class ScrapeEnsembl():
'''
'''
def __init__(self, query, hg_version):
self.query = query.replace("chr","")
self.hg_version = ScrapeEnsembl.genome.get(hg_version) # convert to ensembl release
self.hg = EnsemblRelease(self.hg_version) # convert to ensembl release object
genome = {"hg19": 75, "hg38": 83}
def get_gene_info(self):
''' Get the gene information at a given genomic position
'''
# check if the input is a genomic position or genomic range
if re.search(r"[-:]", self.query) and self.query.replace(":","").isdigit():
chrom = int(self.query.split(":")[0])
pos = int(self.query.split(":")[1])
gene_name = self.hg.gene_names_at_locus(contig=chrom, position=pos)
if not gene_name:
msg = " ".join(("No gene found at",self.query,"for genome version",
str(self.hg_version)))
return msg
gene_info = self.hg.genes_by_name(gene_name[0])
# gene_info[0].loaction doesn't work, hence the mess below
gene_location = str(gene_info[0]).split(",")[-1][:-1].split("=")[1]
gene_info = (gene_info[0].name, gene_info[0].id,
gene_info[0].biotype, gene_location)
return(gene_info)
def get_canonical_transcript(self, gene_name):
''' Determine and return the canonical transcript of the given gene
'''
all_transcripts = self.hg.transcript_ids_of_gene_name(gene_name)
all_transcript_details = [self.hg.transcript_by_id(x) for x in all_transcripts]
protein_coding_transcripts = []
for x in all_transcript_details:
split_transcript_info = re.split(r"[=,]",str(x))
transcript = split_transcript_info[1]
transcript_type = split_transcript_info[9]
location = split_transcript_info[-1][:-1]
start = re.split(r"[:-]", location)[1]
stop = re.split(r"[:-]", location)[2]
size = int(stop) - int(start)
if transcript_type == "protein_coding":
protein_coding_transcripts.append((size,transcript,transcript_type))
# sort by size and return the largest protein coding transcript
if protein_coding_transcripts:
canonical_transcript = sorted(protein_coding_transcripts)[-1][1]
return canonical_transcript
