Created
December 17, 2013 11:02
-
-
Save avrilcoghlan/8003234 to your computer and use it in GitHub Desktop.
Use the Ensembl Compara Perl API to get the multiple alignment corresponding to the family with the stable id ENSFM00250000006121
This file contains hidden or 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 perl | |
# Get the multiple alignment corresponding to the family with the stable id ENSFM00250000006121 | |
# Note: this prints some warnings about uninitialised values in the Compara api | |
use strict; | |
use warnings; | |
use Bio::EnsEMBL::Registry; | |
use Bio::AlignIO; | |
my $registry = 'Bio::EnsEMBL::Registry'; | |
$registry->load_registry_from_db( | |
-host => 'ensembldb.ensembl.org', | |
-user => 'anonymous' | |
); | |
my $fa = $registry->get_adaptor( 'multi', 'compara', 'family' ); | |
my $family = $fa->fetch_by_stable_id("ENSFM00250000006121"); | |
my $desc = $family->description(); # a description of the family, based on a consensus of descriptions of its members | |
my $score = $family->description_score(); # a score for the description, saying how well it agrees between members | |
print "family desc_score=$score desc=$desc\n"; | |
my $aln = $family->get_SimpleAlign(-APPEND_TAXON_ID => 'TRUE'); # gets the alignment. -APPEND_TAXON_ID => 'TRUE' appends the NCBI taxon id. to the sequence name | |
# Get the alignIO object from BioPerl | |
my $alignIO = Bio::AlignIO->newFh(-format => "clustalw"); # -format => 'fasta' would give fasta format | |
# Print the alignment | |
print $alignIO $aln; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment