Files
rdkit/Code/GraphMol/CIPLabeler/CIPMol.cpp
Ric d54e77e375 Add new CIP labelling algorithm (#3234)
* add port of centres

* Several changes:
    - Added a test based on RDKit issue 2984
        (default RDKit fails it, this gets it right)
    - Use bond directions for bond stereo (label is no longer required)
    - Fix bugs in rules 4b and 5new
    - Fix some mem errors
    - clang-formatted
    - some other minor cleanups

* Several changes and some improvements:
    - Added LGPL license, as well as a mention in the doc.
    - Fix/update/add some comments
    - Fix typo/bug in Mancude calculation
    - Fix bug in rules 4b, 5New
    - Fix Sp2 Bond dir reference
    - Re clang-format
    - other minor changes suggested by Dan

* Another bunch of changes:
  - require integer-order bonds; kekulize when required
  - fix fraction comparison
  - rename sq Cis/Trans e/z
  - replace queues with vectors
  - update copyright notices
  - revert LGPL changes
  - fix Asymmetric typo

* move to separate lib/mod, add python validation test

* Moving away from the original implementation:
    - Rename to CIPLabeler
    - Remove the abstraction layer
    - Remove some stats stuff
    - Push some CIPMol functions down to Node
    - Use RDKit's isotope info

* Another bundle of changes. The most relevant ones:
    - fix parity translation
    - use cis trans as bond reference -- breaks #2984 test
    - kill a lot of unused code
    - use lists for queues
    - store nodes and edges in digraph
    - add prefixes to class data member names
    - update changeRoot() test
    - use fastFindRings() for mancude rings
    - update docs
    - add references to the scientific paper
    - Document the Mancude functions
    - Fix Mancude atom types and their comments
    - remove mol data member from SequenceRule
    - replace Fraction with boost::rational
    - update comments, docstrings and the doc

* fix building the test

* Changes here include:
    - adding bitset overload for the labeling function
    - python wrap of the overload
    - handling trigonal pyramids with implicit H
    - setting bond labels sets stereo atoms, cis/trans
    - nix LEFT/RIGHT/TOGETHER/OPPOSITE constants
    - don't use GLOB in cmake
    - a decent amount of refactoring

* Minor edits to new_CIP_labeling (#6)

* Some changes for clarity

Added some documentation and changed some variable names to match
my understanding. Also a ran clang-tidy to ensure that all blocks
were brace-enclosed.

* Return a reference instead of a copy for performance

This is called many times and showed up after some light
profiling. This change bumped throughput by about 20%

* move out of Graphmol

* move .hpp headers to .h

* update documentation; add label set of atoms test

* Address comments:
    - Added references to centres to CIPLabeler.h and Python Wrap.
    - Update validation test to skip sanitization.
    - Document mancude fractional atomic number calculation.
    - Use unittest assertions in python test.
    - Update mancude docstrings to 'resonance' instad of 'tautomers'.
    - Rename prioritise() to prioritize().
    - Add postcondition to check carriers size in Tetrahedral.cpp.
    - Use getNeighbors() in Tetrahedral.cpp.
    - Move findStereoAtoms to Chirality namespace.
    - Move code back into GraphMol.
    - Fix typos and reformat doc.

* More comments:
    - Mention why we use boost's unordered map rather than the std one.
    - Fix include in Python wrapper.

* Addressed second batch of comments:
    - fix the bug in rule 4b
    - fix docstring for rule 2
    - move atomic mass calculation from rule 2 to node
    - addressed some build warnings
    - simplify sp2bond::label(comp)
    - add start/end atoms to Sp2Bond constructor
    - update system/local includes

Co-authored-by: Dan N <dan.nealschneider@schrodinger.com>
2020-07-07 20:34:33 +02:00

98 lines
2.5 KiB
C++

//
//
// Copyright (C) 2020 Schrödinger, LLC
//
// @@ 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 <GraphMol/MolOps.h>
#include "CIPMol.h"
namespace RDKit {
namespace CIPLabeler {
CIPMol::CIPMol(ROMol &mol) : d_mol{mol} {}
boost::rational<int> CIPMol::getFractionalAtomicNum(Atom *atom) const {
PRECONDITION(atom, "bad atom")
if (d_atomnums.empty())
const_cast<CIPMol *>(this)->d_atomnums = calcFracAtomNums(*this);
return d_atomnums[atom->getIdx()];
}
unsigned CIPMol::getNumAtoms() const { return d_mol.getNumAtoms(); }
unsigned CIPMol::getNumBonds() const { return d_mol.getNumBonds(); };
Atom *CIPMol::getAtom(int idx) const { return d_mol.getAtomWithIdx(idx); };
CXXAtomIterator<MolGraph, Atom *> CIPMol::atoms() const {
return d_mol.atoms();
}
Bond *CIPMol::getBond(int idx) const { return d_mol.getBondWithIdx(idx); };
CIPMolSpan<Bond *, ROMol::OEDGE_ITER> CIPMol::getBonds(Atom *atom) const {
PRECONDITION(atom, "bad atom")
return {d_mol, d_mol.getAtomBonds(atom)};
}
CIPMolSpan<Atom *, ROMol::ADJ_ITER> CIPMol::getNeighbors(Atom *atom) const {
PRECONDITION(atom, "bad atom")
return {d_mol, d_mol.getAtomNeighbors(atom)};
}
bool CIPMol::isInRing(Bond *bond) const {
PRECONDITION(bond, "bad bond")
const auto rings = d_mol.getRingInfo();
if (!rings->isInitialized()) {
MolOps::fastFindRings(d_mol);
}
return rings->numBondRings(bond->getIdx()) != 0u;
};
int CIPMol::getBondOrder(Bond *bond) const {
PRECONDITION(bond, "bad bond")
if (dp_kekulized_mol == nullptr) {
auto tmp = new RWMol(d_mol);
MolOps::Kekulize(*tmp);
const_cast<CIPMol *>(this)->dp_kekulized_mol.reset(tmp);
}
const auto kekulized_bond = dp_kekulized_mol->getBondWithIdx(bond->getIdx());
// Dative bonds might need to be considered with a different bond order
// for the end atom at the end of the bond.
switch (kekulized_bond->getBondType()) {
case Bond::ZERO:
case Bond::HYDROGEN:
case Bond::DATIVE:
case Bond::DATIVEL:
case Bond::DATIVER:
return 0;
case Bond::SINGLE:
return 1;
case Bond::DOUBLE:
return 2;
case Bond::TRIPLE:
return 3;
case Bond::QUADRUPLE:
return 4;
case Bond::QUINTUPLE:
return 5;
case Bond::HEXTUPLE:
return 6;
default:
throw std::runtime_error("Non integer-order bonds are not allowed.");
}
};
} // namespace CIPLabeler
} // namespace RDKit