#include <boost/filesystem/fstream.hpp>
#include <boost/serialization/base_object.hpp>
+#include <boost/serialization/export.hpp>
#include <boost/serialization/list.hpp>
#include <boost/serialization/nvp.hpp>
#include <boost/serialization/string.hpp>
+#include <boost/serialization/shared_ptr.hpp>
#include <boost/serialization/utility.hpp>
-#include <boost/serialization/export.hpp>
+#include <boost/serialization/version.hpp>
+#include <boost/serialization/vector.hpp>
+
+#include <boost/shared_ptr.hpp>
+#include <boost/enable_shared_from_this.hpp>
-#include <list>
-#include <string>
-#include <vector>
#include <iostream>
+#include "alphabet.hpp"
+#include "seq.hpp"
+#include "seq_span.hpp"
+
// Sequence data class
//! Attach annotation information to a sequence track
};
BOOST_CLASS_EXPORT(motif);
+
//! sequence track for mussa.
class Sequence
{
public:
- typedef std::string::difference_type difference_type;
- typedef std::string::iterator iterator;
- typedef std::string::const_iterator const_iterator;
- typedef std::string::reference reference;
- typedef std::string::const_reference const_reference;
- typedef std::string::size_type size_type;
- static const size_type npos = std::string::npos;
-
- // some standard dna alphabets
- // Include nl (\012), and cr (\015) to make sequence parsing eol
- // convention independent.
-
- static const std::string dna_alphabet;
- static const std::string rna_alphabet;
- //! this is the general iupac alphabet for nucleotides
- static const std::string nucleic_iupac_alphabet;
- //! the protein alphabet
- static const std::string protein_alphabet;
-
- Sequence();
- ~Sequence();
- Sequence(const char* seq);
- Sequence(const std::string& seq);
+ typedef SeqString::value_type value_type;
+ typedef SeqString::difference_type difference_type;
+ typedef SeqString::iterator iterator;
+ typedef SeqString::reverse_iterator reverse_iterator;
+ typedef SeqString::const_iterator const_iterator;
+ typedef SeqString::const_reverse_iterator const_reverse_iterator;
+ typedef SeqString::reference reference;
+ 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 };
+
+ Sequence(AlphabetRef a = reduced_nucleic_alphabet);
+ Sequence(const char* seq,
+ AlphabetRef a = reduced_nucleic_alphabet);
+ Sequence(const std::string& seq,
+ AlphabetRef a = reduced_nucleic_alphabet);
Sequence(const Sequence& seq);
+ Sequence(const Sequence *);
+ Sequence(const SeqSpanRef&);
+ ~Sequence();
//! assignment to constant sequences
Sequence &operator=(const Sequence&);
- // dangerous since they create large copies
- //operator std::string();
- //operator std::string() const;
-
friend std::ostream& operator<<(std::ostream&, const Sequence&);
friend bool operator<(const Sequence&, const Sequence&);
friend bool operator==(const Sequence&, const Sequence&);
+ friend bool operator!=(const Sequence&, const Sequence&);
const_reference operator[](size_type) const;
//! set sequence to a (sub)string containing nothing but AGCTN
- void set_filtered_sequence(const std::string& seq,
- std::string::size_type start=0,
- std::string::size_type count=0);
+ void set_filtered_sequence(const std::string& seq,
+ AlphabetRef a,
+ size_type start=0,
+ size_type count=npos,
+ strand_type strand=UnknownStrand);
//! retrive element at specific position
- const_reference at(size_type n) const;
+ const_reference at(size_type i) const { return seq->at(i); }
//! clear the sequence and its annotations
void clear();
+ //! return a non-null terminated c pointer to the sequence data
+ const char *data() const { return seq->data(); }
//! forward iterator
- iterator begin();
- const_iterator begin() const;
- iterator end();
- const_iterator end() const;
+ const_iterator begin() const { return seq->begin(); }
+ //! last iterator
+ const_iterator end() const { return seq->end(); }
//! is our sequence empty?
- bool empty() const;
+ bool empty() const { return (seq) ? seq->empty() : true ; }
+ //! find first
+ size_type find_first_not_of(const std::string& q, size_type index=0) { return seq->find_first_not_of(q, index); }
//! how many base pairs are there in our sequence
- size_type size() const;
+ size_type size() const { return (seq) ? seq->size() : 0; }
//! alias for size (used by string)
- size_type length() const;
+ size_type length() const { return size(); }
+ //! reverse iterator
+ const_reverse_iterator rbegin() const { return seq->rbegin(); }
+ //! reverse end iterator
+ const_reverse_iterator rend() const { return seq->rend(); }
+ //! is our sequence empty?
+ //! start position relative to "base" sequence
+ size_type start() const { return seq->parentStart(); }
+ //! one past the last position relative to "base" sequence
+ size_type stop() const { return seq->parentStop(); }
//! return a subsequence, copying over any appropriate annotation
- Sequence subseq(int start=0, int count = std::string::npos) const;
- //! return a reverse compliment
- std::string rev_comp() const;
+ Sequence subseq(size_type start=0, size_type count = npos) 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 &);
+ void set_sequence(const std::string &, AlphabetRef);
//! get sequence
std::string get_sequence() const;
//! set species name
std::string get_fasta_header() const;
//! get name (will return the first non-empty, of fasta_header, species)
std::string get_name() const;
+ //! return a reference to whichever alphabet we're currently representing
+ const Alphabet& get_alphabet() const;
+ //! load sequence from fasta file using the sequences current alphabet
+ void load_fasta(const boost::filesystem::path file_path, int seq_num=1,
+ int start_index=0, int end_index=0);
//! load sequence AGCT from fasta file
//! \throw mussa_load_error
//! \throw sequence_empty_error
//! \throw sequence_empty_file_error
- void load_fasta(const boost::filesystem::path file_path, int seq_num=1,
- int start_index=0, int end_index=0);
+ void load_fasta(const boost::filesystem::path file_path,
+ AlphabetRef a,
+ int seq_num=1,
+ int start_index=0, int end_index=0);
+ void load_fasta(std::istream& file,
+ int seq_num=1, int start_index=0, int end_index=0);
//! load sequence from stream
//! \throw mussa_load_error
//! \throw sequence_empty_error
//! \throw sequence_empty_file_error
- void load_fasta(std::iostream& file, int seq_num=1,
- int start_index=0, int end_index=0);
+ void load_fasta(std::istream& file,
+ AlphabetRef a,
+ int seq_num=1,
+ int start_index=0, int end_index=0);
//! load sequence annotations
//! \throws mussa_load_error
void load_annot(const boost::filesystem::path file_path, int start_index, int end_index);
//! load sequence annotations
//! \throws mussa_load_error
void load_annot(std::fstream& data_stream, int start_index, int end_index);
- bool parse_annot(std::string data, int start_index=0, int end_index=0);
+ //! parse annotation file
+ /*! \throws annotation_load_error
+ */
+ 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;
//! add a motif to our list of motifs
- //! \throws motif_normalize_error if there's something wrong with a_motif
void add_motif(const Sequence& a_motif);
//! clear our list of found motifs
void clear_motifs();
//! search a sequence for a_motif
//! \throws motif_normalize_error if there's something wrong with a_motif
- std::vector<int> find_motif(const std::string& a_motif) const;
- //! search a sequence for a_motif
- //! \throws motif_normalize_error if there's something wrong with a_motif
- std::vector<int> find_motif(const Sequence& a_motif) const;
- //! convert IUPAC symbols to upperase
- //! \throws motif_normalize_error if there is an invalid symbol
- static std::string motif_normalize(const std::string& a_motif);
-
+ std::vector<int> find_motif(const Sequence& a_motif) const;
//! annotate the current sequence with other sequences
void find_sequences(std::list<Sequence>::iterator start,
std::list<Sequence>::iterator end);
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);
-private:
- std::string seq;
+protected:
+ SeqSpanRef seq;
+ //! strand orientation
+ strand_type strand;
+ //! fasta header
std::string header;
+ //! species name
std::string species;
+ //! store our oldstyle annotations
std::list<annot> annots;
//! a seperate list for motifs since we're currently not saving them
std::list<motif> motif_list;
- void motif_scan(std::string a_motif, std::vector<int> * motif_match_starts) const;
+ //! copy over all our annotation children
+ void copy_children(Sequence &, size_type start, size_type count) const;
+
+ void motif_scan(const Sequence& a_motif, std::vector<int> * motif_match_starts) const;
std::string rc_motif(std::string a_motif) const;
//! look for a string sequence type and and it to an annotation list
void add_string_annotation(std::string a_seq, std::string name);
template<class Archive>
void serialize(Archive& ar, const unsigned int /*version*/) {
ar & BOOST_SERIALIZATION_NVP(seq);
+ ar & BOOST_SERIALIZATION_NVP(strand);
ar & BOOST_SERIALIZATION_NVP(header);
ar & BOOST_SERIALIZATION_NVP(species);
ar & BOOST_SERIALIZATION_NVP(annots);
}
};
BOOST_CLASS_EXPORT(Sequence);
-
#endif
projects / mussa.git / blobdiff