1 #ifndef _MUSSA_SEQUENCE_H_
2 #define _MUSSA_SEQUENCE_H_
3 // This file is part of the Mussa source distribution.
4 // http://mussa.caltech.edu/
5 // Contact author: Tristan De Buysscher, tristan@caltech.edu
7 // This program and all associated source code files are Copyright (C) 2005
8 // the California Institute of Technology, Pasadena, CA, 91125 USA. It is
9 // under the GNU Public License; please see the included LICENSE.txt
10 // file for more information, or contact Tristan directly.
13 // ----------------------------------------
14 // ---------- sequence.hh -----------
15 // ----------------------------------------
24 // Sequence data class
26 //! Attach annotation information to a sequence track
30 annot(int start, int end, std::string type, std::string name);
38 /* The way that motifs are found currently doesn't really
39 * indicate that the match was a reverse compliment
41 struct motif : public annot
45 //! this constructor is for when we're adding motifs to our annotations
46 motif(int start, std::string motif);
49 //! sequence track for mussa.
52 friend class ConnView;
59 std::list<annot> annots;
60 //! a seperate list for motifs since we're currently not saving them
61 std::list<motif> motif_list;
63 void motif_scan(std::string a_motif, std::vector<int> * motif_match_starts);
64 std::string rc_motif(std::string a_motif);
66 typedef std::string::iterator iterator;
67 typedef std::string::const_iterator const_iterator;
68 typedef std::string::size_type size_type;
71 Sequence(std::string seq);
72 //! assignment to constant sequences
73 Sequence &operator=(const Sequence&);
74 Sequence &operator=(const std::string &);
75 friend std::ostream& operator<<(std::ostream& out, const Sequence& seq);
77 //! set sequence to a (sub)string containing nothing but AGCTN
78 void set_filtered_sequence(const std::string& seq,
79 std::string::size_type start=0,
80 std::string::size_type count=0);
82 //! load sequence AGCT from fasta file
83 /*! \throws mussa_load_error
85 void load_fasta(const std::string file_path, int seq_num=1,
86 int start_index=0, int end_index=0);
87 //! load sequence annotations
88 /*! \throws mussa_load_error
90 void load_annot(const std::string file_path, int start_index, int end_index);
91 const std::list<annot>& annotations() const;
92 const std::list<motif>& motifs() const;
94 // simple access functions
95 void set_seq(const std::string& a_seq);
96 const std::string& get_seq() const;
97 const char *c_seq() const;
98 std::string subseq(int start, int end) const;
99 std::string rev_comp() const;
101 // string-like functions
103 const_iterator begin() const;
105 const_iterator end() const;
107 //! alias for size, (included as this is much like a string)
108 std::string::size_type length() const;
109 //! the number of base pairs in this sequence
110 std::string::size_type size() const;
113 const std::string& get_header() const;
114 //! add a motif to our list of motifs
115 /*! \throws motif_normalize_error if there's something wrong with a_motif
117 void add_motif(std::string a_motif);
118 //! clear our list of found motifs
120 //! search a sequence for a_motif
121 /*! \throws motif_normalize_error if there's something wrong with a_motif
123 std::vector<int> find_motif(std::string a_motif);
124 //! convert IUPAC symbols to upperase
125 /*! \throws motif_normalize_error if there is an invalid symbol
127 static std::string motif_normalize(std::string a_motif);
128 void save(std::fstream &save_file);
129 void load_museq(std::string load_file_path, int seq_num);