su_block_multiple_alignment.hpp

ncbi源码

/*
 * ===========================================================================
 * PRODUCTION $Log: su_block_multiple_alignment.hpp,v $
 * PRODUCTION Revision 1000.0  2004/06/01 18:14:33  gouriano
 * PRODUCTION PRODUCTION: IMPORTED [GCC34_MSVC7] Dev-tree R1.7
 * PRODUCTION
 * ===========================================================================
 */

/*  $Id: su_block_multiple_alignment.hpp,v 1000.0 2004/06/01 18:14:33 gouriano Exp $
* ===========================================================================
*
*                            PUBLIC DOMAIN NOTICE
*               National Center for Biotechnology Information
*
*  This software/database is a "United States Government Work" under the
*  terms of the United States Copyright Act.  It was written as part of
*  the author's official duties as a United States Government employee and
*  thus cannot be copyrighted.  This software/database is freely available
*  to the public for use. The National Library of Medicine and the U.S.
*  Government have not placed any restriction on its use or reproduction.
*
*  Although all reasonable efforts have been taken to ensure the accuracy
*  and reliability of the software and data, the NLM and the U.S.
*  Government do not and cannot warrant the performance or results that
*  may be obtained by using this software or data. The NLM and the U.S.
*  Government disclaim all warranties, express or implied, including
*  warranties of performance, merchantability or fitness for any particular
*  purpose.
*
*  Please cite the author in any work or product based on this material.
*
* ===========================================================================
*
* Authors:  Paul Thiessen
*
* File Description:
*      Classes to hold alignment data
*
* ===========================================================================
*/

#ifndef SU_BLOCK_MULTIPLE_ALIGNMENT__HPP
#define SU_BLOCK_MULTIPLE_ALIGNMENT__HPP

#include <corelib/ncbistl.hpp>
#include <corelib/ncbiobj.hpp>

#include <objects/seqalign/Seq_align.hpp>

#include <list>
#include <vector>
#include <map>

// forward declaration of BLAST_Matrix
struct _blast_matrix;
typedef struct _blast_matrix BLAST_Matrix_;


BEGIN_SCOPE(struct_util)

class Sequence;
class Block;
class UngappedAlignedBlock;
class UnalignedBlock;

class BlockMultipleAlignment : public ncbi::CObject
{
public:
    enum {
        eUndefined = kMax_UInt
    };

    typedef std::vector < const Sequence * > SequenceList;
    BlockMultipleAlignment(const SequenceList& sequenceList);   // first sequence is master
    ~BlockMultipleAlignment(void);

    // add a new aligned block - will be "owned" and deallocated by BlockMultipleAlignment
    bool AddAlignedBlockAtEnd(UngappedAlignedBlock *newBlock);

    // these two should be called after all aligned blocks have been added; fills out
    // unaligned blocks inbetween aligned blocks (and at ends). Also sets length.
    bool AddUnalignedBlocks(void);

    // Fills out the BlockMap for mapping alignment column -> block+column, special colors,
    // and sets up conservation colors (although they're not calculated until needed).
    bool UpdateBlockMap(bool clearRowInfo = true);

    // find out if a residue is aligned, by row
    bool IsAligned(unsigned int row, unsigned int seqIndex) const;

    // stuff regarding master sequence
    const Sequence * GetMaster(void) const { return m_sequences[0]; }
    bool IsMaster(const Sequence *sequence) const { return (sequence == m_sequences[0]); }

    // return sequence for given row
    const Sequence * GetSequenceOfRow(unsigned int row) const
    {
        if (row < m_sequences.size())
            return m_sequences[row];
        else
            return NULL;
    }

    // will be used to control padding of unaligned blocks
    enum eUnalignedJustification {
        eLeft,
        eRight,
        eCenter,
        eSplit
    };

    // return alignment position of left side first aligned block (eUndefined if no aligned blocks)
    unsigned int GetFirstAlignedBlockPosition(void) const;

    // makes a new copy of itself
    BlockMultipleAlignment * Clone(void) const;

    // character query interface - "column" must be in alignment range [0 .. AlignmentWidth()-1]
    bool GetCharacterAt(unsigned int alignmentColumn, unsigned int row,
        eUnalignedJustification justification, char *character) const;

    // get sequence and index (if any) at given position, and whether that residue is aligned
    bool GetSequenceAndIndexAt(unsigned int alignmentColumn, unsigned int row,
        eUnalignedJustification justification,
        const Sequence **sequence, unsigned int *index, bool *isAligned) const;

    // given row and sequence index, return alignment index; not the most efficient function - use sparingly
    unsigned int GetAlignmentIndex(unsigned int row, unsigned int seqIndex, eUnalignedJustification justification);

    // fill in a vector of UngappedAlignedBlocks
    typedef std::vector < const UngappedAlignedBlock * > UngappedAlignedBlockList;
    void GetUngappedAlignedBlocks(UngappedAlignedBlockList *blocks) const;
    typedef std::vector < UngappedAlignedBlock * > ModifiableUngappedAlignedBlockList;
    void GetModifiableUngappedAlignedBlocks(ModifiableUngappedAlignedBlockList *blocks);

    // PSSM for this alignment (cached)
    const BLAST_Matrix_ * GetPSSM(void) const;
    void RemovePSSM(void) const;

    // NULL if block before is aligned; if NULL passed, retrieves last block (if unaligned; else NULL)
    const UnalignedBlock * GetUnalignedBlockBefore(const UngappedAlignedBlock *aBlock) const;

    unsigned int NBlocks(void) const { return m_blocks.size(); }
    unsigned int NAlignedBlocks(void) const;
    unsigned int NRows(void) const { return m_sequences.size(); }
    unsigned int AlignmentWidth(void) const { return m_totalWidth; }

    // return a number from 1..n for aligned blocks, eUndefined for unaligned
    unsigned int GetAlignedBlockNumber(unsigned int alignmentIndex) const
        { return m_blockMap[alignmentIndex].alignedBlockNum; }

    // for storing/querying info
    double GetRowDouble(unsigned int row) const { return m_rowDoubles[row]; }
    void SetRowDouble(unsigned int row, double value) const { m_rowDoubles[row] = value; }
    const std::string& GetRowStatusLine(unsigned int row) const { return m_rowStrings[row]; }
    void SetRowStatusLine(unsigned int row, const std::string& value) const { m_rowStrings[row] = value; }

    // empties all rows' infos
    void ClearRowInfo(void) const
    {
        for (unsigned int r=0; r<NRows(); ++r) {
            m_rowDoubles[r] = 0.0;
            m_rowStrings[r].erase();
        }
    }


    ///// editing functions /////

    // if in an aligned block, give block column and width of that position; otherwise eUndefined
    void GetAlignedBlockPosition(unsigned int alignmentIndex,
        unsigned int *blockColumn, unsigned int *blockWidth) const;

    // get seqIndex of slave aligned to the given master seqIndex; eUndefined if master residue unaligned
    unsigned int GetAlignedSlaveIndex(unsigned int masterSeqIndex, unsigned int slaveRow) const;

    // returns true if any boundary shift actually occurred
    bool MoveBlockBoundary(unsigned int columnFrom, unsigned int columnTo);

    // splits a block such that alignmentIndex is the first column of the new block;
    // returns false if no split occurred (e.g. if index is not inside aligned block)
    bool SplitBlock(unsigned int alignmentIndex);

    // merges all blocks that overlap specified range - assuming no unaligned blocks
    // in that range. Returns true if any merge(s) occurred, false otherwise.
    bool MergeBlocks(unsigned int fromAlignmentIndex, unsigned int toAlignmentIndex);

    // creates a block, if given region of an unaligned block in which no gaps
    // are present. Returns true if a block is created.
    bool CreateBlock(unsigned int fromAlignmentIndex, unsigned int toAlignmentIndex,
        eUnalignedJustification justification);

    // deletes the block containing this index; returns true if deletion occurred.
    bool DeleteBlock(unsigned int alignmentIndex);

    // deletes all blocks; returns true if there were any blocks to delete
    bool DeleteAllBlocks(void);

    // shifts (horizontally) the residues in and immediately surrounding an
    // aligned block; returns true if any shift occurs.