Created
May 24, 2011 01:52
-
-
Save jeetsukumaran/988016 to your computer and use it in GitHub Desktop.
Using DendroPy to Download GenBank Data
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
#! /usr/bin/env python | |
from dendropy.interop import ncbi | |
entrez = ncbi.Entrez(generate_labels=True, | |
label_num_desc_components=2, | |
label_separator='_', | |
exclude_gbnum_from_label=True, | |
sort_taxa_by_label=True) | |
cr_ids = ["EU%d" % i for i in range(888892, 888900)] + \ | |
["DQ885482", "DQ885485", "DQ885486"] | |
atpase_ids = ["EU%d" % i for i in range(910196, 910206)] + \ | |
["DQ886665", "DQ886667", "DQ886668"] | |
s7_nums = range(379563, 379566) + range(910206, 910215) | |
s7_ids = ["EU%d" % i for i in s7_nums] | |
name_ids_map = { "cr" : cr_ids, "atpase" : atpase_ids, "s7" : s7_ids } | |
output_prefix = "wobbegong" | |
for name, ids in name_ids_map.items(): | |
data = entrez.fetch_nucleotide_accessions(ids) | |
data.write_to_path(output_prefix + "_" + name + ".unaligned.fasta", | |
"fasta") | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment