RDKit MaxMinPicker example

gistfile1.cpp

//
//  Copyright (C) 2014 Greg Landrum
//   @@ All Rights Reserved @@
//  This file is part of the RDKit.
//  The contents are covered by the terms of the BSD license
//  which is included in the file license.txt, found at the root
//  of the RDKit source tree.
//
/*
  Can be built with:
   g++ -o maxmin_demo.exe maxmin_demo.cpp -I$RDBASE/Code -I$RDBASE/Extern \
       -L$RDBASE/lib -lFingerprints -lFileParsers -lSimDivPickers \
       -lGraphMol -lDataStructs -lRDGeometryLib -lRDGeneral
*/

#include <RDGeneral/Invariant.h>
#include <GraphMol/RDKitBase.h>
#include <GraphMol/FileParsers/MolSupplier.h>
#include <GraphMol/Fingerprints/MorganFingerprints.h>
#include <DataStructs/ExplicitBitVect.h>
#include <DataStructs/BitOps.h>
#include <SimDivPickers/MaxMinPicker.h>

#include <RDGeneral/RDLog.h>
#include <vector>
#include <algorithm>
#include <boost/shared_ptr.hpp>

using namespace RDKit;

void LoadAndFingerprintMols(std::string filename,
                            std::vector<boost::shared_ptr<ExplicitBitVect> > &fps){
  BOOST_LOG(rdInfoLog)<<"Load Mols"<<std::endl;
  SDMolSupplier suppl(filename);
  while(!suppl.atEnd()){
    ROMol *mol=suppl.next();
    ExplicitBitVect *fp=MorganFingerprints::getFingerprintAsBitVect(*mol,2,2048);
    fps.push_back(boost::shared_ptr<ExplicitBitVect>(fp));
    if(!(fps.size()%1000)){
      BOOST_LOG(rdInfoLog)<<"   done: "<<fps.size()<<std::endl;
    }
    delete mol;
  }
}

struct distFunctor{
  const std::vector<boost::shared_ptr<ExplicitBitVect> > &_fps;
  distFunctor(const std::vector<boost::shared_ptr<ExplicitBitVect> > &fps) : _fps(fps) {};
  double operator()(unsigned int i,unsigned int j){
    return 1.-TanimotoSimilarity(*_fps[i].get(),*_fps[j].get());
  }
};
  
void LazyPickSubset(const std::vector<boost::shared_ptr<ExplicitBitVect> > &fps,
                INT_VECT &picks,unsigned int nToPick){
  BOOST_LOG(rdInfoLog)<<"LazyPickSubset()"<<std::endl;
  unsigned int n=fps.size();
  distFunctor df(fps);
  
  RDPickers::MaxMinPicker picker;
  BOOST_LOG(rdInfoLog)<<"   picking"<<std::endl;
  INT_VECT seedPicks;
  picks = picker.lazyPick(df,n,nToPick,seedPicks,0xF00D);
  BOOST_LOG(rdInfoLog)<<"   done"<<std::endl;

}

void PickSubset(const std::vector<boost::shared_ptr<ExplicitBitVect> > &fps,
                INT_VECT &picks,unsigned int nToPick){
  BOOST_LOG(rdInfoLog)<<"PickSubset()"<<std::endl;
  unsigned int n=fps.size();
  double *dm = new double[n*(n-1)];
  unsigned int idx=0;
  BOOST_LOG(rdInfoLog)<<"   generating distance matrix"<<std::endl;
  for(unsigned int i=0;i<n;++i){
    for(unsigned int j=i+1;j<n;++j){
      dm[idx++] = 1.-TanimotoSimilarity(*fps[i].get(),*fps[j].get());
    }
  }
  BOOST_LOG(rdInfoLog)<<"   done"<<std::endl;
  
  RDPickers::MaxMinPicker picker;
  BOOST_LOG(rdInfoLog)<<"   picking"<<std::endl;
  INT_VECT seedPicks;
  picks = picker.pick(dm,n,nToPick,seedPicks,0xF00D);
  BOOST_LOG(rdInfoLog)<<"   done"<<std::endl;
  delete [] dm;
}

int
main(int argc, char *argv[])
{
  RDLog::InitLogs();
  std::vector<boost::shared_ptr<ExplicitBitVect> > fps;
  LoadAndFingerprintMols("znp.sdf",fps);
  INT_VECT picks;
  //PickSubset(fps,picks,20);
  LazyPickSubset(fps,picks,100);
}