restriction_sites.cpp

来自「ncbi源码」· C++ 代码 · 共 651 行 · 第 1/2 页

/*
 * ===========================================================================
 * PRODUCTION $Log: restriction_sites.cpp,v $
 * PRODUCTION Revision 1000.5  2004/06/01 20:55:43  gouriano
 * PRODUCTION PRODUCTION: UPGRADED [GCC34_MSVC7] Dev-tree R1.32
 * PRODUCTION
 * ===========================================================================
 */

/*  $Id: restriction_sites.cpp,v 1000.5 2004/06/01 20:55:43 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:  Josh Cherry
 *
 * File Description:  gbench plugin for finding restriction sites
 *
 */

#include <ncbi_pch.hpp>
#include "restriction_sites.hpp"
#include "rebase.hpp"

#include <algo/sequence/restriction.hpp>
#include <algo/sequence/seq_match.hpp>
#include <algorithm>
#include <corelib/ncbiapp.hpp>
#include <corelib/ncbireg.hpp>
#include <gui/core/plugin_utils.hpp>
#include <gui/utils/system_path.hpp>
#include <gui/core/version.hpp>
#include <gui/dialogs/col/multi_col_dlg.hpp>
#include <gui/plugin/PluginCommandSet.hpp>
#include <gui/plugin/PluginInfo.hpp>
#include <gui/plugin/PluginRequest.hpp>
#include <gui/plugin/PluginValueConstraint.hpp>
#include <gui/utils/message_box.hpp>
#include <gui/objutils/utils.hpp>
#include <objects/general/Dbtag.hpp>
#include <objects/general/Object_id.hpp>
#include <objects/seqfeat/Rsite_ref.hpp>
#include <objects/seqloc/Seq_point.hpp>
#include <objmgr/seq_vector.hpp>
#include <objmgr/util/sequence.hpp>


BEGIN_NCBI_SCOPE


CAlgoPlugin_RestrictionSites::~CAlgoPlugin_RestrictionSites()
{
}


// standard plugin announce bopilerplate
void CAlgoPlugin_RestrictionSites::GetInfo(CPluginInfo& info)
{
    info.Reset();
    
    // version info macro
    info.SetInfo(CPluginVersion::eMajor, CPluginVersion::eMinor, 0,
                 string(__DATE__) + " " + string(__TIME__),
                 "CAlgoPlugin_RestrictionSites", "Search/Find restriction sites",
                 "Search a DNA sequence for restriction sites",
                 "");

    // command info
    CPluginCommandSet& cmds = info.SetCommands();
    CPluginCommand&    args = cmds.AddAlgoCommand(eAlgoCommand_run);
    args.AddArgument("locs", "Locations to evaluate",
                     CSeq_loc::GetTypeInfo(),
                     CPluginArg::TData::e_Array);
    args.SetConstraint("locs",
                       (*CPluginValueConstraint::CreateSeqMol(),
                        CSeq_inst::eMol_na,
                        CSeq_inst::eMol_dna,
                        CSeq_inst::eMol_rna));
    args.AddDefaultArgument("which_enzymes", "Which restriction enzymes",
                            CPluginArg::eString, "commercially available");
    args.SetConstraint("which_enzymes", (*CPluginValueConstraint::CreateSet(),
                                "commercially available",
                                "prototypes", "all"));
    args.AddDefaultArgument("combine_isoschizomers",
                            "Combine isoschizomers",
                            CPluginArg::eBoolean, "true");
    args.AddArgument("sort_by_number_of_sites",
                     "Sort results by number of (definite) cuts by enzyme",
                     CPluginArg::eBoolean);
}


// helper functor for sorting CRef<CREnzResult> by the enzyme name
struct SEnzymeNameCompare
{
    bool operator()
        (const CRef<CREnzResult>& lhs, const CRef<CREnzResult>& rhs) const
    {
        return lhs->GetEnzymeName() < rhs->GetEnzymeName();
    }
};


// helper functor for sorting CREnzyme by the enzyme name
struct SNameCompare
{
    bool operator()
        (const CREnzyme& lhs, const CREnzyme& rhs) const
    {
        return lhs.GetName() < rhs.GetName();
    }
};


// helper functor for sorting by the number of definite sites
struct SLessDefSites
{
    bool operator() 
        (const CRef<CREnzResult>& lhs, const CRef<CREnzResult>& rhs) const
    {
        return lhs->GetDefiniteSites().size() < rhs->GetDefiniteSites().size();
    }
};


// helper functor for sorting CRef<CSeq_loc>s by location
struct SLessSeq_loc
{
    bool operator() 
        (const CRef<CSeq_loc>& lhs, const CRef<CSeq_loc>& rhs) const
    {
        return (lhs->Compare(*rhs) < 0);
    }
};


static
void s_AddSitesToAnnot(const vector<CRSite>& sites,
                       const CREnzResult&    result,
                       CSeq_annot&           annot,
                       const CSeq_loc&       parent_loc,
                       bool                  definite = true)
{
    const CSeq_id& id = sequence::GetId(parent_loc);

    ITERATE (vector<CRSite>, site, sites) {
        // create feature
        CRef<CSeq_feat> feat(new CSeq_feat());

        // start to set up Rsite
        feat->SetData().SetRsite().SetDb().SetDb("REBASE");
        feat->SetData().SetRsite().SetDb()
            .SetTag().SetStr("REBASE");

        string str(result.GetEnzymeName());
        if ( !definite ) {
            str = "Possible " + str;
        }
        feat->SetData().SetRsite().SetStr(str);

        //
        // build our location
        //

        vector< CRef<CSeq_loc> > locs;

        // a loc for the recognition site
        CRef<CSeq_loc> recog_site(new CSeq_loc);
        recog_site->SetInt().SetFrom(site->GetStart());
        recog_site->SetInt().SetTo  (site->GetEnd());
        recog_site->SetId(id);
        locs.push_back(recog_site);

        // locs for the cleavage sites
        int negative_cut_locs = 0;  // count these exceptions
        ITERATE (vector<int>, cut, site->GetPlusCuts()) {
            if (*cut >= 0 ) {
                CRef<CSeq_loc> cut_site(new CSeq_loc);
                cut_site->SetPnt().SetPoint(*cut);
                // indicate that the cut is to the "left"
                cut_site->SetPnt()
                    .SetFuzz().SetLim(CInt_fuzz::eLim_tl);
                cut_site->SetPnt().SetStrand(eNa_strand_plus);
                cut_site->SetId(id);
                locs.push_back(cut_site);
            } else {
                negative_cut_locs++;
            }
        }

        ITERATE (vector<int>, cut, site->GetMinusCuts()) {
            if (*cut >= 0 ) {
                CRef<CSeq_loc> cut_site(new CSeq_loc);
                cut_site->SetPnt().SetPoint(*cut);
                // indicate that the cut is to the "left"
                cut_site->SetPnt()
                    .SetFuzz().SetLim(CInt_fuzz::eLim_tl);
                cut_site->SetPnt().SetStrand(eNa_strand_minus);
                cut_site->SetId(id);
                locs.push_back(cut_site);
            } else {
                negative_cut_locs++;
            }
        }

        // comment for those few cases where there are
        // cuts before the sequence begins
        if (negative_cut_locs > 0) {
            string a_comm = NStr::IntToString(negative_cut_locs)
                + " cleavage sites are located before the"
                " beginning of the sequence and are not reported";
            feat->SetComment(a_comm);
        }

        sort(locs.begin(), locs.end(), SLessSeq_loc());
        copy(locs.begin(), locs.end(),
             back_inserter(feat->SetLocation().SetMix().Set()));

        feat->SetLocation
            (*CSeqUtils::RemapChildToParent(parent_loc, feat->GetLocation()));

        // save in annot
        annot.SetData().SetFtable().push_back(feat);
    }
}


void CAlgoPlugin_RestrictionSites::RunCommand(CPluginMessage& msg)
{
    const CPluginCommand& args = msg.GetRequest().GetCommand();
    CPluginReply& reply = msg.SetReply();
    _TRACE("CAlgoPlugin_RestrictionSites::RunCommand()");
    

    // load patterns from file
    CRebase::EEnzymesToLoad which_enzymes 
        = x_DecodeWhichEnzymes(args["which_enzymes"].AsString());
    vector<CREnzyme> enzymes;
    try {
        x_LoadREnzymeData(enzymes, which_enzymes);
    }
    catch (const exception& e) {
        NcbiMessageBox(e.what());
        reply.SetStatus(eMessageStatus_failed);
        return;
    }

    // optionally lump together all enzymes with identical specificities
    if (args["combine_isoschizomers"].AsBoolean()) {
        // first sort alphabetically by enzyme name
        sort(enzymes.begin(), enzymes.end(), SNameCompare());
        // now combine isoschizomers
        CREnzyme::CombineIsoschizomers(enzymes);
    }

    if ( !m_Dialog.get() ) {
        m_Dialog.reset(new CMultiColDlg());

        m_Dialog->SetWindowSize(1000, 500);
        m_Dialog->SetTitle("Restriction Sites");
        
        m_Dialog->SetColumn(0, "Sequence", FL_ALIGN_LEFT, 0.3f);
        m_Dialog->SetColumn(1, "Location", FL_ALIGN_LEFT, 0.5f);
        m_Dialog->SetColumn(2, "Enzyme", FL_ALIGN_LEFT, 0.4f);
        m_Dialog->SetColumn(3, "Number of Sites", FL_ALIGN_CENTER, 0.5f);
        m_Dialog->SetColumn(4, "Recog. Site Loc.", FL_ALIGN_CENTER, 0.75f);
        m_Dialog->SetColumn(5, "Plus Strand Cuts", FL_ALIGN_CENTER, 0.75f);
        m_Dialog->SetColumn(6, "Minus Strand Cuts", FL_ALIGN_CENTER, 0.75f);
    }

    m_Dialog->SetRows(0);  // to clear any previous contents

    int row = 0;
    plugin_args::TLocList locs;
    GetArgValue(args["locs"], locs);


    ITERATE (plugin_args::TLocList, iter, locs) {
        const CSeq_loc&  loc = *iter->second;
        const IDocument& doc = *iter->first;

        // find the best ID for this bioseq
        try {
            CBioseq_Handle handle = doc.GetScope().GetBioseqHandle(loc);
            // get sequence in binary (8na) form
            CSeqVector vec =
                handle.GetSequenceView(loc,
                                       CBioseq_Handle::eViewConstructed,
                                       CBioseq_Handle::eCoding_Ncbi);

            string& id_str  = m_Dialog->SetCell(row, 0);
            string& loc_str = m_Dialog->SetCell(row, 1);

            const CSeq_id& best_id =
                sequence::GetId(handle, sequence::eGetId_Best);
            id_str.erase();
            best_id.GetLabel(&id_str);
            loc_str = CPluginUtils::GetLabel(loc, &doc.GetScope());

            // a new feature table
            CRef<CSeq_annot> annot(new CSeq_annot());

            // a place to store results (one per enzyme)
            typedef vector<CRef<CREnzResult> > TResults;
            TResults results;