|
0
|
1 # $Id: HMMERHSP.pm,v 1.3 2002/10/22 07:45:17 lapp Exp $
|
|
|
2 #
|
|
|
3 # BioPerl module for Bio::Search::HSP::HMMERHSP
|
|
|
4 #
|
|
|
5 # Cared for by Jason Stajich <jason@bioperl.org>
|
|
|
6 #
|
|
|
7 # Copyright Jason Stajich
|
|
|
8 #
|
|
|
9 # You may distribute this module under the same terms as perl itself
|
|
|
10
|
|
|
11 # POD documentation - main docs before the code
|
|
|
12
|
|
|
13 =head1 NAME
|
|
|
14
|
|
|
15 Bio::Search::HSP::HMMERHSP - A HSP object for HMMER results
|
|
|
16
|
|
|
17 =head1 SYNOPSIS
|
|
|
18
|
|
|
19 use Bio::Search::HSP::HMMERHSP;
|
|
|
20 # us it just like a Bio::Search::HSP::GenericHSP object
|
|
|
21
|
|
|
22 =head1 DESCRIPTION
|
|
|
23
|
|
|
24 This object is a specialization of L<Bio::Search::HSP::GenericHSP>.
|
|
|
25
|
|
|
26 =head1 FEEDBACK
|
|
|
27
|
|
|
28 =head2 Mailing Lists
|
|
|
29
|
|
|
30 User feedback is an integral part of the evolution of this and other
|
|
|
31 Bioperl modules. Send your comments and suggestions preferably to
|
|
|
32 the Bioperl mailing list. Your participation is much appreciated.
|
|
|
33
|
|
|
34 bioperl-l@bioperl.org - General discussion
|
|
|
35 http://bioperl.org/MailList.shtml - About the mailing lists
|
|
|
36
|
|
|
37 =head2 Reporting Bugs
|
|
|
38
|
|
|
39 Report bugs to the Bioperl bug tracking system to help us keep track
|
|
|
40 of the bugs and their resolution. Bug reports can be submitted via
|
|
|
41 email or the web:
|
|
|
42
|
|
|
43 bioperl-bugs@bioperl.org
|
|
|
44 http://bugzilla.bioperl.org/
|
|
|
45
|
|
|
46 =head1 AUTHOR - Jason Stajich
|
|
|
47
|
|
|
48 Email jason@bioperl.org
|
|
|
49
|
|
|
50 Describe contact details here
|
|
|
51
|
|
|
52 =head1 CONTRIBUTORS
|
|
|
53
|
|
|
54 Additional contributors names and emails here
|
|
|
55
|
|
|
56 =head1 APPENDIX
|
|
|
57
|
|
|
58 The rest of the documentation details each of the object methods.
|
|
|
59 Internal methods are usually preceded with a _
|
|
|
60
|
|
|
61 =cut
|
|
|
62
|
|
|
63
|
|
|
64 # Let the code begin...
|
|
|
65
|
|
|
66
|
|
|
67 package Bio::Search::HSP::HMMERHSP;
|
|
|
68 use vars qw(@ISA);
|
|
|
69 use strict;
|
|
|
70 use Bio::Search::HSP::GenericHSP;
|
|
|
71
|
|
|
72 @ISA = qw(Bio::Search::HSP::GenericHSP);
|
|
|
73
|
|
|
74 =head2 new
|
|
|
75
|
|
|
76 Title : new
|
|
|
77 Usage : my $obj = new Bio::Search::HSP::HMMERHSP();
|
|
|
78 Function: Builds a new Bio::Search::HSP::HMMERHSP object
|
|
|
79 Returns : Bio::Search::HSP::HMMERHSP
|
|
|
80 Args :
|
|
|
81
|
|
|
82 Plus Bio::Seach::HSP::GenericHSP methods
|
|
|
83
|
|
|
84 -algorithm => algorithm used (BLASTP, TBLASTX, FASTX, etc)
|
|
|
85 -evalue => evalue
|
|
|
86 -pvalue => pvalue
|
|
|
87 -bits => bit value for HSP
|
|
|
88 -score => score value for HSP (typically z-score but depends on
|
|
|
89 analysis)
|
|
|
90 -hsp_length=> Length of the HSP (including gaps)
|
|
|
91 -identical => # of residues that that matched identically
|
|
|
92 -conserved => # of residues that matched conservatively
|
|
|
93 (only protein comparisions;
|
|
|
94 conserved == identical in nucleotide comparisons)
|
|
|
95 -hsp_gaps => # of gaps in the HSP
|
|
|
96 -query_gaps => # of gaps in the query in the alignment
|
|
|
97 -hit_gaps => # of gaps in the subject in the alignment
|
|
|
98 -query_name => HSP Query sequence name (if available)
|
|
|
99 -query_start => HSP Query start (in original query sequence coords)
|
|
|
100 -query_end => HSP Query end (in original query sequence coords)
|
|
|
101 -hit_name => HSP Hit sequence name (if available)
|
|
|
102 -hit_start => HSP Hit start (in original hit sequence coords)
|
|
|
103 -hit_end => HSP Hit end (in original hit sequence coords)
|
|
|
104 -hit_length => total length of the hit sequence
|
|
|
105 -query_length=> total length of the query sequence
|
|
|
106 -query_seq => query sequence portion of the HSP
|
|
|
107 -hit_seq => hit sequence portion of the HSP
|
|
|
108 -homology_seq=> homology sequence for the HSP
|
|
|
109 -hit_frame => hit frame (only if hit is translated protein)
|
|
|
110 -query_frame => query frame (only if query is translated protein)
|
|
|
111
|
|
|
112 =cut
|
|
|
113
|
|
|
114 =head2 Bio::Search::HSP::HSPI methods
|
|
|
115
|
|
|
116 Implementation of Bio::Search::HSP::HSPI methods follow
|
|
|
117
|
|
|
118 =head2 algorithm
|
|
|
119
|
|
|
120 Title : algorithm
|
|
|
121 Usage : my $r_type = $hsp->algorithm
|
|
|
122 Function: Obtain the name of the algorithm used to obtain the HSP
|
|
|
123 Returns : string (e.g., BLASTP)
|
|
|
124 Args : [optional] scalar string to set value
|
|
|
125
|
|
|
126 =cut
|
|
|
127
|
|
|
128 =head2 pvalue
|
|
|
129
|
|
|
130 Title : pvalue
|
|
|
131 Usage : my $pvalue = $hsp->pvalue();
|
|
|
132 Function: Returns the P-value for this HSP or undef
|
|
|
133 Returns : float or exponential (2e-10)
|
|
|
134 P-value is not defined with NCBI Blast2 reports.
|
|
|
135 Args : [optional] numeric to set value
|
|
|
136
|
|
|
137 =cut
|
|
|
138
|
|
|
139 =head2 evalue
|
|
|
140
|
|
|
141 Title : evalue
|
|
|
142 Usage : my $evalue = $hsp->evalue();
|
|
|
143 Function: Returns the e-value for this HSP
|
|
|
144 Returns : float or exponential (2e-10)
|
|
|
145 Args : [optional] numeric to set value
|
|
|
146
|
|
|
147 =cut
|
|
|
148
|
|
|
149 =head2 frac_identical
|
|
|
150
|
|
|
151 Title : frac_identical
|
|
|
152 Usage : my $frac_id = $hsp->frac_identical( ['query'|'hit'|'total'] );
|
|
|
153 Function: Returns the fraction of identitical positions for this HSP
|
|
|
154 Returns : Float in range 0.0 -> 1.0
|
|
|
155 Args : arg 1: 'query' = num identical / length of query seq (without gaps)
|
|
|
156 'hit' = num identical / length of hit seq (without gaps)
|
|
|
157 'total' = num identical / length of alignment (with gaps)
|
|
|
158 default = 'total'
|
|
|
159 arg 2: [optional] frac identical value to set for the type requested
|
|
|
160
|
|
|
161 =cut
|
|
|
162
|
|
|
163 =head2 frac_conserved
|
|
|
164
|
|
|
165 Title : frac_conserved
|
|
|
166 Usage : my $frac_cons = $hsp->frac_conserved( ['query'|'hit'|'total'] );
|
|
|
167 Function : Returns the fraction of conserved positions for this HSP.
|
|
|
168 This is the fraction of symbols in the alignment with a
|
|
|
169 positive score.
|
|
|
170 Returns : Float in range 0.0 -> 1.0
|
|
|
171 Args : arg 1: 'query' = num conserved / length of query seq (without gaps)
|
|
|
172 'hit' = num conserved / length of hit seq (without gaps)
|
|
|
173 'total' = num conserved / length of alignment (with gaps)
|
|
|
174 default = 'total'
|
|
|
175 arg 2: [optional] frac conserved value to set for the type requested
|
|
|
176
|
|
|
177 =cut
|
|
|
178
|
|
|
179 =head2 gaps
|
|
|
180
|
|
|
181 Title : gaps
|
|
|
182 Usage : my $gaps = $hsp->gaps( ['query'|'hit'|'total'] );
|
|
|
183 Function : Get the number of gaps in the query, hit, or total alignment.
|
|
|
184 Returns : Integer, number of gaps or 0 if none
|
|
|
185 Args : arg 1: 'query' = num gaps in query seq
|
|
|
186 'hit' = num gaps in hit seq
|
|
|
187 'total' = num gaps in whole alignment
|
|
|
188 default = 'total'
|
|
|
189 arg 2: [optional] integer gap value to set for the type requested
|
|
|
190
|
|
|
191 =cut
|
|
|
192
|
|
|
193 =head2 query_string
|
|
|
194
|
|
|
195 Title : query_string
|
|
|
196 Usage : my $qseq = $hsp->query_string;
|
|
|
197 Function: Retrieves the query sequence of this HSP as a string
|
|
|
198 Returns : string
|
|
|
199 Args : [optional] string to set for query sequence
|
|
|
200
|
|
|
201
|
|
|
202 =cut
|
|
|
203
|
|
|
204 =head2 hit_string
|
|
|
205
|
|
|
206 Title : hit_string
|
|
|
207 Usage : my $hseq = $hsp->hit_string;
|
|
|
208 Function: Retrieves the hit sequence of this HSP as a string
|
|
|
209 Returns : string
|
|
|
210 Args : [optional] string to set for hit sequence
|
|
|
211
|
|
|
212
|
|
|
213 =cut
|
|
|
214
|
|
|
215
|
|
|
216 =head2 homology_string
|
|
|
217
|
|
|
218 Title : homology_string
|
|
|
219 Usage : my $homo_string = $hsp->homology_string;
|
|
|
220 Function: Retrieves the homology sequence for this HSP as a string.
|
|
|
221 : The homology sequence is the string of symbols in between the
|
|
|
222 : query and hit sequences in the alignment indicating the degree
|
|
|
223 : of conservation (e.g., identical, similar, not similar).
|
|
|
224 Returns : string
|
|
|
225 Args : [optional] string to set for homology sequence
|
|
|
226
|
|
|
227 =cut
|
|
|
228
|
|
|
229 =head2 length
|
|
|
230
|
|
|
231 Title : length
|
|
|
232 Usage : my $len = $hsp->length( ['query'|'hit'|'total'] );
|
|
|
233 Function : Returns the length of the query or hit in the alignment
|
|
|
234 (without gaps)
|
|
|
235 or the aggregate length of the HSP (including gaps;
|
|
|
236 this may be greater than either hit or query )
|
|
|
237 Returns : integer
|
|
|
238 Args : arg 1: 'query' = length of query seq (without gaps)
|
|
|
239 'hit' = length of hit seq (without gaps)
|
|
|
240 'total' = length of alignment (with gaps)
|
|
|
241 default = 'total'
|
|
|
242 arg 2: [optional] integer length value to set for specific type
|
|
|
243
|
|
|
244 =cut
|
|
|
245
|
|
|
246 =head2 percent_identity
|
|
|
247
|
|
|
248 Title : percent_identity
|
|
|
249 Usage : my $percentid = $hsp->percent_identity()
|
|
|
250 Function: Returns the calculated percent identity for an HSP
|
|
|
251 Returns : floating point between 0 and 100
|
|
|
252 Args : none
|
|
|
253
|
|
|
254
|
|
|
255 =cut
|
|
|
256
|
|
|
257
|
|
|
258 =head2 frame
|
|
|
259
|
|
|
260 Title : frame
|
|
|
261 Usage : $hsp->frame($queryframe,$subjectframe)
|
|
|
262 Function: Set the Frame for both query and subject and insure that
|
|
|
263 they agree.
|
|
|
264 This overrides the frame() method implementation in
|
|
|
265 FeaturePair.
|
|
|
266 Returns : array of query and subjects if return type wants an array
|
|
|
267 or query frame if defined or subject frame
|
|
|
268 Args : none
|
|
|
269 Note : Frames are stored in the GFF way (0-2) not 1-3
|
|
|
270 as they are in BLAST (negative frames are deduced by checking
|
|
|
271 the strand of the query or hit)
|
|
|
272
|
|
|
273 =cut
|
|
|
274
|
|
|
275
|
|
|
276 =head2 get_aln
|
|
|
277
|
|
|
278 Title : get_aln
|
|
|
279 Usage : my $aln = $hsp->gel_aln
|
|
|
280 Function: Returns a Bio::SimpleAlign representing the HSP alignment
|
|
|
281 Returns : Bio::SimpleAlign
|
|
|
282 Args : none
|
|
|
283
|
|
|
284 =cut
|
|
|
285
|
|
|
286 sub get_aln {
|
|
|
287 my ($self) = shift;
|
|
|
288 $self->warn("Innapropriate to build a Bio::SimpleAlign from a HMMER HSP object");
|
|
|
289 return undef;
|
|
|
290 }
|
|
|
291
|
|
|
292 =head2 num_conserved
|
|
|
293
|
|
|
294 Title : num_conserved
|
|
|
295 Usage : $obj->num_conserved($newval)
|
|
|
296 Function: returns the number of conserved residues in the alignment
|
|
|
297 Returns : inetger
|
|
|
298 Args : integer (optional)
|
|
|
299
|
|
|
300
|
|
|
301 =cut
|
|
|
302
|
|
|
303 =head2 num_identical
|
|
|
304
|
|
|
305 Title : num_identical
|
|
|
306 Usage : $obj->num_identical($newval)
|
|
|
307 Function: returns the number of identical residues in the alignment
|
|
|
308 Returns : integer
|
|
|
309 Args : integer (optional)
|
|
|
310
|
|
|
311
|
|
|
312 =cut
|
|
|
313
|
|
|
314 =head2 seq_inds
|
|
|
315
|
|
|
316 Title : seq_inds
|
|
|
317 Purpose : Get a list of residue positions (indices) for all identical
|
|
|
318 : or conserved residues in the query or sbjct sequence.
|
|
|
319 Example : @s_ind = $hsp->seq_inds('query', 'identical');
|
|
|
320 : @h_ind = $hsp->seq_inds('hit', 'conserved');
|
|
|
321 : @h_ind = $hsp->seq_inds('hit', 'conserved', 1);
|
|
|
322 Returns : List of integers
|
|
|
323 : May include ranges if collapse is true.
|
|
|
324 Argument : seq_type = 'query' or 'hit' or 'sbjct' (default = query)
|
|
|
325 : ('sbjct' is synonymous with 'hit')
|
|
|
326 : class = 'identical' or 'conserved' or 'nomatch' or 'gap'
|
|
|
327 : (default = identical)
|
|
|
328 : (can be shortened to 'id' or 'cons')
|
|
|
329 :
|
|
|
330 : collapse = boolean, if true, consecutive positions are merged
|
|
|
331 : using a range notation, e.g., "1 2 3 4 5 7 9 10 11"
|
|
|
332 : collapses to "1-5 7 9-11". This is useful for
|
|
|
333 : consolidating long lists. Default = no collapse.
|
|
|
334 Throws : n/a.
|
|
|
335 Comments :
|
|
|
336
|
|
|
337 See Also : L<Bio::Search::BlastUtils::collapse_nums()|Bio::Search::BlastUtils>, L<Bio::Search::Hit::HitI::seq_inds()|Bio::Search::Hit::HitI>
|
|
|
338
|
|
|
339 =cut
|
|
|
340
|
|
|
341 =head2 Inherited from Bio::SeqFeature::SimilarityPair
|
|
|
342
|
|
|
343 These methods come from Bio::SeqFeature::SimilarityPair
|
|
|
344
|
|
|
345 =head2 query
|
|
|
346
|
|
|
347 Title : query
|
|
|
348 Usage : my $query = $hsp->query
|
|
|
349 Function: Returns a SeqFeature representing the query in the HSP
|
|
|
350 Returns : Bio::SeqFeature::Similarity
|
|
|
351 Args : [optional] new value to set
|
|
|
352
|
|
|
353
|
|
|
354 =head2 hit
|
|
|
355
|
|
|
356 Title : hit
|
|
|
357 Usage : my $hit = $hsp->hit
|
|
|
358 Function: Returns a SeqFeature representing the hit in the HSP
|
|
|
359 Returns : Bio::SeqFeature::Similarity
|
|
|
360 Args : [optional] new value to set
|
|
|
361
|
|
|
362
|
|
|
363 =head2 significance
|
|
|
364
|
|
|
365 Title : significance
|
|
|
366 Usage : $evalue = $obj->significance();
|
|
|
367 $obj->significance($evalue);
|
|
|
368 Function: Get/Set the significance value
|
|
|
369 Returns : numeric
|
|
|
370 Args : [optional] new value to set
|
|
|
371
|
|
|
372
|
|
|
373 =head2 score
|
|
|
374
|
|
|
375 Title : score
|
|
|
376 Usage : my $score = $hsp->score();
|
|
|
377 Function: Returns the score for this HSP or undef
|
|
|
378 Returns : numeric
|
|
|
379 Args : [optional] numeric to set value
|
|
|
380
|
|
|
381 =cut
|
|
|
382
|
|
|
383 =head2 bits
|
|
|
384
|
|
|
385 Title : bits
|
|
|
386 Usage : my $bits = $hsp->bits();
|
|
|
387 Function: Returns the bit value for this HSP or undef
|
|
|
388 Returns : numeric
|
|
|
389 Args : none
|
|
|
390
|
|
|
391 =cut
|
|
|
392
|
|
|
393
|
|
|
394 1;
|
