def functionsGoNOW(sampleNames, path, runTrimMetadata, commands):
print "\nPerforming quality checks on assemblies."
quastList = quastProcesses(sampleNames, path, runTrimMetadata, commands)
quastMeta = metadataFiller.filler(runTrimMetadata, quastList)
runTrimAssemblyMetadata = quastMetadata(sampleNames, path, quastMeta)
jsonReportR.jsonR(sampleNames, path, runTrimAssemblyMetadata, "Collection")
return runTrimAssemblyMetadata
def functionsGoNOW(correctedFiles, path, metadata, fLength, commands):
"""Run the helper function"""
print("\nAssembling reads.")
flagMetadataList = spadesPrepProcesses(correctedFiles, path, fLength, metadata, commands)
flagMetadata = metadataFiller.filler(metadata, flagMetadataList)
updatedMetadata = contigFileFormatter(correctedFiles, path, flagMetadata)
assembledFiles = completionist(correctedFiles, path)
jsonReportR.jsonR(correctedFiles, path, updatedMetadata, "Collection")
return updatedMetadata, assembledFiles
def functionsGoNOW(sampleNames, path, runTrimMetadata, commands):
"""Calls all the functions in a way that they can be multi-processed"""
inputData = referenceFiletoAssembly(path, sampleNames)
print "\nSampling fastq files."
sampleMeta = sampleFastq(path, sampleNames, runTrimMetadata, commands)
indexList = indexTargetsProcesses(path, inputData, sampleMeta, commands)
indexMeta = metadataFiller.filler(runTrimMetadata, indexList)
#Start the mapping operations
mappingList = mappingProcesses(path, inputData, indexMeta, commands)
mappingMeta = metadataFiller.filler(runTrimMetadata, mappingList)
extractingList = extractingProcesses(path, inputData, mappingMeta, commands)
extractingMeta = metadataFiller.filler(runTrimMetadata, extractingList)
graphingList = graphingProcesses(path, inputData, extractingMeta, commands)
graphingMeta = metadataFiller.filler(runTrimMetadata, graphingList)
os.chdir(path)
runTrimInsertMetadata = formatOutput(path, sampleNames, graphingMeta)
jsonReportR.jsonR(sampleNames, path, runTrimInsertMetadata, "Collection")
return runTrimInsertMetadata
def functionsGoNow(files, path, metadata, fLength, commands):
# print path, fLength
commandList = spadesPrepProcesses(files, path, fLength, metadata, commands)
commandMetadata = metadataFiller.filler(metadata, commandList)
updatedMetadata = contigFileFormatter(files, path, commandMetadata)
assembledFiles = completionist(files, path)
# moreMetadata = pipelineMetadata(path, updatedMetadata, assembledFiles)
jsonReportR.jsonR(files, path, updatedMetadata, "Collection")
return updatedMetadata, assembledFiles
def functionsGoNOW(assembledFiles, path, assemblyMetadata, refFilePath, commands):
print "\nPerforming GeneSeekr analysis"
# Clear out any summary reports from a previous iteration of the pipeline
reportRemover(path)
# Do everything - uniVec screening, geneSeeking, V-typing, and MLST analysis
geneSeekrMetadataList = geneSeekrPrepProcesses(assembledFiles, path, assemblyMetadata, refFilePath, commands)
# print json.dumps(geneSeekrMetadata, sort_keys=True, indent=4, separators=(',', ': '))
geneSeekrMetadata = metadataFiller.filler(assemblyMetadata, geneSeekrMetadataList)
jsonReportR.jsonR(assembledFiles, path, geneSeekrMetadata, "Collection")
return geneSeekrMetadata
def functionsGoNOW(sampleNames, path, runMetadata, fLength, commands):
"""Run the functions"""
print('\nPerforming error correction on fastq files.')
# Removed the multiprocessing aspect of this function - it seemed to be unreliable.
# Sometimes, fastq files with more data would not be corrected.
os.chdir(path)
print "Preparing fastq files for processing"
prepList = quakePrepProcesses(sampleNames, path, fLength, runMetadata, commands)
prepMetadata = metadataFiller.filler(runMetadata, prepList)
print "Determining cut-off values for error correction"
cutoffList = quakeCutOffProcesses(sampleNames, path, prepMetadata, commands)
cutoffMetadata = metadataFiller.filler(prepMetadata, cutoffList)
print "Correcting errors"
correctList = quakeCorrectProcesses(sampleNames, path, fLength, cutoffMetadata, commands)
correctMetadata = metadataFiller.filler(runMetadata, correctList)
# runQuake(sampleNames, path)
os.chdir(path)
# Run completionist to determine unprocessable files, and acquire metadata
runTrimMetadata, correctedList = completionist(sampleNames, path, correctMetadata, fLength)
# Clean up tmp files
tmpFileRemover(path, correctedList)
# Return important variables
jsonReportR.jsonR(correctedList, path, runTrimMetadata, "Collection")
return correctedList, runTrimMetadata
