wbplg_splign.cpp

来自「ncbi源码」· C++ 代码 · 共 275 行

/*
 * ===========================================================================
 * PRODUCTION $Log: wbplg_splign.cpp,v $
 * PRODUCTION Revision 1000.0  2004/06/01 21:26:20  gouriano
 * PRODUCTION PRODUCTION: IMPORTED [GCC34_MSVC7] Dev-tree R1.5
 * PRODUCTION
 * ===========================================================================
 */

/*  $Id: wbplg_splign.cpp,v 1000.0 2004/06/01 21:26:20 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:  Yuri Kapustin
 *
 * File Description:
 *     Splign Genome Workbench Plugin
 */

#include <ncbi_pch.hpp>
#include "wbplg_splign.hpp"

#include <algo/align/splign/splign_simple.hpp>
#include <corelib/ncbitime.hpp>
#include <gui/core/doc_manager.hpp>
#include <gui/core/idocument.hpp>
#include <gui/core/plugin_utils.hpp>
#include <gui/core/version.hpp>
#include <gui/plugin/PluginArgSet.hpp>
#include <gui/plugin/PluginCommandSet.hpp>
#include <gui/plugin/PluginInfo.hpp>
#include <gui/plugin/PluginMessage.hpp>
#include <gui/plugin/PluginRequest.hpp>
#include <gui/plugin/PluginValueConstraint.hpp>
#include <gui/utils/message_box.hpp>
#include <gui/objutils/label.hpp>

#include <objects/seqalign/Dense_seg.hpp>
#include <objects/seqalign/Seq_align.hpp>
#include <objmgr/seq_vector.hpp>
#include <objmgr/util/feature.hpp>
#include <objmgr/util/sequence.hpp>


//////////


BEGIN_NCBI_SCOPE
USING_SCOPE(objects);


const char kStrand_plus[] = "plus";
const char kStrand_minus[] = "minus";

// GetInfo()
// static interface to retrieve plugin registration information
void CAlgoPlugin_Splign::GetInfo(CPluginInfo& info)
{
    info.Reset();

    // version info macro
    info.SetInfo(CPluginVersion::eMajor, CPluginVersion::eMinor, 0,
                 string(__DATE__) + " " + string(__TIME__),
                 "CAlgoPlugin_Splign",
                 "Alignments/Spliced Alignment",
                 "Compute cDNA-to-genomic alignments",
                 "");

    // command info
    CPluginCommandSet& cmds = info.SetCommands();
    CPluginCommand&    args = cmds.AddAlgoCommand(eAlgoCommand_run);
    args.AddArgument("seqs", "Sequences to align",
                     CSeq_loc::GetTypeInfo(),
                     CPluginArg::TData::e_Array);

    args.SetConstraint("seqs",
                       (*CPluginValueConstraint::CreateSeqMol(),
                        CSeq_inst::eMol_na,
                        CSeq_inst::eMol_dna,
                        CSeq_inst::eMol_rna));

    args.AddDefaultArgument("strand", "cDna strand",
                            CPluginArg::eString,
                            kStrand_plus);
    args.SetConstraint("strand", (*CPluginValueConstraint::CreateSet(),
                                  kStrand_plus, kStrand_minus));

    args.AddDefaultArgument("compartment_penalty",
                            "Compartment penalty",
                            CPluginArg::eDouble,
                            ".75");
    args.SetConstraint("compartment_penalty",
                       *(CPluginValueConstraint::CreateRange("0", "1")));

    args.AddDefaultArgument("min_idty",
                            "Min exon identity",
                            CPluginArg::eDouble,
                            "0.75");
    args.SetConstraint("min_idty",
                       *(CPluginValueConstraint::CreateRange("0", "1")));
}



void CAlgoPlugin_Splign::RunCommand(CPluginMessage& msg)
{
    const CPluginCommand& cmd = msg.GetRequest().GetCommand();
    CPluginReply& reply = msg.SetReply();
    reply.SetStatus(eMessageStatus_failed);

    // check to see that we were passed sequences to begin with
    if ( !CPluginUtils::IsValid(cmd["seqs"]) ) {
        reply.SetStatus(eMessageStatus_failed);
        return;
    }

    // make sure we have exactly two sequences
    plugin_args::TLocList locs;
    GetArgValue(cmd["seqs"], locs);
    if (locs.size() != 2) {
        reply.SetStatus(eMessageStatus_ignored);
        return;
    }

    // make sure that the sequences are of a known type; fetch the seqlocs
    CRef<CScope> new_scope;
    ITERATE (plugin_args::TLocList, loc_iter, locs) {
        const CSeq_loc&  loc = *loc_iter->second;
        const IDocument& doc = *loc_iter->first;
        CScope& scope = doc.GetScope();
        if ( !new_scope ) {
            new_scope.Reset(&scope);
        }

        if ( !sequence::IsOneBioseq(loc, &scope) ) {
            string msg = CPluginUtils::GetLabel(loc, &doc.GetScope());
            LOG_POST(Info << "CAlgoPlugin_Splign: "
                     "location on multiple bioseqs ignored: " << msg);
            continue;
        }
    }

    CConstRef<CSeq_loc> seqloc_cDna (locs.front().second);
    CConstRef<CSeq_loc> seqloc_genomic (locs.back().second);

    try {

        CSplignSimple splign_simple (*seqloc_cDna, *seqloc_genomic,
                                     *new_scope);

        CSplign& splign = splign_simple.SetSplignObject();

        splign.SetEndGapDetection(true);
        splign.SetPolyaDetection(true);
        splign.SetStrand(cmd["strand"].AsString() == kStrand_plus);
        splign.SetMaxGenomicExtension(75000);
        splign.SetMinQueryCoverage(0.01);
        splign.SetCompartmentPenalty(cmd["compartment_penalty"].AsDouble());
        splign.SetMinExonIdentity(cmd["min_idty"].AsDouble());

        splign_simple.Run();

        CRef<CSeq_align_set> seqalign_set = splign_simple.GetResultsAsAln();

        // pack the alignment in a Seq-annot and label it appropriately
        CRef<CSeq_annot> seqannot (new CSeq_annot());
        CSeq_annot::TData::TAlign& seqannot_align = 
            seqannot->SetData().SetAlign(); 
        ITERATE(CSeq_align_set::Tdata, align, seqalign_set->Get()) {
            seqannot_align.push_back(*align);
        }
        // prepare a title
        string str = "Spliced alignment of ";
        CLabel::GetLabel(*seqloc_cDna, &str,
                         CLabel::eDefault, new_scope);
        str += " and ";
        CLabel::GetLabel(*seqloc_genomic, &str,
                         CLabel::eDefault, new_scope);
        
        seqannot->AddTitle(str);

        CTime time;
        time.GetLocalTime();
        seqannot->SetCreateDate(time);

        //
        // pass back to the system.  We may use the same scope and just attach,
        // if that is appropriate
        //
        CConstRef<IDocument> doc_ref;

        ITERATE (plugin_args::TLocList, iter, locs) {
            if ( !doc_ref ) {
                doc_ref.Reset(iter->first);
            } else if (iter->first != doc_ref) {
                doc_ref.Reset();
                break;
            }
        }

        if ( !doc_ref ) {
            //
            // query and targets come from different documents
            // create a new one to handle the results
            //
            CRef<CScope> new_scope(new CScope(CDocManager::GetObjectManager()));
            ITERATE (plugin_args::TLocList, iter, locs) {
                new_scope->AddScope(iter->first->GetScope());
            }
            doc_ref.Reset(CDocManager::CreateDocument(*new_scope, *seqannot));
        } else {
            reply.AddAction(CPluginReplyAction::e_Add_to_document);
        }
        reply.AddObject(*doc_ref, *seqannot);
        reply.SetStatus(eMessageStatus_success);
    }
    catch (CException& e) {
        NcbiMessageBox("Spliced alignment failed:\n" + e.GetMsg());
    }
    catch(exception& e) {
        NcbiMessageBox(string("Spliced alignment failed:\n") + e.what());
    }
}


END_NCBI_SCOPE


/*
 * ===========================================================================
 * $Log: wbplg_splign.cpp,v $
 * Revision 1000.0  2004/06/01 21:26:20  gouriano
 * PRODUCTION: IMPORTED [GCC34_MSVC7] Dev-tree R1.5
 *
 * Revision 1.5  2004/05/21 22:27:46  gorelenk
 * Added PCH ncbi_pch.hpp
 *
 * Revision 1.4  2004/05/20 12:36:43  dicuccio
 * Minor code clean-up.  Reordered constraints to be next to arguments.  Use
 * CLabel for labels instead of native label functions.  Use
 * CSeq_annot::SetCreateTime() instead of doing this manually
 *
 * Revision 1.3  2004/05/18 17:49:47  kapustin
 * Shorten argument descriptions to fit workbench plugin title space
 *
 * Revision 1.2  2004/05/17 20:53:03  kapustin
 * Fix the seqs constraint
 *
 * Revision 1.1  2004/05/17 15:11:44  kapustin
 * Initial revision
 *
 * ===========================================================================
*/