gbseq.h

Go to the documentation of this file.

//file gbmodel.h
//a generalized genbank entry model, for both DNA and Protein
// right now this is mainly used for processing protein entries

#ifndef GBMODEL_H
#define GBMODEL_H

#include <string>
#include <vector>
#include <iostream>
#include "gbfn.h"
//#include "ref.h"
//#include "Reference.h"
#include "Refreader.h"
#include "strformat.h"
#include "pfeature.h"

using namespace std;

class feature;  // this one not needed

//enum Moltype { genomic, protein, mRNA, unknown };
//enum fileType { dna, protein };

class gbseq {
        public:
                //gbseq() : seqLength(-1), _moltype(unknown)  { line.reserve(84); sequence.reserve(5000); }
                gbseq() : seqLength(-1), features(), seg(0), segtotal(0), orgacronym()  
                { line.reserve(84); sequence.reserve(5000); }

                virtual ~gbseq() { for (int i=0; i<references.size(); i++) delete references[i]; }

                /* Read one record.  Return true if not end of file
                 * It will remove the ending period of certain fields:
                 *      Definition, Author, taxonomy,   Keyword
                 */
                virtual bool read(istream &ins);
                // add snp file
                virtual void writeAce(ostream &ous, ostream &sub, ostream &snp) = 0;

                void writeSpecies(ostream& ous);
                 
                int getLength() const; 
                int getSeqlen() const { return sequence.length(); }

                string getDate() const { return locus.substr(56, 11); }
                // clear the base part, derived class have to clear
                // additional members.
                void clear();  // for repeated read this must be called
                string getKey() const { return accession[0]; }
                string getLocusName() const { return firstword(locus); }
                string getSegmentLocus() const;

                string getType() const { string tmp= locus.substr(35,6); trim(tmp); return tmp; }
                string getMolType() const;  // from the source feature
                // Moltype getMoltype() const { return _moltype; }
                // void setMoltype(Moltype mtyp) { _moltype = mtyp; }
                string getOrgAcronym() const;
                string getOrganism() const { return organism; }
                // feature exist at a particular location(b,e)
                bool hasFeature(const string &f, int b, int e) const;
                bool isSegment() const { return seg>0; }

                static const int VAL_START = 12;  // value field start index
                /*
                 * longText from GB are not exactly the same, they are very 
                 * similiar being generated by computer.
                static map<string, int> lt2id;
                static void setLongtextid(int i) { longtextid = i; }
                static int nextLongtextid() { return longtextid++; }  // run the sequence
                static int currLongtextid() { return longtextid; }
                static void loadLongtext(string &inf);
                */

                static void init();
                static void loadOrgmap(const string &file);
                static void dumpOrgmap(const string &file);
                //static getOrgKey(const string& org);

        protected:
                //static int longtextid;

                // raw data then produce secondary data
                string locus;  // the whole locus line
                mutable int seqLength;
                //mutable Moltype _moltype;  // this one is redundant with the locus line
                // future version should consolidate this one
/*
Positions  Contents
---------  --------
01-05      'LOCUS'
06-12      spaces
13-28      Locus name
29-29      space
30-40      Length of sequence, right-justified
41-41      space
42-43      bp
44-44      space
45-47      spaces, ss- (single-stranded), ds- (double-stranded), or
           ms- (mixed-stranded)
48-53      NA, DNA, RNA, tRNA (transfer RNA), rRNA (ribosomal RNA), 
           mRNA (messenger RNA), uRNA (small nuclear RNA), snRNA,
           snoRNA. Left justified.
54-55      space
56-63      'linear' followed by two spaces, or 'circular'
64-64      space
65-67      The division code (see Section 3.3)
68-68      space
69-79      Date, in the form dd-MMM-yyyy (e.g., 15-MAR-1991)
*/
                string definition;
                vector<string> accession; // one or more
                string version[2];        // version GI:int_id
                string dbsource;          // only in protein record
                string keywords;
                // organism information
                int seg, segtotal;   // segment # and total, optional
                string source;
           string organism;
                string taxonomy;    // the taxon tree branch leading to root

      //vector<Reference> references;
      vector<Ref*> references;
      string comment;               // optional
                vector<feature> features;
                string sequence;  // could be DNA or Protein

                /* buffer for performance */
                string line;
                mutable string orgacronym; // organism acronym == key

                static map<string,string> orgmap;  // maps organism name to key
                static set<string> orgacronyms;       // assistance for search
                static set<string> taxons;   // all taxons, including species
};

class gbprtseq : public gbseq {
        public:
                bool read(istream &ins);
                //void writeAce(ostream &ous, ostream &sub, ostream &aut);
                // the snp seems to be useless for protein object
                void writeAce(ostream &ous, ostream &sub, ostream &snp);
};

class gbdnaseq : public gbseq {
        public:
                gbdnaseq() : gbseq(), subcnt(1) {}
                bool read(istream &ins);
                //void writeAce(ostream &ous, ostream &sub, ostream &aut);
                void writeAce(ostream &ous, ostream &sub, ostream &snp);
                void clear(); // only clear the added part
                string getStrand() const { return locus.substr(32, 3); } // ds- by default, ss-, or ms-
                int nextsub() const { return subcnt++; }
                int currsub() const { return subcnt; }

        private:
                int A, C, G, T, O;
                mutable int subcnt;  // for all subsequences
};

#endif