blast_util.cpp

来自「ncbi源码」· C++ 代码 · 共 287 行

/*
 * ===========================================================================
 * PRODUCTION $Log: blast_util.cpp,v $
 * PRODUCTION Revision 1000.2  2004/06/01 20:54:19  gouriano
 * PRODUCTION PRODUCTION: UPGRADED [GCC34_MSVC7] Dev-tree R1.4
 * PRODUCTION
 * ===========================================================================
 */

/*  $Id: blast_util.cpp,v 1000.2 2004/06/01 20:54:19 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:  Mike DiCuccio
 *
 * File Description:
 *
 */

#include <ncbi_pch.hpp>
#include "blast_util.hpp"
#include <objects/seqfeat/Genetic_code.hpp>
#include <objects/seqfeat/Genetic_code_table.hpp>
#include <gui/plugin/PluginValueConstraint.hpp>
#include <gui/core/plugin_utils.hpp>
#include <util/static_map.hpp>
#include <algo/blast/api/blast_types.hpp>

BEGIN_NCBI_SCOPE
USING_SCOPE(objects);


// figure out the id of the genetic code the user wants
inline
int x_DecodeGeneticCode(const string& s)
{
    const CGenetic_code_table& code_table = CGen_code_table::GetCodeTable();
    const CGenetic_code_table::Tdata& codes = code_table.Get();
    ITERATE (CGenetic_code_table::Tdata, code, codes) {
        if ((*code)->GetName() == s) {
            return (*code)->GetId();
        }
    }
    // if we got here, nothing matched
    NCBI_THROW(CException, eUnknown,
               "x_DecodeGeneticCode: no genetic code matched " + s);
}




void CBlastUtils::AddBlastArgs(CPluginCommand& args, blast::EProgram prog)
{
    switch (prog) {
    case blast::eBlastn:
        args.AddDefaultArgument("word", "Word Size",
                                CPluginArg::eInteger, "11");

        args.AddDefaultArgument("expect", "Expect Value",
                                CPluginArg::eDouble, "10.0");

        args.AddArgument("greedy", "Perform a greedy alignment",
                         CPluginArg::eBoolean);

        //
        // hidden argument for program type
        //
        {{
            CPluginArg& arg = args.AddArgument("prog", "Program Type",
                                               CPluginArg::eString);
            arg.SetHidden(true);
            arg.SetString("blastn");
        }}
        break;

    case blast::eBlastx:
        args.AddDefaultArgument("thresh", "Threshold",
                                CPluginArg::eInteger, "12");

        args.AddDefaultArgument("word", "Word Size",
                                CPluginArg::eInteger, "3");

        args.AddDefaultArgument("expect", "Expect Value",
                                CPluginArg::eDouble, "10.0");

        // genetic code argument
        {{
            const CGenetic_code_table& code_table =
                CGen_code_table::GetCodeTable();
            const list<CRef<CGenetic_code> >& codes = code_table.Get();
            args.AddDefaultArgument("gencode", "Genetic code",
                                    CPluginArg::eString,
                                    codes.front()->GetName());
            CPluginValueConstraint *code_list =
                CPluginValueConstraint::CreateSet();
            ITERATE (list<CRef<CGenetic_code> >, code, codes) {
                code_list->SetSet().push_back((*code)->GetName());
            }
            args.SetConstraint("gencode", *code_list);
        }}

        //
        // hidden argument for program type
        //
        {{
            CPluginArg& arg = args.AddArgument("prog", "Program Type",
                                               CPluginArg::eString);
            arg.SetHidden(true);
            arg.SetString("blastx");
        }}
        break;

    case blast::eBlastp:
        args.AddDefaultArgument("thresh", "Threshold",
                                CPluginArg::eInteger, "11");

        args.AddDefaultArgument("word", "Word Size",
                                CPluginArg::eInteger, "3");

        args.AddDefaultArgument("expect", "Expect Value",
                                CPluginArg::eDouble, "10.0");

        //
        // hidden argument for program type
        //
        {{
            CPluginArg& arg = args.AddArgument("prog", "Program Type",
                                               CPluginArg::eString);
            arg.SetHidden(true);
            arg.SetString("blastp");
        }}
        break;

    case blast::eTblastx:
        args.AddDefaultArgument("thresh", "Threshold",
                                CPluginArg::eInteger, "13");

        args.AddDefaultArgument("word", "Word Size",
                                CPluginArg::eInteger, "3");

        args.AddDefaultArgument("expect", "Expect Value",
                                CPluginArg::eDouble, "10.0");

        // genetic code argument
        {{
            const CGenetic_code_table& code_table =
                CGen_code_table::GetCodeTable();
            const list<CRef<CGenetic_code> >& codes = code_table.Get();
            args.AddDefaultArgument("gencode", "Genetic code",
                                    CPluginArg::eString,
                                    codes.front()->GetName());
            CPluginValueConstraint *code_list =
                CPluginValueConstraint::CreateSet();
            ITERATE (list<CRef<CGenetic_code> >, code, codes) {
                code_list->SetSet().push_back((*code)->GetName());
            }
            args.SetConstraint("gencode", *code_list);
        }}

        //
        // hidden argument for program type
        //
        {{
            CPluginArg& arg = args.AddArgument("prog", "Program Type",
                                               CPluginArg::eString);
            arg.SetHidden(true);
            arg.SetString("tblastx");
        }}
        break;

    default:
        LOG_POST(Error << "unhandled BLAST program");
        break;
    }
}


void CBlastUtils::ArgsToBlastOptions(const CPluginCommand& cmd,
                                     blast::CBlastOptions& opts)
{
    if (cmd.HasArgument("word")  &&
        CPluginUtils::IsValid(cmd["word"])) {
        int word_size = cmd["word"].AsInteger();
        opts.SetWordSize(word_size);
        _TRACE("CBlastBase: word size = " << word_size);
    }

    if (cmd.HasArgument("expect")  &&
        CPluginUtils::IsValid(cmd["expect"])) {
        double expect = cmd["expect"].AsDouble();
        opts.SetEvalueThreshold(expect);
        _TRACE("CBlastBase: expect = " << expect);
    }

    if (cmd.HasArgument("thresh")  &&
        CPluginUtils::IsValid(cmd["thresh"])) {
        int thresh = cmd["thresh"].AsInteger();
        opts.SetWordThreshold(thresh);
        _TRACE("CBlastBase: threshold = " << thresh);
    }

    if (cmd.HasArgument("greedy")  &&
        CPluginUtils::IsValid(cmd["greedy"])) {
        bool greedy = cmd["greedy"].AsBoolean();
        if (greedy) {
            opts.SetGapExtnAlgorithm(eGreedyWithTracebackExt);
        }
        _TRACE("CBlastBase: greedy = " << greedy);
    }

    if (cmd.HasArgument("gencode")  &&
        CPluginUtils::IsValid(cmd["gencode"])) {
        string code = cmd["gencode"].AsString();
        opts.SetDbGeneticCode(x_DecodeGeneticCode(code.c_str()));
        _TRACE("CBlastBase: genetic code = " << code);
    }
}


blast::EProgram CBlastUtils::GetBlastProgram(const string& str)
{
    typedef pair<const char*, blast::EProgram> TProgPair;
    static const TProgPair sc_ProgPairs[] = {
        TProgPair("blastn", blast::eBlastn),
        TProgPair("blastp", blast::eBlastp),
        TProgPair("blastx", blast::eBlastx),
        TProgPair("tblastn", blast::eTblastn),
        TProgPair("tblastx", blast::eTblastx)
    };
    typedef CStaticArrayMap<const char*, blast::EProgram, PCase> TProgDictionary;
    static const TProgDictionary sc_Progs(sc_ProgPairs, sizeof(sc_ProgPairs));

    TProgDictionary::const_iterator iter = sc_Progs.find(str.c_str());
    if (iter != sc_Progs.end()) {
        return iter->second;
    }

    return blast::eBlastProgramMax;
}



END_NCBI_SCOPE


/*
 * ===========================================================================
 * $Log: blast_util.cpp,v $
 * Revision 1000.2  2004/06/01 20:54:19  gouriano
 * PRODUCTION: UPGRADED [GCC34_MSVC7] Dev-tree R1.4
 *
 * Revision 1.4  2004/05/21 22:27:46  gorelenk
 * Added PCH ncbi_pch.hpp
 *
 * Revision 1.3  2004/05/17 18:00:09  ucko
 * Int algorithm_type replaced with enum EBlastPrelimGapExt
 *
 * Revision 1.2  2004/04/16 14:41:22  dicuccio
 * Added GetBlastProgram() - convert text-based program name to enum
 *
 * Revision 1.1  2004/01/13 20:35:27  dicuccio
 * Initial revision
 *
 * ===========================================================================
 */