From 534434abeee27f88137df4b004b12d36973dd4ba Mon Sep 17 00:00:00 2001
From: Paul-Davis <pad@ebi.ac.uk>
Date: Tue, 19 May 2020 11:17:02 +0100
Subject: [PATCH] Added code to dump and incorporate a Transposon_CDS peptide
 file into the release.

---
 scripts/autoace_builder.pl |  1 +
 scripts/fasta_dumper.pl    | 11 +++++++++--
 scripts/make_FTP_sites.pl  | 13 ++++++++++---
 scripts/release_letter.pl  |  1 +
 4 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/scripts/autoace_builder.pl b/scripts/autoace_builder.pl
index 6b0c3adee..83b4cce1f 100755
--- a/scripts/autoace_builder.pl
+++ b/scripts/autoace_builder.pl
@@ -181,6 +181,7 @@
     my @options = "-classmethod CDS:Transposon_CDS:Transposon-mRNA -classmethod Pseudogene:Transposon_Pseudogene:Transposon-pseudogenic_transcript -classmethod Transcript:Transposon_ncRNA:Transposon-non-coding_transcript";
     $wormbase->run_script( "fasta_dumper.pl @options -output $seqdir/transposon_transcripts.dna", $log);
     $wormbase->run_script( "fasta_dumper.pl -classmethod Transposon:Transposon -output $seqdir/transposons.dna", $log);
+    $wormbase->run_script( "fasta_dumper.pl -classmethod CDS:Transposon_cds -pep -output $seqdir/transposon_cds.pep", $log);
   }
 }
 
diff --git a/scripts/fasta_dumper.pl b/scripts/fasta_dumper.pl
index dc6801203..52344d8f9 100644
--- a/scripts/fasta_dumper.pl
+++ b/scripts/fasta_dumper.pl
@@ -19,7 +19,7 @@
 use Bio::SeqIO;
 
 my ($debug, $store, $verbose, $database, $test, $wormbase, $species, 
-    @classmethodlabel, $out, @seqs);
+    @classmethodlabel, $out, @seqs, $pep);
 
 GetOptions ( "debug:s"               => \$debug, 
 	     "verbose"               => \$verbose,           #verbose quces a little more info to screen
@@ -29,6 +29,7 @@
 	     "test"                  => \$test,       #invoke test env
 	     "store:s"               => \$store,      #supply a storable
 	     "species:s"             => \$species,    #needed to work out what species is being processed
+             "pep"                   => \$pep         #peptide dump 
 	   ) ;
 
 
@@ -68,7 +69,13 @@
 
   my $object_it = $connection->fetch_many(-query => $query);
   while(my $object = $object_it->next){
-    my $dna = $object->asDNA();
+      my $dna;
+      if ($pep) {
+          $dna = $object->asPeptide();
+      }
+      else {
+          $dna = $object->asDNA();
+      }
     my @dna = split(/\n/, $dna);
     shift @dna;
     $dna = join("", @dna);
diff --git a/scripts/make_FTP_sites.pl b/scripts/make_FTP_sites.pl
index e615cf184..4e09464b6 100755
--- a/scripts/make_FTP_sites.pl
+++ b/scripts/make_FTP_sites.pl
@@ -345,10 +345,16 @@ sub copy_dna_files{
       map { $copied_files{$_} = 1 } ($dna_file, $masked_file, $soft_file);
       
       # copy over outstanding dna files
-      foreach my $dna_file (glob("$seqdir/*.dna.gz"), glob("$seqdir/*.dna")) {
+      foreach my $dna_file (glob("$seqdir/*.dna.gz"), glob("$seqdir/*.dna"), glob("$seqdir/*.pep")) {
         if (not exists $copied_files{$dna_file}) {
-          my ($prefix) = $dna_file =~ /$seqdir\/(\S+)\.dna/;
-          my $target = "$dna_dir/${gspecies}.${bioproj}.${WS_version_name}.$prefix.fa.gz";
+          my ($prefix) = $dna_file =~ /$seqdir\/(\S+)\./;
+          my $target;
+          if ($dna_file =~ /pep/) {
+              $target = "$dna_dir/${gspecies}.${bioproj}.${WS_version_name}.$prefix.pep.gz";
+          }
+          else {
+              $target = "$dna_dir/${gspecies}.${bioproj}.${WS_version_name}.$prefix.fa.gz";
+          }
           if ($dna_file =~ /\.gz$/) {
             $wormbase->run_command("cp -f $dna_file $target", $log);
           } else {
@@ -1379,6 +1385,7 @@ sub checkfile {
 GSPECIES.BIOPROJ.WSREL.wormpep_package.tar.gz
 GSPECIES.BIOPROJ.WSREL.transposon_transcripts.fa.gz
 GSPECIES.BIOPROJ.WSREL.transposons.fa.gz
+GSPECIES.BIOPROJ.WSREL.transposon_cds.pep.gz
 
 [CORE]species/GSPECIES/BIOPROJ/annotation
 GSPECIES.BIOPROJ.WSREL.functional_descriptions.txt.gz
diff --git a/scripts/release_letter.pl b/scripts/release_letter.pl
index 4cdb99e09..7bcc7c19f 100755
--- a/scripts/release_letter.pl
+++ b/scripts/release_letter.pl
@@ -172,6 +172,7 @@
 printf $rlfh "     - G_SPECIES.BIOPROJECT.WS$ver.pseudogenic_transcripts.fa.gz  - Spliced cDNA sequence for pseudogenic transcripts\n";
 printf $rlfh "     - G_SPECIES.BIOPROJECT.WS$ver.transposon_transcripts.fa.gz   - Spliced cDNA sequence for mRNAs and pseudogenes located in Transposons\n";
 printf $rlfh "     - G_SPECIES.BIOPROJECT.WS$ver.transposons.fa.gz              - DNA sequence of curated and predicted Transposons\n";
+printf $rlfh "     - G_SPECIES.BIOPROJECT.WS$ver.transposon_cds.pep.gz          - Protein sequence of curated CDSs associated with Transposons\n";
 printf $rlfh "     - G_SPECIES.BIOPROJECT.WS$ver.intergenic_sequences.fa.gz     - DNA sequence between pairs of adjacent genes\n";
 printf $rlfh "     - G_SPECIES.BIOPROJECT.WS$ver.annotations.gff[2|3].gz        - Sequence features in either GFF2 or GFF3 format\n";
 printf $rlfh "     - G_SPECIES.BIOPROJECT.WS$ver.protein_annotation.gff3.gz     - Sequence features in proteins in GFF3 format\n";