def formatPhenoFile(fl):
expr_group_dir = fl.GroupsFile()
expr_batch_dir = string.replace(expr_group_dir,'groups.','batch.')
pheno_dir = string.replace(expr_group_dir,'groups.','pheno.')
import gene_associations
group_db = gene_associations.importGeneric(expr_group_dir)
bath_db = gene_associations.importGeneric(expr_batch_dir)
pheno_obj = export.ExportFile(pheno_dir)
pheno_obj.write('sample\tgroup\tbatch\n')
for sample in group_db:
group_name = group_db[sample][-1]
batch_number = bath_db[sample][0]
pheno_obj.write(string.join([sample,group_name,batch_number],'\t')+'\n')
pheno_obj.close()
return pheno_dir
def formatPhenoFile(fl):
expr_group_dir = fl.GroupsFile()
expr_batch_dir = string.replace(expr_group_dir,'groups.','batch.')
pheno_dir = string.replace(expr_group_dir,'groups.','pheno.')
import gene_associations
group_db = gene_associations.importGeneric(expr_group_dir)
bath_db = gene_associations.importGeneric(expr_batch_dir)
pheno_obj = export.ExportFile(pheno_dir)
pheno_obj.write('sample\tgroup\tbatch\n')
for sample in group_db:
group_name = group_db[sample][-1]
batch_number = bath_db[sample][0]
pheno_obj.write(string.join([sample,group_name,batch_number],'\t')+'\n')
pheno_obj.close()
return pheno_dir
def formatPhenoFile(fl):
expr_group_dir = fl.GroupsFile()
expr_batch_dir = string.replace(expr_group_dir, "groups.", "batch.")
pheno_dir = string.replace(expr_group_dir, "groups.", "pheno.")
import gene_associations
group_db = gene_associations.importGeneric(expr_group_dir)
bath_db = gene_associations.importGeneric(expr_batch_dir)
pheno_obj = export.ExportFile(pheno_dir)
pheno_obj.write("sample\tgroup\tbatch\n")
for sample in group_db:
group_name = group_db[sample][-1]
batch_number = bath_db[sample][0]
pheno_obj.write(string.join([sample, group_name, batch_number], "\t") + "\n")
pheno_obj.close()
return pheno_dir
def importHMDBMetaboCardFlatFile():
filename = 'BuildDBs/HMDB/metabocards.txt'
fields_to_store = [
'hmdb_id', 'description', 'name', 'secondary_id', 'iupac', 'biocyc_id',
'cas_number', 'chebi_id', 'kegg_compound_id', 'pubchem_compound_id',
'pathway_1_kegg_id'
]
fields_to_store += [
'metabolic_enzyme_1_gene_name', 'metabolic_enzyme_1_swissprot_id',
'metabolic_enzyme_2_gene_name', 'metabolic_enzyme_2_swissprot_id'
]
fields_to_store += [
'pathway_1_smpdb_id', 'pathway_2_smpdb_id', 'pathway_3_smpdb_id',
'pathway_1_name', 'pathway_2_name', 'pathway_3_name',
'pathway_2_kegg_id', 'pathway_3_kegg_id'
]
fn = filepath(filename)
field_data = ''
field_name = ''
entry_data = {}
hmdb = []
global kegg_pathways
kegg_pathways = gene_associations.importGeneric(
'BuildDBs/HMDB/map_title.tab')
x = 0
for line in open(fn, 'rU').xreadlines():
data = cleanUpLine(line)
if len(data) > 0:
if data[0] == '#': field_name = data[2:-1]
else: field_data += data
else:
if field_name in fields_to_store:
entry_data[field_name] = field_data
#else: print [field_name]
field_name = ''
field_data = ''
if 'END_METABOCARD' in data:
ed = HMBDInfo(entry_data)
hmdb.append(ed)
entry_data = {}
x += 1
#if x>5: break
print len(hmdb), 'HMDB entries obtained'
exportTables(hmdb)