mirror of
https://github.com/rdkit/rdkit.git
synced 2026-06-03 21:44:30 +08:00
d2d87909de
* support read-only access to cstates from python * expose GetBrackets * expose getAttachPoints too remove vestigial SubstanceGroupCState_VECT * backup * backup * basics working * backup * add label_mol_abbreviations * fix a bug in the chirality handling * add linkers, needs more testing * add another peptide test * sanitize results by default * just need rings * getting started with the C++ form of abbreviations * a bit of error handling * add findApplicableMatches * actually apply the abbreviations * make the getDefault functions more efficient * add labeling (creating s groups) * docs * basic python wrappers (maybe this is enough?) * add _displayLabel and _displayLabelW support to MolDraw2D update the docs for that * use displayLabel props * add more default abbrevs * change default linker defns add parseLinkers convenience function * make sure attachment point atoms aren't aromatic * change the color of dummies to be darker gray * remove python implementation * support abbreviations in the java wrappers * add abbreviations to the csharp wrappers * add abbreviations to the js wrappers * add molParity to the list of atom props not written to CXSMILES * support condensing SUP substance groups * add that to the python wrappers * Update testAbbreviations.py * clear ring info if we added it * document that the molecules with abbreviations removed have not been sanitized
101 lines
4.4 KiB
C++
101 lines
4.4 KiB
C++
//
|
|
// Copyright (C) 2020 Greg Landrum and T5 Informatics GmbH
|
|
//
|
|
// @@ 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 <RDBoost/python.h>
|
|
#include <boost/python/suite/indexing/vector_indexing_suite.hpp>
|
|
#include <GraphMol/GraphMol.h>
|
|
#include <RDBoost/Wrap.h>
|
|
|
|
#include <GraphMol/Abbreviations/Abbreviations.h>
|
|
|
|
namespace python = boost::python;
|
|
using namespace RDKit;
|
|
|
|
namespace {
|
|
|
|
ROMol *condenseMolAbbreviationsHelper(const ROMol *mol,
|
|
python::object pyabbrevs,
|
|
double maxCoverage, bool sanitize) {
|
|
RWMol *res = new RWMol(*mol);
|
|
auto abbrevs =
|
|
pythonObjectToVect<Abbreviations::AbbreviationDefinition>(pyabbrevs);
|
|
Abbreviations::condenseMolAbbreviations(*res, *abbrevs, maxCoverage,
|
|
sanitize);
|
|
return rdcast<ROMol *>(res);
|
|
}
|
|
|
|
ROMol *condenseAbbreviationSGroupHelper(const ROMol *mol) {
|
|
RWMol *res = new RWMol(*mol);
|
|
Abbreviations::condenseAbbreviationSubstanceGroups(*res);
|
|
return rdcast<ROMol *>(res);
|
|
}
|
|
|
|
ROMol *labelMolAbbreviationsHelper(const ROMol *mol, python::object pyabbrevs,
|
|
double maxCoverage) {
|
|
RWMol *res = new RWMol(*mol);
|
|
auto abbrevs =
|
|
pythonObjectToVect<Abbreviations::AbbreviationDefinition>(pyabbrevs);
|
|
Abbreviations::labelMolAbbreviations(*res, *abbrevs, maxCoverage);
|
|
return rdcast<ROMol *>(res);
|
|
}
|
|
} // namespace
|
|
|
|
BOOST_PYTHON_MODULE(rdAbbreviations) {
|
|
python::scope().attr("__doc__") =
|
|
"Module containing functions for working with molecular abbreviations";
|
|
// RegisterVectorConverter<Abbreviations::AbbreviationMatch>();
|
|
RegisterVectorConverter<Abbreviations::AbbreviationDefinition>();
|
|
|
|
python::class_<Abbreviations::AbbreviationDefinition>(
|
|
"AbbreviationDefinition", "Abbreviation Definition", python::init<>())
|
|
.def_readwrite("label", &Abbreviations::AbbreviationDefinition::label,
|
|
"the label")
|
|
.def_readwrite(
|
|
"displayLabel", &Abbreviations::AbbreviationDefinition::displayLabel,
|
|
"the label in a drawing when the bond comes from the right")
|
|
.def_readwrite("displayLabelW",
|
|
&Abbreviations::AbbreviationDefinition::displayLabelW,
|
|
"the label in a drawing when the bond comes from the west")
|
|
.def_readwrite(
|
|
"mol", &Abbreviations::AbbreviationDefinition::mol,
|
|
"the query molecule (should have a dummy as the first atom)");
|
|
|
|
python::def("GetDefaultAbbreviations",
|
|
&Abbreviations::Utils::getDefaultAbbreviations,
|
|
"returns a list of the default abbreviation definitions");
|
|
python::def("GetDefaultLinkers", &Abbreviations::Utils::getDefaultLinkers,
|
|
"returns a list of the default linker definitions");
|
|
python::def("ParseAbbreviations", &Abbreviations::Utils::parseAbbreviations,
|
|
(python::arg("text"), python::arg("removeExtraDummies") = false,
|
|
python::arg("allowConnectionToDummies") = false),
|
|
"returns a set of abbreviation definitions from a string");
|
|
python::def("ParseLinkers", &Abbreviations::Utils::parseLinkers,
|
|
(python::arg("text")),
|
|
"returns a set of linker definitions from a string");
|
|
python::def(
|
|
"CondenseMolAbbreviations", &condenseMolAbbreviationsHelper,
|
|
(python::arg("mol"), python::arg("abbrevs"),
|
|
python::arg("maxCoverage") = 0.4, python::arg("sanitize") = true),
|
|
python::return_value_policy<python::manage_new_object>(),
|
|
"Finds and replaces abbreviations in a molecule. The result is not sanitized.");
|
|
python::def("LabelMolAbbreviations", &labelMolAbbreviationsHelper,
|
|
(python::arg("mol"), python::arg("abbrevs"),
|
|
python::arg("maxCoverage") = 0.4),
|
|
python::return_value_policy<python::manage_new_object>(),
|
|
"Finds abbreviations and adds to them to a molecule as \"SUP\" "
|
|
"SubstanceGroups");
|
|
python::def(
|
|
"CondenseAbbreviationSubstanceGroups", &condenseAbbreviationSGroupHelper,
|
|
(python::arg("mol")),
|
|
python::return_value_policy<python::manage_new_object>(),
|
|
"Finds and replaces abbrevation (i.e. \"SUP\") substance groups in a "
|
|
"molecule. The result is not sanitized.");
|
|
}
|