def getDataPackage():
softfile = "data/GDS2545.soft.gz"
gnfile = "data/c2.biocarta.v2.5.symbols.gmt"
synfile = "data/Homo_sapiens.gene_info.gz"
gnf = GMTParser.GMTParser(gnfile)
sp = SOFTParser.SOFTParser(softfile)
normal = []
tumor = []
for line in sp.column_heading_info[0]:
if string.find(line[1], 'normal prostate tissue free') > 0:
normal.append(line[0].strip())
elif string.find(line[1], 'tumor') > 0:
tumor.append(line[0].strip())
dt = DataCleaner.DataTable()
dt.getSOFTData(sp)
dp = DataPackager.dataPackager()
dp.addGeneNetwork(gnf.getAllNetworks())
dp.addDataTable(dt)
dp.addSynonyms(synfile)
dp.createClassification("Tumor")
dp.createClassification("Normal")
for samp in tumor:
dp.addToClassification("Tumor", dt.dt_id, samp)
for samp in normal:
dp.addToClassification("Normal", dt.dt_id, samp)
return dp
sp3 = SOFTParser.SOFTParser("data/GDS3329.soft.gz")
gnfile = "data/c2.biocarta.v2.5.symbols.gmt"
print "creating Table"
dt1 = DataCleaner.DataTable()
print "importing parser"
dt1.getSOFTData(sp)
print "gene parser"
dt2 = DataCleaner.DataTable()
print "importing parser"
dt2.getSOFTData(sp2)
dt3 = DataCleaner.DataTable()
print "importing parser"
dt3.getSOFTData(sp3)
gnf = GMTParser.GMTParser(gnfile)
print "data packager"
dp = DataPackager.dataPackager()
dp.addGeneNetwork(gnf.getAllNetworks())
print "adding data table 1"
dp.addDataTable(dt1)
print "adding data table 2"
dp.addDataTable(dt2)
dp.addDataTable(dt3)
dp.createClassification("first")
dp.createClassification("post")
for val in dt1.getSamples()[:len(dt1.getSamples())/2]:
dp.addToClassification("first", dt1.dt_id, val)
for val in dt2.getSamples()[len(dt2.getSamples())/2:]:
dp.addToClassification("post", dt2.dt_id, val)
for val in dt3.getSamples()[len(dt3.getSamples())/2:]:
dp.addToClassification("post", dt3.dt_id, val)
