def main():
# Create the Tkinter dialog.
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createMultipleFileSelector(
"Bed Mutation File:", 0, "singlenuc_" + DataTypeStr.mutations + ".bed",
("Bed Files", ".bed"))
dialog.createDropdown("Expansion Context", 1, 0,
("Trinuc/Quadrunuc", "Pentanuc/Hexanuc"))
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
# Get the user's input from the dialog.
selections: Selections = dialog.selections
inputBedFilePaths = list(selections.getFilePathGroups())[
0] # A list of paths to original bed mutation files
expansionContext = list(selections.getDropdownSelections())[
0] # What context the file should be expanded to.
if expansionContext == "Trinuc/Quadrunuc":
expansionContextNum = 3
elif expansionContext == "Pentanuc/Hexanuc":
expansionContextNum = 5
else:
raise ValueError("Matching strings is hard.")
expandContext(inputBedFilePaths, expansionContextNum)
def main():
#Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createMultipleFileSelector("Custom bed Input Files:", 0,
"custom_input.bed",
("bed files", ".bed"))
dialog.createFileSelector("Genome Fasta File:", 1, ("Fasta Files", ".fa"))
dialog.createCheckbox("Stratify data by microsatellite stability?", 2, 0)
dialog.createCheckbox("Stratify by mutation signature?", 2, 1)
dialog.createCheckbox("Separate individual cohorts?", 3, 0)
dialog.createCheckbox("Only use single nucleotide substitutions?", 4, 0)
dialog.createCheckbox("Include indels in output?", 4, 1)
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
# Get the user's input from the dialog.
selections: Selections = dialog.selections
bedInputFilePaths = selections.getFilePathGroups()[0]
genomeFilePath = selections.getIndividualFilePaths()[0]
stratifyByMS = selections.getToggleStates()[0]
stratifyByMutSig = selections.getToggleStates()[1]
separateIndividualCohorts = selections.getToggleStates()[2]
onlySingleBaseSubs = selections.getToggleStates()[3]
includeIndels = selections.getToggleStates()[4]
parseCustomBed(bedInputFilePaths, genomeFilePath, stratifyByMS,
stratifyByMutSig, separateIndividualCohorts,
onlySingleBaseSubs, includeIndels)
def main():
#Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createMultipleFileSelector("Bed Mutation Files:", 0,
DataTypeStr.mutations + ".bed",
("Bed Files", ".bed"))
dialog.createDropdown(
"Background Context", 1, 0,
("Singlenuc/Dinuc", "Trinuc/Quadrunuc", "Pentanuc/Hexanuc"))
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
# Get the user's input from the dialog.
selections: Selections = dialog.selections
mutationFilePaths = list(selections.getFilePathGroups())[
0] # A list of paths to the bed mutation files
backgroundContext: str = list(selections.getDropdownSelections())[
0] # What context should be used to generate the background.
# Convert background context to int
if backgroundContext == "Singlenuc/Dinuc":
backgroundContextNum = 1
elif backgroundContext == "Trinuc/Quadrunuc":
backgroundContextNum = 3
elif backgroundContext == "Pentanuc/Hexanuc":
backgroundContextNum = 5
else:
raise ValueError("Matching strings is hard.")
generateMutationBackground(mutationFilePaths, backgroundContextNum)
def main():
#Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createMultipleFileSelector("ICGC Mutation Files:", 0, ".tsv.gz",
("gzip files", ".gz"))
dialog.createFileSelector("Genome Fasta File:", 1, ("Fasta Files", ".fa"))
dialog.createCheckbox("Create individual bed files for each donor.", 2, 0)
dialog.createCheckbox("Stratify results by microsatellite stability", 3, 0)
dialog.createCheckbox("Stratify results by mutation signature", 4, 0)
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
# Get the user's input from the dialog.
selections: Selections = dialog.selections
ICGCFilePaths = list(selections.getFilePathGroups())[
0] # A list of ICGC mutation file paths
genomeFilePath = list(selections.getIndividualFilePaths())[0]
separateDonors = list(selections.getToggleStates())[0]
stratifyByMS = list(selections.getToggleStates())[1]
stratifyByMutSig = list(selections.getToggleStates())[2]
parseICGC(ICGCFilePaths, genomeFilePath, separateDonors, stratifyByMS,
stratifyByMutSig)
def main():
# Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createMultipleFileSelector("Feature Files (e.g. mutations):", 0,
"bin_me.bed", ("Bed Files", ".bed"))
dialog.createFileSelector("Gene Designations:", 1, ("Bed Files", ".bed"))
dialog.createCheckbox("Color Domain is present in 7th (index=6) column", 2,
0)
flankDialog = dialog.createDynamicSelector(3, 0)
flankDialog.initCheckboxController(
"Gene designations include flanking regions")
flankSizeDialog = flankDialog.initDisplay(True, "FlankSize")
flankSizeDialog.createTextField("Flanking bin size:",
0,
0,
defaultText="0")
flankSizeDialog.createTextField("Flanking bin number:",
1,
0,
defaultText="0")
flankDialog.initDisplayState()
fileSuffixDialog = dialog.createDynamicSelector(4, 0)
fileSuffixDialog.initCheckboxController("Custom file suffix")
suffixDialog = fileSuffixDialog.initDisplay(True, "Suffix")
suffixDialog.createTextField("File Suffix:", 0, 0, defaultText="all_genes")
fileSuffixDialog.initDisplayState()
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
if dialog.selections.getToggleStates()[0]: colorColIndex = 6
else: colorColIndex = None
if flankDialog.getControllerVar():
flankBinSize = int(dialog.selections.getTextEntries("FlankSize")[0])
flankBinNum = int(dialog.selections.getTextEntries("FlankSize")[1])
else:
flankBinSize = 0
flankBinNum = 0
if fileSuffixDialog.getControllerVar():
fileSuffix = dialog.selections.getTextEntries("Suffix")[0]
else:
fileSuffix = ""
binInGenes(dialog.selections.getFilePathGroups()[0],
dialog.selections.getIndividualFilePaths()[0], flankBinSize,
flankBinNum, fileSuffix, colorColIndex)
def main():
#Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createMultipleFileSelector("Mutation Background Files:", 0,
DataTypeStr.mutBackground + ".tsv",
("Tab Seperated Values Files", ".tsv"))
dialog.createMultipleFileSelector("Nucleosome Map Files:", 1,
"nucleosome_map.bed",
("Bed Files", ".bed"))
selectSingleNuc = dialog.createDynamicSelector(2, 0)
selectSingleNuc.initCheckboxController(
"Generate background with a single nucleosome radius (73 bp)")
linkerSelectionDialog = selectSingleNuc.initDisplay(1, "singleNuc")
linkerSelectionDialog.createCheckbox(
"Include 30 bp linker DNA on either side of single nucleosome radius.",
0, 0)
selectSingleNuc.initDisplay(0)
selectSingleNuc.initDisplayState()
dialog.createCheckbox(
"Generate background with a nucleosome group radius (1000 bp)", 3, 0)
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
# Get the user's input from the dialog.
selections: Selections = dialog.selections
mutationBackgroundFilePaths = selections.getFilePathGroups()[
0] # A list of mutation file paths
nucleosomeMapNames = [
getIsolatedParentDir(nucleosomeMapFile)
for nucleosomeMapFile in selections.getFilePathGroups()[1]
]
if selectSingleNuc.getControllerVar():
useSingleNucRadius = True
includeLinker = selections.getToggleStates("singleNuc")[0]
else:
useSingleNucRadius = False
includeLinker = False
useNucGroupRadius = selections.getToggleStates()[0]
if includeLinker: linkerOffset = 30
else: linkerOffset = 0
generateNucleosomeMutationBackground(mutationBackgroundFilePaths,
nucleosomeMapNames,
useSingleNucRadius, useNucGroupRadius,
linkerOffset)
def main():
#Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createMultipleFileSelector(
"Background Nucleosome Mutation Counts Files:", 0,
DataTypeStr.nucMutBackground + ".tsv",
("Tab Seperated Values Files", ".tsv"))
customBackgroundSelector = dialog.createDynamicSelector(1, 0)
customBackgroundSelector.initCheckboxController(
"Include files with another data set as custom background.")
customBackgroundFileSelector = customBackgroundSelector.initDisplay(
True, "customBackground")
customBackgroundFileSelector.createMultipleFileSelector(
"Raw nucleosome counts to be normalized", 0,
DataTypeStr.rawNucCounts + ".tsv", ("TSV Files", ".tsv"))
customBackgroundFileSelector.createFileSelector(
"Data Directory for nucleosome counts to be used as background",
1,
directory=True)
customBackgroundSelector.initDisplayState()
dialog.createCheckbox(
"Include alternative scaling factor indepedent of nucleosome map.", 2,
0)
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
# Get the user's input from the dialog.
selections: Selections = dialog.selections
backgroundCountsFilePaths = selections.getFilePathGroups()[
0] # A list of background mutation counts file paths
if customBackgroundSelector.getControllerVar():
customRawCountsFilePaths = selections.getFilePathGroups(
"customBackground")[0]
customBackgroundCountsDir = selections.getIndividualFilePaths(
"customBackground")[0]
else:
customRawCountsFilePaths = None
customBackgroundCountsDir = None
includeAlternativeScaling = selections.getToggleStates()[0]
normalizeCounts(backgroundCountsFilePaths, customRawCountsFilePaths,
customBackgroundCountsDir, includeAlternativeScaling)
def main():
# Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createMultipleFileSelector("Bed Files:",0,"I_have_bad_chromosomes.bed",("Bed Files",".bed"))
dialog.createFileSelector("Genome Fasta File:",1,("Fasta Files",".fa"))
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
removeUnacceptableChromosomes(dialog.selections.getFilePathGroups()[0], dialog.selections.getIndividualFilePaths()[0])
def main():
# Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createFileSelector("RNAseq File:", 0, ("Bed Files", ".bed"))
dialog.createFileSelector("Gene Designations (color in 7th column):", 1,
("Bed Files", ".bed"))
# Run the UI
dialog.mainloop()
binRNASeqByChromatinDomainInGenes(
dialog.selections.getIndividualFilePaths()[0],
dialog.selections.getIndividualFilePaths()[1], 6)
def main():
# Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createFileSelector("H1 centers:",0,("Bed Files",".bed"))
dialog.createFileSelector("Nucleosome Dyad Center Positions:",1,("Bed Files",".bed"))
dialog.createFileSelector("Output File:",2,("TSV Files",".tsv"), newFile = True)
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
getNucleosomeH1Density(dialog.selections.getIndividualFilePaths()[0], dialog.selections.getIndividualFilePaths()[1],
dialog.selections.getIndividualFilePaths()[2])
def main():
#Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createMultipleFileSelector("Prepared Input Files:",0,DataTypeStr.mutations + ".bed",("bed files",".bed"))
dialog.createFileSelector("Genome Fasta File:",1,("Fasta Files",".fa"))
dialog.createCheckbox("Skip formatting checks for all but the first line",2,0)
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
# Get the user's input from the dialog.
parsePreparedInput(dialog.selections.getFilePathGroups()[0], dialog.selections.getIndividualFilePaths()[0],
not dialog.selections.getToggleStates()[0])
def main():
# Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createMultipleFileSelector("Genome Feature Positions Files:", 0,
"context_mutations.bed",
("Bed Files", ".bed"))
dialog.createFileSelector("Gene Ranges File (merged):", 1,
("Bed Files", ".bed"))
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
splitGenicAndIntergenic(dialog.selections.getFilePathGroups()[0],
dialog.selections.getIndividualFilePaths()[0])
def main():
# Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createFileSelector("Encompassing Feature File:", 0,
("Bed Files", ".bed"))
dialog.createFileSelector("Nucleosome Dyad Center Positions:", 1,
("Bed Files", ".bed"))
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
stratifyNucleosomesByEncompassment(
dialog.selections.getIndividualFilePaths()[0],
dialog.selections.getIndividualFilePaths()[1])
def main():
#Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createMultipleFileSelector("Mutation Files:", 0,
DataTypeStr.mutations + ".bed",
("Bed Files", ".bed"))
dialog.createMultipleFileSelector("Binding Motifs Files:", 1,
"binding_motifs.bed",
("Bed Files", ".bed"))
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
countInBindingMotifs(dialog.selections.getFilePathGroups()[0],
dialog.selections.getFilePathGroups()[1])
def main():
#Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createMultipleFileSelector("Tab-Separated Nucleosome Counts Files:",0,
DataTypeStr.generalNucCounts + ".tsv",("tsv files",".tsv"))
dialog.createMultipleFileSelector("R Nucleosome Mutation Analysis Files:",1,
".rda",("rda files",".rda"))
fileNumSelector = dialog.createDynamicSelector(2,0)
fileNumSelector.initCheckboxController("Export to one file (as opposed to one file for each graph)")
oneFileDialog = fileNumSelector.initDisplay(1, "oneFile")
oneFileDialog.createFileSelector("Export File", 0, ("pdf file",".pdf"), newFile = True)
manyFilesDialog = fileNumSelector.initDisplay(0, "manyFiles")
manyFilesDialog.createFileSelector("Export Directory", 0, directory = True)
fileNumSelector.initDisplayState()
dialog.createCheckbox("Omit Outliers", 3, 0)
dialog.createCheckbox("Smooth Nuc Group results", 3, 1)
dialog.createCheckbox("Strand align results", 4, 0)
#dialog.createCheckbox("Use normalized values from rda input", 5, 0)
#dialog.createCheckbox("Use raw values from rda input", 5, 1)
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
# Get the user's input from the dialog.
selections = dialog.selections
tsvFilePaths = selections.getFilePathGroups()[0]
rdaFilePaths = selections.getFilePathGroups()[1]
if fileNumSelector.getControllerVar(): exportPath = selections.getIndividualFilePaths("oneFile")[0]
else: exportPath = selections.getIndividualFilePaths("manyFiles")[0]
omitOutliers = bool(selections.getToggleStates()[0])
smoothNucGroup = bool(selections.getToggleStates()[1])
strandAlign = bool(selections.getToggleStates()[2])
generateFigures(tsvFilePaths, rdaFilePaths, exportPath, omitOutliers, smoothNucGroup,
strandAlign)
def main():
#Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createMultipleFileSelector("CPD Files:", 0, "CPD_data.bed",
("Bed Files", ".bed"))
dialog.createMultipleFileSelector("Deamination Files:", 1,
"deamination_data.bed",
("Bed Files", ".bed"))
dialog.createFileSelector("Genome Fasta File:", 2, ("Fasta File", ".fa"))
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
parseDeaminationData(dialog.selections.getFilePathGroups()[0],
dialog.selections.getFilePathGroups()[1],
dialog.selections.getIndividualFilePaths()[0])
def main():
# Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createFileSelector("Original Nucleosome Map Directory:",
0,
directory=True)
dialog.createMultipleFileSelector("Stratifying Feature Ranges:", 1,
"stratifying_feature_ranges.narrowPeak",
("Bed Files", ".bed"),
("Narrow Peak File", ".narrowPeak"))
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
stratifyNucleosomeMap(dialog.selections.getIndividualFilePaths()[0],
dialog.selections.getFilePathGroups()[0])
def main():
#Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createFileSelector("Data Set Directory:", 0, directory=True)
# TODO: Maybe allow for different cohort selections here. Right now, I'm assuming that we group MS data by mut sigs.
# This will probably work best if it communicates with the project manager to some capacity (what cohort data is available?)
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
# Get the user's input from the dialog.
selections: Selections = dialog.selections
dataSetDirectory = selections.getFilePaths()[0]
groupCohorts(dataSetDirectory)
def cleanDataDirectory(directory=getDataDirectory()):
itemsRemoved = 0
# Iterate through the given directory
for item in os.listdir(directory):
path = os.path.join(directory, item)
# When an intermediate_files directory is encountered, delete all the files within.
if item == "intermediate_files":
for itemToDelete in os.listdir(path):
pathToDelete = os.path.join(path, itemToDelete)
if os.path.isdir(pathToDelete): os.rmdir(pathToDelete)
else: os.remove(pathToDelete)
itemsRemoved += 1
# Recursively search any directories that are not intermediate directories
elif os.path.isdir(path):
itemsRemoved += cleanDataDirectory(path)
return itemsRemoved
def main():
# Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createMultipleFileSelector("Quartile Files:", 0, "quartile.tsv",
("Tab Separated Files", ".tsv"))
dialog.createFileSelector("Nucleosome Directory:", 1, directory=True)
dialog.createDropdown("Stratification Type", 2, 0, ["h1 density", "other"])
dialog.createCheckbox("Sloppy Copy?", 3, 0)
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
getQuartileNucleosomePositions(
dialog.selections.getFilePathGroups()[0],
dialog.selections.getIndividualFilePaths()[0],
dialog.selections.getDropdownSelections()[0].replace(' ', '_'),
dialog.selections.getToggleStates()[0])
def main():
# Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createMultipleFileSelector("Genome Feature Positions Files:", 0,
"context_mutations.bed",
("Bed Files", ".bed"))
dialog.createFileSelector("Nucleosome Dyad Center Positions:", 1,
("Bed Files", ".bed"))
dialog.createCheckbox("Only Count Linker", 2, 0)
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
countFeaturesAboutNucleosomes(
dialog.selections.getFilePathGroups()[0],
dialog.selections.getIndividualFilePaths()[0],
dialog.selections.getToggleStates()[0])
def main():
#Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createMultipleFileSelector("Mutation Files:", 0,
DataTypeStr.mutations + ".bed",
("Bed Files", ".bed"))
dialog.createFileSelector("Domain Range File:", 1, ("Bed File", ".bed"))
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
# Get the user's input from the dialog.
selections: Selections = dialog.selections
mutationFilePaths = selections.getFilePathGroups()[
0] # A list of mutation file paths
domainRangesFilePath = selections.getIndividualFilePaths()[
0] # The gene positions file path
separateByChromatinRegions(mutationFilePaths, domainRangesFilePath)
def main():
# Create the Tkinter dialog.
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createMultipleFileSelector("Bed Mutation Files:", 0,
DataTypeStr.mutations + ".bed",
("Bed Files", ".bed"))
dialog.createMultipleFileSelector("Nucleosome Map Files", 1,
"nucleosome_map.bed",
("Bed Files", ".bed"))
normalizationSelector = dialog.createDynamicSelector(2, 0)
normalizationSelector.initDropdownController(
"Normalization Method",
("No Normalization", "Singlenuc/Dinuc", "Trinuc/Quadrunuc",
"Pentanuc/Hexanuc", "Custom Background"))
customBackgroundFileSelector = normalizationSelector.initDisplay(
"Custom Background", "customBackground")
customBackgroundFileSelector.createFileSelector(
"Custom Background Directory:",
0, ("Bed Files", ".bed"),
directory=True)
customBackgroundFileSelector.createCheckbox("Generate Background now", 1,
0)
normalizationSelector.initDisplayState()
dialog.createCheckbox(
"Include alternative scaling factor indepedent of nucleosome map.", 3,
0)
dialog.createLabel('', 4, 0)
selectNucleosomeDyadRadius = dialog.createDynamicSelector(5, 0)
selectNucleosomeDyadRadius.initCheckboxController(
"Run analysis with a single nucleosome dyad radius (73 bp)")
linkerSelectionDialog = selectNucleosomeDyadRadius.initDisplay(
1, "singleNuc")
linkerSelectionDialog.createCheckbox(
"Include 30 bp linker DNA on either side of single nucleosome dyad radius.",
0, 0)
selectNucleosomeDyadRadius.initDisplayState()
dialog.createCheckbox("Count with a nucleosome group radius (1000 bp)", 6,
0)
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
# Get the user's input from the dialog.
selections: Selections = dialog.selections
mutationFilePaths = selections.getFilePathGroups()[
0] # A list of paths to bed mutation files
nucleosomeMapNames = [
getIsolatedParentDir(nucleosomeMapFile)
for nucleosomeMapFile in selections.getFilePathGroups()[1]
]
normalizationMethod = normalizationSelector.getControllerVar(
) # The normalization method to be used.
if normalizationMethod == "Custom Background":
customBackgroundDir = selections.getFilePaths("customBackground")[
0] # Where to find raw counts files to use as custom background
generateCustomBackgroundNow = selections.getToggleStates(
"customBackground"
)[0] # Whether or not to generate the custom background counts on the fly
else:
customBackgroundDir = None
generateCustomBackgroundNow = False
useSingleNucRadius = selectNucleosomeDyadRadius.getControllerVar(
) # Whether or not to generate data with a 73 bp single nuc dyad radius
if useSingleNucRadius:
includeLinker = selections.getToggleStates(
"singleNuc"
)[0] # Whether or not to include 30 bp linker DNA in nucleosome dyad positions
else:
includeLinker = False
useNucGroupRadius = selections.getToggleStates(
)[1] # Whether or not to generate data with a 1000 bp nuc group dyad radius
includeAlternativeScaling = selections.getToggleStates()[
0] # Whether or not to include scaling independent of nucleosome map
# If requested, generate the background counts file(s).
if generateCustomBackgroundNow:
generateCustomBackground(customBackgroundDir, nucleosomeMapNames,
useSingleNucRadius, includeLinker,
useNucGroupRadius)
runAnalysisSuite(mutationFilePaths, nucleosomeMapNames,
normalizationMethod, customBackgroundDir,
useSingleNucRadius, includeLinker, useNucGroupRadius,
includeAlternativeScaling)
xRSeqInputDataPipeline = XRSeqInputDataPipeline(inputDataFilePath, callParamsFilePath, genomeFilePath)
print("Generating trimmed reads bed file...")
xRSeqInputDataPipeline.generateTrimmedReads()
print("Locating and writing lesion locations to final output file...")
xRSeqOutputFilePaths.append(xRSeqInputDataPipeline.generateLesionsBedOutputFile())
# Send the output files to the custom bed parser.
parseCustomBed(xRSeqOutputFilePaths, genomeFilePath, False, False, False)
if __name__ == "__main__":
# Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createMultipleFileSelector("XR-seq bigwig data (plus strand):",0,
"+.bigWig",("BigWig Files",".bigWig"))
dialog.createMultipleFileSelector("XR-seq bed data (alternative to bigwig):",1,"aligned_reads.bed",
("Bed Files",".bed"), additionalFileEndings=("rep1.bed","rep2.bed"))
dialog.createFileSelector("Lesion Call Parameter File:", 2, ("Tab Seperated Values",".tsv"))
dialog.createFileSelector("Genome Fasta File:",3,("Fasta Files",".fa"))
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
def main():
#Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory(),
scrollable=True)
dialog.createMultipleFileSelector(
"Nucleosome Mutation Counts files:",
0,
DataTypeStr.normNucCounts + ".tsv",
("Tab Seperated Values Files", ".tsv"),
additionalFileEndings=(DataTypeStr.rawNucCounts + ".tsv", ))
dialog.createFileSelector("Output File",
1, ("R Data File", ".rda"),
("Tab Separated Values File", ".tsv"),
newFile=True)
dialog.createCheckbox(
"Use expected periodicity from nucleosome maps instead of peak periodicity",
2, 0)
dialog.createCheckbox(
"Align both DNA strands to run 5' to 3' before running the analysis",
3, 0)
dialog.createLabel('', 4, 0)
mainGroupSearchRefine = dialog.createDynamicSelector(5, 0)
mainGroupSearchRefine.initCheckboxController("Filter counts files")
mainGroupSearchRefine.initDisplay(True).createNucMutGroupSubDialog(
"MainGroup", 0)
mainGroupSearchRefine.initDisplayState()
periodicityComparison = dialog.createDynamicSelector(6, 0)
periodicityComparison.initCheckboxController(
"Compare periodicities between two groups")
periodicityGroupType = periodicityComparison.initDisplay(
True, "periodicityGroupType")
periodicityGroupTypeSelector = periodicityGroupType.createDynamicSelector(
0, 0)
periodicityGroupTypeSelector.initDropdownController(
"Compare periodicities...",
("Within original selection", "Against a newly selected group"))
periodicityGroupsWithin = periodicityGroupTypeSelector.initDisplay(
"Within original selection", "withinGroup")
secondaryPeriodicityGroup = periodicityGroupTypeSelector.initDisplay(
"Against a newly selected group", "secondaryGroupFilePaths")
# Create two "sub-dialogs" for each of the groups, allowing the user to specify the make-up of that group for the "withinGroup" dialog.
for i, dialogID in enumerate(("Sub-Group 1", "Sub-Group 2")):
periodicityGroupsWithin.createNucMutGroupSubDialog(dialogID, i + 1)
# Create one multiple file selector and one sub-dialog for the "secondaryGroup" dialog
secondaryPeriodicityGroup.createMultipleFileSelector(
"Nucleosome Mutation Counts files:",
0,
DataTypeStr.normNucCounts + ".tsv",
("Tab Seperated Values Files", ".tsv"),
additionalFileEndings=(DataTypeStr.rawNucCounts + ".tsv", ))
secondaryPeriodicityGroupSearchRefine = secondaryPeriodicityGroup.createDynamicSelector(
2, 0)
secondaryPeriodicityGroupSearchRefine.initCheckboxController(
"Filter counts files")
secondaryPeriodicityGroupSearchRefine.initDisplay(
True).createNucMutGroupSubDialog("Secondary Group", 0)
secondaryPeriodicityGroupSearchRefine.initDisplayState()
periodicityGroupTypeSelector.initDisplayState()
periodicityComparison.initDisplayState()
# Run the UI
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
# Get the user's input from the dialog.
selections: Selections = dialog.selections
nucleosomeMutationCountsFilePaths = selections.getFilePathGroups()[0]
if periodicityGroupTypeSelector.getControllerVar(
) == "Against a newly selected group":
secondaryNucMutCountsFilePaths = selections.getFilePathGroups(
"secondaryGroupFilePaths")[0]
outputFilePath = list(selections.getIndividualFilePaths())[0]
# Get the default periodicity value, testing the string to see if it is a valid float, if necessary.
overridePeakPeriodWithExpected = bool(selections.getToggleStates()[0])
alignStrands = bool(selections.getToggleStates()[1])
# If group comparisons were requested, get the respective groups.
filePathGroups: List[list] = list()
for i in range(3):
filePathGroups.append(list())
groups = ["MainGroup"]
if periodicityComparison.getControllerVar():
if periodicityGroupTypeSelector.getControllerVar(
) == "Within original selection":
groups += ("Sub-Group 1", "Sub-Group 2")
else:
groups.append("Secondary Group")
for i, dialogID in enumerate(groups):
# Was filtering even requested for the main group?
if i == 0 and not mainGroupSearchRefine.getControllerVar():
filePathGroups[0] = nucleosomeMutationCountsFilePaths
continue
# If we are examining the secondary group, check to see if filtering was even requested.
if dialogID == "Secondary Group" and not secondaryPeriodicityGroupSearchRefine.getControllerVar(
):
assert i == 1, "Secondary group encountered on unexpected iteration of for loop: " + str(
i)
filePathGroups[2] = secondaryNucMutCountsFilePaths
filePathGroups[1] = filePathGroups[0].copy()
filePathGroups[0] += filePathGroups[2]
continue
# Determine what normalization methods were requested
normalizationMethods = list()
normalizationSelections = selections.getToggleStates(dialogID)[:5]
if normalizationSelections[0]: normalizationMethods += (1, 2)
if normalizationSelections[1]: normalizationMethods += (3, 4)
if normalizationSelections[2]: normalizationMethods += (5, 6)
if normalizationSelections[3]: normalizationMethods.append(-1)
if normalizationSelections[4]: normalizationMethods.append(0)
# Determine what microsatellite stability states were requested.
acceptableMSCohorts = dict()
if selections.getToggleStates(dialogID)[7]:
MSSelection = selections.getDropdownSelections(dialogID + "MS")[0]
if MSSelection == "MSS": acceptableMSCohorts["MSS"] = None
elif MSSelection == "MSI": acceptableMSCohorts["MSI"] = None
else:
acceptableMSCohorts["MSS"] = None
acceptableMSCohorts["MSI"] = None
# Determine what mutation signature states were requested.
acceptableMutSigCohorts = dict()
if selections.getToggleStates(dialogID)[8]:
with open(
selections.getIndividualFilePaths(dialogID + "MutSig")[0],
'r') as mutSigsFile:
for line in mutSigsFile:
acceptableMutSigCohorts["mut_sig_" + line.strip()] = None
# Check for custom cohort input
acceptableCustomCohorts = dict()
if selections.getToggleStates(dialogID)[9]:
customCohortsFilePath = selections.getIndividualFilePaths(
dialogID + "CustomCohorts")[0]
with open(customCohortsFilePath, 'r') as customCohortsFile:
for line in customCohortsFile:
acceptableCustomCohorts[line.strip()] = None
# Check for nucleosome map input
acceptableNucleosomeMaps = dict()
if selections.getToggleStates(dialogID)[10]:
acceptableNucMapsFilePath = selections.getIndividualFilePaths(
dialogID + "NucleosomeMaps")[0]
with open(acceptableNucMapsFilePath, 'r') as acceptableNucMapsFile:
for line in acceptableNucMapsFile:
acceptableNucleosomeMaps[line.strip()] = None
# Get the file paths associated with the given parameters.
if dialogID != "Secondary Group":
filePathGroups[i] += getFilePathGroup(
nucleosomeMutationCountsFilePaths, normalizationMethods,
selections.getToggleStates(dialogID)[5],
selections.getToggleStates(dialogID)[6], acceptableMSCohorts,
acceptableMutSigCohorts, acceptableCustomCohorts,
acceptableNucleosomeMaps)
else:
assert i == 1, "Secondary group encountered on unexpected iteration of for loop: " + str(
i)
filePathGroups[2] += getFilePathGroup(
secondaryNucMutCountsFilePaths, normalizationMethods,
selections.getToggleStates(dialogID)[5],
selections.getToggleStates(dialogID)[6], acceptableMSCohorts,
acceptableMutSigCohorts, acceptableCustomCohorts,
acceptableNucleosomeMaps)
filePathGroups[1] = filePathGroups[0].copy()
filePathGroups[0] += filePathGroups[2]
#If this is the first pass through the loop, set the file paths list to the newly filtered list.
if i == 0: nucleosomeMutationCountsFilePaths = filePathGroups[0]
runNucleosomeMutationAnalysis(filePathGroups[0], outputFilePath,
overridePeakPeriodWithExpected, alignStrands,
filePathGroups[1], filePathGroups[2])
