From ac66263b645cf17d720433940eec0aa041d59e04 Mon Sep 17 00:00:00 2001
From: Paul-Davis <pad@ebi.ac.uk>
Date: Tue, 3 Oct 2017 17:27:15 +0100
Subject: [PATCH 01/11] Added quick check for invalid isoformer annotations
that slip through sometimes.
---
scripts/check_predicted_genes.pl | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/scripts/check_predicted_genes.pl b/scripts/check_predicted_genes.pl
index 3ed6d5343..bfe45def7 100755
--- a/scripts/check_predicted_genes.pl
+++ b/scripts/check_predicted_genes.pl
@@ -262,6 +262,20 @@
$seen{$gg}=1;
}
+ my @isoformer_genes = $db->fetch (-query => "FIND $qclass where \"*iso*\"");
+ foreach my $g (@isoformer_genes) {
+my $gg=$g->name;
+ if ($ignore{$gg}) {next}
+ if (exists $seen{$gg}) {
+ $s=' (seen already)';
+ } else {
+ $s='';
+ }
+ $log->write_to("Error: $qclass $gg should be removed $s\n");
+ $seen{$gg}=1;
+ }
+
+
my @no_Sparent_genes = $db->fetch (-query => "FIND $qclass where !S_parent");
foreach my $g (@no_Sparent_genes) {
my $gg=$g->name;
From 44209f665a25941e8a792d78ee0910f602fb1d6b Mon Sep 17 00:00:00 2001
From: Kevin Howe <klh@ebi.ac.uk>
Date: Wed, 11 Oct 2017 13:50:19 +0100
Subject: [PATCH 02/11] Ensembl now supports antisense_RNA biotype, so use that
---
scripts/ENSEMBL/lib/WormBase2Ensembl.pm | 6 ------
1 file changed, 6 deletions(-)
diff --git a/scripts/ENSEMBL/lib/WormBase2Ensembl.pm b/scripts/ENSEMBL/lib/WormBase2Ensembl.pm
index 0a35d0733..9f50d05e3 100644
--- a/scripts/ENSEMBL/lib/WormBase2Ensembl.pm
+++ b/scripts/ENSEMBL/lib/WormBase2Ensembl.pm
@@ -457,12 +457,6 @@ sub parse_genes_gff3_fh {
my $bt = "ncRNA";
$transcript->biotype($bt);
$gene_biotypes{$bt}++;
- } elsif ( $gff_type eq 'antisense_RNA') {
- # not acknowledged as a biotype by Ensembl; change to default ncRNA
- $transcript->analysis($nc_ana);
- my $bt = "antisense";
- $transcript->biotype($bt);
- $gene_biotypes{$bt}++;
} else {
$transcript->analysis($nc_ana);
my $bt = ($gff_type =~ /RNA/) ? $gff_type : 'ncRNA';
From 56829a78ab86b624594feeda6956688a66baa3ac Mon Sep 17 00:00:00 2001
From: Paul-Davis <pad@ebi.ac.uk>
Date: Wed, 11 Oct 2017 16:58:01 +0100
Subject: [PATCH 03/11] Now ignores ensembl gene stubs from reporting.
---
scripts/NAMEDB/geneace_nameDB_comm.pl | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/scripts/NAMEDB/geneace_nameDB_comm.pl b/scripts/NAMEDB/geneace_nameDB_comm.pl
index 0e39c2e8c..ddd9d0b81 100644
--- a/scripts/NAMEDB/geneace_nameDB_comm.pl
+++ b/scripts/NAMEDB/geneace_nameDB_comm.pl
@@ -100,8 +100,13 @@
# any genes left in the acedb list are absent from the nameserver
foreach (keys %ace_genes ){
+ if ($_ =~ /ENS/) {
+ print "Skipping ENSEMBL ID:$_\n" if $debug;
+ }
+ else {
$log->error("ERROR: $_ absent from nameserver\n");
$errorcount++;
+ }
}
$log->write_to("INFO: $errorcount errors found\n") if ($log->report_errors > 0);
$log->write_to("No errors found\n") if ($log->report_errors == 0);
From b0d3cacd5c6fa9a37ae73f24e36dbdbefe5ac1d9 Mon Sep 17 00:00:00 2001
From: Gary Williams <gw3@ebi.ac.uk>
Date: Thu, 12 Oct 2017 09:41:47 +0100
Subject: [PATCH 04/11] Added caltech_Analysis
---
autoace_config/elegans.config | 1 +
1 file changed, 1 insertion(+)
diff --git a/autoace_config/elegans.config b/autoace_config/elegans.config
index 1f0930f12..f352487a2 100644
--- a/autoace_config/elegans.config
+++ b/autoace_config/elegans.config
@@ -70,6 +70,7 @@ db=citace file=caltech_CDS.ace class=CDS format="Interaction WBInteraction\d{
db=citace file=caltech_Cell.ace class=Cell format="Reference WBPaper\d{8}" format="Anatomy_term WBbt:\d{7}"
db=citace file=caltech_Cell_group.ace class=Cell_group format="Reference WBPaper\d{8}" format="Anatomy_term WBbt:\d{7}"
db=citace file=caltech_Condition.ace class=Condition
+db=citace file=caltech_Analysis.ace class=Analysis format="Reference WBPaper\d{8}" format="Conducted_by WBPerson\d{1,5}"
db=citace file=caltech_DO_defs.ace class=DO_term format="Reference WBPaper\d{8}"
db=citace file=caltech_Database.ace class=Database
db=citace file=caltech_Expr_pattern.ace class=Expr_pattern format="Gene WBGene\d{8}" format="Reference WBPaper\d{8}"
From 09178a0b773995ce3b36e4cdd2f449c4cc5cbdcc Mon Sep 17 00:00:00 2001
From: Gary Williams <gw3@ebi.ac.uk>
Date: Thu, 12 Oct 2017 10:07:23 +0100
Subject: [PATCH 05/11] ensure the caltech_Analysis is linked to a Sample
---
autoace_config/elegans.config | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/autoace_config/elegans.config b/autoace_config/elegans.config
index f352487a2..155002dfa 100644
--- a/autoace_config/elegans.config
+++ b/autoace_config/elegans.config
@@ -70,7 +70,7 @@ db=citace file=caltech_CDS.ace class=CDS format="Interaction WBInteraction\d{
db=citace file=caltech_Cell.ace class=Cell format="Reference WBPaper\d{8}" format="Anatomy_term WBbt:\d{7}"
db=citace file=caltech_Cell_group.ace class=Cell_group format="Reference WBPaper\d{8}" format="Anatomy_term WBbt:\d{7}"
db=citace file=caltech_Condition.ace class=Condition
-db=citace file=caltech_Analysis.ace class=Analysis format="Reference WBPaper\d{8}" format="Conducted_by WBPerson\d{1,5}"
+db=citace file=caltech_Analysis.ace class=Analysis query=(Sample) format="Reference WBPaper\d{8}" format="Conducted_by WBPerson\d{1,5}"
db=citace file=caltech_DO_defs.ace class=DO_term format="Reference WBPaper\d{8}"
db=citace file=caltech_Database.ace class=Database
db=citace file=caltech_Expr_pattern.ace class=Expr_pattern format="Gene WBGene\d{8}" format="Reference WBPaper\d{8}"
From f266ae2f453e64b621c69a76208b1ef8ba0c7152 Mon Sep 17 00:00:00 2001
From: Gary Williams <gw3@ebi.ac.uk>
Date: Fri, 13 Oct 2017 11:41:52 +0100
Subject: [PATCH 06/11] New utility to produce a Feature_data ACE file from a
GFF file.
---
scripts/gff2feature_data.pl | 465 ++++++++++++++++++++++++++++++++++++
1 file changed, 465 insertions(+)
create mode 100755 scripts/gff2feature_data.pl
diff --git a/scripts/gff2feature_data.pl b/scripts/gff2feature_data.pl
new file mode 100755
index 000000000..fad0c1ea2
--- /dev/null
+++ b/scripts/gff2feature_data.pl
@@ -0,0 +1,465 @@
+#!/software/bin/perl -w
+#
+# Small script to convert GFF regions to Feature_data objects
+#
+# Last updated by: $Author: klh $
+# Last updated on: $Date: 2012-06-22 08:56:52 $
+
+use strict;
+use lib $ENV{'CVS_DIR'};
+use Wormbase;
+use Getopt::Long;
+use Carp;
+use Log_files;
+use Storable;
+#use Ace;
+#use Sequence_extract;
+use Coords_converter;
+use Modules::Remap_Sequence_Change;
+
+######################################
+# variables and command-line options #
+######################################
+
+my ($help, $debug, $test, $verbose, $store, $wormbase);
+my ($input, $output, $species);
+my %features;
+
+GetOptions ("help" => \$help,
+ "debug=s" => \$debug,
+ "test" => \$test,
+ "verbose" => \$verbose,
+ "store:s" => \$store,
+ "input:s" => \$input, # the GFF file
+ "output:s" => \$output,
+ "features:s" => \%features, # feature(s) to select column 3 of the GFF, takes value of method
+ "species:s" => \$species,
+ );
+# use multiple features definitions e.g. -features Poly-A=RNASeq_polyA -features SL1=RNASeq_SL1 -features SL2=RNASeq_SL2
+
+if ( $store ) {
+ $wormbase = retrieve( $store ) or croak("Can't restore wormbase from $store\n");
+} else {
+ $wormbase = Wormbase->new( -debug => $debug,
+ -test => $test,
+ -organism => $species,
+ );
+}
+
+# Display help if required
+&usage("Help") if ($help);
+
+# in test mode?
+if ($test) {
+ print "In test mode\n" if ($verbose);
+
+}
+
+# establish log file.
+my $log = Log_files->make_build_log($wormbase);
+
+
+#################################
+# check input arguments
+#################################
+
+
+$species = $wormbase->full_name;
+
+
+#################################
+
+my $database = $wormbase->autoace;
+my $coords = Coords_converter->invoke($database, 0, $wormbase);
+my $virtual;
+
+# suck the data in
+open (IN, "<$input") || die "Can't open $input\n";
+open (ACE, ">$output") || die "Can't open $output\n";
+
+my (@tiles, @whole_chromosome);
+
+my $sequence = '';
+my $sequence_len = 0;
+my %scores; # a list of the scores for each feature, so that we can find the median scores
+
+while (my $line = <IN>) {
+
+ if ($line =~ /^#/) {next;}
+
+ my @cols = split /\s+/, $line;
+ my $chrom = $cols[0];
+ my $ft = $cols[2];
+ my $start = $cols[3];
+ my $end = $cols[4];
+ my $reads = $cols[5];
+ my $sense = $cols[6];
+
+ # ignore lines that are not from the feature we want
+ if (!exists $features{$ft}) {next;}
+ my $method = $features{$ft};
+
+ # assume we are dealing with strand-sensitive data, in which case we
+ # need to be able to distinguish strands by making the smallest
+ # region 2 bases long so that reverse strand is different to forward
+ # strand.
+ if ($start == $end) {
+ if ($sense eq '+') {$end++}
+ if ($sense eq '-') {$start--}
+ }
+ if ($sense eq '-') {
+ ($end, $start) = ($start, $end);
+ }
+
+ if ($chrom ne $sequence) { # new sequence
+
+ write_tiles(\@tiles, \@whole_chromosome, $sequence, $sequence_len); # write the old data
+
+ $sequence = $chrom;
+ $sequence_len = initialise_tiles($chrom, \@tiles, $coords);
+
+ }
+
+ store_feature_in_tile(\@tiles, \@whole_chromosome, $method, $start, $end, $reads, $ft);
+
+
+}
+
+# write the last sequence
+write_tiles(\@tiles, \@whole_chromosome, $virtual, $sequence, $sequence_len); # write the old data
+
+# work out the median score and write the Method object
+write_method();
+
+
+close(ACE);
+close(IN);
+
+
+
+$log->mail();
+print "Finished.\n" if ($verbose);
+exit(0);
+
+
+
+
+
+
+##############################################################
+#
+# Subroutines
+#
+##############################################################
+
+
+
+##########################################
+
+sub usage {
+ my $error = shift;
+
+ if ($error eq "Help") {
+ # Normal help menu
+ system ('perldoc',$0);
+ exit (0);
+ }
+}
+
+##########################################
+# find the tile to store the Feature in
+sub store_feature_in_tile {
+ my ($tiles_aref, $whole_chromosome_aref, $method, $start, $end, $reads, $text) = @_;
+ # $text is the $feature from the GFF column 3
+
+ # store the score so that we can get the median score
+ if ($reads =~ /^\d+$/) {
+ push @{$scores{$method}}, $reads;
+ }
+
+ my $found = 0;
+ for( my $tile_idx = 1; $tile_idx <= @{$tiles_aref}; $tile_idx++) {
+ my $tile = $tiles_aref->[$tile_idx-1];
+ if ($start < $end) {
+ if ($start > $tile->{start} && $end <= $tile->{end}) { # find the tile containing this forward Feature
+ push @{$tile->{segs}}, [$method, $start - $tile->{start} + 1, $end - $tile->{start} + 1, $reads, $text];
+ $found = 1;
+ }
+ } else {
+ if ($end > $tile->{start} && $start <= $tile->{end}) { # find the tile containing this reverse Feature
+ push @{$tile->{segs}}, [$method, $start - $tile->{start} + 1, $end - $tile->{start} + 1, $reads, $text];
+ $found = 1;
+ }
+ }
+ }
+ if (!$found) { # it falls between two tiles, so place it on the top-level Sequence
+ push @{$whole_chromosome_aref}, [$method, $start, $end, $reads, $text];
+ }
+}
+
+##########################################
+sub write_tiles {
+ my ($tiles_aref, $whole_chromosome_aref, $sequence, $sequence_len) = @_;
+
+
+ # output the new Sequence lines
+
+ foreach my $method (values %features) {
+ if (!defined $sequence || $sequence eq '') {last}
+ my $virtual = "${sequence}:${method}";
+
+ my @sequence_out;
+ my @feature_out;
+
+ if (scalar @{$tiles_aref}) {
+ push @sequence_out, "\nSequence : \"${sequence}\"\n";
+
+ for(my $tile_idx = 1; $tile_idx <= @{$tiles_aref}; $tile_idx++) {
+ my $tile = $tiles_aref->[$tile_idx-1];
+
+ my $vseq = "${virtual}:$tile_idx";
+
+ if (@{$tile->{segs}}) {
+ push @sequence_out, "S_Child Feature_data ". $vseq ." ". $tile->{start} ." ". $tile->{end} ."\n";
+
+ push @feature_out, "\nFeature_data : \"$vseq\"\n";
+ foreach my $seg (@{$tile->{segs}}) {
+ if ($seg->[0] eq $method) {
+ push @feature_out, "Feature @$seg\n";
+ }
+ }
+ }
+ }
+ }
+
+
+ if (scalar @{$whole_chromosome_aref}) {
+ push @sequence_out, "\nSequence : \"${sequence}\"\n";
+ push @sequence_out, "S_Child Feature_data ${virtual} 1 $sequence_len\n";
+ push @feature_out, "\nFeature_data : ${virtual}\n";
+ foreach my $seg (@{$whole_chromosome_aref}) {
+ if ($seg->[0] eq $method) {
+ push @feature_out, "Feature @$seg\n";
+ }
+ }
+ }
+
+ print ACE @sequence_out;
+ print ACE "\n"; # acezip.pl concatenates another line to the last line if this is not blank
+
+ print ACE @feature_out;
+ print ACE "\n";
+
+ }
+
+ @{$tiles_aref} = ();
+ @{$whole_chromosome_aref} = ();
+}
+##########################################
+sub initialise_tiles {
+ my ($sequence, $tiles_aref, $coords) = @_;
+
+ my $chr_len = $coords->Superlink_length($sequence);
+ if (!defined $chr_len) {$log->log_and_die("Can't find the length of the Sequence $sequence\n")}
+
+ for(my $i=0; $i < $chr_len; $i += 300000) {
+ my $chr_start = $i + 1;
+ my $chr_end = $chr_start + 300000 - 1;
+ $chr_end = $chr_len if $chr_end > $chr_len;
+ push @{$tiles_aref}, {
+ start => $chr_start,
+ end => $chr_end,
+ segs => [],
+ }
+ }
+ return $chr_len;
+}
+##########################################
+# work out the median score and write the Method object
+
+sub write_method {
+
+ foreach my $feature (keys %features) {
+ my $method = $features{$feature};
+ my $median_score = median(@{$scores{$method}});
+ my $score_max = 10 * $median_score;
+ print "$method\t median score: $median_score\n";
+ my $colour = get_colour($method); # convert the method name into a colour value
+
+ print ACE "\n";
+ print ACE "Method : $method\n";
+ print ACE "Remark \"This data was produced by $ENV{USER} with the script gff2feature_data.gff from the data file $input using the feature column '$feature'.\"\n";
+ print ACE "Show_up_strand\n";
+ print ACE "Score_by_width\n";
+ print ACE "Score_bounds 1 $score_max\n";
+ print ACE "Overlap\n";
+ print ACE "Right_priority 1.5\n";
+ print ACE "Colour $colour\n";
+ print ACE "\n";
+
+ }
+
+
+}
+##########################################
+# return the median value of a list of values
+sub median {
+
+ my @vals = sort {$a <=> $b} @_;
+ my $len = @vals;
+ if($len%2) #odd?
+ {
+ return $vals[int($len/2)];
+ }
+ else #even
+ {
+ return ($vals[int($len/2)-1] + $vals[int($len/2)])/2;
+ }
+}
+##########################################
+# return colour from a string that is hased to a value from 1 to 16
+sub get_colour {
+ my ($text) = @_;
+
+ my @colours = qw(
+ WHITE
+ BLACK
+ LIGHTGRAY
+ DARKGRAY
+ RED
+ GREEN
+ BLUE
+ YELLOW
+ CYNA
+ MAGENTA
+ LIGHTRED
+ LIGHTGREEN
+ LIGHTBLUE
+ DARKRED
+ DARKGREEN
+ DARKBLUE
+ PALERED
+ PALEGREEN
+ PALEBLUE
+ PALEYELLOW
+ PALECYAN
+ PALEMAGENTA
+ BROWN
+ ORANGE
+ PALEORANGE
+ PURPLE
+ VIOLET
+ PALEVIOLET
+ GRAY
+ PALEGRAY
+ CERISE
+ MIDBLUE
+ );
+
+ my $value = 0;
+ foreach my $letter (split //, $text) {
+ $value += ord $letter
+ }
+ $value %= 32;
+ return $colours[$value];
+}
+##########################################
+
+# Add perl documentation in POD format
+# This should expand on your brief description above and
+# add details of any options that can be used with the program.
+# Such documentation can be viewed using the perldoc command.
+
+
+__END__
+
+=pod
+
+=head2 NAME - gff3ace.pl
+
+=head1 USAGE
+
+=over 4
+
+=item gff3ace.pl [-options]
+
+=back
+
+This script reads in a GFF file of locations and writes out an Feature_data ACE file.
+
+
+
+
+script_template.pl MANDATORY arguments:
+
+=over 4
+
+=item -input input file of gene predictions in GFF3 format
+
+=back
+
+=over 4
+
+=item -output output ACE file of CDS objects
+
+=back
+
+=over 4
+
+=item -feature feature GFF3 field name to fnd and use and the method to use. specify as many times as you wish e.g. -features Poly-A=RNASeq_polyA -features SL1=RNASeq_SL1 -features SL2=RNASeq_SL2
+
+=back
+
+
+
+
+script_template.pl OPTIONAL arguments:
+
+=over 4
+
+=item -species species_name. By default, this script will write ACE data specifying the species as 'elegans'. This specifies a different species.
+
+=back
+
+=over 4
+
+=item -h, Help
+
+=back
+
+=over 4
+
+=item -debug, Debug mode, set this to the username who should receive the emailed log messages. The default is that everyone in the group receives them.
+
+=back
+
+=over 4
+
+=item -test, Test mode, run the script, but don't change anything.
+
+=back
+
+=over 4
+
+=item -verbose, output lots of chatty test messages
+
+=back
+
+
+=head1 REQUIREMENTS
+
+=over 4
+
+=item None at present.
+
+=back
+
+=head1 AUTHOR
+
+=over 4
+
+=item Gary Williams
+
+=back
+
+=cut
From fdbd991597e3c7ffc1753d98350ae23bba26929d Mon Sep 17 00:00:00 2001
From: Paul-Davis <pad@ebi.ac.uk>
Date: Mon, 16 Oct 2017 15:53:03 +0100
Subject: [PATCH 07/11] fixed the previous commit code to actually test for the
presence of the real file including location.
---
scripts/confirm_genes.pl | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/scripts/confirm_genes.pl b/scripts/confirm_genes.pl
index f9ea6848e..034fd4f9a 100755
--- a/scripts/confirm_genes.pl
+++ b/scripts/confirm_genes.pl
@@ -1,3 +1,6 @@
+
+
+
#!/usr/local/bin/perl5.8.0 -w
#
# confirm_genes.pl
@@ -620,7 +623,7 @@ sub create_transcript_file {
}else {
$prefix = $wormbase->chromosome_prefix."${chrom}_";
}
- my $trinity = -e "${prefix}BLAT_Trinity_BEST.gff" ? "${prefix}BLAT_Trinity_BEST.gff" : '';
+ my $trinity = -e "${gffdir}/${prefix}BLAT_Trinity_BEST.gff" ? "${prefix}BLAT_Trinity_BEST.gff" : '';
$wormbase->run_command("cd $gffdir; cat ${prefix}BLAT_EST_BEST.gff ${prefix}BLAT_mRNA_BEST.gff $trinity > ${prefix}BLAT_TRANSCRIPT_BEST.gff", $log) unless (-e "$gffdir/${prefix}BLAT_TRANSCRIPT_BEST.gff");
# only elegans has OSTs and RSTs
From 8508eacd1c2bf3edd68cebb0e1e98bc551572568 Mon Sep 17 00:00:00 2001
From: Gary Williams <gw3@ebi.ac.uk>
Date: Mon, 16 Oct 2017 16:16:59 +0100
Subject: [PATCH 08/11] check for yeast and worm in Homol_data, not
Feature_data
---
scripts/next_builder_checks.pl | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/scripts/next_builder_checks.pl b/scripts/next_builder_checks.pl
index 108bc76f8..5c6183b1b 100755
--- a/scripts/next_builder_checks.pl
+++ b/scripts/next_builder_checks.pl
@@ -159,7 +159,7 @@
# human, japonica, pristionchus, remanei, slimSwissProt,
# worm, yeast)
my @expected = qw(fly brenneri briggsae human japonica pristionchus remanei slimSwissProt worm yeast);
- &check_for_missing_data2(\@hd, \@expected, 'Feature_data', 'what is expected');
+ &check_for_missing_data2(\@hd, \@expected, 'Homol_data', 'what is expected');
# if($count < 11) {
# $log->error("\tERROR: $clone has wublastx Homol_data objects missing\n");
From e90108d772f7c07dcd3314568a6488bf04e5e4d3 Mon Sep 17 00:00:00 2001
From: Paul-Davis <pad@ebi.ac.uk>
Date: Mon, 16 Oct 2017 16:36:42 +0100
Subject: [PATCH 09/11] Removed some of the sub_classes that dont exist for non
elegans/briggsae species
---
scripts/check_class.pl | 6 ------
1 file changed, 6 deletions(-)
diff --git a/scripts/check_class.pl b/scripts/check_class.pl
index 2508a3a3b..730705784 100755
--- a/scripts/check_class.pl
+++ b/scripts/check_class.pl
@@ -601,14 +601,10 @@ sub set_classes {
@classes = (
"Sequence",
"CDS",
- "Transposon",
"Transcript",
"Pseudogene",
"Transposon_CDS",
"cDNA_sequence",
- "${species}_CDS",
- "${species}_pseudogenes",
- "${species}_RNA_genes",
"Class",
"Model",
"Method",
@@ -628,8 +624,6 @@ sub set_classes {
"Peptide",
"Protein",
"Species",
- "Transposon_family",
- "Comment",
"Database",
"Display",
"DNA",
From 3dbff487ec186af125467e6bc4d31bd1ee95bff1 Mon Sep 17 00:00:00 2001
From: Paul-Davis <pad@ebi.ac.uk>
Date: Tue, 17 Oct 2017 12:41:21 +0100
Subject: [PATCH 10/11] Updated the Allele/Engineered_allele xace query.
---
scripts/data_checks.pl | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/scripts/data_checks.pl b/scripts/data_checks.pl
index bffc13b53..975c4eb6a 100644
--- a/scripts/data_checks.pl
+++ b/scripts/data_checks.pl
@@ -258,7 +258,7 @@ sub read_GFF_queries {
$i++;
$queries[$i]{'DESC'} = "Allele";
$queries[$i]{'GFF'} = "\tAllele\tsequence_alteration";
- $queries[$i]{'QUERY'} = 'find Variation flanking_sequences AND method = "Allele"';
+ $queries[$i]{'QUERY'} = 'find Variation Flanking_sequences AND (method = "Allele" OR method = "Engineered_allele")';
$i++;
$queries[$i]{'DESC'} = "Transposon_insertion";
From a79a2afadc758d905c85c94f01b4b7edafdced70 Mon Sep 17 00:00:00 2001
From: Paul-Davis <pad@ebi.ac.uk>
Date: Fri, 20 Oct 2017 14:18:21 +0100
Subject: [PATCH 11/11] moved the tablemaker query inside the script as the
previous path failed to resolve for all users/envs.
---
scripts/NAMEDB/variation_server_compare.pl | 51 +++++++++++++++++++++-
1 file changed, 49 insertions(+), 2 deletions(-)
diff --git a/scripts/NAMEDB/variation_server_compare.pl b/scripts/NAMEDB/variation_server_compare.pl
index 9196d053d..64278f2f0 100644
--- a/scripts/NAMEDB/variation_server_compare.pl
+++ b/scripts/NAMEDB/variation_server_compare.pl
@@ -36,9 +36,13 @@
my $acedb = ($database or $wormbase->database('geneace'));
$log->write_to("Checking $acedb for errors\n");
-my $def = "$ENV{CVS_DIR}/../wquery/geneace/variation_nameserver_comm.def";
+#my $def = "$ENV{CVS_DIR}/../wquery/geneace/variation_nameserver_comm.def";
+my $tmdef = &get_table_maker_def();
+my $command = "Table-maker -p $tmdef\nquit\n";
+$log->write_to("\nRetrieving Variation data, using Table-maker and query ${tmdef}...\n");
-my $TABLE = $wormbase->table_maker_query($acedb, $def);
+
+my $TABLE = $wormbase->table_maker_query($acedb, $tmdef);
my %ace_ids;
while(<$TABLE>) {
next unless /WBVar/;
@@ -127,3 +131,46 @@
$log->write_to("Work Done!\n");
$log->mail();
exit(0);
+
+
+sub get_table_maker_def {
+
+ my $def = '/tmp/nsvar.def';
+ open TMP,">$def" or $log->log_and_die("cant write $def: $!\n");
+ my $txt = <<END;
+
+Sortcolumn 1
+
+Colonne 1
+Width 12
+Optional
+Visible
+Class
+Class Variation
+From 1
+
+Colonne 2
+Width 12
+Mandatory
+Visible
+Next_Tag
+From 1
+Tag Status
+
+Colonne 3
+Width 12
+Optional
+Visible
+Class
+Class Variation_name
+From 1
+Tag Public_name
+
+// End of these definitions
+END
+
+ print TMP $txt;
+ close TMP;
+
+ return $def;
+}