def main(args):
print args
builder=TtdBuilderFactory().get_instance(args.builder, db=args.db_name,
clear_table=args.clear_table,
uniprot_gene_fn=args.uniprot_gene_fn)
reader=ttd_reader(args.in_fn, builder, args.burn_lines)
g=reader.read()
print dump(builder.stats)
def main(args):
print args
builder=DrugcardBuilderFactory().get_instance(args.builder,
clear_table=args.clear_table,
uniprot_gene_fn=args.uniprot_gene_fn)
reader=DrugbankReader(fn=args.in_fn, builder=builder)
for dc in reader:
print '%s saved' % dc.id
print dump(builder.stats)
def main(args):
print args
# clear dbs:
if False:
dao_og=dao_django(cls=OncotatorGene)
dao_og.remove({})
dao_op=dao_django(cls=UniprotProtein)
dao_op.remove({})
genes=readgenes(args.in_fn)
base_url=args.base_url
stats={'n_genes':0, 'n_prots':0}
for gn in genes:
try:
gene=OncotatorGene.objects.get(name=gn)
print '%s: already loaded' % gn
continue
except OncotatorGene.DoesNotExist:
pass
url=base_url+gn
res=requests.get(url)
if res.status_code != 200:
print '%s: error/nothing found' % gn
continue
print gn
dct=json.loads(res.content)
# for k,v in dct.items():
# print '%s: %s' % (k,v)
gene=OncotatorGene(name=gn,
full_name=dct['full_name'],
chr=dct['chr'],
location=dct['location'],
start=dct['start'],
end=dct['end'],
strand=dct['strand'])
gene.save()
stats['n_genes']+=1
prot_accs=[dct['uniprot_accession']]
try:
prot_accs.extend(dct['alt_uniprot_accessions'])
except KeyError:
pass
for acc in prot_accs:
prot=UniprotProtein(id=acc, gene=gene)
prot.save()
stats['n_prots']+=1
print dump(stats)
def tripNegAll(genelist, g2s):
print 'trip_neg genes:'
stats={'n_found':0, 'n_missing':0, 'n_total':len(genelist)}
def get_targets(gene_syns):
for gene in gene_syns:
ts=Target.objects.filter(gene_sym=gene)
if len(ts)>0:
return ts, gene
return [],None
for gene in genelist:
genes=[gene]
try:
syns=g2s.g2s[gene]
genes.extend(syns)
except KeyError:
pass
ts, g2=get_targets(genes)
if len(ts)>0:
stats['n_found']+=1
else:
stats['n_missing']+=1
# print '%d targets for %s (%s)' % (len(ts), genes, g2)
# for t in ts:
# print 'gene %s: target %s' % (gene, t)
print 'tripNeg: %s' % dump(stats)
def SamGenesWithUniprot(genelist, u2g):
''' tabulate the sam genes that can have a uniprot associated with them '''
stats={'n_found':0, 'n_missing':0, 'n_total':len(genelist)}
for gene in genelist:
try:
u=u2g.g2u[gene]
stats['n_found']+=1
except KeyError:
stats['n_missing']+=1
print 'uniprot: %s' % dump(stats)
def SamGenes(genelist):
''' find the targets that have a sam gene associated with them (via gene_sym) '''
stats={'n_found':0, 'n_missing':0, 'n_total':len(genelist)}
for gene in genelist:
ttd_tars=Target.objects.filter(gene_sym=gene)
if len(ttd_tars)>0:
# print '%d targets for gene %s' % (len(ttd_tars), gene)
stats['n_found']+=1
else:
stats['n_missing']+=1
print 'SamGenes stats: %s' % dump(stats)
def main(args):
'''
load the variation data from one of three sources (LOVD, umd, or nhgri)
into the database.
'''
print args
Variation.objects.filter(gene=args.gene, source=args.src).delete()
stats={'n_vars':0}
fn=get_fn(args)
with open(fn) as f:
reader=csv.reader(f, delimiter='\t')
for line in reader:
try:
dnaVar=line[0]
protVar=line[1]
assay=line[2]
except IndexError:
continue
var=Variation(dnaVariation=dnaVar, protVariation=protVar, assay=assay, gene=args.gene, source=args.src)
var.save()
stats['n_vars']+=1
print dump(stats)
