Comment out lines in FTHelper that convert specific tags to notes, ad…

…d a test that checks for duplicated note tags, all tests pass
bioperl · Aug 25, 2011 · 5ffa0a8 · 5ffa0a8
1 parent c588c1b
commit 5ffa0a8
Show file tree

Hide file tree

Showing 3 changed files with 80 additions and 5 deletions.
diff --git a/Bio/SeqIO/FTHelper.pm b/Bio/SeqIO/FTHelper.pm
@@ -207,12 +207,19 @@ sub from_SeqFeature {
   $fth->loc($locstr);
   $fth->key($key);
   $fth->field->{'note'} = [];
+
+  # the lines below take specific tags (e.g. /score=23 ) and re-enter them as
+  # new tags like /note="score=25" - if the file is round-tripped this creates
+  # duplicate values
+
   #$sf->source_tag && do { push(@{$fth->field->{'note'}},"source=" . $sf->source_tag ); };
 
-  ($sf->can('score') && $sf->score) && do { push(@{$fth->field->{'note'}},
-                                                 "score=" . $sf->score ); };
-  ($sf->can('frame') && $sf->frame) && do { push(@{$fth->field->{'note'}},
-                                                 "frame=" . $sf->frame ); };
+  #($sf->can('score') && $sf->score) && do { push(@{$fth->field->{'note'}},
+  #                                               "score=" . $sf->score ); };
+
+  #($sf->can('frame') && $sf->frame) && do { push(@{$fth->field->{'note'}},
+  #                                               "frame=" . $sf->frame ); };
+
   #$sf->strand && do { push(@{$fth->field->{'note'}},"strand=" . $sf->strand ); };
 
   foreach my $tag ( $sf->get_all_tags ) {

diff --git a/t/SeqIO/genbank.t b/t/SeqIO/genbank.t
@@ -7,7 +7,7 @@ BEGIN {
     use lib '.';
 	use Bio::Root::Test;
 
-	test_begin(-tests => 272 );
+	test_begin(-tests => 274 );
 
     use_ok('Bio::SeqIO::genbank');
 }
@@ -581,3 +581,23 @@ $seq = $ast->next_seq;
 ok my @ctg = $seq->annotation->get_Annotations('contig');
 like $ctg[0]->value, qr/join\(.*?gap.*?complement/;
 
+# write_seq() and FTHelper duplicate specific tags, need to check a round-trip
+$ast = Bio::SeqIO->new(-format => 'genbank' ,
+                       -verbose => $verbose,
+                       -file => test_input_file('singlescore.gbk'));
+$as = $ast->next_seq();
+($cds) = grep { $_->primary_tag eq 'CDS' } $as->get_SeqFeatures();
+my @notes = $cds->get_tag_values('note');
+is(scalar @notes, 2);
+$testfile = test_output_file();
+$out = Bio::SeqIO->new(-file => ">$testfile",
+                       -format => 'genbank');
+$out->write_seq($as);
+$out->close();
+$ast = Bio::SeqIO->new(-format => 'genbank' ,
+                       -verbose => $verbose,
+                       -file => $testfile );
+$as = $ast->next_seq;
+($cds) = grep { $_->primary_tag eq 'CDS' } $as->get_SeqFeatures();
+my @notes = $cds->get_tag_values('note');
+is(scalar @notes, 2);
diff --git a/t/data/singlescore.gbk b/t/data/singlescore.gbk
@@ -0,0 +1,48 @@
+LOCUS       test0001                1500 bp    dna     linear   UNK 
+DEFINITION  [organism=Test test] [strain=test0001] [gcode=11] [date=8-24-2011]
+ACCESSION   test0001
+KEYWORDS    .
+FEATURES             Location/Qualifiers
+     fasta_record    1..1200
+                     /name="contig00002"
+                     /note="untiled"
+     CDS             16..1215
+                     /locus_tag="test0001_10"
+                     /inference="similar to AA sequence:BLASTX:2.2.18"
+                     /score="463"
+                     /product="tRNA uridine 5-carboxymethylaminomethyl
+                     modification enzyme MnmG n=70 Tax=Proteobacteria
+                     RepID=MNMG_ALTMD"
+                     /note="score=463"
+                     /note="similar to tRNA uridine 5-carboxymethylaminomethyl
+                     modification enzyme GidA PRK05192"
+     gene            16..1215
+                     /locus_tag="test0001_10"
+                     /inference="ab initio prediction:glimmer3:3.0.2"
+ORIGIN      
+        1 ctaacacaaa gtaatatgag tttttattct agatcagttg tattatcaac aggtaccttt
+       61 ctaggtggaa aaatacacat aggtttagaa agttattctg ctggaagaaa aggagaaaaa
+      121 gcatctatag atttagctct tcgtttaaga gatttgcctt ttcgtgtgga tagattaaaa
+      181 actggaacac cacctcgaat tgatattaat acaattaatt ttgaaaattt atttgtccag
+      241 catggtgatg ttcctactcc tgttttttct tttatggggg atatttctaa tcatcctctt
+      301 caaataccgt gttttcttac acacactaat gaaaaaacgc atgaaataat acgtaaaaat
+      361 ttacataaga gtcctctata tacaggtatt attaaaggtg tgggacctcg atattgtcct
+      421 tctattgaag ataaaattgt acgtttccct gataggaaat cacatcaaat ttttttagag
+      481 ccagaaggat taactagtat tgaaatatat ccaaatggta tctcaactag tttaccctta
+      541 gatgttcaaa aagaaatagt aagttctgta aaaggtttag aaaagtctaa aattattact
+      601 cctggttatg ctgtagaata tgattttttt gatcctaagg atttaaatct tactttagag
+      661 agtaaatgga ttaaaggtct ttttttagct ggtcaaatta atggtactac tggttatgaa
+      721 gaagctgcgt ctcaaggact tttagcaggt ttaaatgcag ctttaagtgc aaaagattgc
+      781 aaacaatggt ttcctagacg tgatcaagct tatttaggtg ttcttattga tgatttaact
+      841 actcaaggtg cgaatgaacc ttatcgaatg tttacttcaa gatctgaata tcggttaact
+      901 ttaagagaag ataatgctga tttacgttta actgaaatag cttataaatt gggattagta
+      961 gataatccaa gatggattcg ttataatgaa aaagtactaa atatcagtaa tgaaaaaaat
+     1021 cgtttaaaaa aaataaaaat atatcctaaa tcctctgata gtactatttt aaatcagtta
+     1081 tttaatattg ttttaactaa agaaattaat attttaaatt tattaaaacg tccagaaatt
+     1141 acatatgaaa atttaaagta tttaaaaaat tttaaagtag gtatttctga tttagaagca
+     1201 nnnttaatta attaannngg tgagtttact tctagtgatt tattaaaacg tattttttct
+     1261 accttttgca taggaaaata agaatataat ttttgcccgg aggcggaatt gaaccaccga
+     1321 cacggggatt ttcagtcccc tgctctaccg actgagctat ccgggcaatt tttacattaa
+     1381 atcatcaaag ataaaacttt gtcaatcttt ttttgtagaa gttaatttga aattttgatt
+     1441 taactaatat cttttctatt ttgaaaatat aaaataaaaa taaaaaaata attttttccc
+//