def run(study, pop, assoc, alpha=0.05, p_value=0.05, compare=False, ratio=None, obo='go-basic.obo', no_propagate_counts=False,
method='bonferroni,sidak,holm', pvalcalc='fisher'):
'''
This is the wrapper of the Goatools function.
:param study: a list of study gene
:param pop: a list of population gene
:param assoc: the association from the gene to the go term
:return:
'''
if type(study) == str and type(pop) == str:
# load the study and pop from the file
study, pop = GO._read_geneset(study, pop, compare=compare)
else:
# convert to the set
study = frozenset(study)
pop = set(pop)
methods = method.split(",")
if obo == 'go-basic.obo':
obo = os.path.dirname(os.path.realpath(__file__)) + "/obo/go.obo"
if not os.path.exists(obo):
print("obo file not found, start to download")
wget.download('http://purl.obolibrary.org/obo/go/go-basic.obo', obo)
obo_dag = GODag(obo)
propagate_counts = not no_propagate_counts
if type(assoc) == dict:
buf = ""
for k, v in assoc.items():
if not v: continue
line = ";".join([str(x) for x in v if x])
buf += "{}\t{}\n".format(k, line)
path = os.path.dirname(os.path.realpath(__file__)) + "/assoc"
with open(path, 'w') as fp:
fp.write(buf)
assoc = read_associations(path)
elif type(assoc) == defaultdict:
pass
else:
# if from a file
assoc = read_associations(assoc)
g = GOEnrichmentStudy(pop, assoc, obo_dag,
propagate_counts=propagate_counts,
alpha=alpha,
pvalcalc=pvalcalc,
methods=methods)
results = g.run_study(study)
# g.print_summary(results, min_ratio=ratio, indent=False, pval=p_value)
r = 'GO\tNS\tenrichment\tname\tratio_in_study\tratio_in_pop\tp_uncorrected\tdepth\tstudy_count\tp_bonferroni\tp_sidak\tp_holm\thit\n'
for x in results:
r += x.__str__() + "\n"
tb = pd.read_table(StringIO(r))
return GO(tb, study, pop, assoc, alpha, p_value, compare, ratio, obo, no_propagate_counts, method, pvalcalc, obo_dag)
def __init__(self, go_obo_path='data/go.obo'):
canonical_orfs = paper_orfs
self.obodag = GODag(go_obo_path)
# read genes containing GO Ontology annotations
orfs_with_go = read_sgd_orfs()
# only use canonical orfs dataset
self.orfs_with_go = orfs_with_go.join(canonical_orfs[[]], how='inner')
# create mapping of gene names to set of GO annotaitons
assoc = defaultdict(set)
for idx, gene in self.orfs_with_go.iterrows():
assoc[gene['name']] = set(gene.ontology.split(','))
self.assoc = assoc
self.methods = ['fdr_bh', 'bonferroni']
self.devnull = open('/dev/null', 'w')
# create GO enrichment object to run GO
self.goeaobj = GOEnrichmentStudy(
assoc.keys(), # List of protein-coding genes
assoc, # geneid/GO associations
self.obodag, # Ontologies
propagate_counts=False,
alpha=0.05, # default significance cut-off
methods=self.methods,
log=self.devnull)
def test_i122():
"""Test to re-produce issue#122: Passes currently."""
obj = _Run(9606, 'gene2go', 'go-basic.obo')
study_ids, population_ids = obj.get_genes_study_n_bg()
# Result is the same whether fisher_scipy_stats of fisher
pvalcalc = 'fisher_scipy_stats'
goeaobj = GOEnrichmentStudy(population_ids,
obj.gene2go,
obj.godag,
methods=['bonferroni', 'fdr_bh'],
pvalcalc=pvalcalc)
# Run GOEA Gene Ontology Enrichment Analysis
results_goeas = goeaobj.run_study_nts(study_ids)
print(
'NS GO p stu_ratio pop_ratio p-uncorr bonferro fdr_bh stu '
)
for ntd in results_goeas:
if ntd.study_count == 0:
doprt = False
if ntd.p_bonferroni < 0.05:
assert ntd.enrichment == 'p'
doprt = True
if ntd.p_fdr_bh < 0.05:
assert ntd.enrichment == 'p'
doprt = True
if doprt:
print(obj.str_nt(ntd))
def perform_gene_enrichment_analysis(self, metagene_matrix, method='fdr'):
# Load the Gene Ontology
n_comps = metagene_matrix.shape[1]
self.download_and_cache_resources(
) # Download ontology and annotations, if necessary
gene_ontology = obo_parser.GODag('../DownloadedResources/go-basic.obo')
# Load the human annotations
c = 0
with gzip.open('../DownloadedResources/goa_human.gaf.gz', 'rt') as gaf:
funcs = {}
for entry in GOA.gafiterator(gaf):
c += 1
uniprot_id = entry.pop('DB_Object_Symbol')
funcs[uniprot_id] = entry
# Our population is the set of genes we are analysing
population = self.gene_symbols()
print("We have %d genes in our population" % len(population))
# Build associations from functional annotations we got from the gaf file
associations = {}
for x in funcs:
if x not in associations:
associations[x] = set()
associations[x].add(str(funcs[x]['GO_ID']))
gea = GOEnrichmentStudy(population,
associations,
gene_ontology,
propagate_counts=True,
alpha=0.05,
methods=[method])
gea_results_by_component = {}
rankings = self.ranked_genes_by_component(metagene_matrix)
for ci in range(n_comps):
study_genes = rankings[ci]
print('\nComp. %d: %s...' % (ci, str(study_genes[:10])))
gea_results_by_component[ci] = gea.run_study(study_genes)
# Get results into a dataframe per component. Easiest way is to use routine to
# write a .tsv file, then read back and filter
gea_results_df_by_component = []
for ci in range(n_comps):
ge_df = self._perform_gene_enrichment_analysis_one_component(
ci, gea_results_by_component, gea)
if ge_df is not None:
gea_results_df_by_component += [ge_df]
# Merge the per-component dataframes into a single one
gea_all_sig_results_df = pd.DataFrame()
gea_all_sig_results_df = gea_all_sig_results_df.append(
gea_results_df_by_component)
gea_all_sig_results_df.to_csv(self.cache_dir +
'%s_gea_all.tsv' % self.prefix,
sep='\t')
class GoEnrich():
def __init__(self):
obodag = GODag("../Data/evaluation_reference/goslim_yeast.obo")
background = [line.strip() for line in open('../Data/evaluation_reference/gene_list.txt')]
geneid2gos_yeast = read_associations('../Data/evaluation_reference/geneid2gos_yeast.txt')
self.goeaobj = GOEnrichmentStudy(
background,
geneid2gos_yeast,
obodag,
propogate_counts=False,
alpha=0.05,
methods=['fdr_bh'])
def measure_enrichment(self,
gene_set=['YML106W', 'YKL135C', 'YDR516C',
'YLR420W', 'YNL111C', 'YHR007C',
'YLR014C', 'YKL216W', 'YNL078W',
'YJR005W', 'YJL130C'],
run_name='base',
cluster_id=1):
gene_ids = ['YML106W', 'YKL135C', 'YDR516C', 'YLR420W', 'YNL111C',
'YHR007C', 'YLR014C', 'YKL216W', 'YNL078W', 'YJR005W',
'YJL130C']
goea_results_all = self.goeaobj.run_study(gene_ids)
# we can get significant only
# goea_results_sig = [r for r in goea_results_all if r.p_fdr_bh < 0.05]
self.goeaobj.wr_txt("../Results/" + run_name + "_" + str(cluster_id) +
".txt", goea_results_all)
def __init__(self, dir, params):
"""
"""
super().__init__(dir, params)
set_logger(os.path.join(self.dir, 'experiment.log'),
level=logging.INFO, console=True)
logging.info("Loading disease associations...")
self.diseases_dict = load_diseases(self.params["associations_path"],
self.params["disease_subset"],
exclude_splits=['none'])
logging.info("Loading network...")
self.network = Network(self.params["ppi_network"])
self.degrees = np.array(list(dict(self.network.nx.degree()).values()))
logging.info("Loading weights...")
with open(os.path.join(params["model_path"], "models", "models.tar"), "rb") as f:
split_to_model = pickle.load(f)
self.ci_weights = ci_weights = np.mean([model['ci_weight'][0, 0].numpy()
for model in split_to_model.values()], axis=0)
self.ci_weights_norm = self.ci_weights / np.sqrt(self.degrees)
logging.info("Loading enrichment study...")
geneid2go = read_ncbi_gene2go("data/go/gene2go.txt", taxids=[9606])
obodag = GODag("data/go/go-basic.obo")
self.go_study = GOEnrichmentStudy(self.network.get_names(),
geneid2go,
obodag,
propagate_counts = True,
alpha = 0.05,
methods = ['fdr_bh'])
def check_group_enrichment(tested_gene_file_name, total_gene_file_name):
total_gene_list = load_gene_list(total_gene_file_name)
tested_gene = load_gene_list(tested_gene_file_name)
if not os.path.exists(os.path.join(constants.GO_DIR, constants.GO_FILE_NAME)):
download(constants.GO_OBO_URL, constants.GO_DIR)
obo_dag = GODag(os.path.join(constants.GO_DIR, constants.GO_FILE_NAME))
if not os.path.exists(os.path.join(constants.GO_DIR, constants.GO_ASSOCIATION_FILE_NAME)):
download(constants.GO_ASSOCIATION_GENE2GEO_URL, constants.GO_DIR)
with gzip.open(os.path.join(constants.GO_DIR, os.path.basename(constants.GO_ASSOCIATION_GENE2GEO_URL)), 'rb') as f_in:
with open(os.path.join(constants.GO_DIR, constants.GO_ASSOCIATION_FILE_NAME),'wb') as f_out:
shutil.copyfileobj(f_in, f_out)
assoc = read_ncbi_gene2go(os.path.join(constants.GO_DIR, constants.GO_ASSOCIATION_FILE_NAME), no_top=True)
g = GOEnrichmentStudy([int(cur) for cur in ensembl2entrez_convertor(total_gene_list)],
assoc, obo_dag, methods=["bonferroni", "fdr_bh"])
g_res = g.run_study([int(cur) for cur in ensembl2entrez_convertor(tested_gene)])
GO_results = [(cur.NS, cur.GO, cur.goterm.name, cur.p_uncorrected, cur.p_fdr_bh) for cur in g_res if
cur.p_fdr_bh <= 0.05]
if len(GO_results) > 0:
go_ns, go_terms, go_names, uncorrectd_pvals, FDRs = zip(*GO_results)
else:
go_terms = []
uncorrectd_pvals = []
FDRs = []
go_names = []
go_ns = []
output_rows = [("\r\n".join(e2g_convertor(tested_gene)), "\r\n".join(go_ns),
"\r\n".join(go_terms), "\r\n".join(go_names), "\r\n".join(map(str, uncorrectd_pvals)),
"\r\n".join(map(str, FDRs)))]
print_to_excel(output_rows, tested_gene_file_name, total_gene_file_name)
def test_goea():
"""Test GOEA with method, fdr."""
obo_dag = GODag("go-basic.obo")
assoc = read_associations("../data/association", no_top=True)
popul_ids = [line.rstrip() for line in open("../data/population")]
study_ids = [line.rstrip() for line in open("../data/study")]
goeaobj = GOEnrichmentStudy(popul_ids, assoc, obo_dag, methods=['fdr'])
goea_results = goeaobj.run_study(study_ids)
goeaobj.print_summary(goea_results)
def get_goea_results(method="fdr_bh"):
"""Get GOEA results."""
root_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "data")
obo_fin = os.path.join(root_dir, "goslim_generic.obo")
obo_dag = GODag(obo_fin)
assoc = read_associations(os.path.join(root_dir, "slim_association"), no_top=True)
popul_ids = [line.rstrip() for line in open(os.path.join(root_dir, "small_population"))]
goeaobj = GOEnrichmentStudy(popul_ids, assoc, obo_dag, methods=[method])
study_ids = [line.rstrip() for line in open(os.path.join(root_dir, "small_study"))]
goea_results = goeaobj.run_study(study_ids, methods=[method])
return goea_results
def get_goea_results(method="fdr_bh"):
"""Get GOEA results."""
root_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "data")
obo_fin = os.path.join(root_dir, "goslim_generic.obo")
obo_dag = GODag(obo_fin)
assoc = read_associations(os.path.join(root_dir, "slim_association"), no_top=True)
popul_ids = [line.rstrip() for line in open(os.path.join(root_dir, "small_population"))]
goeaobj = GOEnrichmentStudy(popul_ids, assoc, obo_dag, methods=[method])
study_ids = [line.rstrip() for line in open(os.path.join(root_dir, "small_study"))]
goea_results = goeaobj.run_study(study_ids, methods=[method])
return goea_results
def test_i96():
"""Test to re-produce issue#96: Passes currently."""
# Trying to duplicate: ValueError("All values in table must be nonnegative.
# Get genes
study_ids = _get_geneids()
population_ids = GeneID2nt.keys()
# Get databases
gene2go = get_assoc_ncbi_taxids([9606], loading_bar=None)
fin_obo = os.path.join(os.getcwd(), "go-basic.obo")
godag = get_godag(fin_obo, loading_bar=None)
goeaobj = GOEnrichmentStudy(population_ids, gene2go, godag, methods=['fdr_bh'])
# Run GOEA Gene Ontology Enrichment Analysis
results_goeas = goeaobj.run_study(study_ids)
def _get_pvals(pvalfnc_names, prt=sys.stdout):
fisher2pvals = {}
taxid = 10090 # Mouse study
obo_dag = GODag(download_go_basic_obo(prt=prt))
geneids_pop = GeneID2nt_mus.keys()
assoc_geneid2gos = get_assoc_ncbi_taxids([taxid])
geneids_study = _get_geneid2symbol("nbt.3102-S4_GeneIDs.xlsx", prt)
for fisher in pvalfnc_names:
goeaobj = GOEnrichmentStudy(
geneids_pop, assoc_geneid2gos, obo_dag, propagate_counts=False, alpha=0.05, methods=None, pvalcalc=fisher
)
fisher2pvals[fisher] = goeaobj._get_pval_uncorr(geneids_study, prt)
return fisher2pvals
def run_bonferroni(log):
"""Do Gene Ontology Enrichment Analysis w/Bonferroni multipletest. Print results 3 ways."""
# ---------------------------------------------------------------------
# Run Gene Ontology Analysis (GOEA)
#
# 1. Initialize
obo_dag = GODag("go-basic.obo")
assoc = read_associations("../data/association", no_top=True)
popul_ids = [line.rstrip() for line in open("../data/population")]
study_ids = [line.rstrip() for line in open("../data/study")]
# 2. Run enrichment analysis
goea = GOEnrichmentStudy(popul_ids, assoc, obo_dag, alpha=0.05, methods=['bonferroni'])
results_nt = goea.run_study(study_ids)
return results_nt, goea
def run_bonferroni():
"""Do Gene Ontology Enrichment Analysis w/Bonferroni multipletest. Print results 3 ways."""
# ---------------------------------------------------------------------
# Run Gene Ontology Analysis (GOEA)
#
# 1. Initialize
godag = get_godag(os.path.join(os.getcwd(), "go-basic.obo"), loading_bar=None)
assoc = read_associations(os.path.join(REPO, "data/association"), no_top=True)
popul_ids = [line.rstrip() for line in open(os.path.join(REPO, "data/population"))]
study_ids = [line.rstrip() for line in open(os.path.join(REPO, "data/study"))]
# 2. Run enrichment analysis
goea = GOEnrichmentStudy(popul_ids, assoc, godag, alpha=0.05, methods=['bonferroni'])
results_nt = goea.run_study(study_ids)
return results_nt, goea
def _get_results(godag, propagate_counts, relationships, prt=sys.stdout):
"""Run a GOEA. Return results"""
taxid = 10090 # Mouse study
geneids_pop = set(GeneID2nt_mus.keys())
assoc_geneid2gos = get_assoc_ncbi_taxids([taxid], loading_bar=None)
geneids_study = get_geneid2symbol("nbt.3102-S4_GeneIDs.xlsx")
goeaobj = GOEnrichmentStudy(geneids_pop,
assoc_geneid2gos,
godag,
propagate_counts=propagate_counts,
relationships=relationships,
alpha=0.05,
methods=['fdr_bh'])
return goeaobj.run_study(geneids_study, prt=prt)
def _get_results(godag, propagate_counts, relationships, prt=sys.stdout):
"""Run a GOEA. Return results"""
taxid = 10090 # Mouse study
geneids_pop = set(GeneID2nt_mus.keys())
assoc_geneid2gos = get_assoc_ncbi_taxids([taxid], loading_bar=None)
geneids_study = get_geneid2symbol("nbt.3102-S4_GeneIDs.xlsx")
goeaobj = GOEnrichmentStudy(
geneids_pop,
assoc_geneid2gos,
godag,
propagate_counts=propagate_counts,
relationships=relationships,
alpha=0.05,
methods=['fdr_bh'])
return goeaobj.run_study(geneids_study, prt=prt)
def run_bonferroni():
"""Do Gene Ontology Enrichment Analysis w/Bonferroni multipletest. Print results 3 ways."""
# ---------------------------------------------------------------------
# Run Gene Ontology Analysis (GOEA)
#
# 1. Initialize
godag = get_godag(os.path.join(os.getcwd(), "go-basic.obo"), loading_bar=None)
fin_assc = os.path.join(REPO, "data/association")
assoc = read_associations(fin_assc, 'id2gos', no_top=True)
popul_ids = [line.rstrip() for line in open(os.path.join(REPO, "data/population"))]
study_ids = [line.rstrip() for line in open(os.path.join(REPO, "data/study"))]
# 2. Run enrichment analysis
goea = GOEnrichmentStudy(popul_ids, assoc, godag, alpha=0.05, methods=['bonferroni'])
results_nt = goea.run_study(study_ids)
return results_nt, goea
def go_enrichment_study(self):
if self._go_enrichment_study is None:
# Load the human annotations
c = 0
with gzip.open('../DownloadedResources/goa_human.gaf.gz',
'rt') as gaf:
funcs = {}
for entry in GOA.gafiterator(gaf):
c += 1
uniprot_id = entry.pop('DB_Object_Symbol')
funcs[uniprot_id] = entry
# Our population is the set of genes we are analysing
population = self.gene_symbols()
print("We have %d genes in our population" % len(population))
# Build associations from functional annotations we got from the gaf file
associations = {}
for x in funcs:
if x not in associations:
associations[x] = set()
associations[x].add(str(funcs[x]['GO_ID']))
self._go_enrichment_study = \
GOEnrichmentStudy(population, associations, self._gene_ontology,
propagate_counts=True,
alpha=0.01,
methods=[self.method])
return self._go_enrichment_study
def get_goeaobj(methods=None):
"""Test GOEA with method, fdr."""
obo_dag = GODag("go-basic.obo")
assoc = read_associations("../data/association", no_top=True)
popul_ids = [line.rstrip() for line in open("../data/population")]
goeaobj = GOEnrichmentStudy(popul_ids, assoc, obo_dag, methods=methods)
return goeaobj
def get_goeaobj(methods=None):
"""Test GOEA with method, fdr."""
obo_dag = GODag(ROOT + "goslim_generic.obo")
assoc = read_associations(ROOT + "slim_association", no_top=True)
popul_ids = [line.rstrip() for line in open(ROOT + "small_population")]
goeaobj = GOEnrichmentStudy(popul_ids, assoc, obo_dag, methods=methods)
return goeaobj
def _get_pvals(pvalfnc_names, prt=sys.stdout):
fisher2pvals = {}
taxid = 10090 # Mouse study
obo_dag = GODag(download_go_basic_obo(prt=prt))
geneids_pop = GeneID2nt_mus.keys()
assoc_geneid2gos = get_assoc_ncbi_taxids([taxid])
geneids_study = _get_geneid2symbol("nbt.3102-S4_GeneIDs.xlsx", prt)
for fisher in pvalfnc_names:
goeaobj = GOEnrichmentStudy(geneids_pop,
assoc_geneid2gos,
obo_dag,
propagate_counts=False,
alpha=0.05,
methods=None,
pvalcalc=fisher)
fisher2pvals[fisher] = goeaobj._get_pval_uncorr(geneids_study, prt)
return fisher2pvals
def __init__(self, dir, params):
"""
Constructor
Args:
dir (string) directory of the experiment to be run
"""
super().__init__(dir, params)
# Set the logger
set_logger(os.path.join(self.dir, 'experiment.log'),
level=logging.INFO, console=True)
# Log title
logging.info("Disease Protein Prediction")
logging.info("Sabri Eyuboglu -- SNAP Group")
logging.info("======================================")
logging.info("Loading Disease Associations...")
self.diseases_dict = load_diseases(self.params["associations_path"],
self.params["disease_subset"],
exclude_splits=['none'])
logging.info("Loading Network...")
self.network = Network(self.params["ppi_network"])
logging.info("Loading enrichment study...")
obodag = GODag(self.params["go_path"])
geneid2go = read_ncbi_gene2go(self.params["gene_to_go_path"], taxids=[9606])
self.enrichment_study = GOEnrichmentStudy(self.network.get_names(),
geneid2go,
obodag,
log=None,
**self.params["enrichment_params"])
logging.info("Loading predictions...")
self.method_to_preds = {name: pd.read_csv(os.path.join(preds, "predictions.csv"),
index_col=0)
for name, preds in self.params["method_to_preds"].items()}
outputs_path = os.path.join(self.dir, "outputs.pkl")
if os.path.exists(outputs_path):
logging.info("Loading outputs...")
with open(outputs_path, 'rb') as f:
self.outputs = pickle.load(f)
else:
self.outputs = {}
def _get_pvals(pvalfnc_names, prt=sys.stdout):
fisher2pvals = {}
taxid = 10090 # Mouse study
file_obo = os.path.join(os.getcwd(), "go-basic.obo")
obo_dag = get_godag(file_obo, prt, loading_bar=None)
geneids_pop = GeneID2nt_mus.keys()
assoc_geneid2gos = get_assoc_ncbi_taxids([taxid], loading_bar=None)
geneids_study = get_geneid2symbol("nbt.3102-S4_GeneIDs.xlsx")
for fisher in pvalfnc_names:
goeaobj = GOEnrichmentStudy(geneids_pop,
assoc_geneid2gos,
obo_dag,
propagate_counts=False,
alpha=0.05,
methods=None,
pvalcalc=fisher)
fisher2pvals[fisher] = goeaobj.get_pval_uncorr(geneids_study, prt)
return fisher2pvals
def get_goeaobj(methods=None):
"""Test GOEA with method, fdr."""
obo_fin = os.path.join(REPO, "go-basic.obo")
obo_dag = get_godag(obo_fin, loading_bar=None)
assoc = read_associations("{REPO}/tests/data/small_association".format(REPO=REPO), no_top=True)
popul_fin = "{REPO}/tests/data/small_population".format(REPO=REPO)
popul_ids = [line.rstrip() for line in open(popul_fin)]
goeaobj = GOEnrichmentStudy(popul_ids, assoc, obo_dag, methods=methods)
return goeaobj
def get_goeaobj(self, pop_genes, assoc_geneid2gos):
"""Return a GOEnrichmentStudy specific for user-provided pop_genes and associations."""
return GOEnrichmentStudy(pop_genes,
assoc_geneid2gos,
self.go_dag,
propagate_counts=self.propagate_counts,
alpha=self.alpha,
methods=[self.method],
log=None)
def init_goea(**kws):
"""Initialize GODag and GOEnrichmentStudy."""
godag = get_godag(os.path.join(os.getcwd(), "go-basic.obo"), loading_bar=None)
fin_assc = ROOT + "association"
assoc = read_associations(fin_assc, 'id2gos', no_top=True)
popul_ids = [line.rstrip() for line in open(ROOT + "population")]
methods = kws['methods'] if 'methods' in kws else ['not_bonferroni']
study_ids = [line.rstrip() for line in open(ROOT + "study")]
return GOEnrichmentStudy(popul_ids, assoc, godag, methods=methods), study_ids
def init_goea(**kws):
"""Initialize GODag and GOEnrichmentStudy."""
obo_dag = GODag(ROOT + "go-basic.obo")
assoc = read_associations(ROOT + "association", no_top=True)
popul_ids = [line.rstrip() for line in open(ROOT + "population")]
methods = kws['methods'] if 'methods' in kws else ['not_bonferroni']
study_ids = [line.rstrip() for line in open(ROOT + "study")]
return GOEnrichmentStudy(popul_ids, assoc, obo_dag,
methods=methods), study_ids
def _init_objgoea(self, pop, assoc):
"""Run gene ontology enrichment analysis (GOEA)."""
propagate_counts = not self.args.no_propagate_counts
return GOEnrichmentStudy(pop, assoc, self.godag,
propagate_counts=propagate_counts,
relationships=False,
alpha=self.args.alpha,
pvalcalc=self.args.pvalcalc,
methods=self.methods)
def run_bonferroni(log):
"""Do Gene Ontology Enrichment Analysis w/Bonferroni multipletest. Print results 3 ways."""
# ---------------------------------------------------------------------
# Run Gene Ontology Analysis (GOEA)
#
# 1. Initialize
obo_dag = GODag("go-basic.obo")
assoc = read_associations("../data/association", no_top=True)
popul_ids = [line.rstrip() for line in open("../data/population")]
study_ids = [line.rstrip() for line in open("../data/study")]
# 2. Run enrichment analysis
goea = GOEnrichmentStudy(popul_ids,
assoc,
obo_dag,
alpha=0.05,
methods=['bonferroni'])
results_nt = goea.run_study(study_ids)
return results_nt, goea
def test_i96():
"""Test to re-produce issue#96: Passes currently."""
# Trying to duplicate: ValueError("All values in table must be nonnegative.
# Get genes
print('CWD', os.getcwd())
study_ids = _get_geneids()
population_ids = GENEID2NT.keys()
# Get databases
print(os.getcwd())
fin = os.path.join(REPO, 'gene2go')
dnld_ncbi_gene_file(fin, loading_bar=None)
gene2go = read_ncbi_gene2go(fin, [9606])
fin_obo = os.path.join(REPO, "go-basic.obo")
godag = get_godag(fin_obo, loading_bar=None)
goeaobj = GOEnrichmentStudy(population_ids, gene2go, godag, methods=['fdr_bh'])
# Run GOEA Gene Ontology Enrichment Analysis
results_goeas = goeaobj.run_study(study_ids)
def create_enrichment_study(self):
obj = GOEnrichmentStudy(
self.background, # List of human protein-coding genes (Entrez IDs)
self.geneid2gos_human, # Gene ID / GO associtations
self.obodag, # Ontologies
propagate_counts=False,
alpha=self.alpha, # Significance cutoff
methods=['fdr_bh'] # Multiple hypothesis correction
)
return obj
def __init__(self):
obodag = GODag("../Data/evaluation_reference/goslim_yeast.obo")
background = [line.strip() for line in open('../Data/evaluation_reference/gene_list.txt')]
geneid2gos_yeast = read_associations('../Data/evaluation_reference/geneid2gos_yeast.txt')
self.goeaobj = GOEnrichmentStudy(
background,
geneid2gos_yeast,
obodag,
propogate_counts=False,
alpha=0.05,
methods=['fdr_bh'])
def get_objgoea(pop, assoc, args):
"""Run gene ontology enrichment analysis (GOEA)."""
obo_dag = GODag(obo_file=args.obo)
methods = args.method.split(",")
propagate_counts = not args.no_propagate_counts
return GOEnrichmentStudy(pop,
assoc,
obo_dag,
propagate_counts=propagate_counts,
alpha=args.alpha,
pvalcalc=args.pvalcalc,
methods=methods)
def get_goeaobj(method, geneids_pop, taxid):
"""Load: ontologies, associations, and population geneids."""
obo_dag = get_godag()
assoc_geneid2gos = get_assoc_ncbi_taxids([taxid])
goeaobj = GOEnrichmentStudy(geneids_pop,
assoc_geneid2gos,
obo_dag,
propagate_counts=False,
alpha=0.05,
methods=[method])
# obo_dag is also found in goeaobj.obo_dag
return goeaobj
def test_i122():
"""Test to re-produce issue#122: Passes currently."""
obj = _Run(9606, 'gene2go', 'go-basic.obo')
study_ids, population_ids = obj.get_genes_study_n_bg()
# Result is the same whether fisher_scipy_stats of fisher
pvalcalc = 'fisher_scipy_stats'
goeaobj = GOEnrichmentStudy(population_ids, obj.gene2go, obj.godag, methods=['bonferroni', 'fdr_bh'], pvalcalc=pvalcalc)
# Run GOEA Gene Ontology Enrichment Analysis
results_goeas = goeaobj.run_study_nts(study_ids)
print('NS GO p stu_ratio pop_ratio p-uncorr bonferro fdr_bh stu ')
for ntd in results_goeas:
if ntd.study_count == 0:
doprt = False
if ntd.p_bonferroni < 0.05:
assert ntd.enrichment == 'p'
doprt = True
if ntd.p_fdr_bh < 0.05:
assert ntd.enrichment == 'p'
doprt = True
if doprt:
print(obj.str_nt(ntd))
def test_i96():
"""Test to re-produce issue#96: Passes currently."""
# Trying to duplicate: ValueError("All values in table must be nonnegative.
# Get genes
print('CWD', os.getcwd())
study_ids = _get_geneids()
population_ids = GENEID2NT.keys()
# Get databases
print(os.getcwd())
fin = os.path.join(REPO, 'gene2go')
dnld_ncbi_gene_file(fin, loading_bar=None)
gene2go = read_ncbi_gene2go(fin, [9606])
fin_obo = os.path.join(REPO, "go-basic.obo")
godag = get_godag(fin_obo, loading_bar=None)
goeaobj = GOEnrichmentStudy(population_ids,
gene2go,
godag,
methods=['fdr_bh'])
# Run GOEA Gene Ontology Enrichment Analysis
results_goeas = goeaobj.run_study(study_ids)
def get_goeaobj(method, geneids_pop, taxid):
"""Load: ontologies, associations, and population geneids."""
fin_obo = os.path.join(os.getcwd(), "go-basic.obo")
godag = get_godag(fin_obo, loading_bar=None)
assoc_geneid2gos = get_assoc_ncbi_taxids([taxid], loading_bar=None)
goeaobj = GOEnrichmentStudy(geneids_pop,
assoc_geneid2gos,
godag,
propagate_counts=False,
alpha=0.05,
methods=[method])
# godag is also found in goeaobj.godag
return goeaobj
def return_enrichment_study_obj(gaf_taxfiltered):
'''
Generate go enrichment study object with a background dataset.
'''
obodag = GODag(config_utils.datadir + "/GOData/go-basic.obo")
goeaobj = GOEnrichmentStudy(
gaf_taxfiltered.keys(), #
gaf_taxfiltered, # geneid/GO associations possible with tree used for DB
obodag, # Ontologies
propagate_counts=False,
alpha=0.15, # default significance cut-off
methods=['fdr_bh']) # defult multipletest correction method
return goeaobj
def get_goeaobj(method, geneids_pop, taxid):
"""Load: ontologies, associations, and population geneids."""
fin_obo = "go-basic.obo"
if not os.path.isfile(fin_obo):
wget.download("wget http://geneontology.org/ontology/go-basic.obo")
obo_dag = GODag(fin_obo)
assoc_geneid2gos = get_assoc_ncbi_taxids([taxid])
goeaobj = GOEnrichmentStudy(geneids_pop,
assoc_geneid2gos,
obo_dag,
propagate_counts=False,
alpha=0.05,
methods=[method])
return goeaobj
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,
methods=methods)
results = g.run_study(study)
g.print_summary(results, min_ratio=min_ratio, indent=args.indent, pval=args.pval)
def _ns2o(pop, ns2assoc, godag, propagate_counts, alpha, methods, **kws):
return {
ns:GOEnrichmentStudy(pop, a, godag, propagate_counts, alpha, methods, name=ns, **kws) \
for ns, a in sorted(ns2assoc.items())}
# Data will be stored in this variable
import os
import sys
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import goatools
from goatools.base import download_go_basic_obo
from goatools.base import download_ncbi_associations
from goatools.obo_parser import GODag
from goatools.associations import read_ncbi_gene2go
from goatools.test_data.genes_NCBI_10090_ProteinCoding import GeneID2nt as GeneID2nt_mus
from goatools.go_enrichment import GOEnrichmentStudy
obo_fname = download_go_basic_obo()
gene2go = download_ncbi_associations()
obodag = GODag("go-basic.obo")
geneid2gos_mouse = read_ncbi_gene2go("gene2go", taxids=[10090])
geneid2symbol = {}
print("{N:,} annotated mouse genes".format(N=len(geneid2gos_mouse)))
print(GeneID2nt_mus.keys().head())
goeaobj = GOEnrichmentStudy(
GeneID2nt_mus.keys(), # List of mouse protein-coding genes
geneid2gos_mouse, # geneid/GO associations
obodag, # Ontologies
propagate_counts=False,
alpha=0.05, # default significance cut-off
methods=['fdr_bh']) # defult multipletest correction method
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 = args.method.split(",")
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,
pvalcalc=args.pvalcalc,
methods=methods)
results = g.run_study(study)
if args.outfile is None:
g.print_summary(results, min_ratio=min_ratio, indent=args.indent, pval=args.pval)
else:
# Users can print to both tab-separated file and xlsx file in one run.
outfiles = args.outfile.split(",")
prt_if = None # Print all values
if args.pval is not None:
# Only print out when uncorrected p-value < this value.
prt_if = lambda nt: nt.p_uncorrected < args.pval
for outfile in outfiles:
if outfile.endswith(".xlsx"):
g.wr_xlsx(outfile, results, prt_if=prt_if)
elif snakemake.wildcards.state_type == 'Enhancer':
min_dist = 5000
max_dist = 50000
else:
sys.exit(-1)
with open(snakemake.input.clusters) as f:
for line in f:
cols = line.strip().split()
cluster = chr(int(cols[3]) + 65)
if int(cols[-1]) <= max_dist and int(cols[-1]) >= min_dist:
genes[cluster].add(cols[7])
background.add(cols[7])
obodag = GODag("go-basic.obo")
id2go = read_associations("sym2go.txt")
goeaobj = GOEnrichmentStudy(background, id2go, obodag, propagate_counts=False, alpha=0.05, methods=['fdr_bh'])
outfile = open(snakemake.output.txt, 'w')
for cluster, geneids in sorted(genes.items()):
outfile.write("Cluster {}\n".format(cluster))
goea_results_all = goeaobj.run_study(geneids)
for fdr, name, enrichment in sorted([(r.p_fdr_bh, r.name, r.enrichment) for r in goea_results_all if r.p_fdr_bh < 0.2]):
outfile.write("\t{}\t{}\t{}\n".format(name, fdr, enrichment))
outfile.write("\n")
#GOEnrichmentStudy.print_summary(goea_results_sig)
