def get_canonical_ensembl_names(taxon_id):
beginners = {
7227: 'FLYBASE:',
6239: 'WormBase:',
3702: 'Araport:',
511145: 'EcoGene',
559292: 'SGD'
}
if taxon_id in beginners.keys():
beg = beginners[taxon_id]
else:
beg = 'Ensembl:'
gene_info = meta.gene_info(taxon_id, usecols=['gene_ncbi', 'dbXrefs'])
gene_info = utils.split_text_to_multiple_rows(gene_info, 'dbXrefs',
'\|')
f = gene_info['dbXrefs'].str.startswith(beg)
gene_info = gene_info.loc[f, :].copy()
gene_info['dbXrefs'] = gene_info.loc[:, 'dbXrefs'].str.replace(
r'^' + beg,
'',
)
gene_info = gene_info.drop_duplicates()
canonical_ensembl_names = set(gene_info['dbXrefs'].values)
return canonical_ensembl_names
def _get_gene_ncbi_2_ensembl():
gi = meta.gene_info(taxon_id=9606)
f = gi['dbXrefs'].str.contains('Ensembl:ENSG[0-9]*')
gi.loc[f, 'gene_ensembl'] = gi.loc[f, 'dbXrefs'].str.extract(
'Ensembl:(ENSG[0-9]*)', expand=False)
gi = gi[['gene_ncbi', 'gene_ensembl']].drop_duplicates()
gi = gi.drop_duplicates('gene_ensembl', keep=False)
gi = gi[gi['gene_ncbi'].isin(get_ref_genes())]
return gi
def reference_genes(taxon_id, ref_code):
"""
Obtains a list of reference genes
Input:
taxon_id int
ref_code str; if it contains
l -> at least one medline paper
o -> official nomenclature require
p -> protein-coding only
Output:
ref_genes sorted list of gene identifiers
"""
df = meta.gene_info(taxon_id)
if df.shape[0] == 0:
raise EnvironmentError("""
Did not find gene info for taxon {}""".format(int(taxon_id)))
if 'l' in ref_code:
genes_in_medline = medline.gene2pubmed(taxon_id, ['gene_ncbi'])
f = df.loc[:, 'gene_ncbi'].isin(genes_in_medline['gene_ncbi'])
df = df.loc[f, :]
if df.shape[0] == 0:
raise EnvironmentError("""
After filtering for genes with at least one paper,
no gene is left.""")
if 'o' in ref_code: # official nomeclature
f = df.loc[:, 'Nomenclature_status'] == 'O'
df = df.loc[f, :]
if df.shape[0] == 0:
raise EnvironmentError("""
After filtering for genes with official nomeclature,
no gene is left.""")
if 'p' in ref_code: # protein-coding
f = df.loc[:, 'type_of_gene'] == 'protein-coding'
df = df.loc[f, :]
if df.shape[0] == 0:
raise EnvironmentError("""
After filtering for protein-coding, no gene is
left.""")
if 'r' in ref_code:
genes_in_medline = medline.gene2pubmed(taxon_id,
['pubmed_id', 'gene_ncbi'],
paper_kind='research')
f = df.loc[:, 'gene_ncbi'].isin(genes_in_medline['gene_ncbi'])
df = df.loc[f, :]
if df.shape[0] == 0:
raise EnvironmentError("""
After filtering for genes with at least one research paper,
no gene is left.""")
ref_genes = sorted(df.loc[:, 'gene_ncbi'].values)
return ref_genes
def any_gwas():
ebi_gwas = gwas_studies.ebi_gwas()
f = ebi_gwas['MAPPED_GENE'].str.contains('[;,-]') == True
gwas = ebi_gwas.loc[
~f,
['MAPPED_GENE', 'DISEASE/TRAIT', 'PVALUE_MLOG', 'pubmed_id']].rename(
columns={
'MAPPED_GENE': 'symbol_ambiguous',
'DISEASE/TRAIT': 'trait',
'PVALUE_MLOG': 'log_pvalue'
}
)
gwas = pd.merge(
gwas,
meta.gene_info(taxon_id=9606, usecols=[
'symbol_ncbi', 'gene_ncbi']),
left_on='symbol_ambiguous',
right_on='symbol_ncbi',
how='inner'
).drop('symbol_ambiguous', axis=1).drop('symbol_ncbi', axis=1)
gwas = gwas[gwas['gene_ncbi'].isin(get_ref_genes())]
ge = sorted(gwas['gene_ncbi'].unique())
gwas = gwas.sort_values('log_pvalue', ascending=False)
gwas = gwas.drop_duplicates(
['trait', 'pubmed_id', 'gene_ncbi'],
keep='first')
studies_per_phenotype = gwas[
['pubmed_id', 'trait']].drop_duplicates()[
'trait'].value_counts()
required_studies = 1
important_gwas = gwas.loc[
(
gwas['trait'].isin(
studies_per_phenotype[
studies_per_phenotype >= required_studies].index)), :
][['pubmed_id', 'trait', 'gene_ncbi']].drop_duplicates()
he = pd.merge(
important_gwas.groupby(
['trait', 'gene_ncbi']).size(
).reset_index().rename(columns={0: 'records'}),
studies_per_phenotype.to_frame(
'studies').reset_index().rename(columns={'index': 'trait'}))
he.loc[:, 'fraction_of_any_gwas_studies'] = he['records'] / he['studies']
dd = he.pivot(
index='gene_ncbi',
columns='trait',
values='fraction_of_any_gwas_studies'
)
dd.columns = ['gwas_any_{}'.format(x) for x in dd.columns]
dd = dd.reindex(ge)
dd = dd.fillna(0)
cl = dd > 0.0
cl.loc[:, 'any_gwas'] = cl.any(axis=1)
return cl, dd, ge