def replaceRelations(relations, FASTAHeaders = []): newRelations = [] relationsSorted = stats.sortByIndex(relations, 1) FASTAHeadersSorted = stats.sortByIndex(FASTAHeaders, 0) if len(FASTAHeadersSorted) > 0: for relation in relationsSorted: element = relation[1] searchResult = stats.filterByElement(FASTAHeadersSorted, element, index = 0, sort = False) if len(searchResult) > 0: newRelations.append([relation[0], searchResult[0][1]]) else: return relationsSorted return newRelations
def associateElements(inStats = "", uFile = "", relFile = ""):
results = []
relations = stats.loadRelationsFile(relFile)
relations = stats.sortByIndex(relations, 0)
statsData = stats.loadStatsDataFile(inStats)
ZijList = []
for element in statsData:
ZijList.append([element[3], element[7]])
theorList = []
experList = []
N = len(ZijList)
for i in range(N):
theorList.append([ZijList[i][0], ZijList[i][1], norm.cdf(float(ZijList[i][1]))])
experList.append([ZijList[i][0], ZijList[i][1], (float(i) + 0.5) / float(N)])
higherElements = stats.load2stringList(uFile, removeCommas = True)
# WARNING! higherElements must be a list of lists
# with each sublist being id, n, Z, FDR, X
# begin: jmrc
if not higherElements:
sms = "ERROR: higherElements is empty. The higherElements must be a list of lists with each sublist being id, n, Z, FDR, X"
sys.exit(sms)
# end: jmrc
elementList = []
if higherElements[0] == ['id', 'Z', 'n']:
# this means the list comes from SanXoTSqueezer
# so the header and the extra columns have to be removed
for element in higherElements[1:]:
# switch to id, n, Z, FDR
elementList.append([element[0], element[2], element[1], float("nan"), float("nan")])
if higherElements[0] == ['id', 'n', 'Z', 'FDR']:
# this means it does not contain X, so a nan is put on its place
for element in higherElements[1:]:
elementList.append([element[0], element[1], element[2], element[3], float("nan")])
if higherElements[0] == ['id', 'n', 'Z', 'FDR', 'X']:
for element in higherElements[1:]:
elementList.append([element[0], element[1], element[2], element[3], element[4]])
# otherwise
if higherElements[0] != ['id', 'Z', 'n'] and higherElements[0] != ['id', 'n', 'Z', 'FDR'] and higherElements[0] != ['id', 'n', 'Z', 'FDR', 'X']:
for element in higherElements:
elementList.append([element[0], float("nan"), float("nan"), float("nan"), float("nan")])
statsData = stats.sortByIndex(statsData, 7)
relationsFirstColumn = stats.extractColumns(relations, 0)
relationsSecondColumn = stats.extractColumns(relations, 1)
experListFirstColumn = stats.extractColumns(experList, 0)
for uElement in elementList:
lowerElementList = []
first = stats.firstIndex(relationsFirstColumn, uElement[0])
if first > -1: # -1 means it is not in the list
notInList = 0
last = stats.lastIndex(relationsFirstColumn, uElement[0])
lowerElements = relationsSecondColumn[first:last + 1] # "+1" is to include the last one
for element in lowerElements:
lowerIndex = stats.firstIndex(experListFirstColumn, element)
if lowerIndex > -1: # -1 means it is not in the list
lowerElementList.append(element)
else:
notInList += 1
lowerElementList = stats.sortByIndex(lowerElementList, 0)
results.append([uElement[0], lowerElementList])
else:
if len(uElement[0].strip()) > 0:
results.append([uElement[0], None])
return results, elementList, ""
def getMADDistribution(nextIdX,
mergedData,
k,
variance,
alpha,
medianSide=100,
showGraph=False,
verbose=False):
MADconstant = 1.48260221850560 # *** 1 / DISTR.NORM.ESTAND.INV(3 / 4) get exact number
MADDistribution = []
distrWeight = []
# inputSequences = extractColumns(input, 0)
# outputSequences = extractColumns(output, 0)
newlist = []
for orow in nextIdX:
sequence = orow[0]
# it is important to avoid sorting to keep it fast
# so in next line do not foget sort = False
# this should arrive here already sorted
scanListWithSequence = stats.filterByElement(mergedData,
sequence,
sort=False)
if len(scanListWithSequence
) > 1: # otherwise Xi = Xj --> Xi - Xj = 0 --> does not work
for scanRow in scanListWithSequence:
newrow = []
weight = scanRow[3] # the V
degreesOfFreedom = len(scanListWithSequence)
XiXj = scanRow[2] - orow[1]
newrow.append(sequence) # sequence = 0
newrow.append(scanRow[1]) # scan number = 1
newrow.append(XiXj) # Xi - Xj = 2
newrow.append(weight) # weight = 3
newrow.append(
len(scanListWithSequence)) # degrees of freedom = 4
newrow.append(
fabs(XiXj) * sqrt(
float(degreesOfFreedom) /
(float(degreesOfFreedom - 1)))) # = 5
newrow.append(0) # space to save the median = 6
newrow.append(0) # space to save the MAD formula = 7
newlist.append(newrow)
newlist = stats.sortByIndex(newlist, 3) # sort by weight
# get median + rank
nextlist = []
counter = 0
if len(newlist) < medianSide * 2:
if verbose:
print('Not enough data to perform statistics,')
print('len(newlist) = %s, while medianSide = %s' %
(str(len(newlist)), str(medianSide)))
sys.exit()
for i in range(len(newlist))[medianSide:len(newlist) - medianSide]:
window = newlist[i - medianSide:i + medianSide + 1]
median = stats.medianByIndex(window, 5)
newlist[i][6] = median
# fill the borders
for i in range(len(newlist))[:medianSide]:
newlist[i][6] = newlist[medianSide + 1][6]
for i in range(len(newlist))[len(newlist) - medianSide:]:
newlist[i][6] = newlist[len(newlist) - medianSide - 1][6]
# fill MAD formula
for i in range(len(newlist)):
newlist[i][7] = 1 / (MADconstant * newlist[i][6])**2
MADDistribution.append(newlist[i][7])
distrWeight.append(newlist[i][3])
if verbose:
print('k = %f, var = %f' % (k, variance))
return MADDistribution, distrWeight
def getMADDistribution(nextIdX,
mergedData,
k,
variance,
alpha,
medianSide = 100,
showGraph = False,
verbose = False):
MADconstant = 1.48260221850560 # *** 1 / DISTR.NORM.ESTAND.INV(3 / 4) get exact number
MADDistribution = []
distrWeight = []
# inputSequences = extractColumns(input, 0)
# outputSequences = extractColumns(output, 0)
newlist = []
for orow in nextIdX:
sequence = orow[0]
# it is important to avoid sorting to keep it fast
# so in next line do not foget sort = False
# this should arrive here already sorted
scanListWithSequence = stats.filterByElement(mergedData, sequence, sort = False)
if len(scanListWithSequence) > 1: # otherwise Xi = Xj --> Xi - Xj = 0 --> does not work
for scanRow in scanListWithSequence:
newrow = []
weight = scanRow[3] # the V
degreesOfFreedom = len(scanListWithSequence)
XiXj = scanRow[2] - orow[1]
newrow.append(sequence) # sequence = 0
newrow.append(scanRow[1]) # scan number = 1
newrow.append(XiXj) # Xi - Xj = 2
newrow.append(weight) # weight = 3
newrow.append(len(scanListWithSequence)) # degrees of freedom = 4
newrow.append(fabs(XiXj) * sqrt(float(degreesOfFreedom) / (float(degreesOfFreedom - 1)))) # = 5
newrow.append(0) # space to save the median = 6
newrow.append(0) # space to save the MAD formula = 7
newlist.append(newrow)
newlist = stats.sortByIndex(newlist, 3) # sort by weight
# get median + rank
nextlist = []
counter = 0
if len(newlist) < medianSide * 2:
if verbose:
print('Not enough data to perform statistics,')
print('len(newlist) = %s, while medianSide = %s' % (str(len(newlist)), str(medianSide)))
sys.exit()
for i in range(len(newlist))[medianSide:len(newlist) - medianSide]:
window = newlist[i - medianSide:i + medianSide + 1]
median = stats.medianByIndex(window, 5)
newlist[i][6] = median
# fill the borders
for i in range(len(newlist))[:medianSide]:
newlist[i][6] = newlist[medianSide + 1][6]
for i in range(len(newlist))[len(newlist) - medianSide:]:
newlist[i][6] = newlist[len(newlist) - medianSide - 1][6]
# fill MAD formula
for i in range(len(newlist)):
newlist[i][7] = 1 / (MADconstant * newlist[i][6]) ** 2
MADDistribution.append(newlist[i][7])
distrWeight.append(newlist[i][3])
if verbose:
print('k = %f, var = %f' % (k, variance))
return MADDistribution, distrWeight
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 = "v0.05"
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 getRels(qcInputFile = "", listChangingCats = [], qcInputNoOutsFile = "", modeSanXoTSieve = "newWay", caseSensitive = True, outlierTag = "out"): qcInputRawList = [] qcInput = [] qcInputNoOutsRawList = [] qcInputNoOuts = [] numRelsChangingCats = 0 numOutliersChangingCats = 0 numOutliersNonChangingCats = 0 # lists of lists for filterByElement, needed to speed it up qcInputSortedList = [] qcInputNoOutsSortedList = [] listChangingCatsList = [] listChangingCatsSortedList = [] # when no qcInputFileNoOuts file is present, the newWay option is used # this has already been sorted previously, but just in case... if len(qcInputNoOutsFile) == 0: modeSanXoTSieve = "newWay" qcInputRawList = stats.loadStatsDataFile(qcInputFile, FDRasText = True, ZasText = True, includeTags = True) # next line is needed to nest list within list and make it work with the filterByElement method for cat in listChangingCats: if caseSensitive: listChangingCatsList.append([cat]) else: listChangingCatsList.append([cat.lower()]) # important NOT to sort listChangingCats, as this is not a list of lists and # sorting would only affect the first character instead of the first string listChangingCatsSortedList = stats.sortByIndex(listChangingCatsList, 0) # get list of rels # next line is needed to nest list within list and make it work with the filterByElement method for qc in qcInputRawList: if caseSensitive: qcInput.append([[qc[0], qc[3], qc[9]]]) else: qcInput.append([[qc[0].lower(), qc[3].lower(), qc[9]]]) qcInputSortedList = stats.sortByIndex(qcInput, 0) if modeSanXoTSieve == "newWay": for qc in qcInputSortedList: if len(stats.filterByElement(listChangingCatsSortedList, qc[0][0], sort = False)) > 0: # get list of rels pointing to changing cats # get outlier rels numRelsChangingCats += 1 if stats.tagIsPresent(qc[0][2], outlierTag): numOutliersChangingCats += 1 else: # relations pointing to non changing cats if stats.tagIsPresent(qc[0][2], outlierTag): # outliers pointing to non changing cats numOutliersNonChangingCats += 1 if modeSanXoTSieve == "oldWay": # quitar si sale bien sacándolo fuera # # next line is needed to nest list within list and make it work with the filterByElement method # for qc in qcInputRawList: # # if modeSanXoTSieve == "oldWay" and len(qc) # if caseSensitive: # qcInput.append([[qc[0], qc[3]]]) # else: # qcInput.append([[qc[0].lower(), qc[3].lower()]]) # qcInputSortedList = stats.sortByIndex(qcInput, 0) if len(qcInputNoOutsFile) > 0: qcInputNoOutsRawList = stats.loadStatsDataFile(qcInputNoOutsFile, FDRasText = True, ZasText = True, includeTags = False) # next line is needed to nest list within list and make it work with the filterByElement method for qcno in qcInputNoOutsRawList: if caseSensitive: qcInputNoOuts.append([[qcno[0], qcno[3]]]) else: qcInputNoOuts.append([[qcno[0].lower(), qcno[3].lower()]]) qcInputNoOutsSortedList = stats.sortByIndex(qcInputNoOuts, 0) print print "calculating with %i relations and %i changing categories..." % (len(qcInputSortedList), len(listChangingCats)) for qc in qcInputSortedList: # better do not use something like "if x in list..." because that is quite slow if len(stats.filterByElement(listChangingCatsSortedList, qc[0][0], sort = False)) > 0: # is the category qc[0] in listChangingCatsSorted? If no --> 0 # this relation points to a changing category numRelsChangingCats += 1 if len(stats.filterByElement(qcInputNoOutsSortedList, qc[0][0:2], sort = False)) == 0: # is the relation qc in qcInputNoOuts? If no --> 0 # this relation is an outlier in a changing category # the [0:2] part is to remove the space for tags numOutliersChangingCats += 1 else: # this relation points to a non-changing category if len(stats.filterByElement(qcInputNoOutsSortedList, qc[0][0:2], sort = False)) == 0: # is the relation qc in qcInputNoOuts? If no --> 0 # this relation is an outlier in a non-changing category numOutliersNonChangingCats += 1 return numRelsChangingCats, numOutliersChangingCats, numOutliersNonChangingCats
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")