from gusPyCode.defs.JamesDefs import DotDict
if len(sys.argv) != 3:
exit('USAGE: python %s inFile outFile' % (sys.argv[0].split('/')[-1]))
lines = open(sys.argv[1],'rU').readlines()
outLines = []
groupedLines = groupByField_silent(lines,0,sep=' : ')
groupedLines.sort(key=lambda x: x[0][0])
for miR in groupedLines:
data = DotDict({'name':miR[0][0],
'orthoTypes':[],
'numTot':[None]*4,
'FDRTot':[None]*4,
'm3_to_m8_fdr':[None]*4,
'm2_to_m7_fdr':[None]*4,
'A1_to_m7_fdr':[None]*4,
'm2_to_m8_fdr':[None]*4,
'A1_to_m8_fdr':[None]*4})
for line in miR:
if line[1].startswith("allPassedSeedsFor_"):
orthoType = int(line[1][-1])
data.orthoTypes.append(orthoType)
data.numTot[orthoType] = line[2]
data.FDRTot[orthoType] = line[3]
for i in miR:
if i[2].startswith('orthoType_%s' % (orthoType)):
if i[1]+'_fdr' in data:
data[i[1]+'_fdr'][orthoType] = i[4]
rSet.add(i)
return sorted(list(rSet))
lines = open(sys.argv[1],'rU').readlines()
outLines = []
groupedLines = groupByField_silent(lines,0,sep=' : ')
groupedLines.sort(key=lambda x: x[0][0])
for miR in groupedLines:
data = DotDict({'name':miR[0][0],
'orthoTypes':[],
'numTot':[None]*4,
'FDRTot':[None]*4,
'm3_to_m8_fdr':[None]*4,
'm2_to_m7_fdr':[None]*4,
'A1_to_m7_fdr':[None]*4,
'm2_to_m8_fdr':[None]*4,
'A1_to_m8_fdr':[None]*4})
for line in miR:
if line[1].startswith("allPassedSeedsFor_"):
orthoType = int(line[1][-1])
data.orthoTypes.append(orthoType)
data.numTot[orthoType] = len(getAGAPList(line[5]))
data.FDRTot[orthoType] = line[3]
for i in miR:
if i[2].startswith('orthoType_%s' % (orthoType)):
if i[1]+'_fdr' in data:
data[i[1]+'_fdr'][orthoType] = i[4]
rSet.add(i)
return rSet
lines = open(sys.argv[1],'rU').readlines()
outLines = []
groupedLines = groupByField_silent(lines,0,sep=' : ')
groupedLines.sort(key=lambda x: x[0][0])
mirDict = Bag()
for miR in groupedLines:
data = DotDict({'name':miR[0][0],
'orthoTypes':[],
'numTot':[None]*4,
'AGAPgenes':[None]*4})
for line in miR:
if line[1].startswith("allPassedSeedsFor_"):
orthoType = int(line[1][-1])
data.orthoTypes.append(orthoType)
data.numTot[orthoType] = len(getAGAP(line[5]))
data.AGAPgenes[orthoType] = getAGAP(line[5])
#for i in miR:
#if i[2].startswith('orthoType_%s' % (orthoType)):
#if i[1]+'_fdr' in data:
#data[i[1]+'_fdr'][orthoType] = i[4]
mirDict[data.name] = data