Created
December 3, 2010 21:57
-
-
Save chapmanb/727625 to your computer and use it in GitHub Desktop.
retrieve_gene.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from Bio import Entrez | |
def fetch_gene_coordinates(search_term): | |
handle = Entrez.esearch(db="gene", term=search_term) | |
rec = Entrez.read(handle) | |
gene_id = rec["IdList"][0] # assuming best match works | |
handle = Entrez.efetch(db="gene", id=gene_id, retmode="xml") | |
rec = Entrez.read(handle)[0] | |
gene_locus = rec["Entrezgene_locus"][0] | |
region = gene_locus["Gene-commentary_seqs"][0]["Seq-loc_int"]["Seq-interval"] | |
start = int(region["Seq-interval_from"]) + 1 | |
end = int(region["Seq-interval_to"]) + 1 | |
gi_id = region["Seq-interval_id"]["Seq-id"]["Seq-id_gi"] | |
strand = region["Seq-interval_strand"]["Na-strand"].attributes["value"] | |
return gi_id, start, end, strand | |
def get_fasta_seq(gi_id, start, end, strand): | |
strand = 2 if strand.lower() == "minus" else 1 | |
handle = Entrez.efetch(db="nucleotide", rettype="fasta", id=gi_id, | |
seq_start=start, seq_stop=end, strand=strand) | |
return handle.read() | |
Entrez.email = "yours@mail.com" | |
search_term = "fliC ct18" | |
gi_id, start, end, strand = fetch_gene_coordinates(search_term) | |
print get_fasta_seq(gi_id, start, end, strand) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment