validerror_bioseqset.cpp

来自「ncbi源码」· C++ 代码 · 共 493 行 · 第 1/2 页

/*
 * ===========================================================================
 * PRODUCTION $Log: validerror_bioseqset.cpp,v $
 * PRODUCTION Revision 1000.2  2004/06/01 19:47:54  gouriano
 * PRODUCTION PRODUCTION: UPGRADED [GCC34_MSVC7] Dev-tree R1.14
 * PRODUCTION
 * ===========================================================================
 */

/*  $Id: validerror_bioseqset.cpp,v 1000.2 2004/06/01 19:47:54 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.
 *
 * ===========================================================================
 *
 * Author:  Jonathan Kans, Clifford Clausen, Aaron Ucko......
 *
 * File Description:
 *   validation of bioseq_set 
 *   .......
 *
 */
#include <ncbi_pch.hpp>
#include <corelib/ncbistd.hpp>
#include "validatorp.hpp"

#include <objmgr/util/sequence.hpp>

#include <serial/enumvalues.hpp>
#include <serial/iterator.hpp>

#include <objects/seqset/Seq_entry.hpp>
#include <objects/seqset/Bioseq_set.hpp>

#include <objects/seq/Bioseq.hpp>
#include <objects/seq/MolInfo.hpp>

#include <objects/seqfeat/Seq_feat.hpp>
#include <objects/seqfeat/BioSource.hpp>
#include <objects/seqfeat/Org_ref.hpp>
#include <objects/seqfeat/RNA_ref.hpp>

#include <objmgr/feat_ci.hpp>
#include <objmgr/bioseq_handle.hpp>

BEGIN_NCBI_SCOPE
BEGIN_SCOPE(objects)
BEGIN_SCOPE(validator)
using namespace sequence;


// =============================================================================
//                                     Public
// =============================================================================


CValidError_bioseqset::CValidError_bioseqset(CValidError_imp& imp) :
    CValidError_base(imp)
{
}


CValidError_bioseqset::~CValidError_bioseqset(void)
{
}


void CValidError_bioseqset::ValidateBioseqSet(const CBioseq_set& seqset)
{
    int protcnt = 0;
    int nuccnt  = 0;
    int segcnt  = 0;
    
    // Validate Set Contents
    CTypeConstIterator<CBioseq> seqit(ConstBegin(seqset));
    for (; seqit; ++seqit) {
        
        if ( seqit->IsAa() ) {
            protcnt++;
        } else {
            nuccnt++;
        }
        
        if (seqit->GetInst().GetRepr() == CSeq_inst::eRepr_seg) {
            segcnt++;
        }
    }
    
    switch ( seqset.GetClass() ) {
    case CBioseq_set::eClass_nuc_prot:
        ValidateNucProtSet(seqset, nuccnt, protcnt);
        break;
        
    case CBioseq_set::eClass_segset:
        ValidateSegSet(seqset, segcnt);
        break;
        
    case CBioseq_set::eClass_parts:
        ValidatePartsSet(seqset);
        break;
        
    case CBioseq_set::eClass_pop_set:
        ValidatePopSet(seqset);
        break;
        
    case CBioseq_set::eClass_gen_prod_set:
        ValidateGenProdSet(seqset);
        break;
    case CBioseq_set::eClass_other:
        PostErr(eDiag_Critical, eErr_SEQ_PKG_GenomicProductPackagingProblem, 
            "Genomic product set class incorrectly set to other", seqset);
        break;
    default:
        if ( nuccnt == 0  &&  protcnt == 0 )  {
            PostErr(eDiag_Error, eErr_SEQ_PKG_EmptySet, 
                "No Bioseqs in this set", seqset);
        }
        break;
    }
}


// =============================================================================
//                                     Private
// =============================================================================


bool CValidError_bioseqset::IsMrnaProductInGPS(const CBioseq& seq)
{
    if ( m_Imp.IsGPS() ) {
        CFeat_CI mrna(
            m_Scope->GetBioseqHandle(seq), 
            0, 0,
            CSeqFeatData::e_Rna,
            SAnnotSelector::eOverlap_Intervals,
            SAnnotSelector::eResolve_TSE,
            CFeat_CI::e_Product);
        return (bool)mrna;
    }
    return true;
}


void CValidError_bioseqset::ValidateNucProtSet
(const CBioseq_set& seqset,
 int nuccnt, 
 int protcnt)
{
    if ( nuccnt == 0 ) {
        PostErr(eDiag_Error, eErr_SEQ_PKG_NucProtProblem,
                 "No nucleotides in nuc-prot set", seqset);
    }
    if ( protcnt == 0 ) {
        PostErr(eDiag_Error, eErr_SEQ_PKG_NucProtProblem,
                 "No proteins in nuc-prot set", seqset);
    }

    ITERATE( list< CRef<CSeq_entry> >, se_list_it, seqset.GetSeq_set() ) {
        if ( (**se_list_it).IsSeq() ) {
            const CBioseq& seq = (**se_list_it).GetSeq();
            if ( seq.IsNa()  &&  !IsMrnaProductInGPS(seq) ) {
                PostErr(eDiag_Warning,
                    eErr_SEQ_PKG_GenomicProductPackagingProblem,
                    "Nucleotide bioseq should be product of mRNA "
                    "feature on contig, but is not",
                    seq);
            }
        }

        if ( !(**se_list_it).IsSet() )
            continue;

        const CBioseq_set& set = (**se_list_it).GetSet();
        if ( set.GetClass() != CBioseq_set::eClass_segset ) {

            const CEnumeratedTypeValues* tv = 
                CBioseq_set::GetTypeInfo_enum_EClass();
            const string& set_class = tv->FindName(set.GetClass(), true);

            PostErr(eDiag_Error, eErr_SEQ_PKG_NucProtNotSegSet,
                     "Nuc-prot Bioseq-set contains wrong Bioseq-set, "
                     "its class is \"" + set_class + "\"", set);
            break;
        }
    }
}


void CValidError_bioseqset::ValidateSegSet(const CBioseq_set& seqset, int segcnt)
{
    if ( segcnt == 0 ) {
        PostErr(eDiag_Error, eErr_SEQ_PKG_SegSetProblem,
            "No segmented Bioseq in segset", seqset);
    }

    CSeq_inst::EMol     mol = CSeq_inst::eMol_not_set;
    CSeq_inst::EMol     seq_inst_mol;
    
    ITERATE ( CBioseq_set::TSeq_set, se_list_it, seqset.GetSeq_set() ) {
        if ( (*se_list_it)->IsSeq() ) {
            const CSeq_inst& seq_inst = (*se_list_it)->GetSeq().GetInst();
            
            if ( mol == CSeq_inst::eMol_not_set ||
                 mol == CSeq_inst::eMol_other ) {
                mol = seq_inst.GetMol();
            } else if ( (seq_inst_mol = seq_inst.GetMol()) != CSeq_inst::eMol_other) {
                if ( seq_inst.IsNa() != CSeq_inst::IsNa(mol) ) {
                    PostErr(eDiag_Critical, eErr_SEQ_PKG_SegSetMixedBioseqs,
                        "Segmented set contains mixture of nucleotides"
                        "and proteins", seqset);
                    break;
                }
            }
        } else if ( (*se_list_it)->IsSet() ) {
            const CBioseq_set& set = (*se_list_it)->GetSet();

            if ( set.IsSetClass()  &&  
                 set.GetClass() != CBioseq_set::eClass_parts ) {
                const CEnumeratedTypeValues* tv = 
                    CBioseq_set::GetTypeInfo_enum_EClass();
                const string& set_class_str = 
                    tv->FindName(set.GetClass(), true);
                
                PostErr(eDiag_Critical, eErr_SEQ_PKG_SegSetNotParts,
                    "Segmented set contains wrong Bioseq-set, "
                    "its class is \"" + set_class_str + "\"", set);
                break;
            }