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 // ----------------------------------------
17 #include <boost/filesystem/path.hpp>
18 #include <boost/filesystem/fstream.hpp>
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);
65 //! look for a string sequence type and and it to an annotation list
66 void add_string_annotation(std::string a_seq, std::string name);
69 typedef std::string::iterator iterator;
70 typedef std::string::const_iterator const_iterator;
71 typedef std::string::size_type size_type;
74 Sequence(std::string seq);
75 //! assignment to constant sequences
76 Sequence &operator=(const Sequence&);
77 Sequence &operator=(const std::string &);
78 char operator[](int) const;
79 friend std::ostream& operator<<(std::ostream& out, const Sequence& seq);
81 //! set sequence to a (sub)string containing nothing but AGCTN
82 void set_filtered_sequence(const std::string& seq,
83 std::string::size_type start=0,
84 std::string::size_type count=0);
86 //! load sequence AGCT from fasta file
87 //! \throw mussa_load_error
88 //! \throw sequence_empty_error
89 //! \throw sequence_empty_file_error
90 void load_fasta(const boost::filesystem::path file_path, int seq_num=1,
91 int start_index=0, int end_index=0);
92 //! load sequence from stream
93 //! \throw mussa_load_error
94 //! \throw sequence_empty_error
95 //! \throw sequence_empty_file_error
96 void load_fasta(std::iostream& file, int seq_num=1,
97 int start_index=0, int end_index=0);
98 //! load sequence annotations
99 //! \throws mussa_load_error
100 void load_annot(const boost::filesystem::path file_path, int start_index, int end_index);
101 //! load sequence annotations
102 //! \throws mussa_load_error
103 void load_annot(std::fstream& data_stream, int start_index, int end_index);
104 void parse_annot(std::string data, int start_index, int end_index);
105 const std::list<annot>& annotations() const;
106 const std::list<motif>& motifs() const;
107 const std::string& get_species() const;
109 // simple access functions
110 void set_seq(const std::string& a_seq);
111 const std::string& get_seq() const;
112 const char *c_seq() const;
113 std::string subseq(int start, int count) const;
114 std::string rev_comp() const;
116 // string-like functions
118 const_iterator begin() const;
120 const_iterator end() const;
122 //! alias for size, (included as this is much like a string)
123 std::string::size_type length() const;
124 //! the number of base pairs in this sequence
125 std::string::size_type size() const;
128 void set_header(std::string header);
129 std::string get_header() const;
130 //! add a motif to our list of motifs
131 //! \throws motif_normalize_error if there's something wrong with a_motif
132 void add_motif(std::string a_motif);
133 //! clear our list of found motifs
135 //! search a sequence for a_motif
136 //! \throws motif_normalize_error if there's something wrong with a_motif
137 std::vector<int> find_motif(std::string a_motif);
138 //! convert IUPAC symbols to upperase
139 //! \throws motif_normalize_error if there is an invalid symbol
140 static std::string motif_normalize(std::string a_motif);
142 //! annotate the current sequence with other sequences
143 void find_sequences(std::list<Sequence>::iterator start,
144 std::list<Sequence>::iterator end);
146 void save(boost::filesystem::fstream &save_file);
147 void load_museq(boost::filesystem::path load_file_path, int seq_num);