for line in xmlfile:
if lnum % 2500 == 0:
pbar.updateProgress(lnum)
lnum += 1
cDrug = parseLine(line, cDrug, stack)
pbar.finalize()
print "Targets excluded: ", __excluded_targets
print "Drugs loaded: ", len(__drugs)
print "Targets loaded: ", len(__targets)
if __name__ == "__main__":
# import psyco
# psyco.full()
geneDB.init(os.sep.join(["data","hgnc","hgnc_symbols.txt"]))
print "Loading drug bank database from XML..."
loadXML(os.sep.join(["data","drugbank","drugbank.xml"]))
mapTargetNames(os.sep.join(["data","drugbank","target_links.csv"]))
print __targets[1]
print __targets[3]
print "Named targets: ", len(__target_names)
print "Unnamed targets: ", __targets_unnamed
print "Loading DrugBank drug catalogue..."
drugCat.initDruglist(os.sep.join(["data","drugbank","drug_links.csv"]))
print "Loading DrugBank drug target catalogue..."
drugCat.initTargets(os.sep.join(["data","drugbank","target_links.csv"]),
for line in xmlfile:
if lnum % 2500 == 0:
pbar.updateProgress(lnum)
lnum += 1
cDrug = parseLine(line, cDrug, stack)
pbar.finalize()
print "Targets excluded: ", __excluded_targets
print "Drugs loaded: ", len(__drugs)
print "Targets loaded: ", len(__targets)
if __name__ == "__main__":
# import psyco
# psyco.full()
geneDB.init(os.sep.join(["data", "hgnc", "hgnc_symbols.txt"]))
print "Loading drug bank database from XML..."
loadXML(os.sep.join(["data", "drugbank", "drugbank.xml"]))
mapTargetNames(os.sep.join(["data", "drugbank", "target_links.csv"]))
print __targets[1]
print __targets[3]
print "Named targets: ", len(__target_names)
print "Unnamed targets: ", __targets_unnamed
print "Loading DrugBank drug catalogue..."
drugCat.initDruglist(os.sep.join(["data", "drugbank", "drug_links.csv"]))
print "Loading DrugBank drug target catalogue..."
drugCat.initTargets(
__USE_DRUGBANK_XML = 1
elif sys.argv[i] == "--rm-pseudo":
__EXCLUDE_PSEUDOGENES = 1
elif sys.argv[i] == "--rm-study":
for item in sys.argv[i+1].split(","):
item = item.strip()
included_studies.remove(int(item))
elif sys.argv[i] == "--output-dir":
output_dir = os.sep.join(["results", sys.argv[i+1]])
elif sys.argv[i].startswith("--"):
print "Invalid arg:", sys.argv[i]
sys.exit(1)
print "\nInitializing HGNC Database..."
geneDB.init(os.sep.join(["data","hgnc","hgnc_symbols.txt"]),__EXCLUDE_PSEUDOGENES)
print "\nLoading rapidly evolving proteins..."
studyGenes = loadEvolutionaryGenes(os.sep.join(["data","genelists","positive_selection_gene_lists.txt"]),__ENABLE_GENE_VERIFICATION,__ENABLE_GENE_UPDATES,gene_frequency_filter, included_studies)
if __EXCLUDE_OLFACTORY_PROTEINS:
print "\nExcluding olfactory proteins..."
olfactoryProteins = pyCSV()
olfactoryProteins.load(os.sep.join(["data","genelists","olfactory_genes.csv"]),"\t")
olfactoryGenes = set([item.lower() for item in geneUtils.columnToList(olfactoryProteins, 1, 1)])
for gene in olfactoryGenes:
if gene in studyGenes:
studyGenes.remove(gene)
