])
# pp.pprint(logList)
# sys.exit()
# END REGION: FILE NAMES SETUP
try:
lowerData = stats.loadStatsDataFile(lowerStats)
logList.append(["Lower data files correctly loaded."])
except getopt.GetoptError:
logList.append(["Error while getting lower data files."])
stats.saveFile(logFile, logList, "LOG FILE")
sys.exit(2)
try:
higherData = stats.loadStatsDataFile(higherStats)
logList.append(["Higher data files correctly loaded."])
except getopt.GetoptError:
logList.append(["Error while getting higher data files."])
stats.saveFile(logFile, logList, "LOG FILE")
sys.exit(2)
try:
filteredList = filterNFDRorZ(lowerData,
higherData,
minN=minimumElements,
maxN=maximumElements,
minZ=minimumZ,
maxFDR=maximumFDR,
useFDR=filterByFDR)
filteredList = stats.sortByIndex(filteredList, 1)
logList.append(["Data correctly filtered."])
except getopt.GetoptError:
logList.append(["Error while getting data filtered by N and Z."])
stats.saveFile(logFile, logList, "LOG FILE")
sys.exit(2)
try:
stats.saveFile(outputFile, filteredList, "id\tn\tZ\tFDR\tX")
logList.append(["Output data correctly saved."])
except getopt.GetoptError:
logList.append(["Error while saving output data."])
stats.saveFile(logFile, logList, "LOG FILE")
sys.exit(2)
stats.saveFile(logFile, logList, "LOG FILE")
def main(argv):
version = "v0.23"
verbose = False
showGraph = True
graphLimits = 6.0
showLegend = True
graphDPI = 100 # default of Matplotlib's savefig method
graphLineWidth = 1.0
graphFontSize = 8
analysisName = ""
defaultAnalysisName = "sanxot"
analysisFolder = ""
# input files
inStats = ""
defaultStatsFile = "stats"
defaultRelationsFile = "rels"
defaultTableExtension = ".tsv"
defaultTextExtension = ".txt"
defaultGraphExtension = ".png"
relationsFile = ""
upperLevelToGraphFile = ""
# output files
defaultUpperLevelToGraphFile = "ulst"
defaultOutputGraph = "outGraph"
defaultOutputFile = "outSigmoids"
defaultExtraTableFile = "outExtra"
defaultLogFile = "logFile"
logFile = ""
graphFile = ""
outputFile = ""
extraTableFile = ""
graphTitle = "Z plot"
labelFontSize = 12
minimalGraphTicks = False
xLabel = "Zij"
yLabel = "Rank/N"
logList = [["SanXoTGauss " + version],
["Start: " + strftime("%Y-%m-%d %H:%M:%S")]]
try:
opts, args = getopt.getopt(
argv, "a:p:z:r:c:L:G:o:l:d:W:s:x:t:Z:hgkT", [
"analysis=", "folder=", "statsfile=", "relfile=", "list=",
"logfile=", "graphfile=", "outputfile=", "graphlimits=",
"graphfontsize=", "graphdpi=", "graphlinewidth=",
"extratable=", "graphtitle=", "labelfontsize=", "help",
"no-graph", "no-legend", "minimalgraphticks", "xlabel=",
"ylabel="
])
except getopt.GetoptError:
logList.append(["Error while getting parameters."])
sys.exit(2)
if len(opts) == 0:
printHelp(version)
sys.exit()
for opt, arg in opts:
if opt in ("-a", "--analysis"):
analysisName = arg
if opt in ("-p", "--place", "--folder"):
analysisFolder = arg
if opt in ("-z", "--statsfile"):
inStats = arg
elif opt in ("-r", "--relfile", "--relationsfile"):
relationsFile = arg
elif opt in ("-c", "--list"):
upperLevelToGraphFile = arg
elif opt in ("-L", "--logfile"):
logFile = arg
elif opt in ("-G", "--graphfile"):
graphFile = arg
elif opt in ("-g", "--no-graph"):
showGraph = False
elif opt in ("-k", "--no-legend"):
showLegend = False
elif opt in ("-o", "--outputfile"):
outputFile = arg
elif opt in ("-x", "--extratable"):
extraTableFile = arg
elif opt in ("-s", "--graphfontsize"):
graphFontSize = int(arg)
elif opt in ("-d", "--graphdpi"):
graphDPI = float(arg)
elif opt in ("-W", "--graphlinewidth"):
graphLineWidth = float(arg)
elif opt in ("-t", "--graphtitle"):
graphTitle = arg
elif opt in ("-Z", "--labelfontsize"):
labelFontSize = float(arg)
elif opt in ("-l", "--graphlimits"):
graphLimits = float(arg)
elif opt in ("-T", "--minimalgraphticks"):
minimalGraphTicks = True
elif opt in ("--xlabel"):
xLabel = arg
elif opt in ("--ylabel"):
yLabel = arg
elif opt in ("-h", "--help"):
printHelp(version)
sys.exit()
# REGION: FILE NAMES SETUP
if len(analysisName) == 0:
if len(inStats) > 0:
analysisName = os.path.splitext(os.path.basename(inStats))[0]
else:
analysisName = defaultAnalysisName
if len(os.path.dirname(analysisName)) > 0:
analysisNameFirstPart = os.path.dirname(analysisName)
analysisName = os.path.basename(analysisName)
if len(analysisFolder) == 0:
analysisFolder = analysisNameFirstPart
if len(inStats) > 0 and len(analysisFolder) == 0:
if len(os.path.dirname(inStats)) > 0:
analysisFolder = os.path.dirname(inStats)
# input
if len(inStats) == 0:
inStats = os.path.join(
analysisFolder,
analysisName + "_" + defaultStatsFile + defaultTableExtension)
if len(os.path.dirname(inStats)) == 0 and len(analysisFolder) > 0:
inStats = os.path.join(analysisFolder, inStats)
if len(relationsFile) == 0:
relationsFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultRelationsFile + defaultTableExtension)
if len(upperLevelToGraphFile) == 0:
upperLevelToGraphFile = os.path.join(
analysisFolder, analysisName + "_" + defaultUpperLevelToGraphFile +
defaultTextExtension)
if len(os.path.dirname(relationsFile)) == 0 and len(
os.path.basename(relationsFile)) > 0:
relationsFile = os.path.join(analysisFolder, relationsFile)
if len(os.path.dirname(upperLevelToGraphFile)) == 0 and len(
os.path.basename(upperLevelToGraphFile)) > 0:
upperLevelToGraphFile = os.path.join(analysisFolder,
upperLevelToGraphFile)
# output
if len(outputFile) == 0:
outputFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultOutputFile + defaultTableExtension)
if len(extraTableFile) == 0:
extraTableFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultExtraTableFile + defaultTableExtension)
if len(logFile) == 0:
logFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultLogFile + defaultTextExtension)
if len(graphFile) == 0:
graphFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultOutputGraph + defaultGraphExtension)
if len(os.path.dirname(outputFile)) == 0 and len(
os.path.basename(outputFile)) > 0:
outputFile = os.path.join(analysisFolder, outputFile)
if len(os.path.dirname(extraTableFile)) == 0 and len(
os.path.basename(extraTableFile)) > 0:
extraTableFile = os.path.join(analysisFolder, extraTableFile)
if len(os.path.dirname(logFile)) == 0 and len(
os.path.basename(logFile)) > 0:
logFile = os.path.join(analysisFolder, logFile)
if len(os.path.dirname(graphFile)) == 0 and len(
os.path.basename(graphFile)) > 0:
graphFile = os.path.join(analysisFolder, graphFile)
logList.append([""])
logList.append(["Input stats file: " + inStats])
logList.append(["Relations file: " + relationsFile])
logList.append(["File with sigmoids to depict: " + upperLevelToGraphFile])
logList.append(["Output sigmoids table: " + outputFile])
logList.append(["Output extra table: " + extraTableFile])
logList.append(["Output log file: " + logFile])
logList.append(["Output graph file: " + graphFile])
logList.append([""])
# pp.pprint(logList)
# sys.exit()
# END REGION: FILE NAMES SETUP
try:
data, logListExtraInfo = stats.arrangeSubData(
inStats=inStats,
uFile=upperLevelToGraphFile,
relFile=relationsFile,
ignoreNaNsInFDR=True)
logList.append(logListExtraInfo)
logList.append(["Data files correctly loaded."])
except getopt.GetoptError:
logList.append(["Error while getting data files."])
stats.saveFile(logFile, logList, "LOG FILE")
sys.exit(2)
try:
bigTable, bigTableHeader, extraTable, extraHeader = stats.createBigTable(
data)
logList.append(["Sigmoid table correctly generated."])
except getopt.GetoptError:
logList.append(["Error while generating sigmoid table."])
stats.saveFile(logFile, logList, "LOG FILE")
sys.exit(2)
try:
stats.saveFile(outputFile, bigTable, bigTableHeader)
logList.append(["Sigmoid table correctly saved."])
except getopt.GetoptError:
logList.append(["Error while saving sigmoid table."])
stats.saveFile(logFile, logList, "LOG FILE")
sys.exit(2)
try:
stats.saveFile(extraTableFile, extraTable, extraHeader)
logList.append(["Extra table correctly saved."])
except getopt.GetoptError:
logList.append(["Error while saving extra table."])
stats.saveFile(logFile, logList, "LOG FILE")
sys.exit(2)
try:
stats.graphZij(data,
graphLimits=graphLimits,
graphTitle=graphTitle,
graphFile=graphFile,
showGraph=showGraph,
manySigmoids=True,
showLegend=showLegend,
dpi=graphDPI,
graphFontSize=graphFontSize,
lineWidth=graphLineWidth,
labelFontSize=labelFontSize,
minimalGraphTicks=minimalGraphTicks,
xLabel=xLabel,
yLabel=yLabel)
logList.append(["Graph correctly saved."])
except getopt.GetoptError:
logList.append(["Error while saving graph."])
stats.saveFile(logFile, logList, "LOG FILE")
sys.exit(2)
stats.saveFile(logFile, logList, "LOG FILE")
def main(options, programName, programVersion):
## REGION: DEFAULT VALUES AND VARIABLE ACQUISITION
# *-*-* add any default values here, such as default names of files
# basic default info
inputFile = ""
MSFFileCol = ""
RAWFileCol = ""
scanNumberCol = ""
chargeCol = ""
pepSequenceCol = ""
XCorrCol = ""
initialRow = 1
verbose = False
QuiXMLResults = False # otherwise, QuiXML will be considered
changeOriginalMSFFile = False # False = copy MSF to MSF_zeroed, True = change original file
logFile = ""
analysisName = ""
analysisFolder = ""
defaultAnalysisName = programName.lower()
# default extensions
defaultTableExtension = ".xls"
defaultTextExtension = ".txt"
# default file names
defaultLogFile = "logFile"
leadingFile = "" # *-*-* change this by the data file or any important file defining the operation
# basic log file
logList = [[programName + " " + programVersion], ["Start: " + strftime("%Y-%m-%d %H:%M:%S")]]
# parsing arguments from commandline
# *-*-* add any arguments used
options.add_argument("-a", "--analysis", type = str, default = "", required = True, help = "Use a prefix for the output files.")
options.add_argument("-p", "--place", type = str, default = "", required = True, help = "To use a different common folder for the output files. If this is not provided, the the folder used will be the same as the FASTA file folder.")
options.add_argument("-L", "--logfile", type = str, default = "", required = False, help = "To use a non-default name for the log file.")
# -d[nombre archivo donde están los xcorr = 0]
# -M[columna con nombre del msf]
# -r[rawfilecol]
# -s[scannumbercol]
# -q[chargecol]
# -P[pepsequencecol]
# -x[xcorrcol]
# -R[initialrow]
options.add_argument("-d", "--inputfile", type = str, default = "", required = True, help = "Name of the text file containing the list of PSMs to keep in the MSF.")
options.add_argument("-M", "--msffile", type = str, default = "", required = True, help = "Name of the MSF file having the PSMs to modify.")
options.add_argument("-r", "--rawfilecol", type = str, default = "", required = False, help = "Header of the column contaning the name of the RAW files. Default is \"RAWFileName\".")
options.add_argument("-s", "--scannumbercol", type = str, default = "", required = False, help = "Header of the column containing the scan numbers. Default is \"FirstScan\".")
options.add_argument("-q", "--chargecol", type = str, default = "", required = False, help = "Header of the column containing the charge. Default is \"Charge\".")
options.add_argument("-S", "--pepsequencecol", type = str, default = "", required = False, help = "Header of the column containing the identified peptide sequences. Default is \"Sequence\"")
options.add_argument("-x", "--xcorrcol", type = str, default = "", required = False, help = "Header of the column containing the XCorr. Default is \"XC1D\".")
options.add_argument("-R", "--initialrow", type = str, default = "1", required = False, help = "The position of the row containing the headers. Default is 1.")
options.add_argument("-v", "--verbose", action='store_true', help = "Show extra info while operating.")
options.add_argument("-Q", "--quixml", action='store_true', help = "Use column headers for QuiXML results tab separated table file (otherwise, pRatio results file headers will be used by default).")
options.add_argument("-O", "--changeoriginalmsf", action='store_true', help = "Do not copy the MSF file to be modified, just remove bad PSMs in the original file.")
# *-*-* add easter egg if wanted
arguments = options.parse_args()
# copying parsed arguments
# copy any arguments used
verbose = arguments.verbose
QuiXMLResults = arguments.quixml
changeOriginalMSFFile = arguments.changeoriginalmsf
if QuiXMLResults:
RAWFileCol = "RAWFileName"
scanNumberCol = "FirstScan"
chargeCol = "Charge"
pepSequenceCol = "Sequence"
XCorrCol = "XC1D"
initialRow = 24
else: # pRatio results are default
RAWFileCol = "RAWFile"
scanNumberCol = "FirstScan"
chargeCol = "Charge"
pepSequenceCol = "Sequence"
XCorrCol = "Xcorr1Search"
initialRow = 1
if len(arguments.analysis) > 0: analysisName = arguments.analysis
if len(arguments.place) > 0: analysisFolder = arguments.place
if len(arguments.logfile) > 0: logfile = arguments.logFile
if len(arguments.inputfile) > 0: inputFile = arguments.inputfile
if len(arguments.msffile) > 0: MSFFile = arguments.msffile
if len(arguments.rawfilecol) > 0: RAWFileCol = arguments.rawfilecol
if len(arguments.scannumbercol) > 0: scanNumberCol = arguments.scannumbercol
if len(arguments.chargecol) > 0: chargeCol = arguments.chargecol
if len(arguments.pepsequencecol) > 0: pepSequenceCol = arguments.pepsequencecol
if len(arguments.xcorrcol) > 0: XCorrCol = arguments.xcorrcol
if len(arguments.initialrow) > 0: initialRow = int(arguments.initialrow)
RAWFileCol = "[" + RAWFileCol + "]"
scanNumberCol = "[" + scanNumberCol + "]"
chargeCol = "[" + chargeCol + "]"
pepSequenceCol = "[" + pepSequenceCol + "]"
XCorrCol = "[" + XCorrCol + "]"
## END REGION: DEFAULT VALUES AND VARIABLE ACQUISITION
## **********************************************************
## REGION: FILE NAMES SETUP
# replace leadingfile by the real leading file
if len(analysisName) == 0:
if len(leadingFile) > 0:
analysisName = os.path.splitext(os.path.basename(leadingFile))[0]
else:
analysisName = defaultAnalysisName
if len(os.path.dirname(analysisName)) > 0:
analysisNameFirstPart = os.path.dirname(analysisName)
analysisName = os.path.basename(analysisName)
if len(analysisFolder) == 0:
analysisFolder = analysisNameFirstPart
# input
# *-*-* add input file setup
if len(os.path.dirname(inputFile)) == 0:
inputFile = os.path.join(analysisFolder, inputFile)
if len(os.path.dirname(MSFFile)) == 0:
MSFFile = os.path.join(analysisFolder, MSFFile)
if os.path.splitext(MSFFile)[1] != ".msf":
print
print "Warning: your MSF file does not seem to be an MSF file."
if changeOriginalMSFFile:
newMSFFile = MSFFile
else:
newMSFFile = os.path.splitext(MSFFile)[0] + "_zeroed" + os.path.splitext(MSFFile)[1]
# output
# *-*-* add output file setup
if len(logFile) == 0:
logFile = os.path.join(analysisFolder, analysisName + "_" + defaultLogFile + defaultTextExtension)
if len(os.path.dirname(logFile)) == 0 and len(os.path.basename(logFile)) > 0:
logFile = os.path.join(analysisFolder, logFile)
# *-*-* add to the log the input and output filenames
logList.append([""])
logList.append(["Output log file: " + logFile])
logList.append([""])
## END REGION: FILE NAMES SETUP
## **********************************************************
## REGION: PROGRAM BASIC STRUCTURE
# *-*-* add basic structure
print
if not changeOriginalMSFFile:
message = "Creating new file: %s" % newMSFFile
logList.append([message])
print message
shutil.copyfile(MSFFile, newMSFFile)
message = "Loading PSMs to keep from: %s" % inputFile
logList.append([message])
print message
myList = getDataFromTXT(inputFile,
iField = RAWFileCol,
jField = scanNumberCol,
kField = chargeCol,
lField = pepSequenceCol,
initialRow = initialRow,
filterString = XCorrCol + ">0",
removeDuplicates = True,
removeCommas = True)
if len(myList) == 0:
message = "\nWarning!! No PSMs found in the text file provided,\nDeleting all XCorrs.\n"
else:
message = "PSMs found in text file: %i" % len(myList)
logList.append([message])
print message
compareListIdentified = []
for element in myList:
myRAWFilePath = element[0]
myRAWFile = os.path.basename(myRAWFilePath)
myScanNumber = element[1]
myCharge = element[2]
myPepSequence = element[3] # currently unused
compareListIdentified.append([myRAWFile, int(myScanNumber), int(myCharge)])
connexion = sqlite3.connect(newMSFFile)
c = connexion.cursor()
existingScanQuery = """select
p.peptideid,
fi.filename,
sh.firstscan,
sh.lastscan,
sh.charge,
p.sequence,
ps.scorevalue
from
peptides p,
peptideScores ps,
spectrumHeaders sh,
massPeaks mp,
fileInfos fi,
processingNodeScores scoreNames
where
p.peptideid = ps.peptideid and
sh.spectrumid = p.spectrumid and
(fi.fileid = mp.fileid or mp.fileid = -1) and
mp.masspeakid = sh.masspeakid and
scoreNames.scoreid = ps.scoreid and
scoreNames.ScoreName = 'Xcorr'
order by fi.filename desc,
sh.firstscan asc,
sh.lastscan asc,
sh.charge asc,
ps.scorevalue desc;"""
message = "Searching all PSMs in database..."
logList.append([message])
print message
wholeMSFList = []
for psm in c.execute(existingScanQuery):
wholeMSFList.append(psm)
checked = 0
changed = 0
alreadyZero = 0
message = "Zeroing...!"
logList.append([message])
message = "Original MSF contains %i PSMs." % len(wholeMSFList)
logList.append([message])
logList.append([""])
logList.append(["Zeroed\tRAWFileName\tScanNumber\tCharge\tSequence (without PTMs)\tOriginal XCorr"])
print message
for psm in wholeMSFList:
checked += 1
pepId = int(psm[0])
rawFilePath = str(psm[1])
rawFile = os.path.basename(rawFilePath)
firstScan = int(psm[2])
lastScan = int(psm[3])
charge = int(psm[4])
sequence = str(psm[5])
XCorr = float(psm[6])
# now check whether this is in the given list. If not, then make XCorr = 0
# compareListIdentified.append([myRAWFile, myScanNumber, myCharge, myPepSequence])
compareListInMSF = [rawFile, firstScan, charge]
msfScanPresentInList = (compareListInMSF in compareListIdentified)
if XCorr == 0:
alreadyZero += 1
if not msfScanPresentInList and XCorr != 0:
changed += 1
zeroSettingQuery = """update
peptideScores
set
scoreValue = 0
where
peptideID in (
select
p.peptideID
from
fileinfos fi,
massPeaks mp,
spectrumHeaders sh,
peptides p
where
(fi.fileid = mp.fileid or mp.fileid = -1) and
mp.masspeakid = sh.masspeakid and
sh.spectrumid = p.spectrumid and
sh.firstScan = %i and
sh.charge = %i and
fi.fileName like "%%%s"
) and
scoreID = (
select
scoreId
from
processingNodeScores
where
scoreName = "XCorr"
);""" % (firstScan, charge, rawFile)
# pdb.set_trace()
c.execute(zeroSettingQuery)
message = """%i\t%s\t%i\t%i\t%s\t%f""" % (checked, rawFile, firstScan, charge, sequence, XCorr)
logList.append([message])
if verbose:
message = """Zeroed (%i/%i):\nraw = "%s"\nscan = %i\ncharge = %i\nsequence = %s\nXCorr = %f\n""" % (checked, len(wholeMSFList), rawFile, firstScan, charge, sequence, XCorr)
print message
print
message = "PTMs found: %i,\nPTMs zeroed: %i,\nDifference: %i,\nAlready zero: %i" % (checked, changed, checked - changed, alreadyZero)
print message
logList.append([""])
logList.append([message])
print
print "Saving changes..."
connexion.commit()
print
print "Closing connexion..."
connexion.close()
## END REGION: PROGRAM BASIC STRUCTURE
## **********************************************************
## REGION: SAVING FILES
# *-*-* add any files to be saved here
try:
# operations here
logList.append(["Most probably, everything went fine."])
except getopt.GetoptError:
logList.append(["Error."])
stats.saveFile(logFile, logList, "LOG FILE")
sys.exit(2)
stats.saveFile(logFile, logList, "LOG FILE")
print "Done!"
def main(argv):
version = "v0.05"
analysisName = ""
analysisFolder = ""
logFile = ""
# in data
prefix = ""
extraPrefix = ""
medianTag = "med"
# default filenames
defaultInfoFileSuffix = "_infoFile.txt"
defaultLogFile = "logFile"
defaultAnalysisName = "medianSelection"
# default extensions
defaultTableExtension = ".xls"
defaultTextExtension = ".txt"
verbose = True
logList = [["Anselmo " + version], ["Start: " + strftime("%Y-%m-%d %H:%M:%S")]]
try:
opts, args = getopt.getopt(argv, "a:p:f:g:m:L:hH", ["analysis=", "folder=", "prefix=", "extraprefix=", "mediantag=", "logfile=", "help", "egg", "easteregg"])
except getopt.GetoptError:
logList.append(["Error while getting parameters."])
stats.saveFile(infoFile, logList, "INFO FILE")
sys.exit(2)
if len(opts) == 0:
printHelp(version, True)
sys.exit()
for opt, arg in opts:
if opt in ("-a", "--analysis"):
analysisName = arg
elif opt in ("-p", "--place", "--folder"):
analysisFolder = arg
elif opt in ("-f", "--prefix"):
prefix = arg
elif opt in ("-g", "--extraprefix"):
extraPrefix = arg
elif opt in ("-L", "--logfile"):
logFile = arg
elif opt in ("-m", "--mediantag"):
medianTag = arg
elif opt in ("-h", "--help"):
printHelp(version)
sys.exit()
elif opt in ("-H", "--advanced-help"):
printHelp(version, advanced = True)
sys.exit()
elif opt in ("--egg", "--easteregg"):
easterEgg()
sys.exit()
# REGION: FILE NAMES SETUP
if len(analysisName) == 0:
analysisName = defaultAnalysisName
if len(os.path.dirname(analysisName)) > 0:
analysisNameFirstPart = os.path.dirname(analysisName)
analysisName = os.path.basename(analysisName)
if len(analysisFolder) == 0:
analysisFolder = analysisNameFirstPart
# next "if" disables extra copy when extraPrefix is same as prefix
if len(extraPrefix) > 0 and extraPrefix == prefix:
extraPrefix = ""
# input
# output
if len(logFile) == 0:
logFile = os.path.join(analysisFolder, analysisName + "_" + defaultLogFile + defaultTextExtension)
##logList.append(["Median variance = " + "poner***"])
# END REGION: FILE NAMES SETUP
# get infoFile list
infoFileList = glob.glob(os.path.join(analysisFolder, prefix + "*" + defaultInfoFileSuffix))
logList.append([])
logList.append(["Folder = " + analysisFolder])
logList.append([])
logList.append(["Info files with prefix \"%s\"" % prefix])
varList = []
for varFile in infoFileList:
variance, varianceOk = stats.extractVarianceFromVarFile(varFile, verbose = False)
if varianceOk:
varList.append([varFile, variance])
# get info file with median variance
varList = stats.sortByIndex(varList, 1)
medianVariance = stats.medianByIndex(varList, 1)
medianIndex = getMedianIndex(varList = varList, variance = medianVariance)
for element in varList:
if element[0] == varList[medianIndex][0]:
logList.append(["%s, variance = %f [taken]" % (os.path.basename(element[0]), element[1])])
else:
logList.append(["%s, variance = %f" % (os.path.basename(element[0]), element[1])])
# get prefix of median experiment
medianInfoFile = os.path.basename(varList[medianIndex][0])
randTag = medianInfoFile[len(prefix):len(medianInfoFile) - len(defaultInfoFileSuffix)]
medianPrefix = prefix + randTag
extraMedianPrefix = ""
if len(extraPrefix) > 0: extraMedianPrefix = extraPrefix + randTag
# get file list with specific prefix
medianExperimentFileList = glob.glob(os.path.join(analysisFolder, medianPrefix + "*.*"))
extraPrefixFileList = []
if len(extraMedianPrefix) > 0:
extraPrefixFileList = glob.glob(os.path.join(analysisFolder, extraMedianPrefix + "*.*"))
# copy files including median tag
extraLogList = copyFilesWithPrefix(fileList = medianExperimentFileList,
folder = analysisFolder,
prefix = prefix,
message = "Renamed files:",
tag = medianTag)
logList.extend(extraLogList)
if len(extraPrefixFileList) > 0:
extraLogList = copyFilesWithPrefix(fileList = extraPrefixFileList,
folder = analysisFolder,
prefix = extraPrefix,
message = "Renamed extra files:",
tag = medianTag)
logList.extend(extraLogList)
# save logFile
stats.saveFile(logFile, logList, "INFO FILE")
def main(options, programName, programVersion):
## REGION: DEFAULT VALUES AND VARIABLE ACQUISITION
# basic default info
logFile = ""
analysisName = ""
analysisFolder = ""
defaultAnalysisName = programName.lower()
relFile = ""
DBFile = ""
FASTAFile = ""
previousFile = ""
accNumCol = 1
catCol = 2
catPrefix = ""
header = "idsup\tidinf"
previousList = []
# default extensions
defaultTableExtension = ".tsv"
defaultTextExtension = ".txt"
# default file names
defaultLogFile = "logFile"
defaultRelFile = "rels"
# basic log file
logList = [[programName + " " + programVersion], ["Start: " + strftime("%Y-%m-%d %H:%M:%S")]]
# parsing arguments from commandline
options.add_argument("-a", "--analysis", type = str, default = "", required = True, help = "Use a prefix for the output files.")
options.add_argument("-p", "--place", type = str, default = "", required = True, help = "To use a different common folder for the output files. If this is not provided, the the folder used will be the same as the FASTA file folder.")
options.add_argument("-L", "--logfile", type = str, default = "", required = False, help = "To use a non-default name for the log file.")
options.add_argument("-d", "--dbfile", type = str, default = "", required = True, help = "The input file containing accession numbers and categories.")
options.add_argument("-x", "--previousfile", type = str, default = "", required = False, help = "An optional relation file to which concatenate resulting relations (if omitted, a new file will be produced).")
options.add_argument("-q", "--accnumcol", type = str, default = "1", required = False, help = "Column where accession numbers of genes/proteins are. First column is 1. Default is 1.")
options.add_argument("-c", "--categorycol", type = str, default = "2", required = False, help = "Column where categories are. First column is 1. Default is 2.")
options.add_argument("-f", "--prefix", type = str, default = "", required = False, help = "Prefix to add to all categories found in this parsing (such as \"GO-full_\", \"Panther_\", or \"KEGG=2017-01-10_\".")
options.add_argument("--fasta", type = str, default = "", required = False, help = "FASTA file contaning the identifiers we want to replace by FASTA headers in the final file. Note that identifiers not appearing in this FASTA file will be removed from the final list.")
# add string with category separator
# add string with accNum separator
# *-*-* add easter egg if wanted
arguments = options.parse_args()
# copying parsed arguments
# copy any arguments used
if len(arguments.analysis) > 0: analysisName = arguments.analysis
if len(arguments.place) > 0: analysisFolder = arguments.place
if len(arguments.logfile) > 0: logFile = arguments.logfile
if len(arguments.dbfile) > 0: DBFile = arguments.dbfile
if len(arguments.fasta) > 0: FASTAFile = arguments.fasta
if len(arguments.previousfile) > 0: previousFile = arguments.previousfile
if len(arguments.accnumcol) > 0: accNumCol = int(arguments.accnumcol)
if len(arguments.categorycol) > 0: catCol = int(arguments.categorycol)
if len(arguments.prefix) > 0: catPrefix = arguments.prefix
## END REGION: DEFAULT VALUES AND VARIABLE ACQUISITION
## **********************************************************
## REGION: FILE NAMES SETUP
if len(analysisName) == 0:
if len(DBFile) > 0:
analysisName = os.path.splitext(os.path.basename(DBFile))[0]
else:
analysisName = defaultAnalysisName
if len(os.path.dirname(analysisName)) > 0:
analysisNameFirstPart = os.path.dirname(analysisName)
analysisName = os.path.basename(analysisName)
if len(analysisFolder) == 0:
analysisFolder = analysisNameFirstPart
# input
if len(os.path.dirname(DBFile)) == 0:
DBFile = os.path.join(analysisFolder, DBFile)
if len(previousFile) > 0:
if len(os.path.dirname(previousFile)) == 0:
previousFile = os.path.join(analysisFolder, previousFile)
if len(FASTAFile) > 0:
if len(os.path.dirname(FASTAFile)) == 0:
FASTAFile = os.path.join(analysisFolder, FASTAFile)
# output
if len(logFile) == 0:
logFile = os.path.join(analysisFolder, analysisName + "_" + defaultLogFile + defaultTextExtension)
if len(os.path.dirname(logFile)) == 0 and len(os.path.basename(logFile)) > 0:
logFile = os.path.join(analysisFolder, logFile)
if len(relFile) == 0:
relFile = os.path.join(analysisFolder, analysisName + "_" + defaultRelFile + defaultTableExtension)
if len(os.path.dirname(relFile)) == 0 and len(os.path.basename(relFile)) > 0:
relFile = os.path.join(analysisFolder, relFile)
logList.append([""])
logList.append(["Input table with categories and proteins: " + DBFile])
if len(previousFile) > 0:
logList.append(["Previous file to which new qc relations are added: " + previousFile])
if len(FASTAFile) > 0:
logList.append(["FASTA file to replace identifiers for FASTA headers: " + FASTAFile])
logList.append(["Category column: %i, protein column: %i" % (catCol, accNumCol)])
logList.append(["Prefix added to categories: " + catPrefix])
logList.append(["Output relations file: " + relFile])
logList.append(["Output log file: " + logFile])
logList.append([""])
## END REGION: FILE NAMES SETUP
## **********************************************************
## REGION: PROGRAM BASIC STRUCTURE
if len(previousFile) > 0: #otherwise, previousList = []
previousList = stats.load2stringList(previousFile, removeCommas = True)
header = ""
AccNum2FASTAHeader = getFASTAHeaders(FASTAFile)
gc.collect()
DBList = stats.load2stringList(DBFile, removeCommas = True)
newRelations = getRelations(bigTable = DBList,
qCol = accNumCol,
cCol = catCol,
cPrefix = catPrefix,
FASTAHeaders = AccNum2FASTAHeader)
newRelationsSorted = stats.sortByIndex(newRelations, 0)
relationList = previousList + newRelationsSorted
gc.collect()
## END REGION: PROGRAM BASIC STRUCTURE
## **********************************************************
## REGION: SAVING FILES
try:
stats.saveFile(relFile, relationList, header)
logList.append(["Everything went fine."])
stats.saveFile(logFile, logList, "LOG FILE")
except getopt.GetoptError:
logList.append(["Error."])
stats.saveFile(logFile, logList, "LOG FILE")
sys.exit(2)
def main(argv):
version = "v0.17"
analysisName = ""
analysisFolder = ""
varianceSeed = 0.001
FDRLimit = 0.01
varianceSeedProvided = False
removeDuplicateUpper = False
tags = "!out"
outlierTag = "out"
logicOperatorsAsWords = False
dataFile = ""
relationsFile = ""
newRelFile = ""
removedRelFile = ""
defaultDataFile = "data"
defaultRelationsFile = "rels"
defaultTaggedRelFile = "tagged"
defaultNewRelFile = "cleaned"
defaultRemovedRelFile = "outliers"
defaultOutputInfo = "infoFile"
infoFile = ""
varFile = ""
defaultTableExtension = ".tsv"
defaultTextExtension = ".txt"
defaultGraphExtension = ".png"
verbose = True
oldWay = False # instead of tagging outliers, separating relations files, the old way
modeUsed = mode.onePerHigher
logList = [["SanXoTSieve " + version],
["Start: " + strftime("%Y-%m-%d %H:%M:%S")]]
try:
opts, args = getopt.getopt(argv, "a:p:v:d:r:n:L:V:f:ubDhH", [
"analysis=", "folder=", "varianceseed=", "datafile=", "relfile=",
"newrelfile=", "outlierrelfile=", "infofile=", "varfile=",
"fdrlimit=", "one-to-one", "no-verbose", "randomise",
"removeduplicateupper", "help", "advanced-help", "tags=",
"outliertag=", "oldway", "word-operators"
])
except getopt.GetoptError:
logList.append(["Error while getting parameters."])
stats.saveFile(infoFile, logList, "INFO FILE")
sys.exit(2)
if len(opts) == 0:
printHelp(version)
sys.exit()
for opt, arg in opts:
if opt in ("-a", "--analysis"):
analysisName = arg
if opt in ("-p", "--place", "--folder"):
analysisFolder = arg
if opt in ("-v", "--var", "--varianceseed"):
varianceSeed = float(arg)
varianceSeedProvided = True
elif opt in ("-d", "--datafile"):
dataFile = arg
elif opt in ("-r", "--relfile", "--relationsfile"):
relationsFile = arg
elif opt in ("-n", "--newrelfile"):
removedRelFile = arg
elif opt in ("-L", "--infofile"):
infoFile = arg
elif opt in ("-V", "--varfile"):
varFile = arg
elif opt in ("-u", "--one-to-one"):
modeUsed = mode.onlyOne
elif opt in ("-b", "--no-verbose"):
verbose = False
elif opt in ("--oldway"):
oldWay = True
elif opt in ("-f", "--fdrlimit"):
FDRLimit = float(arg)
elif opt in ("-D", "--removeduplicateupper"):
removeDuplicateUpper = True
elif opt in ("--tags"):
if arg.strip().lower() != "!out":
tags = "!out&(" + arg + ")"
elif opt in ("--word-operators"):
logicOperatorsAsWords = True
elif opt in ("--outliertag"):
outlierTag = "out"
elif opt in ("-h", "--help"):
printHelp(version)
sys.exit()
elif opt in ("-H", "--advanced-help"):
printHelp(version, advanced=True)
sys.exit()
# REGION: FILE NAMES SETUP
if len(analysisName) == 0:
if len(dataFile) > 0:
analysisName = os.path.splitext(os.path.basename(dataFile))[0]
else:
analysisName = defaultAnalysisName
if len(os.path.dirname(analysisName)) > 0:
analysisNameFirstPart = os.path.dirname(analysisName)
analysisName = os.path.basename(analysisName)
if len(analysisFolder) == 0:
analysisFolder = analysisNameFirstPart
if len(dataFile) > 0 and len(analysisFolder) == 0:
if len(os.path.dirname(dataFile)) > 0:
analysisFolder = os.path.dirname(dataFile)
# input
if len(dataFile) == 0:
dataFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultDataFile + defaultTableExtension)
if len(os.path.dirname(dataFile)) == 0 and len(analysisFolder) > 0:
dataFile = os.path.join(analysisFolder, dataFile)
if len(os.path.dirname(varFile)) == 0 and len(
os.path.basename(varFile)) > 0:
varFile = os.path.join(analysisFolder, varFile)
if len(varFile) > 0 and not varianceSeedProvided:
varianceSeed, varianceOk = stats.extractVarianceFromVarFile(
varFile, verbose=verbose, defaultSeed=varianceSeed)
if not varianceOk:
logList.append(["Variance not found in text file."])
stats.saveFile(infoFile, logList, "INFO FILE")
sys.exit()
if len(relationsFile) == 0:
relationsFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultRelationsFile + defaultTableExtension)
if len(os.path.dirname(relationsFile)) == 0:
relationsFile = os.path.join(analysisFolder, relationsFile)
# output
if len(newRelFile) == 0:
if oldWay: # suffix: "cleaned"
newRelFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultNewRelFile + defaultTableExtension)
else: # suffix: "tagged"
newRelFile = os.path.join(
analysisFolder, analysisName + "_" + defaultTaggedRelFile +
defaultTableExtension)
if len(removedRelFile) == 0:
removedRelFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultRemovedRelFile + defaultTableExtension)
if len(os.path.dirname(newRelFile)) == 0:
newRelFile = os.path.join(analysisFolder, newRelFile)
if len(os.path.dirname(removedRelFile)) == 0:
removedRelFile = os.path.join(analysisFolder, removedRelFile)
if len(infoFile) == 0:
infoFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultOutputInfo + defaultTextExtension)
logList.append(["Variance seed = " + str(varianceSeed)])
logList.append(["Input data file: " + dataFile])
logList.append(["Input relations file: " + relationsFile])
if oldWay:
logList.append(
["Output relations file without outliers: " + newRelFile])
logList.append(
["Output relations file with outliers only: " + removedRelFile])
logList.append([
"Removing duplicate higher level elements: " +
str(removeDuplicateUpper)
])
logList.append([
"OldWay option activated: outliers are removed instead of tagged"
])
else:
logList.append(["Relations file tagging outliers: " + newRelFile])
logList.append(["Tags to filter relations: " + tags])
logList.append(["Tag used for outliers: " + outlierTag])
# pp.pprint(logList)
# sys.exit()
# END REGION: FILE NAMES SETUP
relations = stats.loadRelationsFile(relationsFile)
data = stats.loadInputDataFile(dataFile)
if oldWay:
# only for backward compatibility. Note that tags are not supported
newRelations, removedRelations, logResults = \
getRelationsWithoutOutliers(data,
relations,
varianceSeed,
FDRLimit = FDRLimit,
modeUsed = modeUsed,
removeDuplicateUpper = removeDuplicateUpper)
else:
newRelations, removedRelations, logResults = \
tagRelationsWithoutOutliers(data,
relations,
varianceSeed,
FDRLimit = FDRLimit,
modeUsed = modeUsed,
removeDuplicateUpper = removeDuplicateUpper,
tags = tags,
outlierTag = outlierTag,
logicOperatorsAsWords = logicOperatorsAsWords)
if oldWay:
stats.saveFile(newRelFile, newRelations, "idsup\tidinf")
else:
stats.saveFile(newRelFile, newRelations, "idsup\tidinf\ttags")
stats.saveFile(infoFile, logList, "INFO FILE")
if oldWay:
stats.saveFile(removedRelFile, removedRelations, "idsup\tidinf")
def main(argv):
version = "v0.04"
analysisName = ""
cleaveSites = "KR" # trypsin default
removePalindromes = False
defaultAnalysisName = "inversor"
analysisFolder = ""
defaultTableExtension = ".xls"
defaultTextExtension = ".txt"
defaultFastaExtension = ".fasta"
graphFileFormat = "png"
defaultFastaFile = "fastadef"
invertedFastaFile = ""
defaultInvertedFileSuffix = "inv"
defaultLogFile = "logFile"
fastaFile = ""
logFile = ""
logList = [["Inversor " + version],
["Start: " + strftime("%Y-%m-%d %H:%M:%S")]]
try:
opts, args = getopt.getopt(argv, "a:p:f:c:rh", [
"analysis=", "folder=", "fastafile=", "cleavesites=", "place=",
"removepalindromes", "help", "egg", "easteregg"
])
except getopt.GetoptError:
logList.append(["Error while getting parameters."])
sys.exit(2)
if len(opts) == 0:
printHelp(version)
sys.exit()
for opt, arg in opts:
if opt in ("-a", "--analysis"):
analysisName = arg
elif opt in ("-p", "--place", "--folder"):
analysisFolder = arg
elif opt in ("-f", "--fastafile"):
fastaFile = arg
elif opt in ("-c", "--cleavesites"):
cleaveSites = arg.strip()
elif opt in ("-r", "--removepalindromes"):
removePalindromes = True
elif opt in ("-h", "--help"):
printHelp(version)
sys.exit()
elif opt in ("--egg", "--easteregg"):
easterEgg()
sys.exit()
# REGION: FILE NAMES SETUP
if len(analysisName) == 0:
if len(fastaFile) > 0:
analysisName = os.path.splitext(os.path.basename(fastaFile))[0]
else:
analysisName = defaultAnalysisName
if len(os.path.dirname(analysisName)) > 0:
analysisNameFirstPart = os.path.dirname(analysisName)
analysisName = os.path.basename(analysisName)
if len(analysisFolder) == 0:
analysisFolder = analysisNameFirstPart
if len(fastaFile) > 0 and len(analysisFolder) == 0:
if len(os.path.dirname(fastaFile)) > 0:
analysisFolder = os.path.dirname(fastaFile)
# input
if len(os.path.dirname(fastaFile)) == 0 and len(fastaFile) > 0:
fastaFile = os.path.join(analysisFolder, fastaFile)
# output
if len(invertedFastaFile) == 0:
invertedFastaFile = os.path.join(
analysisFolder, analysisName + "_" + defaultInvertedFileSuffix +
defaultFastaExtension)
if len(logFile) == 0:
logFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultLogFile + defaultTextExtension)
logList.append([""])
logList.append(["Input FASTA file: " + fastaFile])
logList.append(["Inverted FASTA file: " + invertedFastaFile])
logList.append(["Cleave sites used: " + cleaveSites])
logList.append([""])
# END REGION: FILE NAMES SETUP
try:
readAndWriteNewFASTAFile(fastaFile,
invertedFastaFile,
digestionPoints=cleaveSites,
removePalindromes=removePalindromes)
logList.append(["Everything went fine."])
except getopt.GetoptError:
logList.append(["Error."])
stats.saveFile(logFile, logList, "LOG FILE")
sys.exit(2)
stats.saveFile(logFile, logList, "LOG FILE")
def main(options, programName, programVersion):
## REGION: DEFAULT VALUES AND VARIABLE ACQUISITION
# basic default info
logFile = ""
analysisName = ""
analysisFolder = ""
defaultAnalysisName = programName.lower()
caFDR = 0.05
modeSanXoTSieve = "newWay" # alternatively, "oldWay"
coordination = 0
caseSensitive = True
# default extensions
defaultTableExtension = ".xls"
defaultTextExtension = ".txt"
# default file names
defaultLogFile = "logFile"
qcInputFile = "qcInput"
qcInputFileNoOuts = ""
caInputFile = "caInput"
# basic log file
logList = [[programName + " " + programVersion], ["Start: " + strftime("%Y-%m-%d %H:%M:%S")]]
# parsing arguments from commandline
options.add_argument("-a", "--analysis", type = str, default = "", required = False, help = "Use a prefix for the output files.")
options.add_argument("-p", "--place", type = str, default = "", required = False, help = "To use a different common folder for the output files. If this is not provided, the the folder used will be the same as the FASTA file folder.")
options.add_argument("-L", "--logfile", type = str, default = "", required = False, help = "To use a non-default name for the log file.")
options.add_argument("-q", "--qcinput", type = str, default = "", required = True, help = "Input outstats file with the q2c integration, including outliers. It must include outliers tagged in new SanXoTSieve files, or, alternatively, it must add the corresponding file with no outliers (see -n argument) for SanXoTSieve in oldWay mode.")
options.add_argument("-n", "--qcinputnoouts", type = str, default = "", required = False, help = "Input outstats file with the q2c integration, NOT including outliers (using this parameter automatically implies the oldWay option has been used in SanXoTSieve, i.e. removing outliers from the relations file, instead of just tagging them).")
options.add_argument("-c", "--cainput", type = str, default = "", required = True, help = "Input outstats file with the c2a integration, defining in the FDR column which cateogries are considered to be changing.")
options.add_argument("--cafdr", type = str, default = "0.05", required = False, help = "To consider a non-default FDR value for changing categories in the c2a integration (default is 0.05).")
options.add_argument("--caseinsensitive", action='store_true', help = "Consider case insensitive categories and protein identifiers (by default, they are case sensitive).")
arguments = options.parse_args()
# copying parsed arguments
# copy any arguments used
if len(arguments.analysis) > 0: analysisName = arguments.analysis
if len(arguments.place) > 0: analysisFolder = arguments.place
if len(arguments.logfile) > 0: logFile = arguments.logfile
if len(arguments.qcinput) > 0: qcInputFile = arguments.qcinput
if len(arguments.qcinputnoouts) > 0:
qcInputFileNoOuts = arguments.qcinputnoouts
modeSanXoTSieve = "oldWay"
if len(arguments.cainput) > 0: caInputFile = arguments.cainput
if len(str(arguments.cafdr)) > 0:
try:
caFDR = float(arguments.cafdr)
except:
message = "Warning: FDR for categories changing could not be parsed, %f will be used instead." % caFDR
logList.append([""])
logList.append([message])
logList.append([""])
print ""
print message
print ""
caseSensitive = not arguments.caseinsensitive
## END REGION: DEFAULT VALUES AND VARIABLE ACQUISITION
## **********************************************************
## REGION: FILE NAMES SETUP
if len(analysisName) == 0:
if len(qcInputFile) > 0:
analysisName = os.path.splitext(os.path.basename(qcInputFile))[0]
else:
analysisName = defaultAnalysisName
if len(os.path.dirname(analysisName)) > 0:
analysisNameFirstPart = os.path.dirname(analysisName)
analysisName = os.path.basename(analysisName)
if len(analysisFolder) == 0:
analysisFolder = analysisNameFirstPart
if len(analysisFolder) == 0:
analysisFolder = os.getcwd()
# input
if len(os.path.dirname(qcInputFile)) == 0:
qcInputFile = os.path.join(analysisFolder, qcInputFile)
if len(os.path.dirname(qcInputFileNoOuts)) == 0 and modeSanXoTSieve == "oldWay":
qcInputFileNoOuts = os.path.join(analysisFolder, qcInputFileNoOuts)
if len(os.path.dirname(caInputFile)) == 0:
caInputFile = os.path.join(analysisFolder, caInputFile)
# output
# the only output is the logFile, which includes a last line with the coordination
if len(logFile) == 0:
logFile = os.path.join(analysisFolder, analysisName + "_" + defaultLogFile + defaultTextExtension)
if len(os.path.dirname(logFile)) == 0 and len(os.path.basename(logFile)) > 0:
logFile = os.path.join(analysisFolder, logFile)
logList.append([""])
logList.append(["Input protein-to-category outstats file: " + qcInputFile])
logList.append(["Input category-to-all outstats file: " + caInputFile])
if len(qcInputFileNoOuts) > 0: logList.append(["Input protein-to-category outstats with NO outliers: " + qcInputFileNoOuts])
logList.append(["Output log file: " + logFile])
logList.append(["category-to-all FDR used: %f" % caFDR])
logList.append(["SanXoTSieve mode: " + modeSanXoTSieve])
logList.append([""])
## END REGION: FILE NAMES SETUP
## **********************************************************
## REGION: PROGRAM BASIC STRUCTURE
listChangingCats = getListChangingCats(caInputFile, caFDR)
numRelsChangingCats, numOutliersChangingCats, numOutliersNonChangingCats = getRels(qcInputFile, listChangingCats, qcInputFileNoOuts, modeSanXoTSieve, caseSensitive)
# explanation
# coord = (C - B)/(C + A)
# where
# C = numRelsChangingCats = qc-relations pointing to categories changing in ca
# B = numOutliersChangingCats = outlier qc-relations in categories changing in ca
# A = numOutliersNonChangingCats = outlier qc-relations in categories not changing in ca
# hence, B + A = outlier qc-relations in any category
coordination = (float(numRelsChangingCats) - float(numOutliersChangingCats)) / (float(numRelsChangingCats) + float(numOutliersNonChangingCats))
## END REGION: PROGRAM BASIC STRUCTURE
## **********************************************************
## REGION: SAVING FILES
try:
message = "Degree of coordination: %f" % coordination
logList.append(["Total number of changing categories: %i" % len(listChangingCats)])
logList.append(["Total number of relations pointing to changing categories: %i" % numRelsChangingCats])
logList.append(["Total number of outlier relations pointing to changing categories: %i" % numOutliersChangingCats])
logList.append(["Total number of outlier relations pointing to non-changing categories: %i" % numOutliersNonChangingCats])
logList.append([message])
print ""
print "Find more details in the log file, at: %s" % logFile
print ""
print message
print ""
except getopt.GetoptError:
logList.append(["Error."])
stats.saveFile(logFile, logList, "LOG FILE")
sys.exit(2)
stats.saveFile(logFile, logList, "LOG FILE")
def main(argv):
version = "v1.14"
verbose = False
similarityLimit = -1.0 # if remain as -1, it will be calculated
graphLimits = 6.0
analysisName = ""
useSubStats = True
defaultAnalysisName = "sanxot"
analysisFolder = ""
# input files
inStats = ""
defaultStatsFile = "stats"
defaultRelationsFile = "rels"
defaultTableExtension = ".tsv"
defaultTextExtension = ".txt"
defaultDOTExtension = ".gv"
relationsFile = ""
upperLevelToGraphFile = ""
# output files
defaultUpperLevelToGraphFile = "ulst"
defaultOutputGraph = "simGraph"
defaultLogFile = "logFile"
defaultSimilarityMatrixFile = "outSimilarities"
defaultOutputGVFileName = "simGraph"
defaultOutputClusterFileName = "outClusters"
logFile = ""
graphFile = ""
dotFile = ""
outCluster = ""
similarityMatrixFile = ""
graphFileFormat = "png"
altMax = 5
selectedNodeColour = "#ff9090"
defaultNodeColour = "#ffff80"
errorNodeColour = "#8080ff"
minColour = "#00ff00"
middleColour = "#ffffff"
maxColour = "#ff0000"
defaultNodeTextColour = "#000000"
nonParetoOpacity = 0.5
minFontSize = 10.0
maxFontSize = 70.0
graphDPI = 96.0
graphRatio = 0.0
logList = [["Sanson " + version], ["Start: " + strftime("%Y-%m-%d %H:%M:%S")]]
try:
opts, args = getopt.getopt(argv, "a:p:z:r:c:L:G:m:l:d:e:s:d:g:N:bhk", ["analysis=", "folder=", "place=", "statsfile=", "relfile=", "relationsfile=", "list=", "logfile=", "graphfile=", "simfile=", "graphlimits=", "similarity=", "dotfile=", "outcluster=", "graphformat=", "altmax=", "selectednodecolour=", "selectednodecolor=", "defaultnodecolour=", "defaultnodecolor=", "defaultnodetextcolour=", "defaultnodetextcolor=", "errornodecolour=", "errornodecolor=", "mincolour=", "mincolor=", "middlecolour=", "middlecolor=", "maxcolour=", "maxcolor=","nonparetoopacity=", "minfontsize=", "maxfontsize=", "graphdpi=", "graphratio=", "nosubstats", "help", "egg", "easteregg"])
except getopt.GetoptError:
logList.append(["Error while getting parameters."])
sys.exit(2)
if len(opts) == 0:
printHelp(version)
sys.exit()
for opt, arg in opts:
if opt in ("-a", "--analysis"):
analysisName = arg
elif opt in ("-p", "--place", "--folder"):
analysisFolder = arg
elif opt in ("-z", "--statsfile"):
inStats = arg
elif opt in ("-r", "--relfile", "--relationsfile"):
relationsFile = arg
elif opt in ("-c", "--list"):
upperLevelToGraphFile = arg
elif opt in ("-L", "--logfile"):
logFile = arg
elif opt in ("-G", "--graphfile"):
graphFile = arg
elif opt in ("-m", "--simfile"):
similarityMatrixFile = arg
elif opt in ("-l", "--graphlimits"):
graphLimits = float(arg)
elif opt in ("-e", "--similarity"):
similarityLimit = float(arg)
elif opt in ("-d", "--dotfile"):
# begin: jmrc
dotFile = arg
# end: jmrc
elif opt in ("-s", "--outcluster"):
outCluster = float(arg)
elif opt in ("-b", "--nosubstats"):
useSubStats = False
elif opt in ("--nonparetoopacity"):
nonParetoOpacity = float(arg)
elif opt in ("-N", "--altmax"):
altMax = int(arg)
elif opt in ("-g", "--graphformat"):
graphFileFormat = arg.lower().strip()
if graphFileFormat == "jpeg": graphFileFormat = "jpg"
if graphFileFormat != "png" and \
graphFileFormat != "svg" and \
graphFileFormat != "jpg" and \
graphFileFormat != "tif" and \
graphFileFormat != "tiff" and \
graphFileFormat != "pdf" and \
graphFileFormat != "bmp" and \
graphFileFormat != "gif":
print()
print("Warning: graph format \"%s\" is not supported,\npng will be used instead." % graphFileFormat)
print()
graphFileFormat = "png"
elif opt in("--selectednodecolour", "--selectednodecolor"):
selectedNodeColour = arg
elif opt in("--defaultnodecolour", "--defaultnodecolor"):
defaultNodeColour = arg
elif opt in("--defaultnodetextcolour", "--defaultnodetextcolor"):
defaultNodeTextColour = arg
elif opt in("--errornodecolour", "--errornodecolor"):
errorNodeColour = arg
elif opt in("--mincolour", "--mincolor"):
minColour = arg
elif opt in("--middlecolour", "--middlecolor"):
middleColour = arg
elif opt in("--maxcolour", "--maxcolor"):
maxColour = arg
elif opt in("--minfontsize"):
minFontSize = float(arg)
elif opt in("--maxfontsize"):
maxFontSize = float(arg)
elif opt in("--graphdpi"):
graphDPI = float(arg)
elif opt in("--graphratio"):
graphRatio = float(arg)
elif opt in ("-h", "--help"):
printHelp(version)
sys.exit()
elif opt in ("--egg", "--easteregg"):
easterEgg()
sys.exit()
# REGION: FILE NAMES SETUP
if minFontSize > maxFontSize: minFontSize = maxFontSize
defaultGraphExtension = "." + graphFileFormat
if len(analysisName) == 0:
if len(inStats) > 0:
analysisName = os.path.splitext(os.path.basename(inStats))[0]
else:
analysisName = defaultAnalysisName
if len(os.path.dirname(analysisName)) > 0:
analysisNameFirstPart = os.path.dirname(analysisName)
analysisName = os.path.basename(analysisName)
if len(analysisFolder) == 0:
analysisFolder = analysisNameFirstPart
if len(inStats) > 0 and len(analysisFolder) == 0:
if len(os.path.dirname(inStats)) > 0:
analysisFolder = os.path.dirname(inStats)
# input
if len(inStats) == 0:
inStats = os.path.join(analysisFolder, analysisName + "_" + defaultStatsFile + defaultTableExtension)
if len(os.path.dirname(inStats)) == 0 and len(analysisFolder) > 0:
inStats = os.path.join(analysisFolder, inStats)
if len(relationsFile) == 0:
relationsFile = os.path.join(analysisFolder, analysisName + "_" + defaultRelationsFile + defaultTableExtension)
if len(upperLevelToGraphFile) == 0:
upperLevelToGraphFile = os.path.join(analysisFolder, analysisName + "_" + defaultUpperLevelToGraphFile + defaultTextExtension)
if len(os.path.dirname(relationsFile)) == 0 and len(os.path.basename(relationsFile)) > 0:
relationsFile = os.path.join(analysisFolder, relationsFile)
if len(os.path.dirname(upperLevelToGraphFile)) == 0 and len(os.path.basename(upperLevelToGraphFile)) > 0:
upperLevelToGraphFile = os.path.join(analysisFolder, upperLevelToGraphFile)
# output
if len(dotFile) == 0:
dotFile = os.path.join(analysisFolder, analysisName + "_" + defaultOutputGVFileName + defaultDOTExtension)
if len(outCluster) == 0:
outCluster = os.path.join(analysisFolder, analysisName + "_" + defaultOutputClusterFileName + defaultTableExtension)
if len(similarityMatrixFile) == 0:
similarityMatrixFile = os.path.join(analysisFolder, analysisName + "_" + defaultSimilarityMatrixFile + defaultTextExtension)
if len(logFile) == 0:
logFile = os.path.join(analysisFolder, analysisName + "_" + defaultLogFile + defaultTextExtension)
if len(graphFile) == 0:
graphFile = os.path.join(analysisFolder, analysisName + "_" + defaultOutputGraph + defaultGraphExtension)
if len(os.path.dirname(dotFile)) == 0 and len(os.path.basename(dotFile)) > 0:
dotFile = os.path.join(analysisFolder, dotFile)
if len(os.path.dirname(outCluster)) == 0 and len(os.path.basename(outCluster)) > 0:
outCluster = os.path.join(analysisFolder, outCluster)
if len(os.path.dirname(similarityMatrixFile)) == 0 and len(os.path.basename(similarityMatrixFile)) > 0:
similarityMatrixFile = os.path.join(analysisFolder, similarityMatrixFile)
if len(os.path.dirname(logFile)) == 0 and len(os.path.basename(logFile)) > 0:
logFile = os.path.join(analysisFolder, logFile)
if len(os.path.dirname(graphFile)) == 0 and len(os.path.basename(graphFile)) > 0:
graphFile = os.path.join(analysisFolder, graphFile)
logList.append([""])
logList.append(["Input stats file: " + inStats])
logList.append(["Relations file: " + relationsFile])
logList.append(["File with sigmoids to depict: " + upperLevelToGraphFile])
logList.append(["Output similarity matrix table: " + similarityMatrixFile])
logList.append(["Output log file: " + logFile])
logList.append(["Output graph file: " + graphFile])
logList.append([""])
if useSubStats: logList.append(["Filling nodes with Z from lower elemenets"])
else: logList.append(["Filling nodes with Z from upper elements"])
logList.append([""])
# pp.pprint(logList)
# sys.exit()
# END REGION: FILE NAMES SETUP
try:
data, extraData, logListExtraInfo = associateElements(inStats = inStats, uFile = upperLevelToGraphFile, relFile = relationsFile)
logList.append(logListExtraInfo)
logList.append(["Data files correctly loaded."])
except getopt.GetoptError:
logList.append(["Error while getting data files."])
stats.saveFile(logFile, logList, "LOG FILE")
sys.exit(2)
if len(data) == 0:
logList.append([""])
errorMessage = "No data were retrieved to create the similarity graph."
print(errorMessage)
print("Exiting...")
logList.append([errorMessage])
else:
similarityMatrix, NMatrix = SMatrix(data)
stats.saveFile(similarityMatrixFile, similarityMatrix)
if useSubStats:
# añadir salida para log ***
subData = stats.arrangeSubData(inStats = inStats,
uFile = upperLevelToGraphFile,
relFile = relationsFile,
ignoreNaNsInFDR = True)
else:
subData = None
if similarityLimit < 0.0 or similarityLimit > 1.0:
# means it has to be calculated
# this includes the default value = -1
FNumber, bestBooleanSimMatrix, bestClusterVector, CNumber = \
getBestFNumber(similarityMatrix,
verbose = False,
stepFNumber = 0.01,
initialFNumber = 0.0,
finalFNumber = 1.0)
logList.append([""])
logList.append(["Creating DOT graph for the best FNumber = %f." % FNumber])
logList.append(["At least %i graphs contain %i nodes." % (CNumber, CNumber)])
else:
FNumber, bestBooleanSimMatrix, bestClusterVector, CNumber = \
getBestFNumber(similarityMatrix,
verbose = False,
stepFNumber = 0.0,
initialFNumber = similarityLimit,
finalFNumber = similarityLimit)
logList.append([""])
logList.append(["Creating DOT graph for the given FNumber = %f." % FNumber])
# begin: jmrc
# print("Best FNumber: %f" % FNumber)
# end: jmrc
paretoInfo, extraDataWithClusters = getParetoInfo(clusterVector = bestClusterVector,
extraData = extraData)
# stats.saveFile(outCluster, bestClusterVector, "CLUSTERS IDENTIFIED")
stats.saveFile(outCluster, extraDataWithClusters, "id\tn\tZ\tFDR\tX\tcluster id\tPareto front?")
createDOTGraph(similarityMatrix,
simLimit = FNumber,
outputGVFile = dotFile,
simGraphFile = graphFile,
extraData = extraData,
subData = subData,
NMatrix = NMatrix,
graphLimits = graphLimits,
graphFileFormat = graphFileFormat,
altMax = altMax,
defaultNodeColour = defaultNodeColour,
errorNodeColour = errorNodeColour,
minColour = minColour,
middleColour = middleColour,
maxColour = maxColour,
defaultNodeTextColour = defaultNodeTextColour,
nonParetoOpacity = nonParetoOpacity,
paretoInfo = paretoInfo,
minFontSize = minFontSize,
maxFontSize = maxFontSize,
graphDPI = graphDPI,
graphRatio = graphRatio)
stats.saveFile(logFile, logList, "LOG FILE")
def main(argv):
version = "v0.01"
analysisName = ""
analysisFolder = ""
relationsFile = ""
dataFiles = ""
outputFile = ""
defaultOutput = "OutStats"
defaultOutputInfo = "infoFile"
defaultRelationsFile = "rels"
defaultDataFiles = "datafile"
defaultTableExtension = ".xls"
defaultTextExtension = ".txt"
defaultGraphExtension = ".png"
defaultAnalysisName = "xpvpAnalysis"
infoFile = ""
logList = [["XVpCollector " + version],
["Start: " + strftime("%Y-%m-%d %H:%M:%S")]]
try:
opts, args = getopt.getopt(argv, "a:p:r:o:d:h", [
"analysis=", "folder=", "relfile=", "outputfile=", "dataFile=",
"help"
])
except getopt.GetoptError:
logList.append(["Error while getting parameters."])
stats.saveFile(infoFile, logList, "INFO FILE")
sys.exit(2)
if len(opts) == 0:
printHelp(version)
sys.exit()
for opt, arg in opts:
if opt in ("-a", "--analysis"):
analysisName = arg
if opt in ("-p", "--place", "--folder"):
analysisFolder = arg
if opt in ("-r", "--relfile"):
relationsFile = arg
if opt in ("-o", "--outputfile"):
outputFile = arg
if opt in ("-d", "--dataFile"):
dataFiles = arg
elif opt in ("-h", "--help"):
printHelp(version)
# REGION: FILE NAMES SETUP
if len(analysisName) == 0:
if len(dataFiles) > 0:
analysisName = os.path.splitext(os.path.basename(dataFiles))[0]
else:
analysisName = defaultAnalysisName
if len(os.path.dirname(analysisName)) > 0:
analysisNameFirstPart = os.path.dirname(analysisName)
analysisName = os.path.basename(analysisName)
if len(analysisFolder) == 0:
analysisFolder = analysisNameFirstPart
if len(dataFiles) > 0 and len(analysisFolder) == 0:
if len(os.path.dirname(dataFiles)) > 0:
analysisFolder = os.path.dirname(dataFiles)
# input
if len(dataFiles) == 0:
dataFiles = os.path.join(
analysisFolder,
analysisName + "_" + defaultDataFiles + defaultTableExtension)
if len(os.path.dirname(dataFiles)) == 0 and len(analysisFolder) > 0:
dataFiles = os.path.join(analysisFolder, dataFiles)
if len(relationsFile) == 0:
relationsFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultRelationsFile + defaultTableExtension)
if len(os.path.dirname(relationsFile)) == 0 and len(analysisFolder) > 0:
relationsFile = os.path.join(analysisFolder, relationsFile)
# output
if len(outputFile) == 0:
outputFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultOutput + defaultTableExtension)
else:
if len(os.path.dirname(outputFile)) == 0:
outputFile = os.path.join(analysisFolder, outputFile)
if len(infoFile) == 0:
infoFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultOutputInfo + defaultTableExtension)
logList.append(["Input dataFiles " + str(dataFiles)])
logList.append(["Input relations file: " + relationsFile])
logList.append(["Input dataFile: " + dataFiles])
logList.append(["Output stats file: " + outputFile])
logList.append(["Output info file: " + infoFile])
outputList = X_VpCollector(dataFiles=dataFiles,
relationsFile=relationsFile)
header = "idsup\tX'sup,\t,V'sup" #"Sequence\tFASTAProteinDescription\tXp\tVp\tcount\tZp" "idsup\tX'sup,\t,V'sup"
#######("Fix the header for Xp and Vp")
stats.saveFile(outputFile, outputList, header)
if len(infoFile) > 0:
stats.saveFile(infoFile, logList, "INFO FILE")
def main(argv):
# begin: jmrc
# version = "v1.17"
version = "v1.19"
# end: jmrc
fileName = ""
outFile = ""
iField = ""
jField = ""
kField = ""
lField = ""
c5Field = ""
analysisName = ""
filterString = ""
inputSeparator = "\t"
useNumbers = False
logicOperatorsAsWords = False # False = Python-style operators (&&, ||), True = word-like operators (\and\ \or\)
curlyBrackets = False # False = normal brackets (), True = curly brackets {}
analysisFolder = ""
defaultFileName = "QuiXML"
defaultOutputFile = "table"
defaultOutputLog = "log"
defaultTableExtension = ".tsv"
defaultTextExtension = ".txt"
defaultGraphExtension = ".png"
defaultXMLExtension = ".xml"
defaultAnalysisName = "aljamia"
removeDuplicates = True
# begin: jmrc
removeEmptyRows = False
# end: jmrc
allowOperationsInFields = ""
tableId = "peptide_match" # default for QuiXML
initialRow = 1 # for xls coming from QuiXML should be 25
logFile = ""
logList = [["Aljamia " + version], ["Start: " + strftime("%Y-%m-%d %H:%M:%S")]]
try:
# begin: jmrc
# opts, args = getopt.getopt(argv, "a:p:x:o:i:j:k:l:t:R:L:f:F:A:cdwh", ["input=", "filename=", "place=", "folder=", "outfile=", "c1=", "c2=", "c3=", "c4=", "c5=", "table=", "initialrow=", "logfile=", "filter=", "allow-operations=", "curly-brackets", "allow-duplicates", "word-operators", "inputseparator", "help", "egg", "easteregg"])
opts, args = getopt.getopt(argv, "a:p:x:o:i:j:k:l:t:R:L:f:F:A:e:cdwh", ["input=", "filename=", "place=", "folder=", "outfile=", "c1=", "c2=", "c3=", "c4=", "c5=", "table=", "initialrow=", "logfile=", "filter=", "allow-operations=", "curly-brackets", "allow-duplicates", "remove-empty=", "word-operators", "inputseparator", "help", "egg", "easteregg"])
# end: jmrc
except getopt.GetoptError:
logList.append(["Error while getting parameters."])
stats.saveFile(logFile, logList, "LOG FILE")
sys.exit(2)
if len(opts) == 0:
printHelp(version)
sys.exit()
for opt, arg in opts:
if opt in ("-a", "--analysis"):
analysisName = arg
if opt in ("-p", "--place", "--folder"):
analysisFolder = arg
if opt in ("-x", "--input", "--filename"):
fileName = arg
if opt in ("-o", "--output"):
outFile = arg
elif opt in ("-i", "--c1"):
iField = arg.strip()
elif opt in ("-j", "--c2"):
jField = arg.strip()
elif opt in ("-k", "--c3"):
kField = arg.strip()
elif opt in ("-l", "--c4"):
lField = arg.strip()
elif opt in ("--c5"):
c5Field = arg.strip()
elif opt in ("-t", "--table"):
tableId = int(arg) # *** check this: int or string?
elif opt in ("-R", "--initialrow"):
initialRow = int(arg)
elif opt in ("-L", "--logfile"):
logFile = arg
elif opt in ("-f", "--filter"):
filterString = arg
useNumbers = False
elif opt in ("-F", "--filter-using-numbers"):
filterString = arg
useNumbers = True
elif opt in ("-A", "--allow-operations"):
allowOperationsInFields = str(arg).strip()
elif opt in ("-d", "--allow-duplicates"):
removeDuplicates = False
# begin: jmrc
elif opt in ("-e", "--remove-empty"):
removeEmptyRows = arg
# end: jmrc
elif opt in ("-c", "--curly-brackets"):
curlyBrackets = True
elif opt in ("-w", "--word-operators"):
logicOperatorsAsWords = True
elif opt in ("-s", "--inputseparator"):
inputSeparator = str(arg)[0]
elif opt in ("-h", "--help"):
printHelp(version)
sys.exit()
elif opt in ("--egg", "--easteregg"):
easterEgg()
sys.exit()
# REGION: FILE NAMES SETUP
if len(analysisName) == 0:
if len(fileName) > 0:
analysisName = os.path.splitext(os.path.basename(fileName))[0]
else:
analysisName = defaultAnalysisName
if len(os.path.dirname(analysisName)) > 0:
analysisNameFirstPart = os.path.dirname(analysisName)
analysisName = os.path.basename(analysisName)
if len(analysisFolder) == 0:
analysisFolder = analysisNameFirstPart
if len(fileName) > 0 and len(analysisFolder) == 0:
if len(os.path.dirname(fileName)) > 0:
analysisFolder = os.path.dirname(fileName)
# input
if len(fileName) == 0:
fileName = os.path.join(analysisFolder, analysisName + "_" + defaultFileName + defaultXMLExtension)
if len(os.path.dirname(fileName)) == 0:
fileName = os.path.join(analysisFolder, fileName)
# output
if len(outFile) == 0:
outFile = os.path.join(analysisFolder, analysisName + "_" + defaultOutputFile + defaultTableExtension)
else:
if len(os.path.dirname(outFile)) == 0:
outFile = os.path.join(analysisFolder, outFile)
if len(logFile) == 0:
logFile = os.path.join(analysisFolder, analysisName + "_" + defaultOutputLog + defaultTextExtension)
logList.append(["Input file: " + fileName])
logList.append(["Output file: " + outFile])
logList.append(["Log file: " + logFile])
# END REGION: FILE NAMES SETUP
# errorsFound = findErrors(xmlDocument, tableId, iField, jField, kField, lField)
# if len(errorsFound) > 0:
# for error in errorsFound:
# print error
# sys.exit()
# else:
# pass
if os.path.splitext(fileName)[1] == ".xml":
try:
#xmlDocument = dom.parse(fileName)
xmlDocument = ElementTree.parse(fileName).getroot()
except:
print("Error while reading xml file2.")
logList.append(["Error while reading xml file."])
stats.saveFile(logFile, logList, "LOG FILE")
sys.exit(2)
resultingData = getDataFromXML(xmlDocument,
Field,
jField,
kField,
lField,
c5Field,
tableId = tableId,
filterString = filterString,
removeDuplicates = removeDuplicates,
useNumbers = useNumbers,
logicOperatorsAsWords = logicOperatorsAsWords,
curlyBrackets = curlyBrackets)
else: # then it should be a tsv
resultingData = getDataFromTXT(fileName,
iField,
jField,
kField,
lField,
c5Field,
filterString = filterString,
removeDuplicates = removeDuplicates,
# begin: jmrc
removeEmptyRows = removeEmptyRows,
# end: jmrc
initialRow = initialRow,
allowOperationsInFields = allowOperationsInFields,
useNumbers = useNumbers,
logicOperatorsAsWords = logicOperatorsAsWords,
curlyBrackets = curlyBrackets,
inputSeparator = inputSeparator)
iTab = ""
if len(iField) > 0: iTab = "%s\t" % iField
jTab = ""
if len(jField) > 0: jTab = "%s\t" % jField
kTab = ""
if len(kField) > 0: kTab = "%s\t" % kField
lTab = ""
if len(lField) > 0: lTab = "%s\t" % lField
c5Tab = ""
if len(c5Field) > 0: c5Tab = "%s\t" % c5Field
header = iTab + jTab + kTab + lTab + c5Tab
header = header[:len(header) - 1]
stats.saveFile(outFile, resultingData, header)
def showGraphTool(inputRawData,
inputRelations,
k,
variance,
alpha,
medianSide,
verbose = False,
showRank = False,
graphFile = None,
graphData = None,
dpi = None,
showGraph = True):
plt.clf()
inputRawData.sort()
inputRelations.sort()
windowWidth = medianSide * 2 + 1
if len(inputRawData) < windowWidth:
print('Error: window for median is bigger than total input size')
sys.exit()
# output = makeStats(k, variance, input = input)
nextIdXData = getNextIdX_klibrate(inputRawData, inputRelations, k, variance, alpha, giveMergedData = True)
nextIdX = nextIdXData[0]
mergedData = nextIdXData[1]
MADdistrOut, weights = getMADDistribution(nextIdX, mergedData, k, variance, alpha, medianSide)
invOfFitOut = getInverseOfFit(mergedData, k, variance, alpha)
MADdistrOut = MADdistrOut[medianSide:len(MADdistrOut) - medianSide + 1]
invOfFitOut = invOfFitOut[medianSide:len(invOfFitOut) - medianSide + 1]
weights = weights[medianSide:len(weights) - medianSide + 1]
# folderToSave = "D:\\DATUMARO\\trabajo\\programas_repositorio\\BioSistemas SanXoT\\MicroArrays\\intento5 CvsCs usando var robusta por partes\\"
# stats.saveFile(folderToSave + "MADdistrOut.txt", MADdistrOut)
# stats.saveFile(folderToSave + "invOfFitOut.txt", invOfFitOut)
# stats.saveFile(folderToSave + "weights.txt", weights)
if showRank:
plt.plot(list(range(len(MADdistrOut))), MADdistrOut, 'g.', list(range(len(invOfFitOut))), invOfFitOut, 'r', linewidth=1.0, markersize=2.0, markeredgewidth=0.0)
plt.xlabel('rank($V_s$)')
plt.ylabel('1 / MSD')
# to save data
# *** use a better filename
dataToSave = []
for i in range(len(MADdistrOut)):
dataToSave.append([i, weights[i], MADdistrOut[i], invOfFitOut[i]])
if graphData:
stats.saveFile(graphData, dataToSave, "rank(Vs)\tweight\tMAD\t1/fit")
else:
# uncomment to graph MSD instead of 1 / MSD
#
# for i in xrange(len(invOfFitOut)):
# invOfFitOut[i] = 1 / invOfFitOut[i]
# for i in xrange(len(MADdistrOut)):
# MADdistrOut[i] = 1 / MADdistrOut[i]
plt.plot(weights, MADdistrOut, 'g.', weights, invOfFitOut, 'r', linewidth=1.0, markersize=2.0, markeredgewidth=0.0)
plt.xlabel('($V_s$)')
plt.ylabel('1 / MSD')
plt.grid(True)
plt.title('k = %g, $\sigma^2$ = %g, alpha = %g' % (k, variance, alpha))
if graphFile:
plt.savefig(graphFile, dpi = dpi)
if showGraph:
plt.show()
def main(argv):
version = "v1.17"
fileName = ""
outFile = ""
iField = ""
jField = ""
kField = ""
lField = ""
c5Field = ""
analysisName = ""
filterString = ""
inputSeparator = "\t"
useNumbers = False
logicOperatorsAsWords = False # False = Python-style operators (&&, ||), True = word-like operators (\and\ \or\)
curlyBrackets = False # False = normal brackets (), True = curly brackets {}
analysisFolder = ""
defaultFileName = "QuiXML"
defaultOutputFile = "table"
defaultOutputLog = "log"
defaultTableExtension = ".tsv"
defaultTextExtension = ".txt"
defaultGraphExtension = ".png"
defaultXMLExtension = ".xml"
defaultAnalysisName = "aljamia"
removeDuplicates = True
allowOperationsInFields = ""
tableId = "peptide_match" # default for QuiXML
initialRow = 1 # for xls coming from QuiXML should be 25
logFile = ""
logList = [["Aljamia " + version], ["Start: " + strftime("%Y-%m-%d %H:%M:%S")]]
try:
opts, args = getopt.getopt(argv, "a:p:x:o:i:j:k:l:t:R:L:f:F:A:cdwh", ["input=", "filename=", "place=", "folder=", "outfile=", "c1=", "c2=", "c3=", "c4=", "c5=", "table=", "initialrow=", "logfile=", "filter=", "allow-operations=", "curly-brackets", "allow-duplicates", "word-operators", "inputseparator", "help", "egg", "easteregg"])
except getopt.GetoptError:
logList.append(["Error while getting parameters."])
stats.saveFile(logFile, logList, "LOG FILE")
sys.exit(2)
if len(opts) == 0:
printHelp(version)
sys.exit()
for opt, arg in opts:
if opt in ("-a", "--analysis"):
analysisName = arg
if opt in ("-p", "--place", "--folder"):
analysisFolder = arg
if opt in ("-x", "--input", "--filename"):
fileName = arg
if opt in ("-o", "--output"):
outFile = arg
elif opt in ("-i", "--c1"):
iField = arg.strip()
elif opt in ("-j", "--c2"):
jField = arg.strip()
elif opt in ("-k", "--c3"):
kField = arg.strip()
elif opt in ("-l", "--c4"):
lField = arg.strip()
elif opt in ("--c5"):
c5Field = arg.strip()
elif opt in ("-t", "--table"):
tableId = int(arg) # *** check this: int or string?
elif opt in ("-R", "--initialrow"):
initialRow = int(arg)
elif opt in ("-L", "--logfile"):
logFile = arg
elif opt in ("-f", "--filter"):
filterString = arg
useNumbers = False
elif opt in ("-F", "--filter-using-numbers"):
filterString = arg
useNumbers = True
elif opt in ("-A", "--allow-operations"):
allowOperationsInFields = str(arg).strip()
elif opt in ("-d", "--allow-duplicates"):
removeDuplicates = False
elif opt in ("-c", "--curly-brackets"):
curlyBrackets = True
elif opt in ("-w", "--word-operators"):
logicOperatorsAsWords = True
elif opt in ("-s", "--inputseparator"):
inputSeparator = str(arg)[0]
elif opt in ("-h", "--help"):
printHelp(version)
sys.exit()
elif opt in ("--egg", "--easteregg"):
easterEgg()
sys.exit()
# REGION: FILE NAMES SETUP
if len(analysisName) == 0:
if len(fileName) > 0:
analysisName = os.path.splitext(os.path.basename(fileName))[0]
else:
analysisName = defaultAnalysisName
if len(os.path.dirname(analysisName)) > 0:
analysisNameFirstPart = os.path.dirname(analysisName)
analysisName = os.path.basename(analysisName)
if len(analysisFolder) == 0:
analysisFolder = analysisNameFirstPart
if len(fileName) > 0 and len(analysisFolder) == 0:
if len(os.path.dirname(fileName)) > 0:
analysisFolder = os.path.dirname(fileName)
# input
if len(fileName) == 0:
fileName = os.path.join(analysisFolder, analysisName + "_" + defaultFileName + defaultXMLExtension)
if len(os.path.dirname(fileName)) == 0:
fileName = os.path.join(analysisFolder, fileName)
# output
if len(outFile) == 0:
outFile = os.path.join(analysisFolder, analysisName + "_" + defaultOutputFile + defaultTableExtension)
else:
if len(os.path.dirname(outFile)) == 0:
outFile = os.path.join(analysisFolder, outFile)
if len(logFile) == 0:
logFile = os.path.join(analysisFolder, analysisName + "_" + defaultOutputLog + defaultTextExtension)
logList.append(["Input file: " + fileName])
logList.append(["Output file: " + outFile])
logList.append(["Log file: " + logFile])
# END REGION: FILE NAMES SETUP
# errorsFound = findErrors(xmlDocument, tableId, iField, jField, kField, lField)
# if len(errorsFound) > 0:
# for error in errorsFound:
# print error
# sys.exit()
# else:
# pass
if os.path.splitext(fileName)[1] == ".xml":
try:
#xmlDocument = dom.parse(fileName)
xmlDocument = ElementTree.parse(fileName).getroot()
except:
print("Error while reading xml file.")
logList.append(["Error while reading xml file."])
stats.saveFile(logFile, logList, "LOG FILE")
sys.exit(2)
resultingData = getDataFromXML(xmlDocument,
Field,
jField,
kField,
lField,
c5Field,
tableId = tableId,
filterString = filterString,
removeDuplicates = removeDuplicates,
useNumbers = useNumbers,
logicOperatorsAsWords = logicOperatorsAsWords,
curlyBrackets = curlyBrackets)
else: # then it should be a tsv
resultingData = getDataFromTXT(fileName,
iField,
jField,
kField,
lField,
c5Field,
filterString = filterString,
removeDuplicates = removeDuplicates,
initialRow = initialRow,
allowOperationsInFields = allowOperationsInFields,
useNumbers = useNumbers,
logicOperatorsAsWords = logicOperatorsAsWords,
curlyBrackets = curlyBrackets,
inputSeparator = inputSeparator)
iTab = ""
if len(iField) > 0: iTab = "%s\t" % iField
jTab = ""
if len(jField) > 0: jTab = "%s\t" % jField
kTab = ""
if len(kField) > 0: kTab = "%s\t" % kField
lTab = ""
if len(lField) > 0: lTab = "%s\t" % lField
c5Tab = ""
if len(c5Field) > 0: c5Tab = "%s\t" % c5Field
header = iTab + jTab + kTab + lTab + c5Tab
header = header[:len(header) - 1]
stats.saveFile(outFile, resultingData, header)
if len(logFile) > 0:
stats.saveFile(logFile, logList, "LOG FILE")
def main(argv):
version = "v0.08"
analysisName = ""
analysisFolder = ""
relationsFile = ""
modifiedPeptidesFile = ""
modifiedPeptidesFile1 = ""
nonModifiedPep2ProtFile = ""
pep2protein = ""
varFile = ""
varFile1 = ""
outputFile = ""
defaultModifiedPeptidesFile = "modPepFile"
defaultModifiedPeptidesFile1 = "modPepFile1"
defaultnonModifiedPeptidesFile = "nonmodPepFile"
defaultpep2protein = "Pep2proteinFile"
defaultOutput = "ModOutStats"
defaultOutputInfo = "infoFile"
defaultRelationsFile = "rels"
defaultTableExtension = ".xls"
defaultTextExtension = ".txt"
defaultGraphExtension = ".png"
defaultAnalysisName = "ghostanalysis"
infoFile = ""
logList = [["SanXoTGhost " + version],
["Start: " + strftime("%Y-%m-%d %H:%M:%S")]]
try:
opts, args = getopt.getopt(argv, "a:p:r:m:M:n:t:o:V:W:L:h", [
"analysis=", "folder=", "relfile=", "modfile=", "modfile1=",
"nonmodfile=", "pep2pro=", "outputfile=", "varfile=", "varFile1=",
"infofile=", "help"
])
except getopt.GetoptError:
logList.append(["Error while getting parameters."])
stats.saveFile(infoFile, logList, "INFO FILE")
sys.exit(2)
if len(opts) == 0:
printHelp(version)
sys.exit()
for opt, arg in opts:
if opt in ("-a", "--analysis"):
analysisName = arg
if opt in ("-p", "--place", "--folder"):
analysisFolder = arg
if opt in ("-m", "--modfile"):
modifiedPeptidesFile = arg
if opt in ("-M", "--modfile1"):
modifiedPeptidesFile1 = arg
if opt in ("-n", "--nonmodfile"):
nonModifiedPep2ProtFile = arg
if opt in ("-t", "--pep2pro"):
pep2protein = arg
if opt in ("-o", "--outputfile"):
outputFile = arg
if opt in ("-r", "--relfile"):
relationsFile = arg
if opt in ("-V", "--varfile"):
varFile = arg
if opt in ("-W", "--varfile1"):
varFile1 = arg
if opt in ("-L", "--infofile"):
infoFile = arg
elif opt in ("-h", "--help"):
printHelp(version)
# REGION: FILE NAMES SETUP
if len(analysisName) == 0:
if len(modifiedPeptidesFile) > 0:
analysisName = os.path.splitext(
os.path.basename(modifiedPeptidesFile))[0]
else:
analysisName = defaultAnalysisName
if len(os.path.dirname(analysisName)) > 0:
analysisNameFirstPart = os.path.dirname(analysisName)
analysisName = os.path.basename(analysisName)
if len(analysisFolder) == 0:
analysisFolder = analysisNameFirstPart
if len(modifiedPeptidesFile) > 0 and len(analysisFolder) == 0:
if len(os.path.dirname(modifiedPeptidesFile)) > 0:
analysisFolder = os.path.dirname(modifiedPeptidesFile)
if len(analysisName) == 0:
if len(modifiedPeptidesFile1) > 0:
analysisName = os.path.splitext(
os.path.basename(modifiedPeptidesFile1))[0]
else:
analysisName = defaultAnalysisName
if len(os.path.dirname(analysisName)) > 0:
analysisNameFirstPart = os.path.dirname(analysisName)
analysisName = os.path.basename(analysisName)
if len(analysisFolder) == 0:
analysisFolder = analysisNameFirstPart
if len(modifiedPeptidesFile1) > 0 and len(analysisFolder) == 0:
if len(os.path.dirname(modifiedPeptidesFile1)) > 0:
analysisFolder = os.path.dirname(modifiedPeptidesFile1)
# input
if len(modifiedPeptidesFile) == 0:
modifiedPeptidesFile = os.path.join(
analysisFolder, analysisName + "_" + defaultModifiedPeptidesFile +
defaultTableExtension)
if len(os.path.dirname(
modifiedPeptidesFile)) == 0 and len(analysisFolder) > 0:
modifiedPeptidesFile = os.path.join(analysisFolder,
modifiedPeptidesFile)
if len(modifiedPeptidesFile1) == 0:
modifiedPeptidesFile1 = os.path.join(
analysisFolder, analysisName + "_" + defaultModifiedPeptidesFile1 +
defaultTableExtension)
if len(os.path.dirname(
modifiedPeptidesFile1)) == 0 and len(analysisFolder) > 0:
modifiedPeptidesFile1 = os.path.join(analysisFolder,
modifiedPeptidesFile1)
if len(nonModifiedPep2ProtFile) == 0:
nonModifiedPep2ProtFile = os.path.join(
analysisFolder, analysisName + "_" +
defaultnonModifiedPeptidesFile + defaultTableExtension)
if len(os.path.dirname(
nonModifiedPep2ProtFile)) == 0 and len(analysisFolder) > 0:
nonModifiedPep2ProtFile = os.path.join(analysisFolder,
nonModifiedPep2ProtFile)
if len(relationsFile) == 0:
relationsFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultRelationsFile + defaultTableExtension)
if len(os.path.dirname(relationsFile)) == 0 and len(analysisFolder) > 0:
relationsFile = os.path.join(analysisFolder, relationsFile)
if len(os.path.dirname(varFile)) == 0 and len(
os.path.basename(varFile)) > 0:
varFile = os.path.join(analysisFolder, varFile)
if len(os.path.dirname(varFile1)) == 0 and len(
os.path.basename(varFile1)) > 0:
varFile1 = os.path.join(analysisFolder, varFile1)
if len(pep2protein) == 0:
pep2protein = os.path.join(
analysisFolder,
analysisName + "_" + defaultpep2protein + defaultTableExtension)
if len(os.path.dirname(pep2protein)) == 0 and len(analysisFolder) > 0:
pep2protein = os.path.join(analysisFolder, pep2protein)
# ************** reviewed up to here
# output
if len(outputFile) == 0:
outputFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultOutput + defaultTableExtension)
else:
if len(os.path.dirname(outputFile)) == 0:
outputFile = os.path.join(analysisFolder, outputFile)
if len(infoFile) == 0:
infoFile = os.path.join(
analysisFolder,
analysisName + "_" + defaultOutputInfo + defaultTableExtension)
logList.append(["Input modifiedPeptideFile " + str(modifiedPeptidesFile)])
logList.append(
["Input modifiedPeptideFile1 " + str(modifiedPeptidesFile1)])
logList.append(
["Input nonMod_PepTOpro_File " + str(nonModifiedPep2ProtFile)])
logList.append(["Input pep to protein file " + str(pep2protein)])
logList.append(["Input relations file: " + relationsFile])
logList.append(["Input varianceFile: " + varFile])
logList.append(["Input Second_varianceFile: " + varFile1])
logList.append(["Output stats file: " + outputFile])
logList.append(["Output info file: " + infoFile])
# pp.pprint(logList)
# sys.exit()
# END REGION: FILE NAMES SETUP
outputList = ZpCalculator(relationsFile=relationsFile,
modifiedPeptidesFile=modifiedPeptidesFile,
modifiedPeptidesFile1=modifiedPeptidesFile1,
nonModifiedPep2ProtFile=nonModifiedPep2ProtFile,
varFile=varFile,
varFile1=varFile1,
pep2protein=pep2protein,
outname=outputFile)
header = "idsup\tXsup\tVsup\tidinf\tXinf\tVinf\tn\tZ\tFDR" #"Sequence\tFASTAProteinDescription\tXp\tVp\tcount\tZp"
#######("Fix the header for Xp and Vp")
stats.saveFile(outputFile, outputList, header)
if len(infoFile) > 0:
stats.saveFile(infoFile, logList, "INFO FILE")