def test_get_pathway():
db = KEGGPathways()
pathway = db.get_pathway('hsa04630')
assert all(
[pathway.node[node]['type'] == 'gene' for node in pathway.nodes])
assert all(
isinstance(attr, list)
for attr in nx.get_edge_attributes(pathway, 'type').values())
assert all([pathway.degree(node) > 0 for node in pathway.nodes])
def run(self, experiment: Experiment) -> SPIAResult:
"""
Returns: a list of pathways: pathway id, pathway name, pNDE, pPERT, pG, FDR correction,
Bonferroni correction, status for each pathway
"""
pvalue = ttest(experiment) <= self.threshold
calc_f = experiment.calculate_fold_change()
all = pvalue.index.tolist()
for a in range(len(all)):
all[a] = all[a].name
p = pvalue[pvalue == True].index.tolist()
de = {}
for i in p:
de[i.name] = calc_f["FC"][i]
json = {}
if len(de) == 0:
# if there are no DEGs anywhere, the problem of finding the impact on various pathways is meaningless
print('No differentialy expressed genes.')
return SPIAResult([])
db = KEGGPathways(self.organism)
pathways = {}
for gene in de.keys():
ps = db.search_by_gene(gene)
for (k, v) in ps.items():
if k not in pathways.keys():
pathways[k] = v
if not pathways:
print('No pathways found in database.')
return SPIAResult([])
for (id, descr) in pathways.items():
pathway = db.get_pathway(id)
path_genes = set(pathway.nodes)
path_genes = list(path_genes)
interaction_list = {i: [] for i in rel}
x = get_edge_attributes(pathway, 'type')
for gene1, interaction in x.items():
interaction = '_'.join(interaction)
if interaction in interaction_list.keys():
interaction_list[interaction].append([
path_genes.index(gene1[0]),
path_genes.index(gene1[1])
])
else:
interaction_list[interaction] = [[
path_genes.index(gene1[0]),
path_genes.index(gene1[1])
]]
interaction_list['row_names'] = path_genes
json[id] = interaction_list
json['id2name'] = pathways
s = SPIA.calculate_spia(de, all, json)
result = SPIAResult(s)
if self.markdown:
result.generate_markdown(self.markdown, 'Results of SPIA:')
return result
def name_geneid(data, geneids):
geneid = []
for geny in geneids:
geneid.append(
KEGGPathways().get_gene_code(gen=geny.name).split()[0])
data['gene_name'] = data.index
data.index = geneid
return data, geneid
def test_keggpathways_init():
db = KEGGPathways()
assert db.organism == "hsa"
db1 = KEGGPathways("Gallus gallus")
db2 = KEGGPathways("gallus gallus")
db3 = KEGGPathways("chicken")
db4 = KEGGPathways("Chicken")
db5 = KEGGPathways("ChIcKeN")
assert all([d.organism == "gga" for d in [db1, db2, db3, db4, db5]])
def run(self, experiment: Experiment) -> ImpactAnalysisResult:
"""
Returns:
list of pathways sorted by their impact factor. Each pathway in the list has values of FDR and
Bonferroni corrections assigned.
"""
self.experiment_genes = set(
[gene.name for gene in experiment.get_all().genes])
# calculate fold change
self.FC = experiment.calculate_fold_change()
# remove genes for witch fold change cannot be calculated correctly
experiment.exclude_genes(
list(self.FC['FC'][isnan(self.FC['FC'])].index))
if self.degs:
self.degs = pd.Series({
Gene(x): True
for x in self.degs if Gene(x) not in self.experiment_genes
})
else:
# select differentialy expressed genes
pvalue = ttest(experiment) <= self.threshold
self.degs = pvalue[pvalue == True]
if self.degs.size == 0:
# if there are no DEGs anywhere, the problem of finding the impact on various pathways is meaningless
print('No differentialy expressed genes.')
return ImpactAnalysisResult([])
db = KEGGPathways(self.org)
pathways = {}
for gene in [g.name for g in list(self.degs.index)]:
ps = db.search_by_gene(gene)
for (k, v) in ps.items():
if k not in pathways.keys():
pathways[k] = v
if not pathways:
print('No pathways found in database.')
return ImpactAnalysisResult([])
res = pd.DataFrame(columns=['name', 'IF', 'pvalue'])
for (code, descr) in pathways.items():
pathway = db.get_pathway(code)
impact_factor, pval = self.calculate_impact_factor(
experiment, pathway)
if impact_factor is not None and pval is not None:
res.loc[len(res.index)] = [descr, impact_factor, pval]
res['FDR'], res['Bonferroni'] = self.calculate_corrections(
res['pvalue'])
ifp_pathways = [IAPathway(res.loc[i]) for i in range(len(res.index))]
ifp_pathways.sort(key=lambda x: x.IF if not isnan(x.IF) else 0,
reverse=True)
result = ImpactAnalysisResult(ifp_pathways)
if self.markdown:
result.generate_markdown(self.markdown,
'Results of Impact Analysis:')
return result
def test_get_gene_code():
gen = KEGGPathways().get_gene_code('BIOINF2018')
assert gen == ''
def test_get_organism_code():
with pytest.raises(KeyError):
KEGGPathways().get_organism_code('H**o bioinformaticus')
def test_search_by_gene():
db = KEGGPathways()
assert isinstance(db.search_by_gene('BRCA2'), dict)
pathways = db.search_by_gene('TheMostImportantGene')
assert pathways == {}