def createDataPackage(dataFile, subset1, subset2 ):
"""
Builds a DataPackager
"""
from AUREA.packager.DataPackager import dataPackager
from AUREA.parser.SOFTParser import SOFTParser
from AUREA.packager.DataCleaner import DataTable
from AUREA.parser.GMTParser import GMTParser
#get soft file
sp = SOFTParser( dataFile )
ss_list = [None, None]
for ss in sp.getSubsets():
if subset1 in ss.attributes['subset_description']:
ss_list[0] = ss
if subset2 in ss.attributes['subset_description']:
ss_list[1] = ss
subsetSamples1 = sp.getSubsetSamples( ss_list[0] )
subsetSamples2 = sp.getSubsetSamples( ss_list[1] )
#make a data table
dt = DataTable()
dt.getSOFTData( sp )
#add stuff to build networks
gene_network_file = AUREA_dir +"/workspace/data/c2.biocarta.v2.5.symbols.gmt"
synonym_file = AUREA_dir + "/workspace/data/Homo_sapiens.gene_info.gz"
#set up classes
dp = dataPackager()
dp.addSynonyms(synonym_file)
gn = GMTParser(gene_network_file)
dp.addGeneNetwork(gn.getAllNetworks())
dp.addDataTable(dt)
dp.createClassification(subset1)
dp.createClassification(subset2)
for sample in subsetSamples1:
dp.addToClassification( subset1, dt.dt_id, sample )
for sample in subsetSamples2:
dp.addToClassification( subset2, dt.dt_id, sample )
return dp
from AUREA.parser.CSVParser import CSVParser
from AUREA.packager.DataCleaner import DataTable
from AUREA.packager.DataPackager import dataPackager
csvFile = "data/testPackagerProbes1.csv"
p = CSVParser(csvFile,probe_column_name="probe", gene_column_name="probe")
print p.getColumnHeadings()
print p.getColumnHeadingsInfo()
#print p.getTable()
print p.getID_REF()
print p.getIDENTIFIER()
dt = DataTable(probe_column="probe", gene_column="probe")
dt.getCSVData(p)
dp = dataPackager()
dp.addDataTable(dt)
dp.writeToCSV("copyofacopy.csv")
from AUREA.parser.SOFTParser import SOFTParser
from AUREA.packager.DataCleaner import DataTable
from AUREA.packager.DataPackager import dataPackager
if __name__ == "__main__":
path = "/home/earls3/Price/AUREA/workspace/data/"
f1 = "GDS2545.soft.gz"
sp = SOFTParser(path + f1)
t1s = []
t2s = []
for x in sp.getSubsets():
if x.attributes['subset_description'][0] == 'normal prostate tissue':
t1s = sp.getSubsetSamples(x)
if x.attributes['subset_description'][0] == 'primary prostate tumor':
t2s = sp.getSubsetSamples(x)
dt = DataTable()
dt.getSOFTData(sp)
dp = dataPackager(merge_cache=".")
dp.addDataTable(dt)
dp.createClassification("Normal")
dp.createClassification("ignore")
for samp in t1s:
dp.addToClassification("Normal", dt.dt_id, samp)
dp.writeToCSV("normal.csv", key='probe')
dp.clearClassification()
dp.createClassification("Tumor")
dp.createClassification("ignore")
for samp in t2s:
dp.addToClassification("Tumor", dt.dt_id, samp)
dp.writeToCSV("tumor.csv", key='probe')