Skip to content
Snippets Groups Projects
Commit 19c0bb3c authored by Glenn Proctor's avatar Glenn Proctor
Browse files

Changed dbname arg to dbpattern, to allow for use of regular expressions to... 

Changed dbname arg to dbpattern, to allow for use of regular expressions to specify a number of databases to run on sequentially.
parent 1360f4a8
No related branches found
No related tags found
No related merge requests found
Hide whitespace changes
Inline Side-by-side
misc-scripts/frameshift_transcript_attribs.pl
+ 77
− 60
View file @ 19c0bb3c
......@@ -10,88 +10,105 @@ use Bio::EnsEMBL::Attribute;
use Getopt::Long;
my ($host, $port, $user, $pass, $dbname, $nostore, $delete);
my ($host, $port, $user, $pass, $dbpattern, $nostore, $delete);
GetOptions('host=s' => \$host,
'user=s' => \$user,
'port=i' => \$port,
'pass=s' => \$pass,
'dbname=s' => \$dbname,
'nostore' => \$nostore,
'delete' => \$delete,
'help' => sub { usage(); exit(0); });
GetOptions('host=s' => \$host,
'user=s' => \$user,
'port=i' => \$port,
'pass=s' => \$pass,
'dbpattern=s' => \$dbpattern,
'nostore' => \$nostore,
'delete' => \$delete,
'help' => sub { usage(); exit(0); });
$port ||= 3306;
usage() if(!$user || !$dbname || !$host);
usage() if(!$user || !$dbpattern || !$host);
my $db = Bio::EnsEMBL::DBSQL::DBAdaptor->new(-host => $host,
-user => $user,
-pass => $pass,
-dbname => $dbname,
-port => $port);
my $dsn = "DBI:mysql:host=$host";
$dsn .= ";port=$port" if ($port);
if ($delete) {
my $db = DBI->connect($dsn, $user, $pass);
print STDERR "Deleting existing 'Frameshift' transcript attributes\n";
my $sth = $db->dbc()->prepare("DELETE ta, at FROM transcript_attrib ta, attrib_type at WHERE at.attrib_type_id=ta.attrib_type_id AND at.code='Frameshift'");
$sth->execute();
my @dbnames = map {$_->[0] } @{ $db->selectall_arrayref( "show databases" ) };
}
for my $dbname ( @dbnames ) {
next if ($dbname !~ /$dbpattern/);
my $attribute_adaptor = $db->get_AttributeAdaptor();
my $transcript_adaptor = $db->get_TranscriptAdaptor();
print $dbname . "\n";
my %biotypes = ();
my $db_adaptor = Bio::EnsEMBL::DBSQL::DBAdaptor->new(-host => $host,
-user => $user,
-pass => $pass,
-dbname => $dbname,
-port => $port);
print STDERR "Finding frameshifts in $dbname, creating transcript attributes ...\n";
print STDERR "Attributes will not be stored in database\n" if ($nostore);
my $attribute_adaptor = $db_adaptor->get_AttributeAdaptor();
my $transcript_adaptor = $db_adaptor->get_TranscriptAdaptor();
my $sth = $db->dbc()->prepare
(qq{SELECT t.transcript_id, g.biotype,
MIN(IF(e1.seq_region_strand = 1,
e2.seq_region_start - e1.seq_region_end - 1,
e1.seq_region_start - e2.seq_region_end - 1)) AS intron_length
FROM exon e1, exon e2, exon_transcript et1, exon_transcript et2,
transcript t, gene g
WHERE et1.exon_id = e1.exon_id
AND et2.exon_id = e2.exon_id
AND et1.transcript_id = et2.transcript_id
AND et1.rank = et2.rank - 1
AND et1.transcript_id = t.transcript_id
AND t.gene_id = g.gene_id
GROUP BY t.transcript_id
HAVING intron_length IN (1,2,4,5)});
if ($delete) {
$sth->execute();
print STDERR "Deleting existing 'Frameshift' transcript attributes\n";
my $dsth = $db_adaptor->dbc()->prepare("DELETE ta, at FROM transcript_attrib ta, attrib_type at WHERE at.attrib_type_id=ta.attrib_type_id AND at.code='Frameshift'");
$dsth->execute();
my ($transcript_id, $biotype, $intron_length, $count);
$sth->bind_columns(\$transcript_id, \$biotype, \$intron_length);
}
while($sth->fetch()){
my %biotypes = ();
my $attribute = Bio::EnsEMBL::Attribute->new(-CODE => 'Frameshift',
-NAME => 'Frameshift',
-DESCRIPTION => 'Frameshift modelled as intron',
-VALUE => $intron_length);
print STDERR "Finding frameshifts in $dbname, creating transcript attributes ...\n";
print STDERR "Attributes will not be stored in database\n" if ($nostore);
my @attribs = ($attribute);
my $sth = $db_adaptor->dbc()->prepare
(qq{SELECT t.transcript_id, g.biotype,
MIN(IF(e1.seq_region_strand = 1,
e2.seq_region_start - e1.seq_region_end - 1,
e1.seq_region_start - e2.seq_region_end - 1)) AS intron_length
FROM exon e1, exon e2, exon_transcript et1, exon_transcript et2,
transcript t, gene g
WHERE et1.exon_id = e1.exon_id
AND et2.exon_id = e2.exon_id
AND et1.transcript_id = et2.transcript_id
AND et1.rank = et2.rank - 1
AND et1.transcript_id = t.transcript_id
AND t.gene_id = g.gene_id
GROUP BY t.transcript_id
HAVING intron_length IN (1,2,4,5)});
my $transcript = $transcript_adaptor->fetch_by_dbID($transcript_id);
$sth->execute();
$attribute_adaptor->store_on_Transcript($transcript, \@attribs) if (!$nostore);
my ($transcript_id, $biotype, $intron_length, $count);
$sth->bind_columns(\$transcript_id, \$biotype, \$intron_length);
$biotypes{$biotype}++;
$count++;
while ($sth->fetch()) {
}
my $attribute = Bio::EnsEMBL::Attribute->new(-CODE => 'Frameshift',
-NAME => 'Frameshift',
-DESCRIPTION => 'Frameshift modelled as intron',
-VALUE => $intron_length);
my @attribs = ($attribute);
my $transcript = $transcript_adaptor->fetch_by_dbID($transcript_id);
$attribute_adaptor->store_on_Transcript($transcript, \@attribs) if (!$nostore);
$biotypes{$biotype}++;
$count++;
}
print "$count short intron attributes\n";
print "Attributes not stored in database\n" if ($nostore);
print "Biotypes of affected genes:\n";
foreach $biotype (keys %biotypes) {
print $biotype . "\t" . $biotypes{$biotype} . "\n";
}
print "$count short intron attributes\n";
print "Attributes not stored in database\n" if ($nostore);
print "\n";
print "Biotypes of affected genes:\n";
foreach my $biotype(keys %biotypes) {
print $biotype . "\t" . $biotypes{$biotype} . "\n";
}
# ----------------------------------------------------------------------
......@@ -115,7 +132,7 @@ sub usage {
--pass Password for user.
--dbname The database to use.
--dbpattern Regular expression to define which databases are affected.
[--nostore] Don't store the attributes, just print results.
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment