def assignIODirectories(self):
assignConfigurationValue('input_directory', self.inputDirectoryText.get())
assignConfigurationValue('output_directory', self.outputDirectoryText.get())
assignConfigurationValue('log_file_location', join(self.outputDirectoryText.get(), 'nanopore-prospector-log.txt'))
assignConfigurationValue('report_file_location', join(self.outputDirectoryText.get(), 'AnalysisReport.txt'))
#self.consensusSequenceFileName = join(self.outputDirectoryText.get(), 'Consensus.fasta')
self.recordAnalysisStep('Initialized Nanopore Prospector Log File')
self.recordAnalysisStep('Read Input Directory:' + getConfigurationValue('input_directory'))
self.recordAnalysisStep('Analysis Output Directory:' + getConfigurationValue('output_directory'))
def reportResults(self, currentMessage):
# This Report is intended to Summarize the prospector / allele calling results.
fullReportMessage = currentMessage + '\n'
if (getConfigurationValue('report_file_location') is None):
print ('The report file name does not exist yet.\nTrying to report this message:\n' + currentMessage)
else:
#print ('Logging message: ' + currentMessage)
# Append the log with the log entry
resultsOutput = open(getConfigurationValue('report_file_location'), 'a')
resultsOutput.write(fullReportMessage)
resultsOutput.close()
def logBlastProgress(blastLogText):
# If we have a log file location from Global Variables, we can use that.
# Otherwise print output to the console.
if getConfigurationValue('log_file_location') is not None:
logMessageToFile(blastLogText)
else:
print(str(blastLogText))
def sortByLocus(self):
self.recordAnalysisStep('Step 2.) Sort reads by HLA Locus')
self.disableGUI()
# TODO: What if it's demultiplexed?
# I should sort each barcode.
# Make a loop, find barcodes, sort each one in a subrdirectory
# What if i use some other sample ID, other than READS
# TODO: Look for fastq files dynamically in output directory.
#sampleID = 'READS'
# TODO: I need to rethink how to handle sampleID when I am demultiplexing.
# I can handle one sample one folder.
# TODO: threadCount should be a parameter somewhere.
# Specified in the options, probably.
threadCount = 4
#preparedReadsInputFile = join(join(self.outputDirectoryText.get(), '1_prepared_reads'),sampleID + '_Pass.fastq')
preparedReadsInput = join(self.outputDirectoryText.get(), '1_prepared_reads')
#sortedReadsOutputDirectory = join(join(self.outputDirectoryText.get(), '2_sorted_reads'), sampleID)
sortedReadsOutputDirectory = join(self.outputDirectoryText.get(), '2_sorted_reads')
if not exists(sortedReadsOutputDirectory):
makedirs(sortedReadsOutputDirectory)
# TODO: Make more than one gene references. Split by locus.
# Fine. That's what I'm doing.
# Make a list of the reference files I need.
referenceFileList = []
print('the configuration value for analyze_hla_a is:' + str(getConfigurationValue('analyze_hla_a')))
if(str(getConfigurationValue('analyze_hla_a')) == '1'):
referenceFileList.append(getBlastSortResourceLocation('HLA_A_BlastReference.fasta'))
if(str(getConfigurationValue('analyze_hla_b')) == '1'):
referenceFileList.append(getBlastSortResourceLocation('HLA_B_BlastReference.fasta'))
if(str(getConfigurationValue('analyze_hla_c')) == '1'):
referenceFileList.append(getBlastSortResourceLocation('HLA_C_BlastReference.fasta'))
if(str(getConfigurationValue('analyze_hla_e')) == '1'):
referenceFileList.append(getBlastSortResourceLocation('HLA_E_BlastReference.fasta'))
if(str(getConfigurationValue('analyze_hla_dra')) == '1'):
referenceFileList.append(getBlastSortResourceLocation('HLA_DRA_BlastReference.fasta'))
if(str(getConfigurationValue('analyze_hla_dqa1')) == '1'):
referenceFileList.append(getBlastSortResourceLocation('HLA_DQA1_BlastReference.fasta'))
if(str(getConfigurationValue('analyze_hla_dqb1')) == '1'):
referenceFileList.append(getBlastSortResourceLocation('HLA_DQB1_BlastReference.fasta'))
if(str(getConfigurationValue('analyze_hla_drb1')) == '1'):
referenceFileList.append(getBlastSortResourceLocation('HLA_DRB1_BlastReference.fasta'))
print('I found this many blast references:' + str(len(referenceFileList)))
sortReferencePath = combineBlastReferences(referenceFileList, join(self.outputDirectoryText.get(), 'blast_sort_reference'))
# the key is the name of the file analyzed.
# The value is a list of minion_read_collections, pertaining to what gene they sorted to.
sortResults = sortDirectory(preparedReadsInput, sortedReadsOutputDirectory, sortReferencePath, threadCount)
# Report the BLAST sorting results in the results summary.
self.reportResults('Read Sorting:\n')
# Loop through the analyzed read files (probably just one here)
for analyzedReadResult in sortResults.keys():
#print ('Looking at this read collection key:' + analyzedReadResult)
blastGeneList = sortResults[analyzedReadResult]
#print ('Looking at this list of sorted read groups\n:' + str(blastGeneList))
self.reportResults(analyzedReadResult + ':')
# loop through each entry in this
for genewiseSortedReadGroup in blastGeneList:
if (genewiseSortedReadGroup.gene is None):
self.reportResults('Unsorted: ' + str(len(genewiseSortedReadGroup.readCollection)) + ' reads.')
else:
self.reportResults('HLA-' + str(genewiseSortedReadGroup.gene) + ': ' + str(len(genewiseSortedReadGroup.readCollection)) + ' reads.')
self.reportResults('')
self.recordAnalysisStep('Done sorting reads by HLA Locus')
self.enableGUI()
def constructInitialReadStats(self):
self.recordAnalysisStep('Step 1.) Calculating initial read stats')
self.disableGUI()
# Set the input and output directories
self.assignIODirectories()
writeConfigurationFile()
# Run nit-picker for output directory
# TODO: fix these parameters, especially sample ID.
# TODO: RUn this in a thread, so the GUI can update.
preparedReadsOutputDirectory = join(getConfigurationValue('output_directory'), '1_prepared_reads')
#if(self.demultiplexReads):
# sampleID = 'READS'
#else:
# sampleID = 'READS'
# TODO: I am always using the leaf directory name. Does this work for multiplexed and demultiplexed samples?
#self.inputDirectoryText.set(currentInputDirectory)
#parentDir = abspath(join(currentInputDirectory, os.pardir))
leafDirName = basename(normpath(self.inputDirectoryText.get()))
sampleID = leafDirName
# suggestedOutputDirectory = join(parentDir,leafDirName + '_analysis')
if not exists(preparedReadsOutputDirectory):
makedirs(preparedReadsOutputDirectory)
# preparedReadResults is a dictionary.
# The result will have 2 arrays
# readstats is a 2d array, with lengths and qualities.
preparedReadResults = None
# If demultiplex option is set to 1, demultiplex is "on".
if (getConfigurationValue('demultiplex_reads') == '1'):
barcodeFilePath = getBarcodeFilePath()
preparedReadResults = prepareReads(getConfigurationValue('input_directory')
, preparedReadsOutputDirectory
, sampleID
, barcodeFilePath
, None # Reference File, we don't have one.
, int(getConfigurationValue('min_length'))
, int(getConfigurationValue('max_length'))
, int(getConfigurationValue('min_quality'))
, int(getConfigurationValue('max_quality'))
, False)
else:
preparedReadResults = prepareReads(getConfigurationValue('input_directory')
, preparedReadsOutputDirectory
, sampleID
, None # No Barcoding file.
, None # No Allele Reference
, int(getConfigurationValue('min_length'))
, int(getConfigurationValue('max_length'))
, int(getConfigurationValue('min_quality'))
, int(getConfigurationValue('max_quality'))
, False)
self.reportReadStats(preparedReadResults)
self.recordAnalysisStep('Done calculating initial read stats')
self.enableGUI()
def loadOptions(self):
# Read the configuration file.
loadConfigurationFile()
#TODO: Number of threads. Configure this.
if getConfigurationValue('demultiplex_reads') is not None:
self.chooseDemultiplexIntVar.set(
int(getConfigurationValue('demultiplex_reads')))
if getConfigurationValue('min_length') is not None:
self.inputMinLength.set(getConfigurationValue('min_length'))
if getConfigurationValue('max_length') is not None:
self.inputMaxLength.set(getConfigurationValue('max_length'))
if getConfigurationValue('min_quality') is not None:
self.inputMinQuality.set(getConfigurationValue('min_quality'))
if getConfigurationValue('max_quality') is not None:
self.inputMaxQuality.set(getConfigurationValue('max_quality'))
if getConfigurationValue('analyze_hla_a') is not None:
self.geneAIntVar.set(getConfigurationValue('analyze_hla_a'))
if getConfigurationValue('analyze_hla_b') is not None:
self.geneBIntVar.set(getConfigurationValue('analyze_hla_b'))
if getConfigurationValue('analyze_hla_c') is not None:
self.geneCIntVar.set(getConfigurationValue('analyze_hla_c'))
if getConfigurationValue('analyze_hla_e') is not None:
self.geneEIntVar.set(getConfigurationValue('analyze_hla_e'))
if getConfigurationValue('analyze_hla_dra') is not None:
self.geneDRAIntVar.set(getConfigurationValue('analyze_hla_dra'))
if getConfigurationValue('analyze_hla_dqa1') is not None:
self.geneDQA1IntVar.set(getConfigurationValue('analyze_hla_dqa1'))
if getConfigurationValue('analyze_hla_dqb1') is not None:
self.geneDQB1IntVar.set(getConfigurationValue('analyze_hla_dqb1'))
if getConfigurationValue('analyze_hla_drb1') is not None:
self.geneDRB1IntVar.set(getConfigurationValue('analyze_hla_drb1'))