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("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():
with TkinterDialog(workingDirectory = getDataDirectory()) as dialog:
dialog.createMultipleFileSelector("Sam Files:", 0, ".sam", ("Sam Files",(".sam.gz",".sam")),
additionalFileEndings = ".sam.gz")
trimmedFastqToSam(dialog.selections.getFilePathGroups()[0])
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 a simple dialog for selecting the gene designation files.
with TkinterDialog(workingDirectory=getDataDirectory()) as dialog:
dialog.createMultipleFileSelector("Bed formatted reads:", 0, ".bed",
("Bed Files", ".bed"))
trimDuplicateReads(dialog.selections.getFilePathGroups()[0])
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():
with TkinterDialog(workingDirectory=getDataDirectory()) as dialog:
dialog.createMultipleFileSelector("Raw fastq reads:", 0, ".fastq.gz",
("Gzipped fastq Files", ".fastq.gz"))
dialog.createFileSelector("Adaptor Sequences:", 1,
("Fasta Files", ".fa"))
trimAdaptorSequences(dialog.selections.getFilePathGroups()[0],
dialog.selections.getIndividualFilePaths()[0])
def main():
# Create the Tkinter UI
dialog = TkinterDialog(workingDirectory=getDataDirectory())
dialog.createFileSelector("Bed Mutation Data:", 0, ("Bed Files", ".bed"))
dialog.createFileSelector("TFBS 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()
recordMutationsInTFBSs(dialog.selections.getIndividualFilePaths()[0],
dialog.selections.getIndividualFilePaths()[1],
dialog.selections.getIndividualFilePaths()[2])
def main():
dialog = TkinterDialog(workingDirectory=os.path.dirname(__file__))
dialog.createFileSelector("Colored Gene Designations:", 0, ("Bed File",".bed"))
dialog.createFileSelector("Colorless Gene Data (e.g. RPKM)", 1, ("Tab separated files",".tsv"))
dialog.mainloop()
# If no input was received (i.e. the UI was terminated prematurely), then quit!
if dialog.selections is None: quit()
assignToDomainByGene(dialog.selections.getIndividualFilePaths()[0],
dialog.selections.getIndividualFilePaths()[1])
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=os.path.dirname(__file__))
dialog.createMultipleFileSelector("Genome Feature Files:", 0,
DataTypeStr.mutations + ".bed",
("Bed Files", ".bed"))
dialog.createFileSelector("Chromosome Sizes File:", 1,
("Text File", ".txt"))
dialog.createDropdown("Bin Size (bp):", 2, 0,
("1000", "10000", "100000", "1000000"))
# 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()
binAcrossGenome(dialog.selections.getFilePathGroups()[0],
dialog.selections.getIndividualFilePaths()[0],
int(dialog.selections.getDropdownSelections()[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("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 getDataDirectory():
# Check for the text file which should contain the path to the data directory.
dataDirectoryTextFilePath = os.path.join(os.getenv("HOME"), ".mutperiod",
"data_dir.txt")
# If it exists, return the directory path within.
if os.path.exists(dataDirectoryTextFilePath):
with open(dataDirectoryTextFilePath, 'r') as dataDirectoryTextFile:
dataDirectory = dataDirectoryTextFile.readline().strip()
# Double check to make sure the data directory is still intact.
# If it isn't, inform the user, and progress through the function to recreate it.
if not os.path.exists(dataDirectory):
print(
"Data directory not found at expected location: {}".format(
dataDirectory))
print(
"Please select a new location to create a data directory.")
else:
return dataDirectory
else:
# Create a simple dialog to select a new data directory location.
from benbiohelpers.TkWrappers.TkinterDialog import TkinterDialog, Selections
checkDirs(os.path.dirname(dataDirectoryTextFilePath))
dialog = TkinterDialog(
workingDirectory=os.path.dirname(dataDirectoryTextFilePath))
dialog.createFileSelector("Location to create new data directory:",
0, ("Fasta Files", ".fa"),
directory=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()
selections: Selections = dialog.selections
dataDirectoryDirectory = selections.getIndividualFilePaths()[0]
# Make sure a valid, writeable directory was given. Then create the new directory (if it doesn't exist already),
# write it to the text file, and return it! (Also create the __external_data directory.)
if not os.path.exists(dataDirectoryDirectory):
raise UserInputError("Given directory: " + dataDirectoryDirectory +
" does not exist.")
dataDirectory = os.path.join(dataDirectoryDirectory, "mutperiod_data")
try:
checkDirs(dataDirectory)
checkDirs(os.path.join(dataDirectory, "__external_data"))
except IOError:
raise InvalidPathError(
dataDirectoryDirectory,
"Given location for data directory is not writeable:")
with open(dataDirectoryTextFilePath, 'w') as dataDirectoryTextFile:
dataDirectoryTextFile.write(dataDirectory + '\n')
return dataDirectory
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("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("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 a simple dialog for selecting the gene designation files.
dialog = TkinterDialog(workingDirectory=os.path.dirname(__file__))
dialog.createFileSelector("Bed File:", 0, ("bed file", ".bed"))
dialog.mainloop()
if dialog.selections is None: quit()
expandToBothStrands(dialog.selections.getIndividualFilePaths()[0], )
def main():
with TkinterDialog(workingDirectory = getDataDirectory()) as dialog:
dialog.createMultipleFileSelector("Trimmed fastq reads:", 0, "trimmed.fastq.gz",
("Gzipped fastq Files", ".fastq.gz"))
dialog.createFileSelector("Bowtie2 Index File (Any):", 1, ("Bowtie2 Index File", ".bt2"))
with dialog.createDynamicSelector(2, 0) as bowtie2BinaryDS:
bowtie2BinaryDS.initCheckboxController("Choose alternative bowtie2 binary")
bowtie2BinarySelector = bowtie2BinaryDS.initDisplay(True, selectionsID = "bowtieBinary")
bowtie2BinarySelector.createFileSelector("bowtie2 binary:", 0, ("Any File", "*"))
dialog.createDropdown("Number of CPU threads to use:", 3, 0, ('1', '2', '3', '4'))
with dialog.createDynamicSelector(4, 0) as customArgsDS:
customArgsDS.initDropdownController("Custom Bowtie2 Arguments:", ("None", "From File", "Direct Input"))
customArgsDS.initDisplay("From File", selectionsID = "customArgs").createFileSelector(
"Custom Arguments File:", 0, ("Text File", ".txt")
)
customArgsDS.initDisplay("Direct Input", selectionsID = "customArgs").createTextField(
"Custom Arguments:", 0, 0, defaultText = ''
)
fastqFilePaths = dialog.selections.getFilePathGroups()[0]
bowtie2IndexBasenamePath: str = dialog.selections.getIndividualFilePaths()[0]
bowtie2IndexBasenamePath = bowtie2IndexBasenamePath.rsplit('.', 2)[0]
if bowtie2IndexBasenamePath.endswith(".rev"): bowtie2IndexBasenamePath = bowtie2IndexBasenamePath.rsplit('.', 1)[0]
if bowtie2BinaryDS.getControllerVar():
bowtie2BinaryPath = dialog.selections.getIndividualFilePaths("bowtieBinary")[0]
else: bowtie2BinaryPath = None
threads = dialog.selections.getDropdownSelections()[0]
if customArgsDS.getControllerVar() == "None":
customBowtie2Arguments = ''
elif customArgsDS.getControllerVar() == "From File":
customBowtie2ArgsFilePath = dialog.selections.getIndividualFilePaths("customArgs")[0]
with open(customBowtie2ArgsFilePath, 'r') as customBowtie2ArgsFile:
customBowtie2Arguments = customBowtie2ArgsFile.readline().strip()
elif customArgsDS.getControllerVar() == "Direct Input":
customBowtie2Arguments = dialog.selections.getTextEntries("customArgs")[0]
trimmedFastqToSam(fastqFilePaths, bowtie2IndexBasenamePath,
bowtie2BinaryPath, threads, customBowtie2Arguments)
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.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=os.path.dirname(__file__))
dialog.createFileSelector("Spivakov File:", 0, ("Text File", ".txt"))
# 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()
parseSpivakovToBed(dialog.selections.getIndividualFilePaths()[0])
def main():
# Create the UI.
with TkinterDialog(workingDirectory=getDataDirectory()) as dialog:
dialog.createFileSelector("SRA run accession IDs:", 0,
("text file", ".txt"))
with dialog.createDynamicSelector(1, 0) as namesDynSel:
namesDynSel.initCheckboxController("Specify Custom Names:")
namesDynSel.initDisplay(True, "namesFilePath").createFileSelector(
"Names File:", 0, ("text file", ".txt"))
# Retrieve values from user input.
selections = dialog.selections
if namesDynSel.getControllerVar():
namesFilePath = selections.getIndividualFilePaths("namesFilePath")[0]
else:
namesFilePath = None
sRA_ToFastq(selections.getIndividualFilePaths()[0], namesFilePath)
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 UI
dialog = TkinterDialog(workingDirectory=os.path.dirname(__file__))
dialog.createFileSelector("Chromatin Domains File:", 0,
("Bed Files", ".bed"))
binnerTypeDS = dialog.createDynamicSelector(1, 0)
binnerTypeDS.initDropdownController("Bins are...",
("Regular", "Specific Ranges"))
regularBinsDialog = binnerTypeDS.initDisplay("Regular", "Regular")
specificRangeBinsDialog = binnerTypeDS.initDisplay("Specific Ranges",
"Specific Ranges")
regularBinsDialog.createFileSelector("Chromosome Sizes File:", 0,
("Text File", ".txt"))
regularBinsDialog.createDropdown("Bin Size (bp):", 1, 0,
("1000", "10000", "100000", "1000000"))
specificRangeBinsDialog.createFileSelector("Ranges to bin:", 0,
("Bed File", ".bed"))
binnerTypeDS.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 binnerTypeDS.getControllerVar() == "Regular":
determineRegularBinColors(
dialog.selections.getIndividualFilePaths()[0],
dialog.selections.getIndividualFilePaths("Regular")[0],
int(dialog.selections.getDropdownSelections("Regular")[0]))
elif binnerTypeDS.getControllerVar() == "Specific Ranges":
determineSpecifiedBinColors(
dialog.selections.getIndividualFilePaths()[0],
dialog.selections.getIndividualFilePaths("Specific Ranges")[0])
def main():
with TkinterDialog(workingDirectory = getDataDirectory()) as dialog:
dialog.createMultipleFileSelector("Bed files of aligned data:", 0, "aligned_reads.bed",
("Bed Files", ".bed"))
dialog.createFileSelector("Genome fasta file (If bed files are provided)", 1,
("Fasta File", ".fa"))
dialog.createMultipleFileSelector("Fasta files of aligned data:", 2, "aligned_reads.fa",
("Fasta Files", ".fa"))
dialog.createCheckbox("Count individual bases", 3, 0)
dialog.createCheckbox("Count dipys", 3, 1)
dialog.createCheckbox("Record second-most enriched positions", 4, 0)
# Get the input for the findEnrichedIndices function
bedFilePaths = dialog.selections.getFilePathGroups()[0]
genomeFastaFilePath = dialog.selections.getIndividualFilePaths()[0]
fastaFilePaths = dialog.selections.getFilePathGroups()[1]
countIndividualBases = dialog.selections.getToggleStates()[0]
countDipys = dialog.selections.getToggleStates()[1]
getSecondPlace = dialog.selections.getToggleStates()[2]
findEnrichedIndices(bedFilePaths, genomeFastaFilePath, fastaFilePaths,
countIndividualBases, countDipys, getSecondPlace)
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 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 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()
