def _process_genes(self, taxid, limit=None):
if self.test_mode:
graph = self.testgraph
else:
graph = self.graph
model = Model(graph)
geno = Genotype(graph)
raw = '/'.join((self.rawdir, self.files[taxid]['file']))
col = list(self.columns['bmq_attributes'])
if taxid != '9606' and 'hgnc_id' in col:
col.remove('hgnc_id')
col_exp = [
self.columns['bmq_headers'][self.columns['bmq_attributes'].index(x)]
for x in col]
LOG.info("Processing Ensembl genes for NCBITaxon:%s", taxid)
with open(raw, 'r', encoding="utf8") as csvfile:
reader = csv.reader(csvfile, delimiter='\t')
row = next(reader)
if not self.check_fileheader(col_exp, row):
pass
for row in reader:
ensembl_gene_id = row[col.index('ensembl_gene_id')]
external_gene_name = row[col.index('external_gene_name')]
description = row[col.index('description')].strip()
gene_biotype = row[col.index('gene_biotype')].strip()
entrezgene = row[col.index('entrezgene_id')].strip()
ensembl_peptide_id = row[col.index('ensembl_peptide_id')].strip()
uniprotswissprot = row[col.index('uniprotswissprot')].strip()
hgnc_curie = None
# in the case of human genes, we also get the hgnc id,
if taxid == '9606' and 'hgnc_id' in col:
hgnc_curie = row[col.index('hgnc_id')].strip()
if self.test_mode and entrezgene != '' and \
entrezgene not in self.gene_ids:
continue
gene_id = 'ENSEMBL:' + ensembl_gene_id
entrez_curie = 'NCBIGene:{}'.format(entrezgene)
if description == '':
description = None
gene_type_id = self.resolve(
gene_biotype, mandatory=False,
default=self.globaltt['polypeptide'])
model.addClassToGraph(
gene_id, external_gene_name, gene_type_id, description)
if entrezgene != '':
if taxid == '9606':
# Use HGNC for eq in human data
model.addXref(gene_id, entrez_curie)
else:
model.addEquivalentClass(gene_id, entrez_curie)
if hgnc_curie is not None and hgnc_curie != '':
model.addEquivalentClass(gene_id, hgnc_curie)
geno.addTaxon('NCBITaxon:' + taxid, gene_id)
if ensembl_peptide_id is not None and ensembl_peptide_id != '':
peptide_curie = 'ENSEMBL:{}'.format(ensembl_peptide_id)
model.addIndividualToGraph(peptide_curie, None, gene_type_id)
geno.addGeneProduct(gene_id, peptide_curie)
if uniprotswissprot != '':
uniprot_curie = 'UniProtKB:{}'.format(uniprotswissprot)
model.addIndividualToGraph(uniprot_curie, None, gene_type_id)
geno.addGeneProduct(gene_id, uniprot_curie)
model.addXref(peptide_curie, uniprot_curie)
if not self.test_mode and limit is not None and reader.line_num > limit:
break
def _process_genes(self, taxid, limit=None):
if self.testMode:
g = self.testgraph
else:
g = self.graph
model = Model(g)
geno = Genotype(g)
raw = '/'.join((self.rawdir, self.files[taxid]['file']))
line_counter = 0
logger.info("Processing Ensembl genes for tax %s", taxid)
with open(raw, 'r', encoding="utf8") as csvfile:
filereader = csv.reader(csvfile, delimiter='\t')
for row in filereader:
if len(row) < 4:
raise ValueError("Data error for file %s", raw)
(ensembl_gene_id, external_gene_name,
description, gene_biotype, entrezgene,
peptide_id, uniprot_swissprot) = row[0:7]
# in the case of human genes, we also get the hgnc id,
# and is the last col
if taxid == '9606':
hgnc_id = row[7]
else:
hgnc_id = None
if self.testMode and entrezgene != '' \
and int(entrezgene) not in self.gene_ids:
continue
line_counter += 1
gene_id = 'ENSEMBL:' + ensembl_gene_id
peptide_curie = 'ENSEMBL:{}'.format(peptide_id)
uniprot_curie = 'UniProtKB:{}'.format(uniprot_swissprot)
entrez_curie = 'NCBIGene:{}'.format(entrezgene)
if description == '':
description = None
# gene_type_id = self._get_gene_type(gene_biotype)
gene_type_id = None
model.addClassToGraph(
gene_id, external_gene_name, gene_type_id, description)
model.addIndividualToGraph(peptide_curie, None, self._get_gene_type("polypeptide"))
model.addIndividualToGraph(uniprot_curie, None, self._get_gene_type("polypeptide"))
if entrezgene != '':
model.addEquivalentClass(gene_id, entrez_curie)
if hgnc_id is not None and hgnc_id != '':
model.addEquivalentClass(gene_id, hgnc_id)
geno.addTaxon('NCBITaxon:'+taxid, gene_id)
if peptide_id != '':
geno.addGeneProduct(gene_id, peptide_curie)
if uniprot_swissprot != '':
geno.addGeneProduct(gene_id, uniprot_curie)
model.addXref(peptide_curie, uniprot_curie)
if not self.testMode \
and limit is not None and line_counter > limit:
break
return
def _process_genes(self, taxid, limit=None):
if self.test_mode:
graph = self.testgraph
else:
graph = self.graph
model = Model(graph)
geno = Genotype(graph)
raw = '/'.join((self.rawdir, self.files[taxid]['file']))
line_counter = 0
LOG.info("Processing Ensembl genes for tax %s", taxid)
with open(raw, 'r', encoding="utf8") as csvfile:
filereader = csv.reader(csvfile, delimiter='\t')
for row in filereader:
if len(row) < 4:
LOG.warning("Too few columns in: " + row)
raise ValueError("Data error for file %s", raw)
(ensembl_gene_id, external_gene_name, description, gene_biotype,
entrezgene, ensembl_peptide_id, uniprotswissprot) = row[0:7]
# in the case of human genes, we also get the hgnc id,
# and is the last col
if taxid == '9606':
hgnc_id = row[7]
else:
hgnc_id = None
if self.test_mode and entrezgene != '' and \
int(entrezgene) not in self.gene_ids:
continue
line_counter += 1
gene_id = 'ENSEMBL:' + ensembl_gene_id
peptide_curie = 'ENSEMBL:{}'.format(ensembl_peptide_id)
uniprot_curie = 'UniProtKB:{}'.format(uniprotswissprot)
entrez_curie = 'NCBIGene:{}'.format(entrezgene)
if description == '':
description = None
gene_biotype = gene_biotype.strip()
gene_type_id = self.resolve(gene_biotype, False)
if gene_type_id == gene_biotype.strip(): # did not resolve
gene_type_id = self.globaltt['polypeptide']
model.addClassToGraph(
gene_id, external_gene_name, gene_type_id, description)
model.addIndividualToGraph(peptide_curie, None, gene_type_id)
model.addIndividualToGraph(uniprot_curie, None, gene_type_id)
if entrezgene != '':
if taxid == '9606':
# Use HGNC for eq in human data
model.addXref(gene_id, entrez_curie)
else:
model.addEquivalentClass(gene_id, entrez_curie)
if hgnc_id is not None and hgnc_id != '':
model.addEquivalentClass(gene_id, hgnc_id)
geno.addTaxon('NCBITaxon:'+taxid, gene_id)
if ensembl_peptide_id != '':
geno.addGeneProduct(gene_id, peptide_curie)
if uniprotswissprot != '':
geno.addGeneProduct(gene_id, uniprot_curie)
model.addXref(peptide_curie, uniprot_curie)
if not self.test_mode and limit is not None and line_counter > limit:
break
return
def _process_genes(self, taxid, limit=None):
if self.testMode:
g = self.testgraph
else:
g = self.graph
model = Model(g)
geno = Genotype(g)
raw = '/'.join((self.rawdir, self.files[taxid]['file']))
line_counter = 0
logger.info("Processing Ensembl genes for tax %s", taxid)
with open(raw, 'r', encoding="utf8") as csvfile:
filereader = csv.reader(csvfile, delimiter='\t')
for row in filereader:
if len(row) < 4:
raise ValueError("Data error for file %s", raw)
(ensembl_gene_id, external_gene_name, description,
gene_biotype, entrezgene, peptide_id,
uniprot_swissprot) = row[0:7]
# in the case of human genes, we also get the hgnc id,
# and is the last col
if taxid == '9606':
hgnc_id = row[7]
else:
hgnc_id = None
if self.testMode and entrezgene != '' \
and int(entrezgene) not in self.gene_ids:
continue
line_counter += 1
gene_id = 'ENSEMBL:' + ensembl_gene_id
peptide_curie = 'ENSEMBL:{}'.format(peptide_id)
uniprot_curie = 'UniProtKB:{}'.format(uniprot_swissprot)
entrez_curie = 'NCBIGene:{}'.format(entrezgene)
if description == '':
description = None
# gene_type_id = self._get_gene_type(gene_biotype)
gene_type_id = None
model.addClassToGraph(gene_id, external_gene_name,
gene_type_id, description)
model.addIndividualToGraph(peptide_curie, None,
self._get_gene_type("polypeptide"))
model.addIndividualToGraph(uniprot_curie, None,
self._get_gene_type("polypeptide"))
if entrezgene != '':
model.addEquivalentClass(gene_id, entrez_curie)
if hgnc_id is not None and hgnc_id != '':
model.addEquivalentClass(gene_id, hgnc_id)
geno.addTaxon('NCBITaxon:' + taxid, gene_id)
if peptide_id != '':
geno.addGeneProduct(gene_id, peptide_curie)
if uniprot_swissprot != '':
geno.addGeneProduct(gene_id, uniprot_curie)
model.addXref(peptide_curie, uniprot_curie)
if not self.testMode \
and limit is not None and line_counter > limit:
break
return
