def add_ensembl_info(genes, ensembl_lines):
"""Add the coordinates from ensembl
Args:
genes(dict): Dictionary with all genes
ensembl_lines(iteable): Iteable with raw ensembl info
"""
LOG.info("Adding ensembl coordinates")
# Parse and add the ensembl gene info
ensembl_genes = parse_ensembl_genes(ensembl_lines)
for ensembl_gene in ensembl_genes:
if not "hgnc_id" in ensembl_gene:
LOG.debug(
"Ensembl gene %s is missing hgnc id. Skipping",
ensembl_gene.get("ensembl_gene_id"),
)
continue
gene_obj = genes.get(ensembl_gene["hgnc_id"])
if not gene_obj:
continue
gene_obj["chromosome"] = ensembl_gene["chrom"]
gene_obj["start"] = ensembl_gene["gene_start"]
gene_obj["end"] = ensembl_gene["gene_end"]
# ensembl ids can differ between builds. The ensembl gene ids from HGNC are only
# true for build 38. So we add correct information from ensembl
gene_obj["ensembl_gene_id"] = ensembl_gene["ensembl_gene_id"]
def add_ensembl_info(genes, ensembl_lines):
"""Add the coordinates from ensembl
Args:
genes(dict): Dictionary with all genes
ensembl_lines(iteable): Iteable with raw ensembl info
"""
LOG.info("Adding ensembl coordinates")
# Parse and add the ensembl gene info
if isinstance(ensembl_lines, DataFrame):
ensembl_genes = parse_ensembl_gene_request(ensembl_lines)
else:
ensembl_genes = parse_ensembl_genes(ensembl_lines)
for ensembl_gene in ensembl_genes:
gene_obj = genes.get(ensembl_gene['hgnc_id'])
if not gene_obj:
continue
gene_obj['chromosome'] = ensembl_gene['chrom']
gene_obj['start'] = ensembl_gene['gene_start']
gene_obj['end'] = ensembl_gene['gene_end']
# ensembl ids can differ between builds. There is one stated in HGNC
# that is true for build 38. So we add information from ensembl
gene_obj['ensembl_gene_id'] = ensembl_gene['ensembl_gene_id']
def add_ensembl_info(genes, ensembl_lines):
"""Add the coordinates from ensembl
Args:
genes(dict): Dictionary with all genes
ensembl_lines(iteable): Iteable with raw ensembl info
"""
LOG.info("Adding ensembl coordinates")
# Parse and add the ensembl gene info
if isinstance(ensembl_lines, DataFrame):
ensembl_genes = parse_ensembl_gene_request(ensembl_lines)
else:
ensembl_genes = parse_ensembl_genes(ensembl_lines)
for ensembl_gene in ensembl_genes:
gene_obj = genes.get(ensembl_gene['hgnc_id'])
if not gene_obj:
continue
gene_obj['chromosome'] = ensembl_gene['chrom']
gene_obj['start'] = ensembl_gene['gene_start']
gene_obj['end'] = ensembl_gene['gene_end']
# ensembl ids can differ between builds. There is one stated in HGNC
# that is true for build 38. So we add information from ensembl
gene_obj['ensembl_gene_id'] = ensembl_gene['ensembl_gene_id']
def exons(ctx, genes, build, exons, chromosome):
"""Generate exons scout. Need to have a ensemble gene file generated from above"""
if chromosome:
chromosome = [chromosome]
ensg_to_hgncid = {}
for gene_info in parse_ensembl_genes(genes):
ensgid = gene_info["ensembl_gene_id"]
hgncid = gene_info["hgnc_id"]
ensg_to_hgncid[ensgid] = hgncid
for i, line in enumerate(fetch_ensembl_exons(build=build, chromosomes=chromosome)):
if i == 0:
header = line.rstrip().split("\t")
click.echo(line)
continue
exon_line = line.rstrip().split("\t")
exon_info = dict(zip(header, exon_line))
gene_id = exon_info["Gene stable ID"]
if not gene_id in ensg_to_hgncid:
continue
click.echo(line)