2 # BioPerl module for Bio::PrimarySeqI
4 # Please direct questions and support issues to <bioperl-l@bioperl.org>
6 # Cared for by Ewan Birney <birney@ebi.ac.uk>
8 # Copyright Ewan Birney
10 # You may distribute this module under the same terms as perl itself
12 # POD documentation - main docs before the code
16 Bio::PrimarySeqI - Interface definition for a Bio::PrimarySeq
20 # Bio::PrimarySeqI is the interface class for sequences.
21 # If you are a newcomer to bioperl, you might want to start with
22 # Bio::Seq documentation.
24 # Test if this is a seq object
25 $obj->isa("Bio::PrimarySeqI") ||
26 $obj->throw("$obj does not implement the Bio::PrimarySeqI interface");
29 $string = $obj->seq();
30 $substring = $obj->subseq(12,50);
31 $display = $obj->display_id(); # for human display
32 $id = $obj->primary_id(); # unique id for this object,
33 # implementation defined
34 $unique_key= $obj->accession_number(); # unique biological id
39 $rev = $obj->revcom();
42 $obj->throw("Could not reverse complement. ".
43 "Probably not DNA. Actual exception\n$@\n");
46 $trunc = $obj->trunc(12,50);
47 # $rev and $trunc are Bio::PrimarySeqI compliant objects
52 This object defines an abstract interface to basic sequence
53 information - for most users of the package the documentation (and
54 methods) in this class are not useful - this is a developers-only
55 class which defines what methods have to be implmented by other Perl
56 objects to comply to the Bio::PrimarySeqI interface. Go "perldoc
57 Bio::Seq" or "man Bio::Seq" for more information on the main class for
60 PrimarySeq is an object just for the sequence and its name(s), nothing
61 more. Seq is the larger object complete with features. There is a pure
62 perl implementation of this in L<Bio::PrimarySeq>. If you just want to
63 use L<Bio::PrimarySeq> objects, then please read that module first. This
64 module defines the interface, and is of more interest to people who
65 want to wrap their own Perl Objects/RDBs/FileSystems etc in way that
66 they "are" bioperl sequence objects, even though it is not using Perl
67 to store the sequence etc.
69 This interface defines what bioperl considers necessary to "be" a
70 sequence, without providing an implementation of this, an
71 implementation is provided in L<Bio::PrimarySeq>. If you want to provide
72 a Bio::PrimarySeq-compliant object which in fact wraps another
73 object/database/out-of-perl experience, then this is the correct thing
74 to wrap, generally by providing a wrapper class which would inherit
75 from your object and this Bio::PrimarySeqI interface. The wrapper class
76 then would have methods lists in the "Implementation Specific
77 Functions" which would provide these methods for your object.
83 User feedback is an integral part of the evolution of this and other
84 Bioperl modules. Send your comments and suggestions preferably to one
85 of the Bioperl mailing lists. Your participation is much appreciated.
87 bioperl-l@bioperl.org - General discussion
88 http://bioperl.org/wiki/Mailing_lists - About the mailing lists
92 Please direct usage questions or support issues to the mailing list:
94 I<bioperl-l@bioperl.org>
96 rather than to the module maintainer directly. Many experienced and
97 reponsive experts will be able look at the problem and quickly
98 address it. Please include a thorough description of the problem
99 with code and data examples if at all possible.
101 =head2 Reporting Bugs
103 Report bugs to the Bioperl bug tracking system to help us keep track
104 the bugs and their resolution. Bug reports can be submitted via the
107 https://redmine.open-bio.org/projects/bioperl/
109 =head1 AUTHOR - Ewan Birney
111 Email birney@ebi.ac.uk
115 The rest of the documentation details each of the object
116 methods. Internal methods are usually preceded with a _
121 # Let the code begin...
124 package Bio
::PrimarySeqI
;
126 use Bio
::Tools
::CodonTable
;
128 use base
qw(Bio::Root::RootI);
130 =head1 Implementation Specific Functions
132 These functions are the ones that a specific implementation must
138 Usage : $string = $obj->seq()
139 Function: Returns the sequence as a string of letters. The
140 case of the letters is left up to the implementer.
141 Suggested cases are upper case for proteins and lower case for
142 DNA sequence (IUPAC standard), but implementations are suggested to
143 keep an open mind about case (some users... want mixed case!)
151 $self->throw_not_implemented();
157 Usage : $substring = $obj->subseq(10,40);
158 Function: Returns the subseq from start to end, where the first base
159 is 1 and the number is inclusive, i.e. 1-2 are the first two
160 bases of the sequence.
162 Start cannot be larger than end but can be equal.
172 $self->throw_not_implemented();
178 Usage : $id_string = $obj->display_id();
179 Function: Returns the display id, also known as the common name of the Sequence
182 The semantics of this is that it is the most likely string
183 to be used as an identifier of the sequence, and likely to
184 have "human" readability. The id is equivalent to the ID
185 field of the GenBank/EMBL databanks and the id field of the
186 Swissprot/sptrembl database. In fasta format, the >(\S+) is
187 presumed to be the id, though some people overload the id
188 to embed other information. Bioperl does not use any
189 embedded information in the ID field, and people are
190 encouraged to use other mechanisms (accession field for
191 example, or extending the sequence object) to solve this.
193 Notice that $seq->id() maps to this function, mainly for
194 legacy/convenience reasons.
204 $self->throw_not_implemented();
208 =head2 accession_number
210 Title : accession_number
211 Usage : $unique_biological_key = $obj->accession_number;
212 Function: Returns the unique biological id for a sequence, commonly
213 called the accession_number. For sequences from established
214 databases, the implementors should try to use the correct
215 accession number. Notice that primary_id() provides the
216 unique id for the implemetation, allowing multiple objects
217 to have the same accession number in a particular implementation.
219 For sequences with no accession number, this method should return
228 sub accession_number
{
229 my ($self,@args) = @_;
230 $self->throw_not_implemented();
238 Usage : $unique_implementation_key = $obj->primary_id;
239 Function: Returns the unique id for this object in this
240 implementation. This allows implementations to manage their
241 own object ids in a way the implementaiton can control
242 clients can expect one id to map to one object.
244 For sequences with no accession number, this method should
245 return a stringified memory location.
255 my ($self,@args) = @_;
256 $self->throw_not_implemented();
263 Usage : if( $obj->can_call_new ) {
264 $newobj = $obj->new( %param );
266 Function: Can_call_new returns 1 or 0 depending
267 on whether an implementation allows new
268 constructor to be called. If a new constructor
269 is allowed, then it should take the followed hashed
272 $myobject->new( -seq => $sequence_as_string,
274 -accession_number => $accession
284 my ($self,@args) = @_;
286 # we default to 0 here
294 Usage : if( $obj->alphabet eq 'dna' ) { /Do Something/ }
295 Function: Returns the type of sequence being one of
296 'dna', 'rna' or 'protein'. This is case sensitive.
298 This is not called "type" because this would cause
299 upgrade problems from the 0.5 and earlier Seq objects.
301 Returns : A string either 'dna','rna','protein'. NB - the object must
302 make a call of the alphabet, if there is no alphabet specified it
312 $self->throw_not_implemented();
318 Usage : Deprecated. Use alphabet() instead.
323 my ($self,@args) = @_;
325 $self->warn("moltype: pre v1.0 method. Calling alphabet() instead...");
326 $self->alphabet(@args);
330 =head1 Optional Implementation Functions
332 The following functions rely on the above functions. An
333 implementing class does not need to provide these functions, as they
334 will be provided by this class, but is free to override these
337 The revcom(), trunc(), and translate() methods create new sequence
338 objects. They will call new() on the class of the sequence object
339 instance passed as argument, unless can_call_new() returns FALSE. In
340 the latter case a Bio::PrimarySeq object will be created. Implementors
341 which really want to control how objects are created (eg, for object
342 persistence over a database, or objects in a CORBA framework), they
343 are encouraged to override these methods
348 Usage : $rev = $seq->revcom()
349 Function: Produces a new Bio::PrimarySeqI implementing object which
350 is the reversed complement of the sequence. For protein
351 sequences this throws an exception of "Sequence is a
352 protein. Cannot revcom".
354 The id is the same id as the original sequence, and the
355 accession number is also indentical. If someone wants to
356 track that this sequence has be reversed, it needs to
357 define its own extensionsj.
359 To do an inplace edit of an object you can go:
361 $seq = $seq->revcom();
363 This of course, causes Perl to handle the garbage
364 collection of the old object, but it is roughly speaking as
365 efficient as an inplace edit.
367 Returns : A new (fresh) Bio::PrimarySeqI object
377 if($self->can_call_new()) {
378 $seqclass = ref($self);
380 $seqclass = 'Bio::PrimarySeq';
381 $self->_attempt_to_load_Seq();
383 my $out = $seqclass->new( '-seq' => $self->_revcom_from_string($self->seq, $self->alphabet),
384 '-is_circular' => $self->is_circular,
385 '-display_id' => $self->display_id,
386 '-accession_number' => $self->accession_number,
387 '-alphabet' => $self->alphabet,
388 '-desc' => $self->desc(),
389 '-verbose' => $self->verbose
395 sub _revcom_from_string
{
396 my ($self, $string, $alphabet) = @_;
398 # Check that reverse-complementing makes sense
399 if( $alphabet eq 'protein' ) {
400 $self->throw("Sequence is a protein. Cannot revcom.");
402 if( $alphabet ne 'dna' && $alphabet ne 'rna' ) {
403 my $msg = "Sequence is not dna or rna, but [$alphabet]. Attempting to revcom, ".
404 "but unsure if this is right.";
405 if( $self->can('warn') ) {
408 warn("[$self] $msg");
412 # If sequence is RNA, map to DNA (then map back later)
413 if( $alphabet eq 'rna' ) {
414 $string =~ tr/uU/tT/;
417 # Reverse-complement now
418 $string =~ tr/acgtrymkswhbvdnxACGTRYMKSWHBVDNX/tgcayrkmswdvbhnxTGCAYRKMSWDVBHNX/;
419 $string = CORE
::reverse $string;
421 # Map back RNA to DNA
422 if( $alphabet eq 'rna' ) {
423 $string =~ tr/tT/uU/;
433 Usage : $subseq = $myseq->trunc(10,100);
434 Function: Provides a truncation of a sequence.
435 Returns : A fresh Bio::PrimarySeqI implementing object.
436 Args : Two integers denoting first and last base of the sub-sequence.
442 my ($self,$start,$end) = @_;
445 if( defined $start && ref($start) &&
446 $start->isa('Bio::LocationI') ) {
447 $str = $self->subseq($start); # start is a location actually
449 $self->throw("trunc start,end -- there was no end for $start");
450 } elsif( $end < $start ) {
451 my $msg = "start [$start] is greater than end [$end]. \n".
452 "If you want to truncated and reverse complement, \n".
453 "you must call trunc followed by revcom. Sorry.";
456 $str = $self->subseq($start,$end);
460 if($self->can_call_new()) {
461 $seqclass = ref($self);
463 $seqclass = 'Bio::PrimarySeq';
464 $self->_attempt_to_load_Seq();
467 my $out = $seqclass->new( '-seq' => $str,
468 '-display_id' => $self->display_id,
469 '-accession_number' => $self->accession_number,
470 '-alphabet' => $self->alphabet,
471 '-desc' => $self->desc(),
472 '-verbose' => $self->verbose
481 Usage : $protein_seq_obj = $dna_seq_obj->translate
483 Or if you expect a complete coding sequence (CDS) translation,
484 with initiator at the beginning and terminator at the end:
486 $protein_seq_obj = $cds_seq_obj->translate(-complete => 1);
488 Or if you want translate() to find the first initiation
489 codon and return the corresponding protein:
491 $protein_seq_obj = $cds_seq_obj->translate(-orf => 1);
493 Function: Provides the translation of the DNA sequence using full
494 IUPAC ambiguities in DNA/RNA and amino acid codes.
496 The complete CDS translation is identical to EMBL/TREMBL
497 database translation. Note that the trailing terminator
498 character is removed before returning the translated protein
501 Note: if you set $dna_seq_obj->verbose(1) you will get a
502 warning if the first codon is not a valid initiator.
504 Returns : A Bio::PrimarySeqI implementing object
506 character for terminator, default '*'
508 character for unknown, default 'X'
510 positive integer frame shift (in bases), default 0
512 integer codon table id, default 1
514 boolean, if true, complete CDS is expected. default false
516 boolean, if true, codons which are incomplete are translated if a
517 suitable amino acid is found. For instance, if the incomplete
518 codon is 'GG', the completed codon is 'GGN', which is glycine
519 (G). Defaults to 'false'; setting '-complete' also makes this
522 boolean, throw exception if ORF not complete, default false
524 if 'longest', find longest ORF. other true value, find
527 optional L<Bio::Tools::CodonTable> object to use for
530 optional three-character string to force as initiation
531 codon (e.g. 'atg'). If unset, start codons are
532 determined by the CodonTable. Case insensitive.
534 optional positive integer offset for fuzzy locations.
535 if set, must be either 1, 2, or 3
539 The -start argument only applies when -orf is set to 1. By default all
540 initiation codons found in the given codon table are used but when
541 "start" is set to some codon this codon will be used exclusively as
542 the initiation codon. Note that the default codon table (NCBI
543 "Standard") has 3 initiation codons!
545 By default translate() translates termination codons to the some
546 character (default is *), both internal and trailing codons. Setting
547 "-complete" to 1 tells translate() to remove the trailing character.
549 -offset is used for seqfeatures which contain the the \codon_start tag
550 and can be set to 1, 2, or 3. This is the offset by which the
551 sequence translation starts relative to the first base of the feature
553 For details on codon tables used by translate() see L<Bio::Tools::CodonTable>.
555 Deprecated argument set (v. 1.5.1 and prior versions) where each argument is an
558 1: character for terminator (optional), defaults to '*'.
559 2: character for unknown amino acid (optional), defaults to 'X'.
560 3: frame (optional), valid values are 0, 1, 2, defaults to 0.
561 4: codon table id (optional), defaults to 1.
562 5: complete coding sequence expected, defaults to 0 (false).
563 6: boolean, throw exception if not complete coding sequence
564 (true), defaults to warning (false)
565 7: codontable, a custom Bio::Tools::CodonTable object (optional).
570 my ($self,@args) = @_;
571 my ($terminator, $unknown, $frame, $codonTableId, $complete,
572 $complete_codons, $throw, $codonTable, $orf, $start_codon, $offset);
574 ## new API with named parameters, post 1.5.1
575 if ($args[0] && $args[0] =~ /^-[A-Z]+/i) {
576 ($terminator, $unknown, $frame, $codonTableId, $complete,
577 $complete_codons, $throw,$codonTable, $orf, $start_codon, $offset) =
578 $self->_rearrange([qw(TERMINATOR
589 ## old API, 1.5.1 and preceding versions
591 ($terminator, $unknown, $frame, $codonTableId,
592 $complete, $throw, $codonTable, $offset) = @args;
595 ## Initialize termination codon, unknown codon, codon table id, frame
596 $terminator = '*' unless (defined($terminator) and $terminator ne '');
597 $unknown = "X" unless (defined($unknown) and $unknown ne '');
598 $frame = 0 unless (defined($frame) and $frame ne '');
599 $codonTableId = 1 unless (defined($codonTableId) and $codonTableId ne '');
600 $complete_codons ||= $complete || 0;
602 ## Get a CodonTable, error if custom CodonTable is invalid
604 $self->throw("Need a Bio::Tools::CodonTable object, not ". $codonTable)
605 unless $codonTable->isa('Bio::Tools::CodonTable');
608 # shouldn't this be cached? Seems wasteful to have a new instance
610 $codonTable = Bio
::Tools
::CodonTable
->new( -id
=> $codonTableId);
613 ## Error if alphabet is "protein"
614 $self->throw("Can't translate an amino acid sequence.") if
615 ($self->alphabet =~ /protein/i);
617 ## Error if -start parameter isn't a valid codon
619 $self->throw("Invalid start codon: $start_codon.") if
620 ( $start_codon !~ /^[A-Z]{3}$/i );
626 $self->throw("Offset must be 1, 2, or 3.") if
627 ( $offset !~ /^[123]$/ );
628 my ($start, $end) = ($offset, $self->length);
629 ($seq) = $self->subseq($start, $end);
631 ($seq) = $self->seq();
634 ## ignore frame if an ORF is supposed to be found
636 my ($orf_region) = $self->_find_orfs_nucleotide( $seq, $codonTable, $start_codon, $orf eq 'longest' ?
0 : 'first_only' );
637 $seq = $self->_orf_sequence( $seq, $orf_region );
639 ## use frame, error if frame is not 0, 1 or 2
640 $self->throw("Valid values for frame are 0, 1, or 2, not $frame.")
641 unless ($frame == 0 or $frame == 1 or $frame == 2);
642 $seq = substr($seq,$frame);
646 my $output = $codonTable->translate($seq, $complete_codons);
647 # Use user-input terminator/unknown
648 $output =~ s/\*/$terminator/g;
649 $output =~ s/X/$unknown/g;
651 ## Only if we are expecting to translate a complete coding region
653 my $id = $self->display_id;
654 # remove the terminator character
655 if( substr($output,-1,1) eq $terminator ) {
658 $throw && $self->throw("Seq [$id]: Not using a valid terminator codon!");
659 $self->warn("Seq [$id]: Not using a valid terminator codon!");
661 # test if there are terminator characters inside the protein sequence!
662 if ($output =~ /\Q$terminator\E/) {
664 $throw && $self->throw("Seq [$id]: Terminator codon inside CDS!");
665 $self->warn("Seq [$id]: Terminator codon inside CDS!");
667 # if the initiator codon is not ATG, the amino acid needs to be changed to M
668 if ( substr($output,0,1) ne 'M' ) {
669 if ($codonTable->is_start_codon(substr($seq, 0, 3)) ) {
670 $output = 'M'. substr($output,1);
672 $self->throw("Seq [$id]: Not using a valid initiator codon!");
674 $self->warn("Seq [$id]: Not using a valid initiator codon!");
680 if ($self->can_call_new()) {
681 $seqclass = ref($self);
683 $seqclass = 'Bio::PrimarySeq';
684 $self->_attempt_to_load_Seq();
686 my $out = $seqclass->new( '-seq' => $output,
687 '-display_id' => $self->display_id,
688 '-accession_number' => $self->accession_number,
689 # is there anything wrong with retaining the
691 '-desc' => $self->desc(),
692 '-alphabet' => 'protein',
693 '-verbose' => $self->verbose
701 Usage : $xseq = $seq->transcribe
702 Function: Convert base T to base U
703 Returns : PrimarySeqI object of alphabet 'rna' or
704 undef if $seq->alphabet ne 'dna'
711 return unless $self->alphabet eq 'dna';
715 if ($self->can_call_new) {
718 $class = 'Bio::PrimarySeq';
719 $self->_attempt_to_load_Seq;
721 my $desc = $self->desc || '';
724 '-alphabet' => 'rna',
725 '-display_id' => $self->display_id,
726 '-accession_number' => $self->accession_number,
727 '-desc' => "${desc}[TRANSCRIBED]",
728 '-verbose' => $self->verbose
732 =head2 rev_transcribe()
734 Title : rev_transcribe
735 Usage : $rtseq = $seq->rev_transcribe
736 Function: Convert base U to base T
737 Returns : PrimarySeqI object of alphabet 'dna' or
738 undef if $seq->alphabet ne 'rna'
745 return unless $self->alphabet eq 'rna';
749 if ($self->can_call_new) {
752 $class = 'Bio::PrimarySeq';
753 $self->_attempt_to_load_Seq;
757 '-alphabet' => 'dna',
758 '-display_id' => $self->display_id,
759 '-accession_number' => $self->accession_number,
760 '-desc' => $self->desc . "[REVERSE TRANSCRIBED]",
761 '-verbose' => $self->verbose
768 Usage : $id = $seq->id()
769 Function: ID of the sequence. This should normally be (and actually is in
770 the implementation provided here) just a synonym for display_id().
779 return $self->display_id();
786 Usage : $len = $seq->length()
788 Returns : Integer representing the length of the sequence.
795 $self->throw_not_implemented();
801 Usage : $seq->desc($newval);
802 $description = $seq->desc();
803 Function: Get/set description text for a seq object
804 Returns : Value of desc
805 Args : newvalue (optional)
810 shift->throw_not_implemented();
817 Usage : if( $obj->is_circular) { /Do Something/ }
818 Function: Returns true if the molecule is circular
819 Returns : Boolean value
825 shift->throw_not_implemented;
828 =head1 Private functions
830 These are some private functions for the PrimarySeqI interface. You do not
831 need to implement these functions
833 =head2 _find_orfs_nucleotide
835 Title : _find_orfs_nucleotide
837 Function: Finds ORF starting at 1st initiation codon in nucleotide sequence.
838 The ORF is not required to have a termination codon.
840 Returns : a list of string coordinates of ORF locations (0-based half-open),
841 sorted descending by length (so that the longest is first)
842 as: [ start, end, frame, length ], [ start, end, frame, length ], ...
843 Args : Nucleotide sequence,
845 (optional) alternative initiation codon (e.g. 'ATA'),
846 (optional) boolean that, if true, stops after finding the
851 sub _find_orfs_nucleotide
{
852 my ( $self, $sequence, $codon_table, $start_codon, $first_only ) = @_;
853 $sequence = uc $sequence;
854 $start_codon = uc $start_codon if $start_codon;
856 my $is_start = $start_codon
857 ?
sub { shift eq $start_codon }
858 : sub { $codon_table->is_start_codon( shift ) };
860 # stores the begin index of the currently-running ORF in each
862 my @current_orf_start = (-1,-1,-1);
864 #< stores coordinates of longest observed orf (so far) in each
868 # go through each base of the sequence, and each reading frame for each base
869 my $seqlen = CORE
::length $sequence;
870 for( my $j = 0; $j <= $seqlen-3; $j++ ) {
873 my $this_codon = substr( $sequence, $j, 3 );
875 # if in an orf and this is either a stop codon or the last in-frame codon in the string
876 if ( $current_orf_start[$frame] >= 0 ) {
877 if ( $codon_table->is_ter_codon( $this_codon ) ||( my $is_last_codon_in_frame = ($j >= $seqlen-5)) ) {
878 # record ORF start, end (half-open), length, and frame
879 my @this_orf = ( $current_orf_start[$frame], $j+3, undef, $frame );
880 my $this_orf_length = $this_orf[2] = ( $this_orf[1] - $this_orf[0] );
882 $self->warn( "Translating partial ORF "
883 .$self->_truncate_seq( $self->_orf_sequence( $sequence, \
@this_orf ))
884 .' from end of nucleotide sequence'
886 if $first_only && $is_last_codon_in_frame;
888 return \
@this_orf if $first_only;
889 push @orfs, \
@this_orf;
890 $current_orf_start[$frame] = -1;
893 # if this is a start codon
894 elsif ( $is_start->($this_codon) ) {
895 $current_orf_start[$frame] = $j;
899 return sort { $b->[2] <=> $a->[2] } @orfs;
903 my ($self,$seq) = @_;
904 return CORE
::length($seq) > 200 ?
substr($seq,0,50).'...'.substr($seq,-50) : $seq;
907 my ($self, $seq, $orf ) = @_;
908 return '' unless $orf;
909 return substr( $seq, $orf->[0], $orf->[2] )
912 =head2 _attempt_to_load_Seq
914 Title : _attempt_to_load_Seq
924 sub _attempt_to_load_Seq
{
927 if( $main::{'Bio::PrimarySeq'} ) {
931 require Bio
::PrimarySeq
;
934 my $text = "Bio::PrimarySeq could not be loaded for [$self]\n".
935 "This indicates that you are using Bio::PrimarySeqI ".
936 "without Bio::PrimarySeq loaded or without providing a ".
937 "complete implementation.\nThe most likely problem is that there ".
938 "has been a misconfiguration of the bioperl environment\n".
939 "Actual exception:\n\n";
940 $self->throw("$text$@\n");