study, pop = read_geneset(study_fn, pop_fn, compare=args.compare)
assoc = read_associations(assoc_fn)
methods = ["bonferroni", "sidak", "holm"]
if args.fdr:
methods.append("fdr")
starttime = time.clock()
# obo_dag = GODag(obo_file=args.obo)
obo_dag = read_data()
endtime = time.clock()
f = open('E:/time.txt', 'w')
f.write(str(endtime - starttime))
f.close()
print(str(endtime - starttime))
# save_data(obo_dag)
# obo_dag=read_data()
g = GOEnrichmentStudy(pop,
assoc,
obo_dag,
alpha=args.alpha,
study=study,
methods=methods)
endtime = time.clock()
f = open('E:/time1.txt', 'w')
f.write(str(endtime - starttime))
f.close()
# print (endtime - starttime)
g.print_summary(min_ratio=min_ratio, indent=args.indent, pval=args.pval)
p.add_option('--fdr', dest='fdr', default=False,
action='store_true',
help="calculate the false discovery rate (alternative to the Bonferroni correction)")
p.add_option('--indent', dest='indent', default=False,
action='store_true', help="indent GO terms")
(opts, args) = p.parse_args()
bad = check_bad_args(args)
if bad:
print bad
sys.exit(p.print_help())
alpha = float(opts.alpha) if opts.alpha else 0.05
min_ratio = opts.ratio
if not min_ratio is None:
assert 1 <= min_ratio <= 2
study_fn, pop_fn, assoc_fn = args
study, pop = read_geneset(study_fn, pop_fn, compare=opts.compare)
assoc = read_associations(assoc_fn)
methods=["bonferroni", "sidak", "holm"]
if opts.fdr:
methods.append("fdr")
obo_dag = GODag(obo_file="gene_ontology.1_2.obo")
g = GOEnrichmentStudy(pop, assoc, obo_dag, alpha=alpha, study=study, methods=methods)
g.print_summary(min_ratio=min_ratio, indent=opts.indent)
action='store_true',
help="Calculate the false discovery rate (alt. to the "
"Bonferroni but slower)")
p.add_option('--indent', dest='indent', default=False,
action='store_true', help="indent GO terms")
(opts, args) = p.parse_args()
bad = check_bad_args(args)
if bad:
print bad
sys.exit(p.print_help())
min_ratio = opts.ratio
if min_ratio is not None:
assert 1 <= min_ratio <= 2
assert 0 < opts.alpha < 1, "Test-wise alpha must fall between (0, 1)"
study_fn, pop_fn, assoc_fn = args
study, pop = read_geneset(study_fn, pop_fn, compare=opts.compare)
assoc = read_associations(assoc_fn)
methods = ["bonferroni", "sidak", "holm"]
if opts.fdr:
methods.append("fdr")
obo_dag = GODag(obo_file="gene_ontology.1_2.obo")
g = GOEnrichmentStudy(pop, assoc, obo_dag, alpha=opts.alpha,
study=study, methods=methods)
g.print_summary(min_ratio=min_ratio, indent=opts.indent, pval=opts.pval)
study, pop = read_geneset(study_fn, pop_fn, compare=args.compare)
print("Study: {0} vs. Population {1}".format(len(study), len(pop)), file=sys.stderr)
if not args.compare: # sanity check
if len(pop) < len(study):
exit("\nERROR: The study file contains more elements than the population file. "
"Please check that the study file is a subset of the population file.\n")
# check the fraction of genomic ids that overlap between study
# and population
overlap = float(len(study & pop)) / len(study)
if 0.7 < overlap < 0.95:
sys.stderr.write("\nWARNING: only {} fraction of genes/proteins in study are found in "
"the population background.\n\n".format(overlap))
if overlap <= 0.7:
exit("\nERROR: only {} of genes/proteins in the study are found in the "
"background population. Please check.\n".format(overlap))
assoc = read_associations(assoc_fn)
methods = ["bonferroni", "sidak", "holm"]
if args.fdr:
methods.append("fdr")
obo_dag = GODag(obo_file=args.obo)
propagate_counts = not args.no_propagate_counts
g = GOEnrichmentStudy(pop, assoc, obo_dag,
propagate_counts=propagate_counts,
alpha=args.alpha,
study=study, methods=methods)
g.print_summary(min_ratio=min_ratio, indent=args.indent, pval=args.pval)
def FindEnrichment(obo, ontology, gi_info, gis):
# Parses the list of gis into lists of gi groups, and creates a mapping from
# gi to group.
groups = [[int(gi) for gi in group.split(',')] for group in gis.split('|')]
gi_to_group = {gi: i for i, group in enumerate(groups) for gi in group}
# Creates a gi to index map for sorting purposes.
gis_index = {
g: i
for i, g in enumerate(gi for group in groups for gi in group)
}
# Creates a gi to gene id mapping.
gis = gis_index.keys()
gi_to_gene = {
gi: d['gene_id']
for d in gi_info.find({'gis': {
'$in': gis
}}) if 'gene_id' in d and d['gene_id'] for gi in d['gis']
}
# Creatss a gene to gis list mapping.
gene_to_gis = defaultdict(set)
for gi, gene in gi_to_gene.iteritems():
gene_to_gis[gene].add(gi)
genes = set(gi_to_gene.itervalues())
# Parameters for goatools:
# Test-wise alpha for multiple testing
alpha = 0.05
# Family-wise alpha (whole experiment), only print out Bonferroni p-value is
# less than this value.
pval = 0.05
# the population file as a comparison group. if this flag is specified, the
# population is used as the study plus the `population/comparison`
compare = False
# only show values where the difference between study and population ratios is
# greater than this. useful for excluding GO categories with small differences
# but containing large numbers of genes. should be a value between 1 and 2.
min_ratio = None
# Calculates the false discovery rate (alt. to the Bonferroni but slower)
fdr = False
# Modifies the associations dictionary to become consistent with the actual term
# ids and gene ids.
associations = {
int(k): set('GO:%s' % str(go).zfill(7) for go in v)
for k, v in ontology['associations'].iteritems()
}
population = set(ontology['population'])
study = genes
methods = ['bonferroni'] # Other methods: sidak, holm, fdr
obo_dag = GODag(obo_file=obo)
# Performs the enrichment analysis
g = GOEnrichmentStudy(population,
associations,
obo_dag,
alpha=alpha,
study=study,
methods=methods)
# Creates a mapping from GO term to gene ids. This is done after the analysis
# since the analysis modifies the associations dictionary to include parent
# terms.
reverse_associations = defaultdict(set)
for k, v in associations.iteritems():
for go in v:
reverse_associations[go].add(k)
# Inserts each record into the final json array of results.
results = []
for record in g.results:
# This is done by default in goatools when print to standard output.
record.update_remaining_fields(min_ratio=min_ratio)
if record.p_bonferroni > pval or not record.is_ratio_different:
continue
# Only returns enriched records.
if record.enrichment != 'e':
continue
result = {}
result['id'] = record.id
level = obo_dag[result['id']].level
# Filteres by GO term depth to avoid GO terms that are too general.
if level < 2 and level >= 0:
continue
# FIlls in remaining fields.
result['term'] = record.description
study_ratio = _EvaluateFraction(record.ratio_in_study)
population_ratio = _EvaluateFraction(record.ratio_in_pop)
result['study_ratio'] = '%.4f' % study_ratio
result['population_ratio'] = '%.4f' % population_ratio
result['fold'] = study_ratio / population_ratio
result['pval'] = '%.3g' % record.p_bonferroni
# Uses the reverse associations dictionary to retrieve the list of gis that
# matched the term.
matched_genes = reverse_associations[result['id']] & genes
matched_gis = set(gi for gene in matched_genes
for gi in gene_to_gis[gene])
matched_gis &= set(gis)
matched_gis = list(matched_gis)
matched_gis.sort(key=lambda x: gis_index[x], reverse=True)
result['all_genes'] = matched_gis
# A representative set of genes is also returned in which only one gi per
# group is returned.
matched_groups = {gi_to_group[gi]: gi for gi in matched_gis}
matched_gis = matched_groups.values()
matched_gis.sort(key=lambda x: gis_index[x])
result['genes'] = matched_gis
results.append(result)
# Results are sorted based on how well the fold change between the study and
# popualtion ratios compares to other results, and how the number of
# representative genes compares to other results.
folds = sorted([r['fold'] for r in results])
lengths = sorted([len(r['genes']) for r in results])
results.sort(
key=lambda r:
(folds.index(r['fold']) + lengths.index(len(r['genes']))) / 2.0,
reverse=True)
return {'results': results}
'$in': list(forward_loci)
}}, {'_id': True})
]
# One of Ana's Sample
study_indexDB = '/home/gstupp/01_2015_mass_spec/H1_11082014/1108_Gly1_2014_12_15_15_29205/dtaselect_results_sfp0.01_p2/DTASelect-filter.txt'
study_ps = build_proteins_from_peptides.main(study_indexDB)
study_loci = set(chain(*[x['forward_loci'] for x in study_ps]))
study = setup_study_pop(study_loci)
# One of Sandip's microbiome samples
pop_indexDB = '/home/gstupp/01_2015_mass_spec/120314_SC_sampleH1sol_HCD35/DTASelect-filter.txt'
pop_ps = build_proteins_from_peptides.main(pop_indexDB)
pop_loci = set(chain(*[x['forward_loci'] for x in pop_ps]))
pop = setup_study_pop(study_loci and pop_loci)
# set up hash -> GO matching
assoc = setup_association(study_loci and pop_loci)
obo_dag = GODag(obo_file=os.path.expanduser("~/go/go-basic.obo"))
study_sub = study[:1000]
g = GOEnrichmentStudy(pop,
assoc,
obo_dag,
alpha=0.05,
study=study,
methods=["fdr"])
g.print_summary(min_ratio=None, indent=False, pval=None)
def check_enrichment(study_fn,
pop_fn,
assoc_fn,
print_summary=False,
save_summary=True,
savepath=None,
obo_dag=None):
p = optparse.OptionParser(__doc__)
p.add_option('--alpha',
default=0.05,
type="float",
help="Test-wise alpha for multiple testing "
"[default: %default]")
p.add_option('--pval',
default=None,
type="float",
help="Family-wise alpha (whole experiment), only print out "
"Bonferroni p-value is less than this value. "
"[default: %default]")
p.add_option('--compare',
dest='compare',
default=False,
action='store_true',
help="the population file as a comparison group. if this "
"flag is specified, the population is used as the study "
"plus the `population/comparison`")
p.add_option('--ratio',
dest='ratio',
type='float',
default=None,
help="only show values where the difference between study "
"and population ratios is greater than this. useful for "
"excluding GO categories with small differences, but "
"containing large numbers of genes. should be a value "
"between 1 and 2. ")
p.add_option('--fdr',
dest='fdr',
default=False,
action='store_true',
help="Calculate the false discovery rate (alt. to the "
"Bonferroni but slower)")
p.add_option('--indent',
dest='indent',
default=False,
action='store_true',
help="indent GO terms")
(opts, args) = p.parse_args()
args = [study_fn, pop_fn, assoc_fn]
bad = check_bad_args(args)
if bad:
print(bad)
sys.exit(p.print_help())
min_ratio = opts.ratio
if min_ratio is not None:
assert 1 <= min_ratio <= 2
assert 0 < opts.alpha < 1, "Test-wise alpha must fall between (0, 1)"
study_fn, pop_fn, assoc_fn = args
study, pop = read_geneset(study_fn, pop_fn, compare=opts.compare)
assoc = read_associations(assoc_fn)
methods = ["bonferroni", "sidak", "holm"]
if opts.fdr:
methods.append("fdr")
if obo_dag is None:
obo_file = "go-basic.obo"
obo_dag = GODag(obo_file=obo_file)
g = GOEnrichmentStudy(pop,
assoc,
obo_dag,
alpha=opts.alpha,
methods=methods)
results = g.run_study(study)
if print_summary:
g.print_summary(results,
min_ratio=min_ratio,
indent=opts.indent,
pval=opts.pval)
if save_summary:
if savepath is None:
savepath = study_fn.replace(
study_fn.split("/")[-1],
"enrichment_" + study_fn.split("/")[-1])
g.wr_tsv(savepath, results)
def term_enrichment(pop_genes,
gene_sets,
obo_path,
assoc_path,
folder,
condition,
regenerate=False,
test_sig=True,
**kwargs):
kwargs.setdefault('alpha', 0.05)
kwargs.setdefault('methods', ["bonferroni", "sidak", "holm"])
# Setup goatools enrichment
if regenerate:
assoc = read_associations(assoc_path)
go_dag = GODag(obo_file=obo_path)
pop = set(pop_genes)
g = GOEnrichmentStudy(pop, assoc, go_dag, **kwargs)
# go_enrich = OrderedDict()
go_enrich = OrderedDict()
for gc, genes in gene_sets.items():
# Write the gene list to a file
out_path = '{}/go_enrich/{}_{}_list.txt'.format(folder, condition, gc)
write_gene_list(genes, out_path)
enrich_path = out_path.replace('list', 'enrich')
try:
if regenerate:
raise ValueError('Override to retrain')
enrich = pd.read_csv(enrich_path, sep='\t', index_col=0)
except (FileNotFoundError, ValueError) as e:
r = g.run_study(frozenset(genes))
g.wr_tsv(enrich_path, r)
enrich = pd.read_csv(enrich_path, sep='\t', index_col=0)
enrich = enrich[(enrich.p_bonferroni < kwargs['alpha'])]
go_enrich[gc] = enrich
# Compile the results
# enrich_df = pd.concat(enrich_df, keys=gene_sets.keys())
# Get the sets
# go = enrich_df.groupby(level=0).apply(lambda x: set(x.index.get_level_values(1)))
go_sizes, go_terms = all_subsets(go_enrich)
all_terms = pd.concat(go_terms.values())
all_depths = all_terms['depth']
all_median = np.median(all_depths)
if test_sig:
for gene_class, terms in go_terms.items():
d = terms['depth'].values
if len(d) < 3:
print(gene_class, ' Skipped')
continue
t_med = np.median(d)
if t_med > all_median:
alternative = 'less'
elif t_med < all_median:
alternative = 'greater'
else:
alternative = 'two.sided'
ks_p = d_ks_test(d, all_depths, alternative=alternative)
print(gene_class, t_med, all_median, ks_p, sep='\t')
return pd.concat(go_terms.values(), keys=go_terms.keys())
