// Sequence data class
-//! Attach annotation information to a sequence track
-struct annot
+/* The way that motifs are found currently doesn't really
+ * indicate that the match was a reverse compliment
+ */
+struct motif
{
- annot();
- annot(int begin, int end, std::string type, std::string name);
- ~annot();
-
+ motif();
+ //motif(int begin, int end, std::string type, std::string name);
+ //! this constructor is for when we're adding motifs to our annotations
+ motif(int begin, std::string motif);
+ ~motif();
+
int begin;
int end;
std::string type;
std::string name;
+ std::string sequence;
+
+ friend bool operator==(const motif& left, const motif& right);
- friend bool operator==(const annot& left, const annot& right);
-private:
// boost::serialization support
+private:
friend class boost::serialization::access;
template<class Archive>
void serialize(Archive& ar, const unsigned int /*version*/) {
ar & BOOST_SERIALIZATION_NVP(end);
ar & BOOST_SERIALIZATION_NVP(type);
ar & BOOST_SERIALIZATION_NVP(name);
- }
-};
-BOOST_CLASS_EXPORT(annot);
-
-
-/* The way that motifs are found currently doesn't really
- * indicate that the match was a reverse compliment
- */
-struct motif : public annot
-{
- std::string sequence;
-
- motif() : annot(), sequence("") {};
- //! this constructor is for when we're adding motifs to our annotations
- motif(int begin, std::string motif);
- ~motif();
-
- // boost::serialization support
-private:
- friend class boost::serialization::access;
- template<class Archive>
- void serialize(Archive& ar, const unsigned int /*version*/) {
- ar & BOOST_SERIALIZATION_BASE_OBJECT_NVP(annot);
ar & BOOST_SERIALIZATION_NVP(sequence);
}
};
BOOST_CLASS_EXPORT(motif);
+class Sequence;
+typedef boost::shared_ptr<Sequence> SequenceRef;
//! sequence track for mussa.
class Sequence
typedef SeqString::const_reference const_reference;
typedef SeqString::size_type size_type;
static const size_type npos = SeqString::npos;
- enum strand_type { UnknownStrand, PlusStrand, MinusStrand, BothStrand };
- enum alphabet_ref { reduced_dna_alphabet, reduced_rna_alphabet, reduced_nucleic_alphabet,
- nucleic_alphabet, protein_alphabet };
+
+ typedef std::list<motif> MotifList;
+ typedef boost::shared_ptr<MotifList> MotifListRef;
- Sequence(alphabet_ref a = reduced_nucleic_alphabet);
- Sequence(const char* seq, alphabet_ref a = reduced_nucleic_alphabet);
- Sequence(const std::string& seq, alphabet_ref a = reduced_nucleic_alphabet);
+ Sequence(AlphabetRef a = reduced_dna_alphabet);
+ Sequence(const char* seq,
+ AlphabetRef a = reduced_dna_alphabet,
+ SeqSpan::strand_type strand = SeqSpan::PlusStrand);
+ Sequence(const std::string& seq,
+ AlphabetRef a = reduced_dna_alphabet,
+ SeqSpan::strand_type strand = SeqSpan::PlusStrand);
+ //! make a new sequence, with the same SeqSpan
Sequence(const Sequence& seq);
+ //! make a new sequence, with the same SeqSpan
Sequence(const Sequence *);
- Sequence(const SeqSpanRef&, alphabet_ref a = reduced_nucleic_alphabet);
+ //! Make a new sequence using a copy of SeqSpan
+ Sequence(const SequenceRef);
+ Sequence(const SeqSpanRef&);
~Sequence();
//! assignment to constant sequences
Sequence &operator=(const Sequence&);
//! set sequence to a (sub)string containing nothing but AGCTN
void set_filtered_sequence(const std::string& seq,
- alphabet_ref a,
+ AlphabetRef a=reduced_dna_alphabet,
size_type start=0,
size_type count=npos,
- strand_type strand=UnknownStrand);
+ SeqSpan::strand_type strand=SeqSpan::PlusStrand);
//! retrive element at specific position
const_reference at(size_type i) const { return seq->at(i); }
size_type stop() const { return seq->parentStop(); }
//! return a subsequence, copying over any appropriate annotation
- Sequence subseq(size_type start=0, size_type count = npos) const;
+ Sequence subseq(size_type start=0,
+ size_type count = npos,
+ SeqSpan::strand_type strand = SeqSpan::SameStrand) const;
//! reverse a character
std::string create_reverse_map() const;
//! return a reverse compliment (this needs to be improved?)
Sequence rev_comp() const;
//! set sequence (filtered)
- void set_sequence(const std::string &, alphabet_ref);
+ void set_sequence(const std::string &, AlphabetRef);
//! get sequence
std::string get_sequence() const;
//! set species name
std::string get_name() const;
//! return a reference to whichever alphabet we're currently representing
const Alphabet& get_alphabet() const;
- //! return a reference to whichever alphabet we're currently representing
- const Alphabet& get_alphabet(alphabet_ref) const;
//! load sequence from fasta file using the sequences current alphabet
void load_fasta(const boost::filesystem::path file_path, int seq_num=1,
//! \throw sequence_empty_error
//! \throw sequence_empty_file_error
void load_fasta(const boost::filesystem::path file_path,
- alphabet_ref a,
+ AlphabetRef a,
int seq_num=1,
int start_index=0, int end_index=0);
void load_fasta(std::istream& file,
//! \throw sequence_empty_error
//! \throw sequence_empty_file_error
void load_fasta(std::istream& file,
- alphabet_ref a,
+ AlphabetRef a,
int seq_num=1,
int start_index=0, int end_index=0);
//! load sequence annotations
*/
void parse_annot(std::string data, int start_index=0, int end_index=0);
//! add an annotation to our list of annotations
- void add_annotation(const annot& a);
- const std::list<annot>& annotations() const;
- const std::list<motif>& motifs() const;
+ void add_annotation(const SeqSpanRef a);
+ //! add an annotation using tristan's mussa file paramenters
+ void add_annotation(std::string name, std::string type, size_type start, size_type stop);
+ //! create an initialized annotation with the "standard" types.
+ SeqSpanRef make_annotation(std::string name, std::string type, size_type start, size_type stop) const;
+ const SeqSpanRefList& annotations() const;
+
+ const MotifList& motifs() const;
//! add a motif to our list of motifs
void add_motif(const Sequence& a_motif);
//! annotate the current sequence with other sequences
void find_sequences(std::list<Sequence>::iterator start,
std::list<Sequence>::iterator end);
+ SeqSpanRef seqspan() { return seq; }
void save(boost::filesystem::fstream &save_file);
- void load_museq(boost::filesystem::path load_file_path, int seq_num);
+ //void load_museq(boost::filesystem::path load_file_path, int seq_num);
+ static SequenceRef load_museq(boost::filesystem::fstream& load_file);
protected:
SeqSpanRef seq;
- //! which alphabet we're using
- alphabet_ref alphabet;
- //! strand orientation
- strand_type strand;
//! fasta header
std::string header;
//! species name
std::string species;
- //! store our oldstyle annotations
- std::list<annot> annots;
+ //! store annotation regions
+ SeqSpanRefListRef annotation_list;
//! a seperate list for motifs since we're currently not saving them
- std::list<motif> motif_list;
+ MotifListRef motif_list;
//! copy over all our annotation children
void copy_children(Sequence &, size_type start, size_type count) const;
template<class Archive>
void serialize(Archive& ar, const unsigned int /*version*/) {
ar & BOOST_SERIALIZATION_NVP(seq);
- ar & BOOST_SERIALIZATION_NVP(alphabet);
- ar & BOOST_SERIALIZATION_NVP(strand);
ar & BOOST_SERIALIZATION_NVP(header);
ar & BOOST_SERIALIZATION_NVP(species);
- ar & BOOST_SERIALIZATION_NVP(annots);
+ ar & BOOST_SERIALIZATION_NVP(annotation_list);
ar & BOOST_SERIALIZATION_NVP(motif_list);
}
};