Files
rdkit/Code/GraphMol/FMCS/TargetMatch.h
Paolo Tosco 350370abe3 - Changed all unsigned to unsigned int for clarity (#6646)
- Switched from dynamic to static allocation for an instance of `MCSParameters`
- Switched to using `auto` where possible
- Added a few `CHECK_INVARIANT` where appropriate before dereferencing pointers
- Moved some inline comments to the previous line to improve readability
- Added a early check for `CompleteRingsOnly` in `checkBondRingMatch()` to improve computational efficiency
- Removed `RingMatchTableSet` entirely as 1) it is unnecessary since its functionality is already provided by `RingInfo` 2) it abused the `userData` pointer. This allows cleaning up and simplifying the code, particularly the Python wrappers which had a significant amount of added complexity to support it
- Removed all the code that was deprecated several releases ago
- Reimplemented ringFusionCheck() from scratch to address several bug reports; also switched from std::set to boost::dynamic_bitset for better efficiency
- Replaced boost::tie with boost::make_iterator_range
- Modernized `for` loops where possible
- Removed entirely the QueryRings structure as its functionality is already available in RingInfo
- Removed entirely the _DFS() function since the same algorithm can be implemented in a simpler and more efficient way using RingInfo (from 2m28.441s to 2m9.859s for the same task)
- Replaced std::vector<bool> with boost::dynamic_bitset
- Replaced C-style casts with C++ casts
- Replaced some size_t with unsigned int
- Refactored checkIfRingsAreClosed() such that checkNoLoneRingAtoms() is not needed anymore
- Added a test for slow runtimes with CompleteRingsOnly
- Setting Timeout to 0 means no timeout, as it should be
- Removed unused `steps` variable from `MaximumCommonSubgraph::growSeeds`
- Storing both Atom and Bond pointers and their indices on Seed and MCS data structures is time-consuming and a potential source of incons
istencies; storing pointers is sufficient
- Promoted `MaximumCommonSubgraph::match` from `private` to `public`
- `NewBonds` was declared `mutable`, but `Seed::fillNewBonds()` was incorrectly declared as `non-const`, which caused the need for an ugly
(and unnecessary) `const_cast`.
I have now removed the `const_cast` and correctly declared functions that alter `NewBonds` as `const`, since `NewBonds` is explicitly `mut
able`
- Removed some useless random scoping that was peppering the MCS code
- Removed a significant amount of duplicate code from the Python wrappers by inheriting from a base `PyMCSWrapper` class
- Fixed #6082
- Fixed #5510
- Fixed #5457
- Fixed #5440
- Fixed #5411
- Fixed #3965
- Fixed #6578

Co-authored-by: ptosco <paolo.tosco@novartis.com>
2023-08-25 06:09:19 +02:00

87 lines
2.6 KiB
C++

//
// Copyright (C) 2014 Novartis Institutes for BioMedical Research
//
// @@ 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.
//
#include <RDGeneral/export.h>
#pragma once
#include <vector>
#include <boost/dynamic_bitset.hpp>
#include "FMCS.h"
#include "MatchTable.h"
namespace RDKit {
namespace FMCS {
struct TargetMatch {
bool Empty{true};
size_t MatchedAtomSize{0};
size_t MatchedBondSize{0};
std::vector<unsigned int> TargetAtomIdx;
std::vector<unsigned int> TargetBondIdx;
boost::dynamic_bitset<> VisitedTargetBonds;
boost::dynamic_bitset<> VisitedTargetAtoms; // for checking rings
public:
TargetMatch() {}
TargetMatch(const TargetMatch& src) { *this = src; }
TargetMatch& operator=(const TargetMatch& src) {
Empty = src.Empty;
if (!Empty) {
MatchedAtomSize = src.MatchedAtomSize;
MatchedBondSize = src.MatchedBondSize;
TargetAtomIdx = src.TargetAtomIdx;
TargetBondIdx = src.TargetBondIdx;
VisitedTargetBonds = src.VisitedTargetBonds;
VisitedTargetAtoms = src.VisitedTargetAtoms;
}
return *this;
}
bool empty() const { return Empty; }
void clear() {
Empty = true;
TargetAtomIdx.clear();
TargetBondIdx.clear();
VisitedTargetBonds.clear();
VisitedTargetAtoms.clear();
}
void init(const Seed& seed, const match_V_t& match, const ROMol& query,
const Target& target) {
TargetAtomIdx.clear();
TargetAtomIdx.resize(query.getNumAtoms(), NotSet);
TargetBondIdx.clear();
TargetBondIdx.resize(query.getNumBonds(), NotSet);
VisitedTargetBonds.resize(target.Molecule->getNumBonds());
VisitedTargetAtoms.resize(target.Molecule->getNumAtoms());
VisitedTargetBonds.reset();
VisitedTargetAtoms.reset();
MatchedAtomSize = match.size();
for (const auto& m : match) {
TargetAtomIdx[seed.MoleculeFragment.Atoms.at(m.first)->getIdx()] =
m.second;
VisitedTargetAtoms.set(m.second);
}
MatchedBondSize = 0;
for (const auto bond : seed.MoleculeFragment.Bonds) {
unsigned int i = bond->getBeginAtomIdx();
unsigned int j = bond->getEndAtomIdx();
unsigned int ti = TargetAtomIdx.at(i);
unsigned int tj = TargetAtomIdx.at(j);
const auto tb = target.Molecule->getBondBetweenAtoms(ti, tj);
if (tb) {
++MatchedBondSize;
TargetBondIdx[bond->getIdx()] = tb->getIdx(); // add
VisitedTargetBonds.set(tb->getIdx());
}
}
Empty = false;
}
};
} // namespace FMCS
} // namespace RDKit