def getGenes(inputFiles):
genes = {}
variationTypes = []
patients = []
headsList = ['patient','gene','log2']
for geneFile in inputFiles:
with open(geneFile, 'r') as inFile:
variationType = geneFile.split('.')[-1]
variationTypes.append(variationType)
header = utility.lineToHeader(inFile.readline(), headsList)
for line in inFile:
patGen = utility.lineToDict(line, header)
gene = patGen['gene']
patient = patGen['patient']
log2 = patGen['log2']
if not gene in genes:
genes[gene] = {}
if not variationType in genes[gene]:
genes[gene][variationType] = {}
if not patient in genes[gene][variationType]:
genes[gene][variationType][patient] = log2
if not patient in patients:
patients.append(patient)
else:
genes[gene][variationType][patient] = max(genes[gene][variationType][patient], log2)
return genes, variationTypes, patients
def getSegments(segmentFile):
segs = []
with open(segmentFile, 'r') as inFile:
header = utility.lineToHeader(inFile.readline())
for line in inFile:
segment = utility.lineToDict(line, header)
segs.append(segment)
return segs
def getGenes(genesFile):
headerList = ['name']
genesList = []
with open(genesFile, 'r') as genFile:
header = utility.lineToHeader(genFile.readline(), headerList)
for line in genFile:
gene = utility.lineToDict(line, header)
genesList.append(gene['name'])
return genesList
def genesFromFile(inputFile):
geneList = []
with open(inputFile, 'r') as inFile:
header = utility.lineToHeader(inFile.readline())
for line in inFile:
segment = utility.lineToDict(line, header)
for gene in segment['genes']:
if not gene in geneList:
geneList.append(gene)
return geneList
def filterSegmentGenes(segmentsFile, geneList):
segments = []
with open(segmentsFile, 'r') as inFile:
header = utility.lineToHeader(inFile.readline())
for line in inFile:
filteredGenes = []
segment = utility.lineToDict(line, header)
for gene in segment['genes']:
if gene in geneList:
filteredGenes.append(gene)
if filteredGenes:
segment['genes'] = filteredGenes
segments.append(segment)
return segments
def getMergedSegments(inputFile, armsDict, maximum, minimum):
mergedSegs = []
toMerge = []
actualArm = ''
actualType = ''
with open(inputFile, 'r') as inFile:
header = utility.lineToHeader(inFile.readline())
for line in inFile:
segment = utility.lineToDict(line, header)
segment = addArm(segment, armsDict)
segment = addEventType(segment, maximum, minimum)
mergedSegs.append(segment)
return mergedSegs
def getArmsInfo(armInputFile):
headList = ['chrom', 'start', 'end', 'name']
headInts = ['start', 'end']
arms = {}
with open(armInputFile, 'r') as inFile:
header = utility.lineToHeader(inFile.readline(), headList)
for line in inFile:
arm = utility.lineToDict(line, header, ints=headInts)
arm['length'] = arm['end'] - arm['start']
arm['name'] = arm['chrom'] + arm['name']
if not arm['chrom'] in arms:
arms[arm['chrom']] = {}
arms[arm['chrom']][arm['name']] = arm
return arms
def annoteSegments(segmentFile, annoteDict):
segments = []
with open(segmentFile, 'r') as inFile:
header = utility.lineToHeader(inFile.readline())
for line in inFile:
segment = utility.lineToDict(line, header)
segment['genes'] = []
if segment['type'] == 'Neu':
continue
chromGenes = annoteDict[segment['chrom']]
for gene in chromGenes:
segment = geneOverlap(segment, gene)
if segment['genes']:
segments.append(segment)
return segments
def getSegmentsFromFile(inputFile, segs, patientId):
with open(inputFile, 'r') as inFile:
header = utility.lineToHeader(inFile.readline())
for line in inFile:
segment = utility.lineToDict(line, header)
segment['patient'] = patientId
if segment['start'] in segs:
if segment['end'] in segs[segment['start']]:
segs[segment['start']][segment['end']]['log2'].append(
segment['log2'])
segs[segment['start']][segment['end']]['pVal'].append(
segment['pVal'])
else:
segment['log2'] = [segment['log2']]
segment['pVal'] = [segment['pVal']]
segs[segment['start']][segment['end']] = segment
else:
segment['log2'] = [segment['log2']]
segment['pVal'] = [segment['pVal']]
segs[segment['start']] = {segment['end']: segment}
return segs
def getAnnotationInfo(annoteFile):
headsList = [
'name2', 'chrom', 'start', 'end', 'exonCount', 'exonStarts', 'exonEnds'
]
annInts = ['exonCount', 'start', 'end']
genes = {}
with open(annoteFile, 'r') as annFile:
header = utility.lineToHeader(annFile.readline(), headsList)
for line in annFile:
gene = utility.lineToDict(line, header, annInts)
gene['chrom'] = gene['chrom'][3:]
gene['exonStarts'] = gene['exonStarts'].split(',')[:-1]
gene['exonStarts'] = list(map(int, gene['exonStarts']))
gene['exonEnds'] = gene['exonEnds'].split(',')[:-1]
gene['exonEnds'] = list(map(int, gene['exonEnds']))
if not gene['chrom'] in genes:
genes[gene['chrom']] = []
genes[gene['chrom']].append(gene)
return genes