|
0
|
1 =head1 LICENSE
|
|
|
2
|
|
|
3 Copyright (c) 1999-2012 The European Bioinformatics Institute and
|
|
|
4 Genome Research Limited. All rights reserved.
|
|
|
5 This software is distributed under a modified Apache license.
|
|
|
6 For license details, please see
|
|
|
7 http://www.ensembl.org/info/about/code_licence.html
|
|
|
8 =head1 CONTACT
|
|
|
9 Please email comments or questions to the public Ensembl
|
|
|
10 developers list at <dev@ensembl.org>.
|
|
|
11 Questions may also be sent to the Ensembl help desk at
|
|
|
12 <helpdesk@ensembl.org>.
|
|
|
13
|
|
|
14 =cut
|
|
|
15 =head1 NAME
|
|
|
16 =head1 SYNOPSIS
|
|
|
17 =head1 DESCRIPTION
|
|
|
18 =head1 METHODS
|
|
|
19 =cut
|
|
|
20
|
|
|
21 package Bio::EnsEMBL::Utils::VegaCuration::Translation;
|
|
|
22 use strict;
|
|
|
23 use warnings;
|
|
|
24 use vars qw(@ISA);
|
|
|
25 use Data::Dumper;
|
|
|
26 use Bio::EnsEMBL::Utils::VegaCuration::Transcript;
|
|
|
27 @ISA = qw(Bio::EnsEMBL::Utils::VegaCuration::Transcript);
|
|
|
28
|
|
|
29 =head2 check_CDS_start_end_remarks
|
|
|
30
|
|
|
31 Args : B::E::Transcript
|
|
|
32 Example : my $results = $support->check_CDS_end_remarks($transcript)
|
|
|
33 Description: identifies incorrect 'CDS end...' transcript remarks in a
|
|
|
34 otter-derived Vega database
|
|
|
35 Returntype : hashref
|
|
|
36
|
|
|
37 =cut
|
|
|
38
|
|
|
39 sub check_CDS_start_end_remarks {
|
|
|
40 my $self = shift;
|
|
|
41 my $trans = shift;
|
|
|
42 # info for checking
|
|
|
43 my @remarks = @{$trans->get_all_Attributes('remark')};
|
|
|
44 my $coding_end = $trans->cdna_coding_end;
|
|
|
45 my $coding_start = $trans->cdna_coding_start;
|
|
|
46 my $trans_end = $trans->length;
|
|
|
47 my $trans_seq = $trans->seq->seq;
|
|
|
48 my $stop_codon = substr($trans_seq, $coding_end-3, 3);
|
|
|
49 my $start_codon = substr($trans_seq, $coding_start-1, 3);
|
|
|
50 #hashref to return results
|
|
|
51 my $results;
|
|
|
52
|
|
|
53 #extra CDS end not found remarks
|
|
|
54 if (grep {$_->value eq 'CDS end not found'} @remarks) {
|
|
|
55 if ( ($coding_end != $trans_end)
|
|
|
56 && ( grep {$_ eq $stop_codon} qw(TGA TAA TAG) ) ) {
|
|
|
57 $results->{'END_EXTRA'} = 1;
|
|
|
58 }
|
|
|
59 }
|
|
|
60 #missing CDS end not found remark
|
|
|
61 if ( $coding_end == $trans_end ) {
|
|
|
62 if (! grep {$_->value eq 'CDS end not found'} @remarks) {
|
|
|
63 if (grep {$_ eq $stop_codon} qw(TGA TAA TAG)) {
|
|
|
64 $results->{'END_MISSING_2'} = 1;
|
|
|
65 }
|
|
|
66 else {
|
|
|
67 $results->{'END_MISSING_1'} = $stop_codon;
|
|
|
68 }
|
|
|
69 }
|
|
|
70 }
|
|
|
71 #extra CDS start not found remark
|
|
|
72 if (grep {$_->value eq 'CDS start not found'} @remarks) {
|
|
|
73 if ( ($coding_start != 1)
|
|
|
74 && ($start_codon eq 'ATG') ) {
|
|
|
75 $results->{'START_EXTRA'} = 1;
|
|
|
76 }
|
|
|
77 }
|
|
|
78 #missing CDS start not found remark
|
|
|
79 if ( $coding_start == 1) {
|
|
|
80 if ( ! grep {$_->value eq 'CDS start not found'} @remarks) {
|
|
|
81 if ($start_codon eq 'ATG') {
|
|
|
82 $results->{'START_MISSING_2'} = 1;
|
|
|
83 } else {
|
|
|
84 $results->{'START_MISSING_1'} = $start_codon;
|
|
|
85 }
|
|
|
86 }
|
|
|
87 }
|
|
|
88 return $results;
|
|
|
89 }
|
|
|
90
|
|
|
91 =head2 check_CDS_start_end_remarks_loutre
|
|
|
92
|
|
|
93 Args : B::E::Transcript
|
|
|
94 Example : my $results = $support->check_CDS_end_remarks($transcript)
|
|
|
95 Description: identifies incorrect 'CDS end...' transcript attribs in a loutre
|
|
|
96 of a loutre-derived Vega database.
|
|
|
97 Returntype : hashref
|
|
|
98
|
|
|
99 =cut
|
|
|
100
|
|
|
101 sub check_CDS_start_end_remarks_loutre {
|
|
|
102 my $self = shift;
|
|
|
103 my $trans = shift;
|
|
|
104
|
|
|
105 # info for checking
|
|
|
106 my @stops = qw(TGA TAA TAG);
|
|
|
107 my %attributes;
|
|
|
108 foreach my $attribute (@{$trans->get_all_Attributes()}) {
|
|
|
109 push @{$attributes{$attribute->code}}, $attribute;
|
|
|
110 }
|
|
|
111 # warn $trans->stable_id;
|
|
|
112 # warn Data::Dumper::Dumper(\%attributes);
|
|
|
113 my $coding_end = $trans->cdna_coding_end;
|
|
|
114 my $coding_start = $trans->cdna_coding_start;
|
|
|
115 my $trans_end = $trans->length;
|
|
|
116 my $trans_seq = $trans->seq->seq;
|
|
|
117 my $stop_codon_offset = 3 + $trans->translation->end_Exon->end_phase;
|
|
|
118 my $initial_exon_phase = $trans->translation->start_Exon->phase;
|
|
|
119 my $stop_codon = substr($trans_seq, $coding_end-3, 3);
|
|
|
120 my $start_codon = substr($trans_seq, $coding_start-1, 3);
|
|
|
121
|
|
|
122 my $start_codon_incorrect = 1;
|
|
|
123 if ($start_codon eq 'ATG' ) {
|
|
|
124 $start_codon_incorrect = 0;
|
|
|
125 }
|
|
|
126 elsif ($start_codon eq 'CTG') {
|
|
|
127 foreach my $attrib (@{$attributes{'remark'}}) {
|
|
|
128 if ($attrib->value =~ /non[- ]ATG start/) {
|
|
|
129 $start_codon_incorrect = 0;
|
|
|
130 }
|
|
|
131 }
|
|
|
132 }
|
|
|
133
|
|
|
134 # warn "$start_codon -- $initial_exon_phase -- $coding_start -- $start_codon_incorrect";
|
|
|
135
|
|
|
136 #hashref to return results
|
|
|
137 my $results;
|
|
|
138
|
|
|
139 #extra CDS end not found remarks
|
|
|
140 if ($attributes{'cds_end_NF'}) {
|
|
|
141 if ( ($attributes{'cds_end_NF'}->[0]->value == 1)
|
|
|
142 && ($coding_end != $trans_end)
|
|
|
143 && ( grep {$_ eq $stop_codon} @stops) ) {
|
|
|
144 # warn $trans->stable_id.": $coding_end--$trans_end--$stop_codon";
|
|
|
145 # warn $trans->translation->end_Exon->end_phase;
|
|
|
146 $results->{'END_EXTRA'} = $stop_codon;
|
|
|
147 }
|
|
|
148 }
|
|
|
149 #missing CDS end not found remark
|
|
|
150 if ( $coding_end == $trans_end ) {
|
|
|
151 if ($attributes{'cds_end_NF'}) {
|
|
|
152 if ($attributes{'cds_end_NF'}->[0]->value == 0 ) {
|
|
|
153 if (! grep {$_ eq $stop_codon} @stops) {
|
|
|
154 # warn $trans->translation->end_Exon->end_phase;
|
|
|
155 $results->{'END_MISSING'}{'WRONG'} = $stop_codon;
|
|
|
156 }
|
|
|
157 }
|
|
|
158 }
|
|
|
159 elsif (! grep {$_ eq $stop_codon} @stops) {
|
|
|
160 $results->{'END_MISSING'}{'ABSENT'} = $stop_codon;
|
|
|
161 }
|
|
|
162 }
|
|
|
163 #extra CDS start not found remark
|
|
|
164 if ( $attributes{'cds_start_NF'}) {
|
|
|
165 if ( ($attributes{'cds_start_NF'}->[0]->value == 1 )
|
|
|
166 && (! $start_codon_incorrect)) {
|
|
|
167 unless ( ($coding_start == 1) && ( $initial_exon_phase > 0)) {
|
|
|
168 $results->{'START_EXTRA'} = $start_codon;
|
|
|
169 }
|
|
|
170 }
|
|
|
171 }
|
|
|
172 #missing CDS start not found remark
|
|
|
173 if ( $coding_start == 1) {
|
|
|
174 if ( $attributes{'cds_start_NF'} ) {
|
|
|
175 if ( $attributes{'cds_start_NF'}->[0]->value == 0 ) {
|
|
|
176 if ($start_codon_incorrect) {
|
|
|
177 $results->{'START_MISSING'}{'ABSENT'} = $start_codon;
|
|
|
178 }
|
|
|
179 elsif ($initial_exon_phase > 0) {
|
|
|
180 $results->{'START_MISSING'}{'INITIAL_PHASE'} = $initial_exon_phase;
|
|
|
181 }
|
|
|
182 }
|
|
|
183 }
|
|
|
184 elsif ($start_codon ne 'ATG') {
|
|
|
185 $results->{'START_MISSING'}{'ABSENT'} = $start_codon;
|
|
|
186 }
|
|
|
187
|
|
|
188 }
|
|
|
189 return $results;
|
|
|
190 }
|
|
|
191
|
|
|
192 =head2 get_havana_seleno_comments
|
|
|
193
|
|
|
194 Args : none
|
|
|
195 Example : my $results = $support->get_havana_seleno_comments
|
|
|
196 Description: parses the HEREDOC containing Havana comments in this module
|
|
|
197 Returntype : hashref
|
|
|
198
|
|
|
199 =cut
|
|
|
200
|
|
|
201 sub get_havana_seleno_comments {
|
|
|
202 my $seen_translations;
|
|
|
203 while (<DATA>) {
|
|
|
204 next if /^\s+$/ or /#+/;
|
|
|
205 my ($obj,$comment) = split /=/;
|
|
|
206 $obj =~ s/^\s+|\s+$//g;
|
|
|
207 $comment =~ s/^\s+|\s+$//g;
|
|
|
208 # We add the origin as now "seen" can come from a number of places, and have
|
|
|
209 # a number of consequences in different cases, not just discounted Secs from this method. -- ds23
|
|
|
210 $seen_translations->{$obj} = [ $comment,"notsec-havana" ];
|
|
|
211 }
|
|
|
212 return $seen_translations;
|
|
|
213 }
|
|
|
214
|
|
|
215 sub check_for_stops {
|
|
|
216 my $support = shift;
|
|
|
217 my ($gene,$seen_transcripts,$log_object) = @_;
|
|
|
218 my $transcripts;
|
|
|
219 my $has_log_object=defined($log_object);
|
|
|
220 if($has_log_object){
|
|
|
221 my @help = $log_object->species_params->get_trans($gene->stable_id);
|
|
|
222 $transcripts=\@help;
|
|
|
223 }else{
|
|
|
224 $log_object=$support;
|
|
|
225 $transcripts=$gene->get_all_Transcripts;
|
|
|
226 }
|
|
|
227
|
|
|
228 my $gname = $gene->get_all_Attributes('name')->[0]->value;
|
|
|
229 my $gsi = $gene->stable_id;
|
|
|
230 my $scodon = 'TGA';
|
|
|
231 my $mod_date = $support->date_format( $gene->modified_date,'%d/%m/%y' );
|
|
|
232 my $hidden_remak_ttributes;
|
|
|
233 TRANS:
|
|
|
234 foreach my $trans (@$transcripts) {
|
|
|
235 my $tsi = $trans->stable_id;
|
|
|
236 my $tID = $trans->dbID;
|
|
|
237 my $tname = $trans->get_all_Attributes('name')->[0]->value;
|
|
|
238 if($has_log_object){
|
|
|
239 $hidden_remak_ttributes=$log_object->species_params->get_attributes->{$tsi}->{'hidden_remark'};
|
|
|
240 }else{
|
|
|
241 $hidden_remak_ttributes=$trans->get_all_Attributes('hidden_remark');
|
|
|
242 }
|
|
|
243 foreach my $rem (@$hidden_remak_ttributes) {
|
|
|
244 if ($rem->value =~ /not_for_Vega/) {
|
|
|
245 #$support->log_verbose("Skipping transcript $tname ($tsi) since 'not_for_Vega'\n",1);
|
|
|
246 $log_object->_save_log('log_verbose', '', $gsi, '', $tsi, '', "Skipping transcript $tname ($tsi) since 'not_for_Vega'");
|
|
|
247 next TRANS;
|
|
|
248 }
|
|
|
249 }
|
|
|
250
|
|
|
251 # go no further if there is a ribosomal framshift attribute
|
|
|
252 foreach my $attrib (@{$trans->get_all_Attributes('_rib_frameshift')}) {
|
|
|
253 if ($attrib->value) {
|
|
|
254 $log_object->_save_log('log', '', $gsi, '', $tsi, '', "Skipping $tsi ($tname) since it has a ribosomal frameshift attribute");
|
|
|
255 next TRANS;
|
|
|
256 }
|
|
|
257 }
|
|
|
258
|
|
|
259 #$support->log_verbose("Studying transcript $tsi ($tname, $tID)\n",1);
|
|
|
260 $log_object->_save_log('log_verbose', '', $gsi, '', $tsi, '', "Studying transcript $tsi ($tname, $tID)");
|
|
|
261 my $peptide;
|
|
|
262
|
|
|
263 # go no further if the transcript doesn't translate or if there are no stops
|
|
|
264 next TRANS unless ($peptide = $trans->translate);
|
|
|
265 my $pseq = $peptide->seq;
|
|
|
266 my $orig_seq = $pseq;
|
|
|
267 # (translate method trims stops from sequence end)
|
|
|
268
|
|
|
269 next TRANS unless ($pseq =~ /\*/);
|
|
|
270 # warn sprintf("Stop codon is '%s'\n",substr($trans->translateable_seq,-3));
|
|
|
271 #$support->log_verbose("Stops found in $tsi ($tname)\n",1);
|
|
|
272 $log_object->_save_log('log_verbose', '', $gsi, '', $tsi, '', "Stops found in $tsi ($tname)");
|
|
|
273
|
|
|
274 # find out where and how many stops there are
|
|
|
275 my @found_stops;
|
|
|
276 my $mrna = $trans->translateable_seq;
|
|
|
277 my $offset = 0;
|
|
|
278 my $tstop;
|
|
|
279 while ($pseq =~ /^([^\*]*)\*(.*)/) {
|
|
|
280 my $pseq1_f = $1;
|
|
|
281 $pseq = $2;
|
|
|
282 my $seq_flag = 0;
|
|
|
283 $offset += length($pseq1_f) * 3;
|
|
|
284 my $stop = substr($mrna, $offset, 3);
|
|
|
285 my $aaoffset = int($offset / 3)+1;
|
|
|
286 push(@found_stops, [ $stop, $aaoffset ]);
|
|
|
287 $tstop .= "$aaoffset ";
|
|
|
288 $offset += 3;
|
|
|
289 }
|
|
|
290
|
|
|
291 # are all stops TGA...?
|
|
|
292 my $num_stops = scalar(@found_stops);
|
|
|
293 my $num_tga = 0;
|
|
|
294 my $positions;
|
|
|
295 foreach my $stop (@found_stops) {
|
|
|
296 $positions .= $stop->[0]."(".$stop->[1].") ";
|
|
|
297 if ($stop->[0] eq $scodon) {
|
|
|
298 $num_tga++;
|
|
|
299 }
|
|
|
300 }
|
|
|
301 my $source = $gene->source;
|
|
|
302 #...no - an internal stop codon error in the database...
|
|
|
303 if ($num_tga < $num_stops) {
|
|
|
304 if ($source eq 'havana') {
|
|
|
305 #$support->log_warning("INTERNAL STOPS HAVANA: Transcript $tsi ($tname) from gene $gname has non \'$scodon\' stop codons [$mod_date]:\nSequence = $orig_seq\nStops at $positions)\n\n");
|
|
|
306 $log_object->_save_log('log_warning', '', $gsi, 'TRANSCRIPT', $tsi, 'VQCT_internal_stop', "INTERNAL STOPS HAVANA: Transcript $tsi ($tname) from gene $gname has non \'$scodon\' stop codons [$mod_date]: Sequence = $orig_seq Stops at $positions)");
|
|
|
307 }
|
|
|
308 else {
|
|
|
309 #$support->log_warning("INTERNAL STOPS EXTERNAL: Transcript $tsi ($tname) from gene $gname has non \'$scodon\' stop codons[$mod_date]:\nSequence = $orig_seq\nStops at $positions)\n\n");
|
|
|
310 $log_object->_save_log('log_warning', '', $gsi, 'TRANSCRIPT', $tsi, 'VQCT_internal_stop', "INTERNAL STOPS EXTERNAL: Transcript $tsi ($tname) from gene $gname has non \'$scodon\' stop codons[$mod_date]: Sequence = $orig_seq Stops at $positions)");
|
|
|
311 }
|
|
|
312 }
|
|
|
313 #...yes - check remarks
|
|
|
314 else {
|
|
|
315 my $flag_remark = 0; # 1 if word seleno has been used
|
|
|
316 my $flag_remark2 = 0; # 1 if existing remark has correct numbering
|
|
|
317 my $alabel = 'Annotation_remark- selenocysteine ';
|
|
|
318 my $alabel2 = 'selenocysteine ';
|
|
|
319 my $annot_stops;
|
|
|
320 my $remarks;
|
|
|
321 my $att;
|
|
|
322 #get both hidden_remarks and remarks
|
|
|
323 foreach my $remark_type ('remark','hidden_remark') {
|
|
|
324 if($has_log_object){
|
|
|
325 $att=$log_object->species_params->get_attributes->{$trans->stable_id}->{$remark_type};
|
|
|
326 }else{
|
|
|
327 $att=$trans->get_all_Attributes($remark_type)
|
|
|
328 }
|
|
|
329 foreach my $attrib ( @$att) {
|
|
|
330 push @{$remarks->{$remark_type}}, $attrib->value;
|
|
|
331 }
|
|
|
332 }
|
|
|
333 #parse remarks to check syntax for location of edits
|
|
|
334 while (my ($attrib,$remarks)= each %$remarks) {
|
|
|
335 foreach my $text (@{$remarks}) {
|
|
|
336 if ( ($attrib eq 'remark') && ($text=~/^$alabel(.*)/) ){
|
|
|
337 #$support->log_warning("seleno remark for $tsi stored as Annotation_remark not hidden remark) [$mod_date]\n");
|
|
|
338 $log_object->_save_log('log_warning', '', $gsi, '', $tsi, 'VQCT_wrong_selC_coord', "seleno remark for $tsi stored as Annotation_remark not hidden remark) [$mod_date]");
|
|
|
339 $annot_stops=$1;
|
|
|
340 }
|
|
|
341 elsif ($text =~ /^$alabel2(.*)/) {
|
|
|
342 my $maybe = $1;
|
|
|
343 if($maybe =~ /^\s*\d+(\s+\d+)*\s*$/) {
|
|
|
344 $annot_stops=$maybe;
|
|
|
345 } else {
|
|
|
346 $log_object->_save_log('log', '', $gene->stable_id, '', $tsi, '', "Maybe annotated stop in incorrect format, maybe just a remark that happens to begin '$alabel2'".
|
|
|
347 " -- might need to investigate: '$alabel2$maybe' [$mod_date]");
|
|
|
348 }
|
|
|
349 }
|
|
|
350 }
|
|
|
351 }
|
|
|
352
|
|
|
353 #check the location of the annotated edits matches actual stops in the sequence
|
|
|
354 my @annotated_stops;
|
|
|
355 if ($annot_stops){
|
|
|
356 my $i = 0;
|
|
|
357 foreach my $offset (split(/\s+/, $annot_stops)) {
|
|
|
358 #OK if it matches a known stop
|
|
|
359 if (
|
|
|
360 defined($found_stops[$i]) && defined($found_stops[$i]->[1]) && ($found_stops[$i]->[1] == $offset)) {
|
|
|
361 push @annotated_stops, $offset;
|
|
|
362 }
|
|
|
363 # catch old annotations where number was in DNA not peptide coordinates
|
|
|
364 elsif (defined($found_stops[$i]) && defined($found_stops[$i]->[1]) && (($found_stops[$i]->[1] * 3) == $offset)) {
|
|
|
365 $log_object->_save_log('log_warning', '', $gene->stable_id, 'DNA', $tsi, 'VQCT_wrong_selC_coord', "DNA: Annotated stop for transcript tsi ($tname) is in DNA not peptide coordinates) [$mod_date]");
|
|
|
366 }
|
|
|
367 # catch old annotations where number off by one
|
|
|
368 elsif (defined($found_stops[$i]) && defined($found_stops[$i]->[1]) && (($found_stops[$i]->[1]) == $offset+1)) {
|
|
|
369 $log_object->_save_log('log_warning', '', $gene->stable_id, 'PEPTIDE', $tsi, 'VQCT_wrong_selC_coord', "PEPTIDE: Annotated stop for transcript $tsi ($tname) is out by one) [$mod_date]");
|
|
|
370 }
|
|
|
371 elsif (defined($offset) && ($offset=~/^\d+$/)){
|
|
|
372 if ($offset == length($orig_seq)+1) {
|
|
|
373 if($seen_transcripts->{$tsi} && $seen_transcripts->{$tsi}->[1] eq 'known-tga-stop') {
|
|
|
374 $log_object->_save_log('log', '', $gene->stable_id, 'TRANSCRIPT', $tsi, '', "Annotated stop for transcript $tsi ($tname) known to be a stop codon. Ok. [$mod_date]");
|
|
|
375 } elsif($seen_transcripts->{$tsi} && $seen_transcripts->{$tsi}->[1] eq 'known-terminal-sec') {
|
|
|
376 $log_object->_save_log('log', '', $gene->stable_id, 'TRANSCRIPT', $tsi, '', "Annotated stop for transcript $tsi ($tname) known to be a terminal Sec. Ok. [$mod_date]");
|
|
|
377 } else {
|
|
|
378 $log_object->_save_log('log_warning', '', $gene->stable_id, 'TRANSCRIPT', $tsi, '', "Annotated stop for transcript $tsi ($tname) \"$offset\" matches actual stop codon yet has no entry in script config to disambiguate it. Please investigate and add appropriate entry to config arrays in add_selcys.pl. [$mod_date]");
|
|
|
379 }
|
|
|
380 }
|
|
|
381 else {
|
|
|
382 $log_object->_save_log('log_warning', '', $gene->stable_id, 'TRANSCRIPT', $tsi, 'VQCT_wrong_selC_coord', "Annotated stop for transcript $tsi ($tname) \"$offset\" does not match a TGA codon) [$mod_date]");
|
|
|
383 push @annotated_stops, $offset;
|
|
|
384 }
|
|
|
385 }
|
|
|
386 $i++;
|
|
|
387 }
|
|
|
388 }
|
|
|
389
|
|
|
390 #check location of found stops matches annotated ones - any new ones are reported
|
|
|
391 foreach my $stop ( @found_stops ) {
|
|
|
392 my $pos = $stop->[1];
|
|
|
393 my $seq = $stop->[0];
|
|
|
394 unless ( grep { $pos == $_} @annotated_stops) {
|
|
|
395 if ($seen_transcripts->{$tsi} && $seen_transcripts->{$tsi}->[1] eq 'notsec-havana') {
|
|
|
396 #$support->log_verbose("Transcript $tsi ($tname) has potential selenocysteines but has been discounted by annotators:\n\t".$seen_transcripts->{$tsi}.") [$mod_date]\n");
|
|
|
397 $log_object->_save_log('log_verbose', '', $gene->stable_id, '', $tsi, 'VQCT_pot_selC', "Transcript $tsi ($tname) has potential selenocysteines but has been discounted by annotators: ".$seen_transcripts->{$tsi}->[0].") [$mod_date]");
|
|
|
398 }
|
|
|
399 else {
|
|
|
400 #$support->log("POTENTIAL SELENO ($seq) in $tsi ($tname, gene $gname) found at $pos [$mod_date]\n");
|
|
|
401 $log_object->_save_log('log', '', $gene->stable_id, '', $tsi, 'VQCT_pot_selC', "POTENTIAL SELENO ($seq) in $tsi ($tname, gene $gname) found at $pos [$mod_date]");
|
|
|
402 }
|
|
|
403 }
|
|
|
404 }
|
|
|
405 }
|
|
|
406 }
|
|
|
407 }
|
|
|
408 sub _save_log{
|
|
|
409 my $self=shift;
|
|
|
410 my $log_type = shift;
|
|
|
411 my $chrom_name=shift || '';
|
|
|
412 my $gsi=shift || '';
|
|
|
413 my $type=shift || '';
|
|
|
414 my $tsi=shift || '';
|
|
|
415 my $tag=shift || '';
|
|
|
416 my $txt=shift || '';
|
|
|
417 $self->$log_type($txt."\n");
|
|
|
418 }
|
|
|
419
|
|
|
420 #details of annotators comments
|
|
|
421 __DATA__
|
|
|
422 OTTHUMT00000144659 = FIXED- changed to transcript
|
|
|
423 OTTHUMT00000276377 = FIXED- changed to transcript
|
|
|
424 OTTHUMT00000257741 = FIXED- changed to nmd
|
|
|
425 OTTHUMT00000155694 = NOT_FIXED- should be nmd but external annotation but cannot be fixed
|
|
|
426 OTTHUMT00000155695 = NOT_FIXED- should be nmd but external annotation but cannot be fixed
|
|
|
427 OTTHUMT00000282573 = FIXED- changed to unprocessed pseudogene
|
|
|
428 OTTHUMT00000285227 = FIXED- changed start site
|
|
|
429 OTTHUMT00000151008 = FIXED- incorrect trimming of CDS, removed extra stop codon
|
|
|
430 OTTHUMT00000157999 = FIXED- changed incorrect stop
|
|
|
431 OTTHUMT00000150523 = FIXED- incorrect trimming of CDS
|
|
|
432 OTTHUMT00000150525 = FIXED- incorrect trimming of CDS
|
|
|
433 OTTHUMT00000150522 = FIXED- incorrect trimming of CDS
|
|
|
434 OTTHUMT00000150521 = FIXED- incorrect trimming of CDS
|
|
|
435 OTTHUMT00000246819 = FIXED- corrected frame
|
|
|
436 OTTHUMT00000314078 = FIXED- corrected frame
|
|
|
437 OTTHUMT00000080133 = FIXED- corrected frame
|
|
|
438 OTTHUMT00000286423 = FIXED- changed to transcript
|
|
|
439 OTTMUST00000055509 = FIXED- error
|
|
|
440 OTTMUST00000038729 = FIXED- corrected frame
|
|
|
441 OTTMUST00000021760 = FIXED- corrected frame
|
|
|
442 OTTMUST00000023057 = FIXED- corrected frame
|
|
|
443 OTTMUST00000015207 = FIXED- corrected frame
|
|
|
444 OTTMUST00000056646 = FIXED- error
|
|
|
445 OTTMUST00000059686 = FIXED- corrected frame
|
|
|
446 OTTMUST00000013426 = FIXED- corrected frame
|
|
|
447 OTTMUST00000044412 = FIXED- error
|
