1 # -*-Perl-*- Test Harness script for Bioperl
2 # $Id: SearchIO_infernal.t 14672 2008-04-22 21:42:50Z cjfields $
10 test_begin(-tests => 496);
12 use_ok('Bio::SearchIO');
15 my ($in, $result, $iter, $hit, $hsp, $algorithm, $meta);
17 ### Infernal v. 1.1 ###
19 # one query vs one database sequence report
20 $in = Bio::SearchIO->new(
21 -format => 'infernal',
22 -file => test_input_file('cmsearch_output.txt')
24 $result = $in->next_result;
25 isa_ok($result, 'Bio::Search::Result::ResultI');
26 is( ref($result), 'Bio::Search::Result::INFERNALResult', 'Check for the correct Result reference type');
27 is( $result->algorithm, 'CMSEARCH', 'Check algorithm' );
28 is( $result->algorithm_version, '1.1.1', 'Check cmsearch algorithm version' );
29 is( $result->cm_name, 'RF00174.cm', 'Check cm_name');
30 is( $result->database_name, 'NC_000913.fna','Check database_name' );
31 is( $result->database_entries, 1, 'Check database_entries' );
32 is( $result->database_letters, 9283304, 'Check database_letters' );
33 is( $result->query_name, 'Cobalamin', 'Check query_name' );
34 is( $result->query_length, 191, 'Check query_length' );
35 is( $result->query_accession, 'RF00174', 'Check query_accession' );
36 is( $result->query_description, '', 'Check query_description' );
37 is( $result->num_hits(), 2, 'Check num_hits' );
41 $hit = $result->next_hit;
42 is( ref($hit), 'Bio::Search::Hit::ModelHit', 'Check for the correct hit reference type' );
43 is( $hit->algorithm, 'CMSEARCH', "Hit algorithm");
44 is( $hit->name, 'gi|556503834|ref|NC_000913.3|', 'Check hit name' );
45 is( $hit->description, 'Escherichia coli str. K-12 substr. MG1655, complete genome', 'Check hit description' );
46 is( $hit->length, 0, 'Check hit length' );
47 is( $hit->score, 98.2, 'Check hit score' );
48 is( $hit->bits, 98.2, 'Check hit bits' );
49 is( $hit->num_hsps, 1, 'Check number of HSPs' );
50 float_is( $hit->significance, 8.7e-16, 'Check hit significance' );
51 is($hit->rank, 1, 'Check hit rank' );
53 $hsp = $hit->next_hsp;
54 is( ref($hsp), 'Bio::Search::HSP::ModelHSP', 'Check for correct hsp reference type' );
55 isa_ok( $hsp, 'Bio::Search::HSP::HSPI' );
56 isa_ok( $hsp->get_aln, 'Bio::Align::AlignI' );
57 isa_ok( $hsp->hit, 'Bio::SeqFeature::Similarity', "Check for hsp hit isa seqfeature similarity" );
59 is( $hsp->hit->seq_id(), 'gi|556503834|ref|NC_000913.3|', 'Check for HSP hit seq_id' );
60 is( $hsp->query->seq_id(), 'Cobalamin', 'Check for HSP query seq_id' );
61 is( $hsp->start('query'), 1, 'Check hsp query start' );
62 is( $hsp->end('query'), 191, 'Check hsp query end' );
63 is( $hsp->start('hit'), 4163384, 'Check hsp hit start' );
64 is( $hsp->end('hit'), 4163574, 'Check hsp hit end' );
65 is( $hsp->score, 98.2, 'Check hsp score' );
66 is( $hsp->bits, 98.2, 'Check hsp bits' );
67 float_is( $hsp->significance, 8.7e-16, 'Check hsp evalue' );
69 is( $hsp->length('query'), 191, 'Check for hsp query length' );
70 is( $hsp->length('hit'), 191, 'Check for hsp hit length' );
71 is( $hsp->length, 207, 'Check for hsp total length' );
72 is( $hsp->gaps('query'), 16, 'Check for hsp query gaps' );
73 is( $hsp->gaps('hit'), 16, 'Check for hsp hit gaps' );
74 is( $hsp->gaps, 32, 'Check for hsp total gaps' );
75 is( $hsp->strand('hit'), 1, 'Check hsp hit strand' );
79 $hit = $result->next_hit;
80 is( $hit->name, 'gi|556503834|ref|NC_000913.3|', 'Check hit name' );
81 is( $hit->description, 'Escherichia coli str. K-12 substr. MG1655, complete genome','Check hit description' );
82 is( $hit->score, 8.4, 'Check hit score' );
83 is( $hit->raw_score, 8.4, "Check hit raw_score");
84 is( $hit->bits, 8.4, 'Check hit bits' );
85 float_is( $hit->significance, 0.63, 'Check hit significance' );
86 is( $hit->length, 0, 'Check hit length' );
87 is($hit->rank, 2, "Hit rank");
89 $hsp = $hit->next_hsp;
90 is( $hsp->hit->seq_id(), 'gi|556503834|ref|NC_000913.3|', 'Check for hit seq_id' );
91 is( $hsp->query->seq_id(), 'Cobalamin', 'Check for query seq_id' );
92 is( $hsp->start('query'), 1, 'Check hsp query start' );
93 is( $hsp->end('query'), 191, 'Check hsp query end' );
94 is( $hsp->start('hit'), 4593356, 'Check hsp hit start' );
95 is( $hsp->end('hit'), 4593565, 'Check hsp hit end' );
96 is( $hsp->score, 8.4, 'Check hsp score' );
97 is( $hsp->bits, 8.4, 'Check hsp bits' );
98 float_is( $hsp->significance, 0.63, 'Check hsp evalue' );
100 is( $hsp->gaps('query'), 67, 'Check for hsp query gaps' );
101 is( $hsp->gaps('hit'), 48, 'Check for hsp hit gaps' );
102 is( $hsp->gaps, 115, 'Check for hsp total gaps' );
103 is( $hsp->strand('hit'), 1, 'Check hsp hit strand' );
105 is( $hsp->noncanonical_string,
106 ' v v v v v v v vvvvvv vvv vvv vvv vvvvvvvvv v v v ',
107 'Check for NC string');
109 ':::::::::::::::[[[[[[,<<<____________>>>,,,,,(((,,,<<<<<_______>>>>>,,<<<____>>>,<<<---<<<<.------<<<<<<-----<<<-<<<<<<_____............................._>>>>>>--->>>>>>>>>----------....................................>>>>----.>>>,,,,)))]]]]]]:::::::::::::::',
110 'Check for CS string');
111 is( $hsp->query_string,
112 'uuaaauugaaacgaugauGGUuccccuuuaaagugaaggguuAAaaGGGAAcccGGUGaaAaUCCgggGCuGcCCCCgCaACuGUAAgcGg.agagcaccccccAauAaGCCACUggcccgcaa.............................gggccGGGAAGGCggggggaaggaaugac....................................cCgcgAGc.CaGGAGACCuGCCaucaguuuuugaaucucc',
113 'Check for query string');
114 is( $hsp->homology_string,
115 ' A AUU+A+++ :UGG :C +U ++ G G: +AA : GGAA: G C :+ GCCCCCGC +C GU+A :: GCA ++ ++ A GCCA G+C G :: +AG+ C GGA AC : CCA: + + + + AU ',
116 'Check for homology string');
117 is( $hsp->hit_string,
118 'GGAGAUUAAUCUUUACGUGGG-UCGUUGAUCGG---CUGACGAACCAGGAAGAUGU-------ACGCCAGUGCCCCCGCUGCGGUGACGCAa-CCGCAGAUGAUUAGU-GCCA---GACGG---aaugagugggugguaucaacaauaaaacc-----------------------------aguaaugaucggcgcaaaagaggcgcagaugaagcuGGCAAAGUuCUGGAUACUGCCCACCGACGCAGUCAUGCGA',
119 'Check for hit string');
120 is( $hsp->posterior_string,
121 '*********************.88877554444...5777779*********9996.......7999********************88873.333333333333333.4544...33333...44566655444444444444444444444.............................566666666666666666666666677777777776788899966*******************************',
122 'Check for posterior probability string');
124 isa_ok($hsp->feature1, 'Bio::SeqFeature::Similarity');
125 isa_ok($hsp->feature2, 'Bio::SeqFeature::Similarity');
126 ($meta) = $hsp->feature1->get_tag_values('meta');
127 is($meta, ':::::::::::::::[[[[[[,<<<____________>>>,,,,,(((,,,<<<<<_______>>>>>,,<<<____>>>,<<<---<<<<.------<<<<<<-----<<<-<<<<<<_____............................._>>>>>>--->>>>>>>>>----------....................................>>>>----.>>>,,,,)))]]]]]]:::::::::::::::', "Check hsp feature1 get_tag_values");
128 ($meta) = $hsp->feature2->get_tag_values('meta');
129 is($meta, ':::::::::::::::[[[[[[,<<<____________>>>,,,,,(((,,,<<<<<_______>>>>>,,<<<____>>>,<<<---<<<<.------<<<<<<-----<<<-<<<<<<_____............................._>>>>>>--->>>>>>>>>----------....................................>>>>----.>>>,,,,)))]]]]]]:::::::::::::::', "Check hsp feature2 get_tag_values");
131 $result = $in->next_result;
132 is( $result, undef, 'Check for undefined result' );
135 # multi query vs multi sequence database report
136 $in = Bio::SearchIO->new(
137 -format => 'infernal',
138 -file => test_input_file('cmsearch.multi.out')
141 $result = $in->next_result;
142 is( $result->num_hits, 12, 'Check result num_hits - multi report');
143 is( $result->query_name, 'tRNA5', 'Check result query_name - multi report');
144 $hit = $result->next_hit;
145 is( $hit->length, 72, 'Check hit length - multi report' );
148 $result = $in->next_result;
149 is( $result->num_hits, 1, 'Check result#2 num_hits - multi report');
150 is( $result->query_name, 'Cobalamin', 'Check result#2 query_name - multi report');
151 $hit = $result->next_hit;
152 is( $hit->length, 0, 'Check result#2 hit length - multi report' );
153 $hsp = $hit->next_hsp;
154 is( $hsp->strand('hit'), -1, 'Check result#2 hsp hit strand - multi report');
157 # report with no hits
158 $in = Bio::SearchIO->new(
159 -format => 'infernal',
160 -file => test_input_file('cmsearch.nohit.out')
162 $result = $in->next_result;
163 is( $result->cm_name, 'Cobalamin.c.cm', 'Check cm_name' );
164 $hit = $result->next_hit;
165 is( $hit, undef, 'Check for undefined hit' );
170 ### Infernal v. 1.0 ####
172 my $searchio = Bio::SearchIO->new( -format => 'infernal',
173 -file => test_input_file('test2.infernal'),
174 -model => 'tRNAtest',
175 -query_acc => 'RF01234',
176 -query_desc => 'tRNA',
179 $result = $searchio->next_result;
180 isa_ok($result, 'Bio::Search::Result::ResultI');
181 is($result->algorithm, 'CMSEARCH', "Result");
182 is($result->algorithm_reference, undef, "Result reference");
183 is($result->algorithm_version, '1.0', "Result version");
184 is($result->available_parameters, 0, "Result parameters");
185 is($result->available_statistics, 0, "Result statistics");
186 is($result->database_entries, '', "Result entries");
187 is($result->database_letters, 600000, "Result letters");
188 is($result->database_name, 'tosearch.300Kb.db',
189 "Result database_name");
190 is($result->num_hits, 1, "Result num_hits");
191 is($result->program_reference, undef, "Result program_reference");
192 is($result->query_accession, 'RF01234', "Result query_accession");
193 is($result->query_description, 'tRNA', "Result query_description");
194 is($result->query_length, 72, "Result query_length");
195 is($result->query_name, 'trna.5-1', "Result query_name");
197 $hit = $result->next_hit;
199 isa_ok($hit, 'Bio::Search::Hit::HitI');
200 is($hit->ncbi_gi, '', "Hit GI");
201 is($hit->accession, 'example', "Hit accession");
202 is($hit->algorithm, 'CMSEARCH', "Hit algorithm");
203 is($hit->bits, '78.06', "Hit bits");
204 is($hit->description, '', "Hit description"); # no hit descs yet
205 is($hit->locus, '', "Hit locus");
206 is($hit->n, 3, "Hit n");
207 is($hit->name, 'example', "Hit name");
208 is($hit->num_hsps, 3, "Hit num_hsps");
210 # These Bio::Search::Hit::HitI methods are currently unimplemented in
211 # Bio::Search::Hit::ModelHit; they may be integrated over time but will require
212 # some reconfiguring for Model-based searches
214 # these need to be replaced by dies_ok() or warnings_like()
215 warning_like { $hit->length_aln() }
216 qr'length_aln not implemented for Model-based searches',
217 "Hit length_aln() not implemented";
218 warning_like {$hit->num_unaligned_hit}
219 qr'num_unaligned_hit/num_unaligned_sbjct not implemented for Model-based searches',
220 "Hit num_unaligned_hit() not implemented";
221 warning_like {$hit->num_unaligned_query}
222 qr'num_unaligned_query not implemented for Model-based searches',
223 "Hit num_unaligned_query() not implemented";
224 warning_like {$hit->num_unaligned_sbjct}
225 qr'num_unaligned_hit/num_unaligned_sbjct not implemented for Model-based searches',
226 "Hit num_unaligned_sbjct() not implemented";
227 warning_like {$hit->start}
228 qr'start not implemented for Model-based searches',
229 'Hit start not implemented';
230 warning_like {$hit->end}
231 qr'end not implemented for Model-based searches',
232 'Hit end not implemented';
233 warning_like {$hit->strand}
234 qr'strand not implemented for Model-based searches',
235 'Hit strand not implemented';
236 warning_like {$hit->logical_length}
237 qr'logical_length not implemented for Model-based searches',
238 'Hit logical_length not implemented';
239 warning_like {$hit->frac_aligned_hit}
240 qr'frac_aligned_hit not implemented for Model-based searches',
241 'Hit frac_aligned_hit not implemented';
242 warning_like {$hit->frac_aligned_query}
243 qr'frac_aligned_query not implemented for Model-based searches',
244 'Hit frac_aligned_query not implemented';
245 warning_like {$hit->frac_conserved}
246 qr'frac_conserved not implemented for Model-based searches',
247 'Hit frac_conserved not implemented';
248 warning_like {$hit->frac_identical}
249 qr'frac_identical not implemented for Model-based searches',
250 'Hit frac_identical not implemented';
251 warning_like {$hit->matches}
252 qr'matches not implemented for Model-based searches',
253 'Hit matches not implemented';
254 warning_like {$hit->gaps}
255 qr'gaps not implemented for Model-based searches',
256 'Hit gaps not implemented';
257 warning_like {$hit->frame}
258 qr'frame not implemented for Model-based searches',
259 'Hit frame not implemented';
260 warning_like {$hit->range}
261 qr'range not implemented for Model-based searches',
262 'Hit range not implemented';
263 warning_like {$hit->seq_inds}
264 qr'seq_inds not implemented for Model-based searches',
265 'Hit seq_inds not implemented';
267 is($hit->length, 0, "Hit length");
268 is($hit->overlap, 0, "Hit overlap");
269 is($hit->query_length, 72, "Hit query_length");
270 is($hit->rank, 1, "Hit rank");
271 is($hit->raw_score, '78.06', "Hit raw_score");
272 is($hit->score, '78.06', "Hit score");
273 float_is($hit->p, '2.906e-26', "Hit p");
274 float_is($hit->significance, '3.133e-21');
276 $hsp = $hit->next_hsp;
277 isa_ok($hsp, 'Bio::Search::HSP::HSPI');
278 is($hsp->algorithm, 'CMSEARCH', "HSP algorithm");
279 float_is($hsp->evalue, '3.133e-21');
280 isa_ok($hsp->feature1, 'Bio::SeqFeature::Similarity');
281 isa_ok($hsp->feature2, 'Bio::SeqFeature::Similarity');
282 ($meta) = $hsp->feature1->get_tag_values('meta');
283 is($meta, '(((((((,,<<<<___.____>>>>,<<<<<_______>>>>>,,,,,<<<<<_______>>>>>))))))):');
284 ($meta) = $hsp->feature2->get_tag_values('meta');
285 is($meta, '(((((((,,<<<<___.____>>>>,<<<<<_______>>>>>,,,,,<<<<<_______>>>>>))))))):');
287 is($hsp->frame('query'), 0, "HSP frame");
288 is($hsp->gaps, 1, "HSP gaps");
289 is($hit->length, 0, "Hit length");
290 isa_ok($hsp->get_aln, 'Bio::Align::AlignI');
291 isa_ok($hsp->hit, 'Bio::SeqFeature::Similarity', "HSP hit");
293 'GCGGAUUUAGCUCAGUuGGGAGAGCGCCAGACUGAAGAUCUGGAGGUCCUGUGUUCGAUCCACAGAAUUCGCA',
295 is($hsp->homology_string,
296 'GC::A::UAGC:CAGU GG AG:GCGCCAG:CUG+++A:CUGGAGGUCC:G:GUUCGAU C:C:G::U::GCA',
297 "HSP homology_string");
298 is($hsp->hsp_group, undef, "HSP hsp_group");
299 is($hsp->hsp_length, 73, "HSP hsp_length");
300 is($hsp->length, 73, "HSP length");
301 is($hsp->links, undef, "HSP links");
302 is($hsp->n, 1, "HSP n");
303 float_is($hsp->pvalue, 2.906e-26, "HSP pvalue");
304 isa_ok($hsp->query, 'Bio::SeqFeature::Similarity', "HSP query");
305 is($hsp->query_string,
306 'gCcgacAUaGcgcAgU.GGuAgcgCgccagccUgucAagcuggAGgUCCgggGUUCGAUuCcccGUgucgGca',
308 is($hsp->range, 72, "HSP range");
309 is($hsp->rank, 1, "HSP rank");
310 float_is($hsp->significance, 3.133e-21);
311 is($hsp->end, 72, "HSP end");
312 float_is($hsp->expect, '3.133e-21', "HSP expect");
314 # These Bio::Search::HSP::HSPI methods are currently unimplemented in
315 # Bio::Search::HSP::ModelHSP; they may be integrated over time but will require
316 # some reconfiguring for Model-based searches
318 warning_like {$hsp->seq_inds}
319 qr'seq_inds not implemented for Model-based searches',
320 'HSP seq_inds not implemented';
321 warning_like {$hsp->matches}
322 qr'matches not implemented for Model-based searches',
323 'HSP matches not implemented';
324 warning_like {$hsp->frac_conserved}
325 qr'frac_conserved not implemented for Model-based searches',
326 'HSP frac_conserved not implemented';
327 warning_like {$hsp->frac_identical}
328 qr'frac_identical not implemented for Model-based searches',
329 'HSP frac_identical not implemented';
330 warning_like {$hsp->num_conserved}
331 qr'num_conserved not implemented for Model-based searches',
332 'HSP num_conserved not implemented';
333 warning_like {$hsp->num_identical}
334 qr'num_identical not implemented for Model-based searches',
335 'HSP num_identical not implemented';
336 warning_like {$hsp->percent_identity}
337 qr'percent_identity not implemented for Model-based searches',
338 'HSP percent_identity not implemented';
339 warning_like {$hsp->cigar_string}
340 qr'cigar_string not implemented for Model-based searches',
341 'HSP cigar_string not implemented';
342 warning_like {$hsp->generate_cigar_string}
343 qr'generate_cigar_string not implemented for Model-based searches',
344 'HSP cigar_string not implemented';
346 isa_ok($hsp->seq, 'Bio::LocatableSeq');
348 'gCcgacAUaGcgcAgU.GGuAgcgCgccagccUgucAagcuggAGgUCCgggGUUCGAUuCcccGUgucgGca',
350 is($hsp->start, 1, "HSP start");
351 is($hsp->custom_score, undef, "HSP custom_score");
353 '(((((((,,<<<<___.____>>>>,<<<<<_______>>>>>,,,,,<<<<<_______>>>>>))))))):',
355 is($hsp->strand('hit'), 1, "HSP strand");
357 $hsp = $hit->next_hsp;
358 isa_ok($hsp, 'Bio::Search::HSP::HSPI');
359 is($hsp->algorithm, 'CMSEARCH', "HSP algorithm");
360 float_is($hsp->evalue, 0.6752);
361 isa_ok($hsp->feature1, 'Bio::SeqFeature::Similarity');
362 isa_ok($hsp->feature2, 'Bio::SeqFeature::Similarity');
363 is($hsp->frame('query'), 0, "HSP frame");
364 is($hsp->gaps, 4, "HSP gaps");
365 # infernal can return alignment data
366 isa_ok($hsp->get_aln, 'Bio::Align::AlignI');
367 isa_ok($hsp->hit, 'Bio::SeqFeature::Similarity', "HSP hit");
369 'UCUGCUAUGGCGUAAUGGCCACGCGC----CCAUCAACAAAGAUAUC*[19]*UAACAGGA',
371 is($hsp->homology_string,
372 ' C:G :AU+GCG:A+UGG :CGCGC C UCAA +++GA +UC U: C:G A',
373 "HSP homology_string");
374 is($hsp->hsp_group, undef, "HSP hsp_group");
375 is($hsp->hsp_length, 73, "HSP hsp_length");
376 is($hsp->length, 73, "HSP length");
377 is($hsp->links, undef, "HSP links");
378 is($hsp->n, 1, "HSP n");
379 float_is($hsp->pvalue, 6.263e-06, "HSP pvalue");
380 isa_ok($hsp->query, 'Bio::SeqFeature::Similarity', "HSP query");
381 is($hsp->query_string,
382 'gCcgacAUaGcgcAgUGGuAgcgCgccagccUgucAagcuggAGgUC*[17]*UgucgGca',
384 is($hsp->range, 72, "HSP range");
385 is($hsp->rank, 2, "HSP rank");
386 float_is($hsp->significance, 0.6752);
387 is($hsp->end, 72, "HSP end");
388 float_is($hsp->expect, 0.6752, "HSP expect");
389 isa_ok($hsp->seq, 'Bio::LocatableSeq');
390 # this should probably default to the hit string
392 'gCcgacAUaGcgcAgUGGuAgcgCgccagccUgucAagcuggAGgUC*[17]*UgucgGca',
394 is($hsp->start, 1, "HSP start");
395 is($hsp->custom_score, undef, "HSP custom_score");
397 '(((((((,,<<<<_______>>>>,<<<<<_______>>>>>,,,,,~~~~~~))))))):',
399 is($hsp->strand('hit'), 1, "HSP strand");
401 ### Infernal pre-v. 1.0 ####
403 $searchio = Bio::SearchIO->new( -format => 'infernal',
404 -file => test_input_file('test.infernal'),
405 # version is reset to the correct one by parser
408 -query_acc => 'RF00167',
409 -query_desc => 'Purine riboswitch',
410 -database => 'b_sub.fas',
415 $result = $searchio->next_result;
416 isa_ok($result, 'Bio::Search::Result::ResultI');
417 $algorithm = $result->algorithm;
418 is($result->algorithm, 'CMSEARCH', "Result $algorithm");
419 is($result->algorithm_reference, undef, "Result $algorithm reference");
420 is($result->algorithm_version, 0.7, "Result $algorithm version");
421 is($result->available_parameters, 0, "Result parameters");
422 is($result->available_statistics, 0, "Result statistics");
423 is($result->database_entries, '', "Result entries");
424 is($result->database_letters, '', "Result letters");
425 is($result->database_name, 'b_sub.fas', "Result database_name");
426 is($result->num_hits, 2, "Result num_hits");
427 is($result->program_reference, undef, "Result program_reference");
428 is($result->query_accession, 'RF00167', "Result query_accession");
429 is($result->query_description, 'Purine riboswitch', "Result query_description");
430 is($result->query_length, 102, "Result query_length");
431 is($result->query_name, 'Purine', "Result query_name");
433 $hit = $result->next_hit;
435 isa_ok($hit, 'Bio::Search::Hit::HitI');
436 is($hit->ncbi_gi, '2239287', "Hit GI");
437 is($hit->accession, 'U51115.1', "Hit accession");
438 is($hit->algorithm, 'CMSEARCH', "Hit algorithm");
439 is($hit->bits, 81.29, "Hit bits");
440 is($hit->description, '', "Hit description"); # no hit descs yet
441 is($hit->locus, 'BSU51115', "Hit locus");
442 is($hit->n, 2, "Hit n");
443 is($hit->name, 'gi|2239287|gb|U51115.1|BSU51115', "Hit name");
444 is($hit->num_hsps, 2, "Hit num_hsps");
446 # p() works but there are no evalues yet for Infernal output, so catch and check...
447 warning_like {$hit->p}
448 qr'P-value not defined. Using significance\(\) instead',
451 is($hit->length, 0, "Hit length");
452 is($hit->overlap, 0, "Hit overlap");
453 is($hit->query_length, 102, "Hit query_length");
454 is($hit->rank, 1, "Hit rank");
455 is($hit->raw_score, 81.29, "Hit raw_score");
456 is($hit->score, 81.29, "Hit score");
457 float_is($hit->significance, undef);
459 $hsp = $hit->next_hsp;
460 isa_ok($hsp, 'Bio::Search::HSP::HSPI');
461 is($hsp->algorithm, 'CMSEARCH', "HSP algorithm");
462 float_is($hsp->evalue, undef);
463 isa_ok($hsp->feature1, 'Bio::SeqFeature::Similarity');
464 isa_ok($hsp->feature2, 'Bio::SeqFeature::Similarity');
465 ($meta) = $hsp->feature1->get_tag_values('meta');
466 is($meta, ':::::::::::::::::((((((((,,,<<<<<<<_______>>>>>>>,,,,,,,,<<<<<<<_______>>>>>>>,,)))).))))::::::::::::::');
467 ($meta) = $hsp->feature2->get_tag_values('meta');
468 is($meta, ':::::::::::::::::((((((((,,,<<<<<<<_______>>>>>>>,,,,,,,,<<<<<<<_______>>>>>>>,,)))).))))::::::::::::::');
470 is($hsp->frame('query'), 0, "HSP frame");
471 is($hsp->gaps, 1, "HSP gaps");
472 is($hit->length, 0, "Hit length");
473 isa_ok($hsp->get_aln, 'Bio::Align::AlignI');
474 isa_ok($hsp->hit, 'Bio::SeqFeature::Similarity', "HSP hit");
476 'CAUGAAAUCAAAACACGACCUCAUAUAAUCUUGGGAAUAUGGCCCAUAAGUUUCUACCCGGCAACCGUAAAUUGCCGGACUAUGcAGGGAAGUGAUCGAUAAA',
478 is($hsp->homology_string,
479 ' A+ A+A+ AAAA A :CUC:UAUAAU: :GGGAAUAUGGCCC: :AGUUUCUACC:GGCAACCGUAAAUUGCC:GACUA:G AG: AA + ++ +++++',
480 "HSP homology_string");
481 is($hsp->hsp_group, undef, "HSP hsp_group");
482 is($hsp->hsp_length, 103, "HSP hsp_length");
483 is($hsp->length, 103, "HSP length");
484 is($hsp->links, undef, "HSP links");
485 is($hsp->n, 1, "HSP n");
486 float_is($hsp->pvalue, undef, "HSP pvalue");
487 isa_ok($hsp->query, 'Bio::SeqFeature::Similarity', "HSP query");
488 is($hsp->query_string,
489 'aAaaauaaAaaaaaaaauaCuCgUAUAaucucgggAAUAUGGcccgagaGUuUCUACCaGgcaaCCGUAAAuugcCuGACUAcG.aGuaAauauuaaauauuu',
491 is($hsp->range, 102, "HSP range");
492 is($hsp->rank, 1, "HSP rank");
493 float_is($hsp->significance, undef);
494 is($hsp->end, 102, "HSP end");
495 float_is($hsp->expect, undef, "HSP expect");
497 isa_ok($hsp->seq, 'Bio::LocatableSeq');
499 'aAaaauaaAaaaaaaaauaCuCgUAUAaucucgggAAUAUGGcccgagaGUuUCUACCaGgcaaCCGUAAAuugcCuGACUAcG.aGuaAauauuaaauauuu',
501 is($hsp->start, 1, "HSP start");
502 is($hsp->custom_score, undef, "HSP custom_score");
504 ':::::::::::::::::((((((((,,,<<<<<<<_______>>>>>>>,,,,,,,,<<<<<<<_______>>>>>>>,,)))).))))::::::::::::::',
506 is($hsp->strand('hit'), 1, "HSP strand");
508 $hsp = $hit->next_hsp;
509 isa_ok($hsp, 'Bio::Search::HSP::HSPI');
510 is($hsp->algorithm, 'CMSEARCH', "HSP algorithm");
511 float_is($hsp->evalue, undef);
512 isa_ok($hsp->feature1, 'Bio::SeqFeature::Similarity');
513 isa_ok($hsp->feature2, 'Bio::SeqFeature::Similarity');
514 is($hsp->frame('query'), 0, "HSP frame");
515 is($hsp->gaps, 0, "HSP gaps");
516 # infernal can return alignment data
517 isa_ok($hsp->get_aln, 'Bio::Align::AlignI');
518 isa_ok($hsp->hit, 'Bio::SeqFeature::Similarity', "HSP hit");
520 'AGAAAUCAAAUAAGAUGAAUUCGUAUAAUCGCGGGAAUAUGGCUCGCAAGUCUCUACCAAGCUACCGUAAAUGGCUUGACUACGUAAACAUUUCUUUCGUUU',
522 is($hsp->homology_string,
523 'A AAAU AAA+AA A+ : CGUAUAAU::CG:GAAUAUGGC:CG::AGU UCUACCA:GC ACCGUAAAU GC:UGACUACG : AU+U +++ UUU',
524 "HSP homology_string");
525 is($hsp->hsp_group, undef, "HSP hsp_group");
526 is($hsp->hsp_length, 103, "HSP hsp_length");
527 is($hsp->length, 103, "HSP length");
528 is($hsp->links, undef, "HSP links");
529 is($hsp->n, 1, "HSP n");
530 float_is($hsp->pvalue, undef, "HSP pvalue");
531 isa_ok($hsp->query, 'Bio::SeqFeature::Similarity', "HSP query");
532 is($hsp->query_string,
533 'aAaaauaaAaaaaaaaauaCuCgUAUAaucucgggAAUAUGGcccgagaGUuUCUACCaGgcaaCCGUAAAuugcCuGACUAcGaGuaAauauuaaauauuu',
535 is($hsp->range, 102, "HSP range");
536 is($hsp->rank, 2, "HSP rank");
537 float_is($hsp->significance, undef);
538 is($hsp->end, 102, "HSP end");
539 float_is($hsp->expect, undef, "HSP expect");
540 #is($hsp->matches, 2, "HSP matches");
541 isa_ok($hsp->seq, 'Bio::LocatableSeq');
542 # this should probably default to the hit string
544 'aAaaauaaAaaaaaaaauaCuCgUAUAaucucgggAAUAUGGcccgagaGUuUCUACCaGgcaaCCGUAAAuugcCuGACUAcGaGuaAauauuaaauauuu',
546 is($hsp->start, 1, "HSP start");
547 is($hsp->custom_score, undef, "HSP custom_score");
549 ':::::::::::::::::((((((((,,,<<<<<<<_______>>>>>>>,,,,,,,,<<<<<<<_______>>>>>>>,,))))))))::::::::::::::',
551 is($hsp->strand('hit'), 1, "HSP strand");
555 $hit = $result->next_hit;
556 isa_ok($hit, 'Bio::Search::Hit::HitI');
557 is($hit->accession, 'X83878.1', "Hit accession");
558 is($hit->ncbi_gi, '633168', "Hit GI");
559 is($hit->algorithm, 'CMSEARCH', "Hit algorithm");
560 is($hit->bits, 79.36, "Hit bits");
561 is($hit->description, '', "Hit description"); # no hit descs yet
562 is($hit->length, 0, "Hit length");
563 is($hit->locus, '', "Hit locus");
564 is($hit->n, 1, "Hit n");
565 is($hit->name, 'gi|633168|emb|X83878.1|', "Hit name");
566 is($hit->num_hsps, 1, "Hit num_hsps");
567 is($hit->overlap, 0, "Hit overlap");
568 is($hit->query_length, 102, "Hit query_length");
569 is($hit->rank, 2, "Hit rank");
570 is($hit->raw_score, 79.36, "Hit raw_score");
571 is($hit->score, 79.36, "Hit score");
572 float_is($hit->significance, undef);
576 $hsp = $hit->next_hsp;
577 isa_ok($hsp, 'Bio::Search::HSP::HSPI');
578 is($hsp->algorithm, 'CMSEARCH', "HSP algorithm");
579 float_is($hsp->evalue, undef);
580 isa_ok($hsp->feature1, 'Bio::SeqFeature::Similarity');
581 isa_ok($hsp->feature2, 'Bio::SeqFeature::Similarity');
582 is($hsp->frame('query'), 0, "HSP frame");
583 is($hsp->gaps, 2, "HSP gaps");
584 isa_ok($hsp->get_aln, 'Bio::Align::AlignI');
585 isa_ok($hsp->hit, 'Bio::SeqFeature::Similarity', "HSP hit");
587 'UUACAAUAUAAUAGGAACACUCAUAUAAUCGCGUGGAUAUGGCACGCAAGUUUCUACCGGGCA-CCGUAAA-UGUCCGACUAUGGGUGAGCAAUGGAACCGC',
589 is($hsp->homology_string,
590 '+ A A++A AA A AA:AC+C:UAUAAU::CG:G AUAUGGC:CG::AGUUUCUACC:G CA CCGUAAA UG C:GACUA:G+GU:A A+U A+ ',
591 "HSP homology_string");
592 is($hsp->hsp_group, undef, "HSP hsp_group");
593 is($hsp->hsp_length, 103, "HSP hsp_length");
594 is($hsp->length, 103, "HSP length");
595 is($hsp->links, undef, "HSP links");
596 is($hsp->n, 1, "HSP n");
597 isa_ok($hsp->query, 'Bio::SeqFeature::Similarity', "HSP query");
598 is($hsp->query_string,
599 'aAaaauaaAaaaaaaaauaCuCgUAUAaucucgggAAUAUGGcccgagaGUuUCUACCaGgcaaCCGUAAAuugcCuGACUAcGaGuaAauauuaaauauuu',
601 is($hsp->range, 102, "HSP range");
602 is($hsp->rank, 1, "HSP rank");
603 float_is($hsp->significance, undef);
604 is($hsp->end, 102, "HSP end");
605 float_is($hsp->expect, undef, "HSP expect");
606 isa_ok($hsp->seq, 'Bio::LocatableSeq');
608 'aAaaauaaAaaaaaaaauaCuCgUAUAaucucgggAAUAUGGcccgagaGUuUCUACCaGgcaaCCGUAAAuugcCuGACUAcGaGuaAauauuaaauauuu',
610 is($hsp->start, 1, "HSP start");
611 is($hsp->custom_score, undef, "HSP custom_score");
613 ':::::::::::::::::((((((((,,,<<<<<<<_______>>>>>>>,,,,,,,,<<<<<<<_______>>>>>>>,,))))))))::::::::::::::',
615 is($hsp->strand('hit'), 1, "HSP strand");
620 'single-strand' => ':',
623 # may add more for quartets, triplets
626 $searchio = Bio::SearchIO->new( -format => 'infernal',
627 -file => test_input_file('test.infernal'),
628 # version is reset to the correct one by parser
631 -query_acc => 'RF00167',
632 -query_desc => 'Purine riboswitch',
633 -database => 'b_sub.fas',
636 -symbols => $symbols,
639 $result = $searchio->next_result;
640 $hit = $result->next_hit;
641 $hsp = $hit->next_hsp;
643 ':::::::::::::::::((((((((:::(((((((:::::::)))))))::::::::(((((((:::::::)))))))::))))-))))::::::::::::::',
645 $hsp = $hit->next_hsp;
647 ':::::::::::::::::((((((((:::(((((((:::::::)))))))::::::::(((((((:::::::)))))))::))))))))::::::::::::::',
649 $hit = $result->next_hit;
650 $hsp = $hit->next_hsp;
652 ':::::::::::::::::((((((((:::(((((((:::::::)))))))::::::::(((((((:::::::)))))))::))))))))::::::::::::::',
654 ($meta) = $hsp->feature1->get_tag_values('meta');
655 is($meta, ':::::::::::::::::((((((((:::(((((((:::::::)))))))::::::::(((((((:::::::)))))))::))))))))::::::::::::::');
656 ($meta) = $hsp->feature2->get_tag_values('meta');
657 is($meta, ':::::::::::::::::((((((((:::(((((((:::::::)))))))::::::::(((((((:::::::)))))))::))))))))::::::::::::::');
659 ## Infernal 0.81 parsing ##
661 $searchio = Bio::SearchIO->new( -format => 'infernal',
662 -file => test_input_file('purine_v081.infernal'),
663 # version is reset to the correct one by parser
664 -query_acc => 'RF00167',
665 -query_desc => 'Purine riboswitch',
666 -database => 'b_sub.fas',
670 $result = $searchio->next_result;
672 isa_ok($result, 'Bio::Search::Result::ResultI');
673 $algorithm = $result->algorithm;
674 is($result->algorithm, 'CMSEARCH', "Result $algorithm");
675 is($result->algorithm_reference, undef, "Result $algorithm reference");
676 is($result->algorithm_version, 0.81, "Result $algorithm version");
677 is($result->available_parameters, 0, "Result parameters");
678 is($result->available_statistics, 0, "Result statistics");
679 is($result->database_entries, '', "Result entries");
680 is($result->database_letters, '', "Result letters");
681 is($result->database_name, 'b_sub.fas', "Result database_name");
682 is($result->num_hits, 3, "Result num_hits");
683 is($result->program_reference, undef, "Result program_reference");
684 is($result->query_accession, 'RF00167', "Result query_accession");
685 is($result->query_description, 'Purine riboswitch', "Result query_description");
686 is($result->query_length, 102, "Result query_length");
687 is($result->query_name, 'Purine', "Result query_name");
689 $hit = $result->next_hit;
690 isa_ok($hit, 'Bio::Search::Hit::HitI');
691 is($hit->ncbi_gi, '633168', "Hit GI");
692 is($hit->accession, 'X83878.1', "Hit accession");
693 is($hit->algorithm, 'CMSEARCH', "Hit algorithm");
694 is($hit->bits, 79.36, "Hit bits");
695 is($hit->description, '', "Hit description"); # no hit descs yet
696 is($hit->locus, '', "Hit locus");
697 is($hit->n, 2, "Hit n");
698 is($hit->name, 'gi|633168|emb|X83878.1|', "Hit name");
699 is($hit->num_hsps, 2, "Hit num_hsps");
701 # p() works but there are no evalues yet for Infernal output, so catch and check...
702 warnings_like {$hit->p} qr'P-value not defined. Using significance\(\) instead',
705 is($hit->length, 0, "Hit length");
706 is($hit->overlap, 0, "Hit overlap");
707 is($hit->query_length, 102, "Hit query_length");
708 is($hit->rank, 1, "Hit rank");
709 is($hit->raw_score, 79.36, "Hit raw_score");
710 is($hit->score, 79.36, "Hit score");
711 float_is($hit->significance, 1.945e-07);
713 $hsp = $hit->next_hsp;
714 isa_ok($hsp, 'Bio::Search::HSP::HSPI');
715 is($hsp->algorithm, 'CMSEARCH', "HSP algorithm");
716 float_is($hsp->evalue, 1.945e-07);
717 isa_ok($hsp->feature1, 'Bio::SeqFeature::Similarity');
718 isa_ok($hsp->feature2, 'Bio::SeqFeature::Similarity');
719 ($meta) = $hsp->feature1->get_tag_values('meta');
720 is($meta, ':::::::::::::::::((((((((,,,<<<<<<<_______>>>>>>>,,,,,,,,<<<<<<<_______>>>>>>>,,))))))))::::::::::::::');
721 ($meta) = $hsp->feature2->get_tag_values('meta');
722 is($meta, ':::::::::::::::::((((((((,,,<<<<<<<_______>>>>>>>,,,,,,,,<<<<<<<_______>>>>>>>,,))))))))::::::::::::::');
724 is($hsp->frame('query'), 0, "HSP frame");
725 is($hsp->gaps, 2, "HSP gaps");
726 is($hit->length, 0, "Hit length");
727 isa_ok($hsp->get_aln, 'Bio::Align::AlignI');
728 isa_ok($hsp->hit, 'Bio::SeqFeature::Similarity', "HSP hit");
730 'UUACAAUAUAAUAGGAACACUCAUAUAAUCGCGUGGAUAUGGCACGCAAGUUUCUACCGGGCA-CCGUAAA-UGUCCGACUAUGGGUGAGCAAUGGAACCGC',
732 is($hsp->homology_string,
733 '+ A A++A AA A AA:AC+C:UAUAAU::CG:G AUAUGGC:CG::AGUUUCUACC:G CA CCGUAAA UG C:GACUA:G+GU:A A+U A+ ',
734 "HSP homology_string");
735 is($hsp->hsp_group, undef, "HSP hsp_group");
736 is($hsp->hsp_length,102, "HSP hsp_length");
737 is($hsp->length, 102, "HSP length");
738 is($hsp->links, undef, "HSP links");
739 is($hsp->n, 1, "HSP n");
740 float_is($hsp->pvalue, 1.945e-07, "HSP pvalue");
741 isa_ok($hsp->query, 'Bio::SeqFeature::Similarity', "HSP query");
742 is($hsp->query_string,
743 'aAaaauaaAaaaaaaaauaCuCgUAUAaucucgggAAUAUGGcccgagaGUuUCUACCaGgcaaCCGUAAAuugcCuGACUAcGaGuaAauauuaaauauuu',
745 is($hsp->range, 102, "HSP range");
746 is($hsp->rank, 1, "HSP rank");
747 float_is($hsp->significance, 1.945e-07);
748 is($hsp->end, 102, "HSP end");
749 float_is($hsp->expect, 1.945e-07, "HSP expect");
751 isa_ok($hsp->seq, 'Bio::LocatableSeq');
753 'aAaaauaaAaaaaaaaauaCuCgUAUAaucucgggAAUAUGGcccgagaGUuUCUACCaGgcaaCCGUAAAuugcCuGACUAcGaGuaAauauuaaauauuu',
755 is($hsp->start, 1, "HSP start");
756 is($hsp->custom_score, undef, "HSP custom_score");
758 ':::::::::::::::::((((((((,,,<<<<<<<_______>>>>>>>,,,,,,,,<<<<<<<_______>>>>>>>,,))))))))::::::::::::::',
760 is($hsp->strand('hit'), 1, "HSP strand");
762 $hsp = $hit->next_hsp;
763 isa_ok($hsp, 'Bio::Search::HSP::HSPI');
764 is($hsp->algorithm, 'CMSEARCH', "HSP algorithm");
765 float_is($hsp->evalue, 6.802);
766 isa_ok($hsp->feature1, 'Bio::SeqFeature::Similarity');
767 isa_ok($hsp->feature2, 'Bio::SeqFeature::Similarity');
768 is($hsp->frame('query'), 0, "HSP frame");
769 is($hsp->gaps, 4, "HSP gaps");
770 # infernal can return alignment data
771 isa_ok($hsp->get_aln, 'Bio::Align::AlignI');
772 isa_ok($hsp->hit, 'Bio::SeqFeature::Similarity', "HSP hit");
774 'CGUGCGGUUCCAUUGCUCACCCAUA-GUCGGACAU-UUACGG-UGCCCGGUAGAAACUUGCGUGCCAUAUCCACGCGAUUaUAUGAGUGUUCCUAUUAUAUUG',
776 is($hsp->homology_string,
777 ' + + A +:AC C:UA +::: :: UA GG :: :::GU AC: G::::CC UA ::::C : UA:G GU: + U+++AUAUU ',
778 "HSP homology_string");
779 is($hsp->hsp_group, undef, "HSP hsp_group");
780 is($hsp->hsp_length, 102, "HSP hsp_length");
781 is($hsp->length, 102, "HSP length");
782 is($hsp->links, undef, "HSP links");
783 is($hsp->n, 1, "HSP n");
784 float_is($hsp->pvalue, 0.9989, "HSP pvalue");
785 isa_ok($hsp->query, 'Bio::SeqFeature::Similarity', "HSP query");
786 is($hsp->query_string,
787 'aAaaauaaAaaaaaaaauaCuCgUAUAaucucgggAAUAUGGcccgagaGUuUCUACCaGgcaaCCGUAAAuugcCuGAC.UAcGaGuaAauauuaaauauuu',
789 is($hsp->range, 102, "HSP range");
790 is($hsp->rank, 2, "HSP rank");
791 float_is($hsp->significance, 6.802);
792 is($hsp->end, 102, "HSP end");
793 float_is($hsp->expect, 6.802, "HSP expect");
794 #is($hsp->matches, 2, "HSP matches");
795 isa_ok($hsp->seq, 'Bio::LocatableSeq');
796 # this should probably default to the hit string
798 'aAaaauaaAaaaaaaaauaCuCgUAUAaucucgggAAUAUGGcccgagaGUuUCUACCaGgcaaCCGUAAAuugcCuGAC.UAcGaGuaAauauuaaauauuu',
800 is($hsp->start, 1, "HSP start");
801 is($hsp->custom_score, undef, "HSP custom_score");
803 ':::::::::::::::::((((((((,,,<<<<<<<_______>>>>>>>,,,,,,,,<<<<<<<_______>>>>>>>,,.))))))))::::::::::::::',
805 is($hsp->strand('hit'), -1, "HSP strand");
809 $hit = $result->next_hit;
810 isa_ok($hit, 'Bio::Search::Hit::HitI');
811 is($hit->accession, 'U51115.1', "Hit accession");
812 is($hit->ncbi_gi, '2239287', "Hit GI");
813 is($hit->algorithm, 'CMSEARCH', "Hit algorithm");
814 is($hit->bits, 81.29, "Hit bits");
815 is($hit->description, '', "Hit description"); # no hit descs yet
816 is($hit->length, 0, "Hit length");
817 is($hit->locus, 'BSU51115', "Hit locus");
818 is($hit->n, 11, "Hit n");
819 is($hit->name, 'gi|2239287|gb|U51115.1|BSU51115', "Hit name");
820 is($hit->num_hsps, 11, "Hit num_hsps");
821 is($hit->overlap, 0, "Hit overlap");
822 is($hit->query_length, 102, "Hit query_length");
823 is($hit->rank, 2, "Hit rank");
824 is($hit->raw_score, 81.29, "Hit raw_score");
825 is($hit->score, 81.29, "Hit score");
826 float_is($hit->significance, 1.259e-07);
830 $hsp = $hit->next_hsp;
831 isa_ok($hsp, 'Bio::Search::HSP::HSPI');
832 is($hsp->algorithm, 'CMSEARCH', "HSP algorithm");
833 float_is($hsp->evalue, 1.259e-07);
834 isa_ok($hsp->feature1, 'Bio::SeqFeature::Similarity');
835 isa_ok($hsp->feature2, 'Bio::SeqFeature::Similarity');
836 is($hsp->frame('query'), 0, "HSP frame");
837 is($hsp->gaps, 0, "HSP gaps");
838 isa_ok($hsp->get_aln, 'Bio::Align::AlignI');
839 isa_ok($hsp->hit, 'Bio::SeqFeature::Similarity', "HSP hit");
841 'AGAAAUCAAAUAAGAUGAAUUCGUAUAAUCGCGGGAAUAUGGCUCGCAAGUCUCUACCAAGCUACCGUAAAUGGCUUGACUACGUAAACAUUUCUUUCGUUU',
843 is($hsp->homology_string,
844 'A AAAU AAA+AA A+ : CGUAUAAU::CG:GAAUAUGGC:CG::AGU UCUACCA:GC ACCGUAAAU GC:UGACUACG : AU+U +++ UUU',
845 "HSP homology_string");
846 is($hsp->hsp_group, undef, "HSP hsp_group");
847 is($hsp->hsp_length, 102, "HSP hsp_length");
848 is($hsp->length, 102, "HSP length");
849 is($hsp->links, undef, "HSP links");
850 is($hsp->n, 1, "HSP n");
851 isa_ok($hsp->query, 'Bio::SeqFeature::Similarity', "HSP query");
852 is($hsp->query_string,
853 'aAaaauaaAaaaaaaaauaCuCgUAUAaucucgggAAUAUGGcccgagaGUuUCUACCaGgcaaCCGUAAAuugcCuGACUAcGaGuaAauauuaaauauuu',
855 is($hsp->range, 102, "HSP range");
856 is($hsp->rank, 1, "HSP rank");
857 float_is($hsp->significance, 1.259e-07);
858 is($hsp->end, 102, "HSP end");
859 float_is($hsp->expect, 1.259e-07, "HSP expect");
860 isa_ok($hsp->seq, 'Bio::LocatableSeq');
862 'aAaaauaaAaaaaaaaauaCuCgUAUAaucucgggAAUAUGGcccgagaGUuUCUACCaGgcaaCCGUAAAuugcCuGACUAcGaGuaAauauuaaauauuu',
864 is($hsp->start, 1, "HSP start");
865 is($hsp->custom_score, undef, "HSP custom_score");
867 ':::::::::::::::::((((((((,,,<<<<<<<_______>>>>>>>,,,,,,,,<<<<<<<_______>>>>>>>,,))))))))::::::::::::::',
869 is($hsp->strand('hit'), 1, "HSP strand");