diff --git a/modules/Bio/EnsEMBL/IdMapping/Cache.pm b/modules/Bio/EnsEMBL/IdMapping/Cache.pm
index 44f0ea5efbe1106c739a755e30a7e05db20e9405..32316da4b7a3e620e1e59b28e9dee93c27fd3db5 100644
--- a/modules/Bio/EnsEMBL/IdMapping/Cache.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/Cache.pm
@@ -322,11 +322,6 @@ sub build_cache_from_genes {
($tr->is_known ? 1 : 0),
]);
- # EG to support improved discrimination, include the name
- if ( defined( $gene->display_xref() ) ) {
- $lgene->gene_name( $gene->display_xref()->display_id() );
- }
-
$lgene->add_Transcript($ltr);
# build transcript caches
@@ -372,10 +367,6 @@ sub build_cache_from_genes {
$need_project,
]);
- # EG to support improved discrimination, include the name of the
- # gene tp which exon belongs
- $lexon->gene_name( $lgene->gene_name() );
-
# get coordinates in common coordinate system if needed
if ($need_project) {
my @seg = @{ $exon->project($self->highest_common_cs,
@@ -389,7 +380,7 @@ sub build_cache_from_genes {
$lexon->common_sr_name($sl->seq_region_name);
}
}
-
+
$ltr->add_Exon($lexon);
$self->add('exons_by_id', $type, $exon->dbID, $lexon);
@@ -922,28 +913,24 @@ sub fetch_value_from_db {
return $c;
}
+
sub get_DBAdaptor {
- my ( $self, $prefix ) = @_;
+ my $self = shift;
+ my $prefix = shift;
- unless ( $self->{'_dba'}->{$prefix} ) {
+ unless ($self->{'_dba'}->{$prefix}) {
# connect to database
- my %args = ( -host => $self->conf->param("${prefix}host"),
- -port => $self->conf->param("${prefix}port"),
- -user => $self->conf->param("${prefix}user"),
- -pass => $self->conf->param("${prefix}pass"),
- -dbname => $self->conf->param("${prefix}dbname"),
- -group => $prefix );
-
- if ( defined( $self->conf()->param('species_id') ) ) { # EG
- $args{-species_id} = $self->conf->param('species_id');
- $args{-species} = $self->conf->param('species_name');
- $args{-multispecies_db} = 1;
- }
-
- my $dba = new Bio::EnsEMBL::DBSQL::DBAdaptor(%args);
-
- # explicitely set the dnadb to itself - by default the Registry
- # assumes a group 'core' for this now
+ my $dba = new Bio::EnsEMBL::DBSQL::DBAdaptor(
+ -host => $self->conf->param("${prefix}host"),
+ -port => $self->conf->param("${prefix}port"),
+ -user => $self->conf->param("${prefix}user"),
+ -pass => $self->conf->param("${prefix}pass"),
+ -dbname => $self->conf->param("${prefix}dbname"),
+ -group => $prefix,
+ );
+
+ # explicitely set the dnadb to itself - by default the Registry assumes
+ # a group 'core' for this now
$dba->dnadb($dba);
$self->{'_dba'}->{$prefix} = $dba;
diff --git a/modules/Bio/EnsEMBL/IdMapping/ExonScoreBuilder.pm b/modules/Bio/EnsEMBL/IdMapping/ExonScoreBuilder.pm
index 23de8009ad0c25c423a3bff20fe652673417f272..a569d2b2dcc332e29bc6ee5befd7017d254ff334 100644
--- a/modules/Bio/EnsEMBL/IdMapping/ExonScoreBuilder.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/ExonScoreBuilder.pm
@@ -430,10 +430,7 @@ sub run_exonerate {
$self->logger->debug("$exonerate_job\n\n");
local *BSUB;
- open BSUB,
- "|bsub "
- . $self->conf()->param('lsf_opt_run')
- . " -J$lsf_name\[1-$num_jobs\] -o $logpath/exonerate.\%I.out"
+ open BSUB, "|bsub -J$lsf_name\[1-$num_jobs\] -o $logpath/exonerate.\%I.out"
or $self->logger->error("Could not open open pipe to bsub: $!\n");
print BSUB $exonerate_job;
@@ -444,10 +441,8 @@ sub run_exonerate {
# submit dependent job to monitor finishing of exonerate jobs
$self->logger->info("Waiting for exonerate jobs to finish...\n", 0, 'stamped');
- my $dependent_job =
- qq{bsub -K -w "ended($lsf_name)" }
- . $self->conf()->param('lsf_opt_run_small')
- . qq{ -o $logpath/exonerate_depend.out /bin/true};
+ my $dependent_job = qq{bsub -K -w "ended($lsf_name)" -q small } .
+ qq{-o $logpath/exonerate_depend.out /bin/true};
system($dependent_job) == 0 or
$self->logger->error("Error submitting dependent job: $!\n");
@@ -673,35 +668,10 @@ sub non_mapped_transcript_rescore {
foreach my $entry (@{ $matrix->get_all_Entries }) {
- # EG reworking of logic to allow no source/target e.g. for new
- # species in multispecies databases
- my $st =
- $self->cache()
- ->get_by_key( 'transcripts_by_exon_id', 'source',
- $entry->source() );
-
- my @source_transcripts = ();
- if ( !defined($st) ) {
- $self->logger->warning(
- "Can't find source transcipts by exon_id for "
- . $entry->source() );
- } else {
- @source_transcripts = @{$st};
- }
-
- my $tt =
- $self->cache()
- ->get_by_key( 'transcripts_by_exon_id', 'target',
- $entry->target() );
-
- my @target_transcripts = ();
- if ( !defined($tt) ) {
- $self->logger->warning(
- "Can't find target transcipts by exon_id for "
- . $entry->target() );
- } else {
- @target_transcripts = @{$tt};
- }
+ my @source_transcripts = @{ $self->cache->get_by_key(
+ 'transcripts_by_exon_id', 'source', $entry->source) };
+ my @target_transcripts = @{ $self->cache->get_by_key(
+ 'transcripts_by_exon_id', 'target', $entry->target) };
my $found_mapped = 0;
@@ -727,84 +697,5 @@ sub non_mapped_transcript_rescore {
}
-sub name_exon_rescore {
-
- # EG name_exon_rescore is additional method for rescoring exons based
- # on name matches
-
- my ( $self, $matrix ) = @_;
-
- if ( !( defined($matrix)
- && ref($matrix)
- && $matrix->isa('Bio::EnsEMBL::IdMapping::ScoredMappingMatrix')
- ) )
- {
- throw('Need a Bio::EnsEMBL::IdMapping::ScoredMappingMatrix.');
- }
-
- my $i = 0;
-
- foreach my $entry ( @{ $matrix->get_all_Entries() } ) {
- my $source_exon =
- $self->cache->get_by_key( 'exons_by_id', 'source',
- $entry->source() );
- my $target_exon =
- $self->cache->get_by_key( 'exons_by_id', 'target',
- $entry->target() );
-
- if ( defined($source_exon)
- && defined($target_exon)
- && $source_exon->gene_name() ne $target_exon->gene_name() )
- {
- $matrix->set_score( $entry->source(), $entry->target(),
- ( $entry->score()*0.75 ) );
- $i++;
- }
- }
-
- $self->logger->debug( "Scored exons with name mismatch: $i\n", 1 );
-} ## end sub name_exon_rescore
-
-sub bounds_exon_rescore {
-
- # EG additional method for rescoring exons based on bounds matching
-
- my ( $self, $matrix ) = @_;
-
- if ( !( defined($matrix)
- && ref($matrix)
- && $matrix->isa('Bio::EnsEMBL::IdMapping::ScoredMappingMatrix')
- ) )
- {
- throw('Need a Bio::EnsEMBL::IdMapping::ScoredMappingMatrix.');
- }
-
- my $i = 0;
-
- foreach my $entry ( @{ $matrix->get_all_Entries() } ) {
- my $source_exon =
- $self->cache->get_by_key( 'exons_by_id', 'source',
- $entry->source() );
- my $target_exon =
- $self->cache->get_by_key( 'exons_by_id', 'target',
- $entry->target() );
-
- if ( defined($target_exon)
- && defined($source_exon)
- && ( $source_exon->strand() != $target_exon->strand()
- || $source_exon->start() != $target_exon->start()
- || $source_exon->end() != $target_exon->end() ) )
- {
- my $new_score = ( $entry->score()*0.5 );
- $matrix->set_score( $entry->source(), $entry->target(),
- $new_score );
- $i++;
- }
- }
-
- $self->logger->debug( "Scored exons with bounds mismatch: $i\n", 1 );
-} ## end sub bounds_exon_rescore
-
-
1;
diff --git a/modules/Bio/EnsEMBL/IdMapping/GeneScoreBuilder.pm b/modules/Bio/EnsEMBL/IdMapping/GeneScoreBuilder.pm
index 7e2ee41057273bd447dea0cd40758c65737b7ed1..af65c6da0d27124c8937c4be5c116771913eabbc 100644
--- a/modules/Bio/EnsEMBL/IdMapping/GeneScoreBuilder.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/GeneScoreBuilder.pm
@@ -424,40 +424,5 @@ sub biotype_gene_rescore {
} ## end sub biotype_gene_rescore
-sub name_gene_rescore {
-
- # EG name_gene_rescore is supplementary method to use to discriminate
- # near identical genes using existing names
-
- my ( $self, $matrix ) = @_;
-
- if ( !( defined($matrix)
- && ref($matrix)
- && $matrix->isa('Bio::EnsEMBL::IdMapping::ScoredMappingMatrix')
- ) )
- {
- throw('Need a Bio::EnsEMBL::IdMapping::ScoredMappingMatrix.');
- }
-
- my $i = 0;
-
- foreach my $entry ( @{ $matrix->get_all_Entries() } ) {
- my $source_gene =
- $self->cache->get_by_key( 'genes_by_id', 'source',
- $entry->source() );
- my $target_gene =
- $self->cache->get_by_key( 'genes_by_id', 'target',
- $entry->target() );
-
- if ( $source_gene->gene_name() ne $target_gene->gene_name() ) {
- $matrix->set_score( $entry->source(), $entry->target(),
- ( $entry->score()*0.8 ) );
- $i++;
- }
- }
-
- $self->logger->debug( "Scored genes with name mismatch: $i\n", 1 );
-} ## end sub name_gene_rescore
-
1;
diff --git a/modules/Bio/EnsEMBL/IdMapping/InternalIdMapper/EnsemblExonGeneric.pm b/modules/Bio/EnsEMBL/IdMapping/InternalIdMapper/EnsemblExonGeneric.pm
index bdb8abb3c7b28d524a9ae2944b38cd9ef4deba8c..61ae2a3968d06669f2920d89a1e99caf01c7f0c9 100644
--- a/modules/Bio/EnsEMBL/IdMapping/InternalIdMapper/EnsemblExonGeneric.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/InternalIdMapper/EnsemblExonGeneric.pm
@@ -86,60 +86,7 @@ sub mapped_transcript {
return ($new_scores, $mappings);
}
-
-sub gene_name {
-
- # EG gene_name is new supplementary method to support discrimination
- # based on name
-
- my ( $self, $num, $gsb, $mappings, $exon_scores ) = @_;
-
- $self->logger->info( "Retry with exon name disambiguation...\n",
- 0, 'stamped' );
-
- if ( !$exon_scores->loaded() ) {
- $gsb->name_exon_rescore($exon_scores);
- $exon_scores->write_to_file();
- }
-
- my $new_mappings =
- $self->basic_mapping( $exon_scores, "exon_mappings$num" );
-
- $num++;
-
- my $new_scores =
- $gsb->create_shrinked_matrix( $exon_scores, $new_mappings,
- "exon_matrix$num" );
-
- return ( $new_scores, $new_mappings );
-} ## end sub gene_name
-
-sub bounds {
-
- # EG new supplementary method to distuinguish based on bounds of exon
-
- my ( $self, $num, $gsb, $mappings, $exon_scores ) = @_;
-
- $self->logger->info( "Retry with exon bounds disambiguation...\n",
- 0, 'stamped' );
-
- if ( !$exon_scores->loaded() ) {
- $gsb->bounds_exon_rescore($exon_scores);
- $exon_scores->write_to_file();
- }
-
- my $new_mappings =
- $self->basic_mapping( $exon_scores, "exon_mappings$num" );
-
- $num++;
-
- my $new_scores =
- $gsb->create_shrinked_matrix( $exon_scores, $new_mappings,
- "exon_matrix$num" );
-
- return ( $new_scores, $new_mappings );
-} ## end sub bounds
-
+
1;
diff --git a/modules/Bio/EnsEMBL/IdMapping/InternalIdMapper/EnsemblGeneGeneric.pm b/modules/Bio/EnsEMBL/IdMapping/InternalIdMapper/EnsemblGeneGeneric.pm
index bfd8c8d45139cb0c055860d532820789ecd315e1..bf921652366b61b6863aed85b50e2aef5bbcdcdc 100644
--- a/modules/Bio/EnsEMBL/IdMapping/InternalIdMapper/EnsemblGeneGeneric.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/InternalIdMapper/EnsemblGeneGeneric.pm
@@ -184,34 +184,5 @@ sub internal_id {
}
-sub gene_name {
-
- # EG gene_name supplementary method for very similar genes (e.g.
- # transposons in bacteria) to penalise where gene name is different
-
- my ( $self, $num, $gsb, $mappings, $gene_scores ) = @_;
-
- $self->logger->info( "Retry with gene name disambiguation...\n",
- 0, 'stamped' );
-
- if ( !$gene_scores->loaded() ) {
- $gsb->name_gene_rescore($gene_scores);
- $gene_scores->write_to_file();
- }
-
- my $new_mappings =
- $self->basic_mapping( $gene_scores, "gene_mappings$num" );
-
- $num++;
-
- my $new_scores =
- $gsb->create_shrinked_matrix( $gene_scores, $new_mappings,
- "gene_matrix$num" );
-
- return ( $new_scores, $new_mappings );
-} ## end sub gene_name
-
-
-
1;
diff --git a/modules/Bio/EnsEMBL/IdMapping/ResultAnalyser.pm b/modules/Bio/EnsEMBL/IdMapping/ResultAnalyser.pm
index 2c3476402967fd7a854720a003b475991e4d4222..26ff16f92d148b6a21c3fa06919fb275b8efe811 100644
--- a/modules/Bio/EnsEMBL/IdMapping/ResultAnalyser.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/ResultAnalyser.pm
@@ -733,33 +733,28 @@ sub create_summary_email {
print $fh "\n";
- # EG genes_lost.txt file may not exist if species is new
- if ( $self->file_exists( 'genes_lost.txt', 'debug' ) ) {
- #
- # clicklist of first 10 deleted genes
- #
-
- print $fh qq(\nFirst 10 deleted known genes:\n);
- print $fh qq(=============================\n\n);
-
- my $in_fh = $self->get_filehandle( 'genes_lost.txt', 'debug', '<' );
- my $prefix = $self->conf->param('urlprefix');
- my $i;
-
- while (<$in_fh>) {
- last if ( ++$i > 10 );
-
- chomp;
- my ( $stable_id, $type ) = split(/\s+/);
-
- next unless ( $type eq 'known' );
+ #
+ # clicklist of first 10 deleted genes
+ #
+ print $fh qq(\nFirst 10 deleted known genes:\n);
+ print $fh qq(=============================\n\n);
- print $fh sprintf( $fmt2, $stable_id, "${prefix}$stable_id" );
- }
+ my $in_fh = $self->get_filehandle('genes_lost.txt', 'debug', '<');
+ my $prefix = $self->conf->param('urlprefix');
+ my $i;
+
+ while (<$in_fh>) {
+ last if (++$i > 10);
+
+ chomp;
+ my ($stable_id, $type) = split(/\s+/);
+
+ next unless ($type eq 'known');
- close($in_fh);
- } ## end if ( $self->file_exists...)
+ print $fh sprintf($fmt2, $stable_id, "${prefix}$stable_id");
+ }
+ close($in_fh);
close($fh);
}
diff --git a/modules/Bio/EnsEMBL/IdMapping/StableIdGenerator/EnsemblBacteria.pm b/modules/Bio/EnsEMBL/IdMapping/StableIdGenerator/EnsemblBacteria.pm
deleted file mode 100644
index a46e9d6f4562012218044174f2c668872a54cff0..0000000000000000000000000000000000000000
--- a/modules/Bio/EnsEMBL/IdMapping/StableIdGenerator/EnsemblBacteria.pm
+++ /dev/null
@@ -1,144 +0,0 @@
-=head1 LICENSE
-
- Copyright (c) 1999-2010 The European Bioinformatics Institute and
- Genome Research Limited. All rights reserved.
-
- This software is distributed under a modified Apache license.
- For license details, please see
-
- http://www.ensembl.org/info/about/code_licence.html
-
-=head1 CONTACT
-
- Please email comments or questions to the public Ensembl
- developers list at <ensembl-dev@ebi.ac.uk>.
-
- Questions may also be sent to the Ensembl help desk at
- <helpdesk@ensembl.org>.
-
-=cut
-
-package Bio::EnsEMBL::IdMapping::StableIdGenerator::EnsemblBacteria;
-use strict;
-use warnings;
-no warnings 'uninitialized';
-use Bio::EnsEMBL::Utils::Exception qw(throw warning);
-use base qw(Bio::EnsEMBL::IdMapping::StableIdGenerator::EnsemblGeneric);
-
-#
-# new generator for EnsemblBacteria
-# 1. generates EB style IDs
-# 2. updates base ID to allow for multi-species DBs to be correctly incremented
-#
-sub initial_stable_id {
- my $self = shift;
- my $type = shift;
- my $base = $self->get_base();
- # retrieve last good stable ID from hash
- my $init_stable_id = $self->{stable_id_list}{$type};
- if ( !$init_stable_id ) {
- $self->logger->debug(
- "Finding new init_stable_id as base for new $type stable IDs.\n");
-
- # use stable ID from configuration if set
- if ( $init_stable_id =
- $self->conf->param("starting_${type}_stable_id") )
- {
- $self->logger->debug(
-"Using pre-configured $init_stable_id as base for new $type stable IDs.\n"
- );
- return $init_stable_id;
- }
- my $s_dba = $self->cache->get_DBAdaptor('source');
- my $s_dbh = $s_dba->dbc->db_handle;
-
- # look in the ${type}_stable_id table first
- my $sql =
-qq(SELECT MAX(stable_id) FROM ${type}_stable_id where stable_id like '${base}%');
- print $sql;
- $init_stable_id = $self->fetch_value_from_db( $s_dbh, $sql );
-
- # also look in gene_archive to make sure there are no larger Ids there
- unless ( $type eq 'exon' ) {
- $sql = qq(SELECT MAX(${type}_stable_id) FROM gene_archive);
- my $archived_stable_id = $self->fetch_value_from_db( $s_dbh, $sql );
- if ( $archived_stable_id
- and $self->is_valid($archived_stable_id)
- and ( $archived_stable_id gt $init_stable_id ) )
- {
- $init_stable_id = $archived_stable_id;
- }
- }
- $self->{stable_id_list}{$type} = $init_stable_id;
- } else {
- $self->logger->debug(
-"Using preexisting initial $init_stable_id as base for new $type stable IDs.\n"
- );
- }
- if ($init_stable_id) {
-
- # since $init_stable_id now is the highest existing stable Id for this
- # object type, we need to increment it to find the first one we want to use
- # for new assignments
- $init_stable_id = $self->increment_stable_id( $init_stable_id, $type );
- $self->logger->debug(
- "Using $init_stable_id as base for new $type stable IDs.\n");
- } else {
- $self->logger->warning(
- "Can't find highest ${type}_stable_id in source db.\n");
- my $pref =
- $self->cache->get_DBAdaptor('target')->get_MetaContainer()
- ->list_value_by_key('species.stable_id_prefix');
- if ($pref) {
- $init_stable_id =
- $pref->[0] . substr( uc($type), 0, 1 ) . '00000000000';
- $self->logger->debug(
- "Using $init_stable_id as base for new $type stable IDs.\n");
- }
- }
- return $init_stable_id;
-}
-
-sub increment_stable_id {
- my $self = shift;
- my $stable_id = shift;
- my $type = shift;
- unless ( $self->is_valid($stable_id) ) {
- throw("Unknown or missing stable ID: $stable_id.");
- }
- my $base = $self->get_base();
- $stable_id =~ /$base([A-Z]{1,4})(\d{11})/;
- my $number = $2;
- my $new_stable_id = $base . $1 . ( ++$number );
- $self->{stable_id_list}{$type} = $new_stable_id;
- return $new_stable_id;
-}
-
-=head2 is_valid
-
- Arg[1] : String $stable_id - the stable Id to check
- Example : unless ($generator->is_valid($stable_id)) {
- die "Invalid stable Id: $stable_id.\n";
- }
- Description : Tests a stable Id to be valid (according to the Ensembl stable
- Id format definition).
- Return type : Boolean - TRUE if valid, FALSE otherwise
- Exceptions : none
- Caller : general
- Status : At Risk
- : under development
-
-=cut
-
-sub is_valid {
- my ( $self, $stable_id ) = @_;
-
- my $base = $self->get_base();
-
- return ( $stable_id
- and ( $stable_id =~ /$base([A-z]{1,4})(\d{11})/ ) );
-}
-
-sub get_base { return 'EB' }
-
-1;
diff --git a/modules/Bio/EnsEMBL/IdMapping/StableIdGenerator/EnsemblFungi.pm b/modules/Bio/EnsEMBL/IdMapping/StableIdGenerator/EnsemblFungi.pm
deleted file mode 100644
index d1cedea771ea0063a6001616e07376a43ff732b3..0000000000000000000000000000000000000000
--- a/modules/Bio/EnsEMBL/IdMapping/StableIdGenerator/EnsemblFungi.pm
+++ /dev/null
@@ -1,44 +0,0 @@
-=head1 LICENSE
-
- Copyright (c) 1999-2010 The European Bioinformatics Institute and
- Genome Research Limited. All rights reserved.
-
- This software is distributed under a modified Apache license.
- For license details, please see
-
- http://www.ensembl.org/info/about/code_licence.html
-
-=head1 CONTACT
-
- Please email comments or questions to the public Ensembl
- developers list at <ensembl-dev@ebi.ac.uk>.
-
- Questions may also be sent to the Ensembl help desk at
- <helpdesk@ensembl.org>.
-
-=cut
-
-package Bio::EnsEMBL::IdMapping::StableIdGenerator::EnsemblFungi;
-
-use strict;
-use warnings;
-no warnings 'uninitialized';
-use Bio::EnsEMBL::Utils::Exception qw(throw warning);
-use base qw(Bio::EnsEMBL::IdMapping::StableIdGenerator::EnsemblBacteria);
-
-# new generator providing EF IDs
-
-sub is_valid {
- my ( $self, $stable_id ) = @_;
-
- my $base = $self->get_base();
-
- return ( $stable_id and ( $stable_id =~ /$base([A-z]{1,4})(\d{11})/
- or $stable_id =~ /SP.*/ ) );
-}
-
-
-sub get_base { return 'EF' }
-
-1;
-
diff --git a/modules/Bio/EnsEMBL/IdMapping/StableIdGenerator/EnsemblGeneric.pm b/modules/Bio/EnsEMBL/IdMapping/StableIdGenerator/EnsemblGeneric.pm
index 2ba059869b0ce45c317ecd4d6cd2e525a23bca12..aa475697813a2813afc111edcd42afe08dbd6b86 100644
--- a/modules/Bio/EnsEMBL/IdMapping/StableIdGenerator/EnsemblGeneric.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/StableIdGenerator/EnsemblGeneric.pm
@@ -120,41 +120,30 @@ sub initial_stable_id {
my $self = shift;
my $type = shift;
- # EG modifications to permit the current stable ID to persist trohough
- # different invocations
- my $init_stable_id = $self->{stable_id_list}{$type};
-
- if ( !defined($init_stable_id) ) {
- # use stable ID from configuration if set
- if ( $init_stable_id =
- $self->conf->param("starting_${type}_stable_id") )
- {
- $self->logger->debug( "Using pre-configured $init_stable_id "
- . "as base for new $type stable IDs.\n" );
- return $init_stable_id;
- }
+ my $init_stable_id;
+
+ # use stable ID from configuration if set
+ if ($init_stable_id = $self->conf->param("starting_${type}_stable_id")) {
+ $self->logger->debug("Using pre-configured $init_stable_id as base for new $type stable IDs.\n");
+ return $init_stable_id;
+ }
- my $s_dba = $self->cache->get_DBAdaptor('source');
- my $s_dbh = $s_dba->dbc->db_handle;
-
- # look in the ${type}_stable_id table first
- my $sql = qq(SELECT MAX(stable_id) FROM ${type}_stable_id);
- $init_stable_id = $self->fetch_value_from_db( $s_dbh, $sql );
-
- # also look in gene_archive to make sure there are no larger Ids
- # there
- unless ( $type eq 'exon' ) {
- $sql = qq(SELECT MAX(${type}_stable_id) FROM gene_archive);
- my $archived_stable_id =
- $self->fetch_value_from_db( $s_dbh, $sql );
- if ( $archived_stable_id
- and $self->is_valid($archived_stable_id)
- and ( $archived_stable_id gt $init_stable_id ) )
- {
- $init_stable_id = $archived_stable_id;
- }
+ my $s_dba = $self->cache->get_DBAdaptor('source');
+ my $s_dbh = $s_dba->dbc->db_handle;
+
+ # look in the ${type}_stable_id table first
+ my $sql = qq(SELECT MAX(stable_id) FROM ${type}_stable_id);
+ $init_stable_id = $self->fetch_value_from_db($s_dbh, $sql);
+
+ # also look in gene_archive to make sure there are no larger Ids there
+ unless ($type eq 'exon') {
+ $sql = qq(SELECT MAX(${type}_stable_id) FROM gene_archive);
+ my $archived_stable_id = $self->fetch_value_from_db($s_dbh, $sql);
+ if ($archived_stable_id and $self->is_valid($archived_stable_id) and
+ ($archived_stable_id gt $init_stable_id)) {
+ $init_stable_id = $archived_stable_id;
}
- } ## end if ( !defined($init_stable_id...))
+ }
if ($init_stable_id) {
# since $init_stable_id now is the highest existing stable Id for this
diff --git a/modules/Bio/EnsEMBL/IdMapping/StableIdGenerator/EnsemblProtists.pm b/modules/Bio/EnsEMBL/IdMapping/StableIdGenerator/EnsemblProtists.pm
deleted file mode 100644
index fe0e1265f3d60cd40acf960b81fe3f33c4067d4a..0000000000000000000000000000000000000000
--- a/modules/Bio/EnsEMBL/IdMapping/StableIdGenerator/EnsemblProtists.pm
+++ /dev/null
@@ -1,41 +0,0 @@
-=head1 LICENSE
-
- Copyright (c) 1999-2010 The European Bioinformatics Institute and
- Genome Research Limited. All rights reserved.
-
- This software is distributed under a modified Apache license.
- For license details, please see
-
- http://www.ensembl.org/info/about/code_licence.html
-
-=head1 CONTACT
-
- Please email comments or questions to the public Ensembl
- developers list at <ensembl-dev@ebi.ac.uk>.
-
- Questions may also be sent to the Ensembl help desk at
- <helpdesk@ensembl.org>.
-
-=cut
-
-package Bio::EnsEMBL::IdMapping::StableIdGenerator::EnsemblProtists;
-use strict;
-use warnings;
-no warnings 'uninitialized';
-use Bio::EnsEMBL::Utils::Exception qw(throw warning);
-use base qw(Bio::EnsEMBL::IdMapping::StableIdGenerator::EnsemblBacteria);
-
-# new generator to create new protist IDs (and also deal with existing plasmodial IDs)
-
-sub is_valid {
- my ( $self, $stable_id ) = @_;
- my $base = $self->get_base();
- return ( $stable_id and ( $stable_id =~ /$base([A-z]{1,4})(\d{11})/
- or $stable_id =~ /PVX.*/
- or $stable_id =~ /PKH.*/ ) );
-
-}
-
-sub get_base { return 'EPr' }
-
-1;
diff --git a/modules/Bio/EnsEMBL/IdMapping/StableIdMapper.pm b/modules/Bio/EnsEMBL/IdMapping/StableIdMapper.pm
index 5d9fda6926da490e24da7b3c1aa16d0b99d06975..9b78008d44a535fad5b55b37c4451236211a3d94 100644
--- a/modules/Bio/EnsEMBL/IdMapping/StableIdMapper.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/StableIdMapper.pm
@@ -150,17 +150,15 @@ sub generate_mapping_session {
$self->logger->info("old_assembly: $old_assembly, new_assembly $new_assembly\n", 2);
}
- print $fh join( "\t",
- $mapping_session_id,
- $self->conf->param('sourcedbname'),
- $self->conf->param('targetdbname'),
- $old_release,
- $new_release,
- $old_assembly,
- $new_assembly,
- $self->mapping_session_date_fmt(),
- $self->conf->param('species_id') # EG
- );
+ print $fh join("\t",
+ $mapping_session_id,
+ $self->conf->param('sourcedbname'),
+ $self->conf->param('targetdbname'),
+ $old_release,
+ $new_release,
+ $old_assembly,
+ $new_assembly,
+ $self->mapping_session_date_fmt);
print $fh "\n";
close($fh);
@@ -187,10 +185,9 @@ sub map_stable_ids {
# check if there are any objects of this type at all
my %all_sources = %{ $self->cache->get_by_name("${type}s_by_id", 'source') };
my %all_targets = %{ $self->cache->get_by_name("${type}s_by_id", 'target') };
- if ( scalar( keys(%all_sources) ) == 0 ) {
- # EG may be possible to have no sources for new species
- $self->logger->warning("No cached ${type}s found.\n\n");
- %all_sources = ();
+ unless (scalar(keys %all_sources)) {
+ $self->logger->info("No cached ${type}s found.\n\n");
+ return;
}
my %stats = map { $_ => 0 }
@@ -284,9 +281,8 @@ sub map_stable_ids {
}
# increment the stable Id (to be assigned to the next unmapped object)
- $new_stable_id =
- $self->stable_id_generator->increment_stable_id( $new_stable_id,
- $type );
+ $new_stable_id = $self->stable_id_generator->increment_stable_id(
+ $new_stable_id);
# stats
$stats{'new'}++;
@@ -638,31 +634,24 @@ sub generate_mapping_stats {
my $novel_total = $stats->{'mapped_novel'} + $stats->{'lost_novel'};
# no split into known and novel for exons
- if ( $type ne 'exon' ) {
- $result .= sprintf( $fmt2, 'known',
- $stats->{'mapped_known'},
- $stats->{'lost_known'}, (
- $known_total
- ? $stats->{'mapped_known'}/$known_total*100
- : 0 ) );
-
- $result .= sprintf( $fmt2, 'novel',
- $stats->{'mapped_novel'},
- $stats->{'lost_novel'}, (
- $novel_total
- ? $stats->{'mapped_novel'}/$novel_total*100
- : 0 ) );
- }
+ unless ( $type eq 'exon' ) {
+ $result .= sprintf( $fmt2,
+ 'known',
+ $stats->{'mapped_known'},
+ $stats->{'lost_known'},
+ ($known_total ? $stats->{'mapped_known'}/$known_total*100 : 0)
+ );
- if ( $mapped_total == 0 ) {
- # EG different calculation needed when no mappings found for new
- # species
- $result .= sprintf( $fmt2, 'total', $mapped_total, $lost_total, 0 );
- } else {
$result .= sprintf( $fmt2,
- 'total', $mapped_total, $lost_total,
- $mapped_total/( $known_total + $novel_total )*100 );
- }
+ 'novel',
+ $stats->{'mapped_novel'},
+ $stats->{'lost_novel'},
+ ($novel_total ? $stats->{'mapped_novel'}/$novel_total*100 : 0)
+ );
+ } ## end unless ( $type eq 'exon' )
+
+ $result .= sprintf($fmt2, 'total', $mapped_total, $lost_total,
+ $mapped_total/($known_total + $novel_total)*100);
# log result
$self->logger->info($result."\n");
diff --git a/modules/Bio/EnsEMBL/IdMapping/SyntenyFramework.pm b/modules/Bio/EnsEMBL/IdMapping/SyntenyFramework.pm
index a3d7fcf12617167a075f3c1383c2cab34432e422..0b2c09339f8a31595cee8c541418ffcffeb2b923 100644
--- a/modules/Bio/EnsEMBL/IdMapping/SyntenyFramework.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/SyntenyFramework.pm
@@ -376,15 +376,12 @@ sub rescore_gene_matrix_lsf {
is_component => 1,
);
- my $cmd = qq{perl -I./modules $Bin/synteny_rescore.pl }
- . qq{$options --index \$LSB_JOBINDEX};
+ my $cmd = qq{$Bin/synteny_rescore.pl $options --index \$LSB_JOBINDEX};
- my $pipe =
- qq{|bsub -J$lsf_name\[1-$num_jobs\] }
- . qq{-o $logpath/synteny_rescore.\%I.out }
- . qq{-e $logpath/synteny_rescore.\%I.err }
- . $self->conf()->param('lsf_opt_run')
- . $self->conf()->param('lsf_opt_synteny_rescore');
+ my $pipe = qq{|bsub -J$lsf_name\[1-$num_jobs\] } .
+ qq{-o $logpath/synteny_rescore.\%I.out } .
+ qq{-e $logpath/synteny_rescore.\%I.err } .
+ $self->conf->param('lsf_opt_synteny_rescore');
# run lsf job array
$self->logger->info("Submitting $num_jobs jobs to lsf.\n");
@@ -402,10 +399,8 @@ sub rescore_gene_matrix_lsf {
# submit dependent job to monitor finishing of jobs
$self->logger->info("Waiting for jobs to finish...\n", 0, 'stamped');
- my $dependent_job =
- qq{bsub -K -w "ended($lsf_name)" }
- . $self->conf()->param('lsf_opt_run_small')
- . qq{ -o $logpath/synteny_rescore_depend.out /bin/true};
+ my $dependent_job = qq{bsub -K -w "ended($lsf_name)" -q small } .
+ qq{-o $logpath/synteny_rescore_depend.out /bin/true};
system($dependent_job) == 0 or
$self->logger->error("Error submitting dependent job: $!\n");
diff --git a/modules/Bio/EnsEMBL/IdMapping/TinyExon.pm b/modules/Bio/EnsEMBL/IdMapping/TinyExon.pm
index e32ede6f4fddd93f36401154a66ead473d5c5d79..e3173c3e93fb9d4aa8589368dbadbaf861bf44fd 100644
--- a/modules/Bio/EnsEMBL/IdMapping/TinyExon.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/TinyExon.pm
@@ -461,28 +461,6 @@ sub is_known {
return 1;
}
-=head2 gene_name
-
- Description : optional name of gene to which exon belongs
- Return type : String + Exceptions : none
- Caller : general
- Status : At Risk
- : under development
-
-=cut
-
-sub gene_name {
- my ($self, $value) = @_;
-
- # EG optional gene name for exon for improved discrimination
-
- if ( defined($value) ) {
- $self->[18] = $value;
- }
-
- return $self->[18];
-}
-
1;
diff --git a/modules/Bio/EnsEMBL/IdMapping/TinyGene.pm b/modules/Bio/EnsEMBL/IdMapping/TinyGene.pm
index 93e6c183fbbf501c06d359cb000a50087a5fb506..c79a5a5ad0d7767c377ff0a2a4f0c92107125c44 100644
--- a/modules/Bio/EnsEMBL/IdMapping/TinyGene.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/TinyGene.pm
@@ -71,8 +71,7 @@ package Bio::EnsEMBL::IdMapping::TinyGene;
# 10 status
# 11 logic_name
# 12 is_known
-# 13 gene_name
-# 14 [transcripts]
+# 13 [transcripts]
use strict;
@@ -260,7 +259,7 @@ sub add_Transcript {
throw('Need a Bio::EnsEMBL::IdMapping::TinyTranscript.');
}
- push @{ $self->[14] }, $tr;
+ push @{ $self->[13] }, $tr;
}
@@ -279,7 +278,7 @@ sub add_Transcript {
=cut
sub get_all_Transcripts {
- return $_[0]->[14] || [];
+ return $_[0]->[13] || [];
}
@@ -300,29 +299,5 @@ sub length {
}
-=head2 gene_name
-
- Description : optional name of gene
- Return type : String
- Exceptions : none
- Caller : general
- Status : At Risk
- : under development
-
-=cut
-
-sub gene_name {
- my ( $self, $value ) = @_;
-
- # EG optional gene name for improved discrimination
-
- if ( defined($value) ) {
- $self->[13] = $value;
- }
-
- return $self->[13];
-}
-
-
1;