From f7805e02580755f646fa1d678c20f8cb4d720cf3 Mon Sep 17 00:00:00 2001
From: Andrew Yates <ayates@ebi.ac.uk>
Date: Wed, 20 Mar 2013 17:18:57 +0000
Subject: [PATCH] removing the adding of species if they are in the
force_speices list. unintented side effect of limiting it to just those force
species
---
modules/Bio/EnsEMBL/DBSQL/SequenceAdaptor.pm | 77 +++++++++++--------
.../Pipeline/FASTA/ReuseSpeciesFactory.pm | 14 +---
modules/t/sequenceAdaptor.t | 12 ++-
3 files changed, 56 insertions(+), 47 deletions(-)
diff --git a/modules/Bio/EnsEMBL/DBSQL/SequenceAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/SequenceAdaptor.pm
index 8c9c192b6e..f59f61ceb6 100644
--- a/modules/Bio/EnsEMBL/DBSQL/SequenceAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/SequenceAdaptor.pm
@@ -39,7 +39,7 @@ An adaptor for the retrieval of DNA sequence from the EnsEMBL database
package Bio::EnsEMBL::DBSQL::SequenceAdaptor;
-use vars qw(@ISA @EXPORT);
+# use vars qw(@ISA @EXPORT);
use strict;
use warnings;
@@ -49,13 +49,14 @@ use Bio::EnsEMBL::Utils::Sequence qw(reverse_comp);
use Bio::EnsEMBL::Utils::Cache;
use Bio::EnsEMBL::Utils::Scalar qw( assert_ref );
-@ISA = qw(Bio::EnsEMBL::DBSQL::BaseAdaptor);
+# @ISA = qw(Bio::EnsEMBL::DBSQL::BaseAdaptor Bio::EnsEMBL::DBSQL::BaseSequenceAdaptor);
+use base qw(Bio::EnsEMBL::DBSQL::BaseAdaptor Bio::EnsEMBL::DBSQL::BaseSequenceAdaptor);
+#
+# our $SEQ_CHUNK_PWR = 18; # 2^18 = approx. 250KB
+# our $SEQ_CACHE_SZ = 5;
+# our $SEQ_CACHE_MAX = (2 ** $SEQ_CHUNK_PWR) * $SEQ_CACHE_SZ;
-our $SEQ_CHUNK_PWR = 18; # 2^18 = approx. 250KB
-our $SEQ_CACHE_SZ = 5;
-our $SEQ_CACHE_MAX = (2 ** $SEQ_CHUNK_PWR) * $SEQ_CACHE_SZ;
-
-@EXPORT = (@{$DBI::EXPORT_TAGS{'sql_types'}});
+our @EXPORT = (@{$DBI::EXPORT_TAGS{'sql_types'}});
=head2 new
@@ -72,16 +73,15 @@ our $SEQ_CACHE_MAX = (2 ** $SEQ_CHUNK_PWR) * $SEQ_CACHE_SZ;
sub new {
my $caller = shift;
-
my $class = ref($caller) || $caller;
-
my $self = $class->SUPER::new(@_);
+ $self->_init_seq_instance();
- # use an LRU cache to limit the size
- my %seq_cache;
- tie(%seq_cache, 'Bio::EnsEMBL::Utils::Cache', $SEQ_CACHE_SZ);
-
- $self->{'seq_cache'} = \%seq_cache;
+ # # use an LRU cache to limit the size
+ # my %seq_cache;
+ # tie(%seq_cache, 'Bio::EnsEMBL::Utils::Cache', $SEQ_CACHE_SZ);
+ #
+ # $self->{'seq_cache'} = \%seq_cache;
#
@@ -107,22 +107,22 @@ sub new {
return $self;
}
-
-=head2 clear_cache
-
- Example : $sa->clear_cache();
- Description : Removes all entries from the associcated sequence cache
- Returntype : None
- Exceptions : None
-
-=cut
-
-sub clear_cache {
- my ($self) = @_;
- %{$self->{seq_cache}} = ();
- return;
-}
-
+#
+# =head2 clear_cache
+#
+# Example : $sa->clear_cache();
+# Description : Removes all entries from the associcated sequence cache
+# Returntype : None
+# Exceptions : None
+#
+# =cut
+#
+# sub clear_cache {
+# my ($self) = @_;
+# %{$self->{seq_cache}} = ();
+# return;
+# }
+#
=head2 fetch_by_Slice_start_end_strand
@@ -442,7 +442,7 @@ sub _rna_edit {
return;
}
-
+=cut
sub _fetch_seq {
my $self = shift;
my $seq_region_id = shift;
@@ -519,6 +519,21 @@ sub _fetch_seq {
return \$tmp_seq;
}
}
+=cut
+sub _fetch_raw_seq {
+ my ($self, $id, $start, $length) = @_;
+ my $sql = <<'SQL';
+SELECT UPPER(SUBSTRING(d.sequence, ?, ?))
+FROM dna d
+WHERE d.seq_region_id =?
+SQL
+ my $seq = $self->dbc()->sql_helper()->execute_single_result(
+ -SQL => $sql,
+ -PARAMS => [[$start, SQL_INTEGER], [$length, SQL_INTEGER], [$id, SQL_INTEGER]],
+ -NO_ERROR => 1
+ );
+ return \$seq;
+}
=head2 store
diff --git a/modules/Bio/EnsEMBL/Pipeline/FASTA/ReuseSpeciesFactory.pm b/modules/Bio/EnsEMBL/Pipeline/FASTA/ReuseSpeciesFactory.pm
index 2dd69c4f90..2302627832 100644
--- a/modules/Bio/EnsEMBL/Pipeline/FASTA/ReuseSpeciesFactory.pm
+++ b/modules/Bio/EnsEMBL/Pipeline/FASTA/ReuseSpeciesFactory.pm
@@ -39,7 +39,7 @@ Allowed parameters are:
=item force_species - Specify species we want to redump even though
our queries of production could say otherwise
-=item run_all - Do not check a thing. Override and run every dump
+=item run_all - Do not check a thing. Schedule every species
=back
@@ -72,7 +72,7 @@ sub param_defaults {
%{$self->SUPER::param_defaults()},
force_species => [],
- force_all_species => 1,
+ run_all => 1,
};
return $p;
}
@@ -94,16 +94,6 @@ sub fetch_input {
return;
}
-#Allows a user to use '-force_species human' rather than '-force_species human -species human'
-sub _add_force_species_to_species {
- my ($self) = @_;
- my $force_species = $self->param('force_species');
- my $species = $self->param('species');
- my %final_species = map { $_ => 1 } (@{$force_species}, @{$species});
- $self->param('species', [keys %final_species]);
- return;
-}
-
sub dna_flow {
my ($self, $dba) = @_;
my $parent_flow = $self->SUPER::dna_flow($dba);
diff --git a/modules/t/sequenceAdaptor.t b/modules/t/sequenceAdaptor.t
index d72abfaabc..67868944c0 100644
--- a/modules/t/sequenceAdaptor.t
+++ b/modules/t/sequenceAdaptor.t
@@ -30,6 +30,10 @@ my $seq_adaptor = $db->get_SequenceAdaptor();
my $slice = $slice_adaptor->fetch_by_region('chromosome', $CHR, $START, $END);
compare_compliments($slice, $seq_adaptor);
+#Bigger than 1Mb
+$slice = $slice_adaptor->fetch_by_region('chromosome', $CHR, $START, $START+2_000_000);
+compare_compliments($slice, $seq_adaptor);
+
$slice = $slice_adaptor->fetch_by_region('clone','AL031658.11');
compare_compliments($slice, $seq_adaptor);
@@ -47,20 +51,20 @@ sub compare_compliments {
my $seq = ${$seq_adaptor->fetch_by_Slice_start_end_strand($slice,1,undef,1)};
debug('FORWARD STRAND SLICE SEQ for ' . $slice->name());
- debug($seq);
+ debug($slice->length);
my $invert_seq =
${$seq_adaptor->fetch_by_Slice_start_end_strand($slice->invert,1,undef,1)};
debug('REVERSE STRAND SLICE SEQ for ' . $slice->name());
- debug($invert_seq);
+
- ok(length($seq) == $slice->length); #sequence is correct length
+ is(length($seq), $slice->length, 'sequence is correct length');
$seq = reverse $seq; #reverse complement seq
$seq =~ tr/ACTG/TGAC/;
- ok($seq eq $invert_seq); #revcom same as seq on inverted slice
+ ok($seq eq $invert_seq, 'revcom same as seq on inverted slice');
}
done_testing();
--
GitLab