def main():
usage = 'usage: %prog [options] <cors file>'
parser = OptionParser(usage)
parser.add_option('--go_min', dest='go_min', type='int', default=10, help='Minimum number of genes assigned a GO term to consider enrichment of that term')
parser.add_option('--go_max', dest='go_max', type='int', default=300, help='Maximum number of genes assigned a GO term to consider enrichment of that term')
parser.add_option('-n', dest='num_shuffles', type='int', default=250, help='Number of shuffles to obtain p-value [Default: %default]')
parser.add_option('-s', dest='size_skip', type='int', default=4, help='Gene set sizes to skip when computing null distributions [Default: %default]')
(options,args) = parser.parse_args()
if len(args) != 1:
parser.error('Must provide correlations file')
else:
cors_file = args[0]
# get genes, correlations
correlations_genes = []
genes = []
for line in open(cors_file):
a = line.split()
correlations_genes.append((abs(float(a[1])),a[0]))
genes.append(a[0])
correlations_genes.sort(reverse=True)
# GO
go_map, go_descs = read_go(set(genes))
# make null distributions
geneset_size_enrichments = make_null_dist(options.go_min, options.go_max, options.num_shuffles, options.size_skip, go_map, correlations_genes, genes)
# do stats
output_cols = []
for go_term in go_map:
go_size = len(go_map[go_term])
if options.go_min <= go_size <= options.go_max:
# compute enrichment
enrichment = gsea_enrichment(correlations_genes, go_map[go_term])
# compute p-value using normal approximation
#p_val = (1+len([e for e in geneset_size_enrichments[go_size] if e >= enrichment])) / float(options.num_shuffles)
(mean, sd) = interpolate_null(geneset_size_enrichments, options.size_skip, go_size)
p_val = max(norm.rvs(1,loc=0,scale=1e-17), 1.0 - norm.cdf(enrichment, loc=mean, scale=sd))
# output
output_cols.append([go_term, enrichment, p_val, 99, go_size, go_descs[go_term]])
# FDR multiple hypothesis correction
p_values = [oc[2] for oc in output_cols]
q_values = fdr.storey(p_values)
for i in range(len(output_cols)):
output_cols[i][3] = q_values[i]
for oc in output_cols:
print '%-12s %.3f %.3e %.3e %4d %s' % tuple(oc)
def main():
usage = 'usage: %prog [options] <cors file> <null file>'
parser = OptionParser(usage)
parser.add_option('--go_min', dest='go_min', type='int', default=10, help='Minimum number of genes assigned a GO term to consider enrichment of that term')
parser.add_option('--go_max', dest='go_max', type='int', default=300, help='Maximum number of genes assigned a GO term to consider enrichment of that term')
parser.add_option('-n', dest='null_samples', type='int', default=50, help='Number of null samples to obtain p-value [Default: %default]')
(options,args) = parser.parse_args()
if len(args) != 2:
parser.error('Must provide correlations file')
else:
cors_file = args[0]
null_file = args[1]
# get genes, correlations
correlations_genes = []
genes = []
for line in open(cors_file):
a = line.split()
correlations_genes.append((abs(float(a[1])),a[0]))
genes.append(a[0])
correlations_genes.sort(reverse=True)
# GO
go_map, go_descs = read_go(set(genes))
consider_go = [go_term for go_term in go_map if options.go_min <= len(go_map[go_term]) <= options.go_max]
# compute null GO term enrichments
null_go_enrichments = {}
header = ''
samples = 0
for line in open(null_file):
if line[0] == '>':
if header:
if samples < options.null_samples:
process_null_sample(null_correlations_genes, null_go_enrichments, go_map, consider_go)
samples += 1
header = line[1:].rstrip()
null_correlations_genes = []
else:
a = line.split()
null_correlations_genes.append((abs(float(a[1])),a[0]))
if samples < options.null_samples:
process_null_sample(null_correlations_genes, null_go_enrichments, go_map, consider_go)
samples += 1
for go_term in consider_go:
null_out = open('null_%s_%d.txt' % (go_term,len(go_map[go_term])), 'w')
print >> null_out, '\n'.join([str(enr) for enr in null_go_enrichments[go_term]])
null_out.close()
# do stats
output_cols = []
for go_term in consider_go:
# compute enrichment
enrichment = gsea_enrichment(correlations_genes, go_map[go_term])
# compute p-value using normal approximation
#p_val = (1+len([e for e in geneset_size_enrichments[go_size] if e >= enrichment])) / float(options.num_shuffles)
(mean, sd) = util.mean_sd(null_go_enrichments[go_term])
p_val = 1.0 - norm.cdf(enrichment, loc=mean, scale=sd)
# output
output_cols.append([go_term, enrichment, p_val, 99, len(go_map[go_term]), go_descs[go_term]])
# FDR multiple hypothesis correction
p_values = [oc[2] for oc in output_cols]
q_values = fdr.storey(p_values)
for i in range(len(output_cols)):
output_cols[i][3] = q_values[i]
for oc in output_cols:
print '%-12s %.3f %.3e %.3e %4d %s' % tuple(oc)
def main():
usage = 'usage: %prog [options] <cors file>'
parser = OptionParser(usage)
parser.add_option(
'--go_min',
dest='go_min',
type='int',
default=10,
help=
'Minimum number of genes assigned a GO term to consider enrichment of that term'
)
parser.add_option(
'--go_max',
dest='go_max',
type='int',
default=300,
help=
'Maximum number of genes assigned a GO term to consider enrichment of that term'
)
parser.add_option(
'-n',
dest='num_shuffles',
type='int',
default=250,
help='Number of shuffles to obtain p-value [Default: %default]')
parser.add_option(
'-s',
dest='size_skip',
type='int',
default=4,
help=
'Gene set sizes to skip when computing null distributions [Default: %default]'
)
(options, args) = parser.parse_args()
if len(args) != 1:
parser.error('Must provide correlations file')
else:
cors_file = args[0]
# get genes, correlations
correlations_genes = []
genes = []
for line in open(cors_file):
a = line.split()
correlations_genes.append((abs(float(a[1])), a[0]))
genes.append(a[0])
correlations_genes.sort(reverse=True)
# GO
go_map, go_descs = read_go(set(genes))
# make null distributions
geneset_size_enrichments = make_null_dist(options.go_min, options.go_max,
options.num_shuffles,
options.size_skip, go_map,
correlations_genes, genes)
# do stats
output_cols = []
for go_term in go_map:
go_size = len(go_map[go_term])
if options.go_min <= go_size <= options.go_max:
# compute enrichment
enrichment = gsea_enrichment(correlations_genes, go_map[go_term])
# compute p-value using normal approximation
#p_val = (1+len([e for e in geneset_size_enrichments[go_size] if e >= enrichment])) / float(options.num_shuffles)
(mean, sd) = interpolate_null(geneset_size_enrichments,
options.size_skip, go_size)
p_val = max(norm.rvs(1, loc=0, scale=1e-17),
1.0 - norm.cdf(enrichment, loc=mean, scale=sd))
# output
output_cols.append(
[go_term, enrichment, p_val, 99, go_size, go_descs[go_term]])
# FDR multiple hypothesis correction
p_values = [oc[2] for oc in output_cols]
q_values = fdr.storey(p_values)
for i in range(len(output_cols)):
output_cols[i][3] = q_values[i]
for oc in output_cols:
print '%-12s %.3f %.3e %.3e %4d %s' % tuple(oc)
