BioResidue.h

Go to the documentation of this file.

/****************************************************************************
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
The BioBhasha : The Biologist's Programming Language 
Version 1.0 (19th December 2001)
Prasad, B.V.L.S.
Contact: burrashiva@yahoo.com
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
*****************************************************************************/
#ifndef BIORESIDUE_H
#define BIORESIDUE_H

#include "BioAtom.h"
#include "BioAminoAcidLibrary.h"

/*****************************************************************************
 *
 * COMMENTARY on Each Class/Concept: Hows and Whys :
 *
 * BioResidue:
 *              A group of Atoms make a Molecule. In the case of Proteins, 
 *              it is a Residue or AminoAcid, or in the case of DNA/RNA, it 
 *              is a Nucleotide or in the case of Carbohydrates, it is a
 *              monosaccharide. 
 *              From this, A Residue "CONTAINS" a group of Atoms or 
 *              a Residue "AGGREGATES"  Atoms.
 *              Hence, BioResidue "Has-A" BioAtom or a BioResidue "Has-A"
 *              BioAtoms.
 *              The Number of Atoms varies from AminoAcid to AminoAcid, 
 *              from Nucleotide to Nucleotide and mono-saccharide to mono-
 *              -saccharide. Hence, vector<T> container has been used. 
 *              Vector is a Container, it belongs to Standard Template
 *              Library Provided with C++. It is one of the most widely 
 *              test, verified and efficiently written template. There
 *              are many Manipulative Methods which make it very suitable
 *              where Number of Elements is not known. It dynamically 
 *              allocates memory for the job. 
 *              While Parsing a file,the number of Atoms and the 
 *              number of Residues is not known as it is very much dependent
 *              on the Protein/DNA which is being parsed. 
 *              Hence to accomodate such a situation, one has to use
 *              DMA(Dynamic Memory Allocation). At this juncture, using vector
 *              of BioAtom Class is ideal. Irrespective of number Of Atoms in 
 *              the Residue or Number of Residues in the Protein, it allocates
 *              automatically the memory.
 *              BioResidue, hence is a group of BioAtoms and many operations can 
 *              be on the data encapsulated in BioResidue. 
 *              For a BioResidue, the ResidueName and ResidueNumber are unique.
 *              This criteria is used in many logical expressions, hence care
 *              should be taken to keep the residueName and residueNumber same
 *              per residue. 
 ******************************************************************************/
class BioResidue
{

        vector < BioAtom > atom;
        string residueName_;
        long residueNumber_;

           friend bool operator >(const BioResidue& , const BioResidue&);
           friend bool operator <(const BioResidue& , const BioResidue&);
           friend bool operator ==(const BioResidue& , const BioResidue&);


public:
// Default Constructor ... Kept this for formality...I hope this is least used...
// very rarely this would be useful..
        BioResidue();
        ~BioResidue();
        BioResidue& operator=(const BioResidue& r);
        BioResidue(const BioResidue& r);


// Similar to the Corresponding Constructor of BioAtom, this also takes a set of 
// first residue only from the PDB file provided as the argument. 
// In this the parsing stops when the residue number and residue name are not 
// equal to the ones which have been pushed into the "atom" vector container.
        BioResidue(const string&);
// A Residue should have minimum, one atom information.For such situations, the following 
// constructor is very useful for instantiation. Normal HOH/WATER information in 
// PDB file has only one Oxygen information. But its a Molecule having 3 Atoms, 
// 1 Oxygen and 2 Hydrogens.  Hence Water molecule should be considered as a residue. 
// the argument sequence follows the PDB format except the last argument. 
// the last argument: string: is provided to give flexibility in altering the RECORD name.
        BioResidue(unsigned long,string, string,long,float, float, float, float, float,string );

//This constructor is useful mostly when a set of Atom coordinates are already loaded. 
//Its needed to qualify the group of Atoms, at that point, all the group of atoms can 
//be held with a residueName and residueNumber. 
  BioResidue(const string& resname_,vector<BioAtom>, const long resnum_ = 0);

// to get residueName and residueNumber
        string getResidueName() const ;
        long getResidueNumber() const ;
        unsigned int getNumberOfAtoms() const ;
                 int getAtomIndex(const string& ) const ; 

// to get the last atom ..in General, set,get, show,  push, find verbs are used to access
// the data encapsulated.
        unsigned long getLastAtomNumber() const ;
        string getLastAtomName() const ;

// this returns the last atom which ever has been added to the vector atom, during reading 
// the file. 
        BioAtom getLastAtom();

        void setResidueName(string res_name) ;
        void setResidueNumber ( long res_num)  ;
// this is very useful to add a set of Atom information to a residue.
// This Method is used to populate the vector atom under some logical conditions.
        void pushAtom(const BioAtom&);

// this overloaded Method is especially used when populating a Residue through a PDB
// file.
        void pushAtom(const unsigned long atnumber,const string& atname,
                      const float x1, const float y1, const float z1,
                      const float oc1, const float bf1,string rec);

// this Method is used to erase Hydrogen Atoms present in the PDB file, if it is 
// Neutron Diffraction Data or Hydrogens are Generated through Xplor or CNS or any other
// Package. The Important thing to note is that the erased Hydrogen set of Atoms are 
// returned as BioResidue type which will not Modify the data which has been entered at
// first.i.e Data is Safe.  
        BioResidue eraseHydrogen();

// these 2 Methods are very very important in the sense, the user is given the ability
// to access the atom which he/she is interested in, either through giving the atomIndex
// or just by giving the AtomName , for example getAtom("CA") or getAtom(0) for accessing 
// the first atom information from the residue information;
        BioAtom getAtom(string);
        BioAtom getAtom(unsigned int ) const;

        bool findAtom(const string& aa) ;

        BioPoint getCentroid();
        

// this Method prints the contents of the Residue in a PDB format, with an optional 
// Chain Id... If the user wants, he/she can redirect into a file through instantiating 
// a proper output file stream.
        void showResidue(ostream& = cout,char = 'A'); 
        friend ostream& operator<<(ostream& os, BioResidue& ip);

// the user has to give the valid atomNames present in the Residue.
        float getTorsionAngle(string, string, string, string);
        float getTorsionAngle(int , int , int , int );
        
        float getDistance(int , float ,float ,float);
        float getDistance(const string& ,float,float, float);

        float getDistance(const string&, const BioAtom& );
        float getDistance(int , const BioAtom& );

// this gives the Chi[1,2,3,4,5] Torsion angles  of the Residue under consideration. 
// this also can be written to file as explained above.  By default it will print 
// to the console or standard Output.
        void showChiAngles(ostream& = cout);
        void chiAngles(ostream& = cout);


};

#endif