Files
rdkit/Code/GraphMol/CIPLabeler/rules/Rule5New.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

109 lines
3.0 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 <list>
#include <RDGeneral/Invariant.h>
#include "Rule5New.h"
#include "../Digraph.h"
namespace RDKit {
namespace CIPLabeler {
Rule5New::Rule5New() = default;
Rule5New::Rule5New(Descriptor ref) : d_ref{ref} {}
int Rule5New::compare(const Edge *a, const Edge *b) const {
const auto &aBeg = a->getBeg();
const auto &aEnd = a->getEnd();
const auto &bBeg = b->getBeg();
const auto &bEnd = b->getEnd();
if (aBeg->getDigraph()->getCurrentRoot() != aBeg ||
bBeg->getDigraph()->getCurrentRoot() != bBeg) {
if (d_ref == Descriptor::NONE) {
return 0;
}
Descriptor aDesc = aEnd->getAux();
Descriptor bDesc = bEnd->getAux();
if (aDesc != Descriptor::NONE && bDesc != Descriptor::NONE &&
aDesc != Descriptor::ns && bDesc != Descriptor::ns) {
bool alike = PairList::ref(d_ref) == PairList::ref(aDesc);
bool blike = PairList::ref(d_ref) == PairList::ref(bDesc);
if (alike && !blike) {
return +1;
}
if (blike && !alike) {
return -1;
}
}
return 0;
} else {
auto listRA = PairList(Descriptor::R);
auto listRB = PairList(Descriptor::R);
auto listSA = PairList(Descriptor::S);
auto listSB = PairList(Descriptor::S);
fillPairs(aEnd, listRA);
fillPairs(aEnd, listSA);
fillPairs(bEnd, listRB);
fillPairs(bEnd, listSB);
int cmpR = listRA.compareTo(listRB);
int cmpS = listSA.compareTo(listSB);
// -2/+2 for psuedo-asymetric
// -1/+1 if not (e.g. the R > R and S > S lists)
if (cmpR < 0) {
return cmpS < 0 ? -1 : -2;
} else if (cmpR > 0) {
return cmpS > 0 ? +1 : +2;
} else {
return 0;
}
}
}
void Rule5New::fillPairs(const Node *beg, PairList &plist) const {
const Rule5New replacement_rule(plist.getRefDescriptor());
const auto &sorter = getRefSorter(&replacement_rule);
auto queue = std::list<const Node *>({beg});
for (const auto &node : queue) {
plist.add(node->getAux());
auto edges = node->getEdges();
sorter.prioritize(node, edges);
for (const auto &edge : edges) {
if (edge->isBeg(node) && !edge->getEnd()->isTerminal()) {
queue.push_back(edge->getEnd());
}
}
}
}
Sort Rule5New::getRefSorter(const SequenceRule *replacement_rule) const {
const auto &rules = getSorter()->getRules();
CHECK_INVARIANT(std::find(rules.begin(), rules.end(), this) != rules.end(),
"Rule5New instance not in rule set");
std::vector<const SequenceRule *> new_rules;
new_rules.reserve(rules.size());
for (const auto &rule : rules) {
if (this != rule) {
new_rules.push_back(rule);
}
}
new_rules.push_back(replacement_rule);
return {new_rules};
}
} // namespace CIPLabeler
} // namespace RDKit