Metadata-Version: 2.4
Name: chython-rxnmap
Version: 2.0
Summary: ONNX model weights for chython atom-to-atom mapping
Author-email: Ramil Nugmanov <nougmanoff@protonmail.com>
License: LGPLv3+
Project-URL: Homepage, https://github.com/chython/chython-rxnmap
Classifier: Environment :: Plugins
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: GNU Lesser General Public License v3 or later (LGPLv3+)
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.10
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Scientific/Engineering :: Chemistry
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Dynamic: license-file

# chython-rxnmap

ONNX model weights for chython atom-to-atom mapping.

Semisupervised model trained on USPTO and Pistachio datasets.

[Publication](https://pubs.acs.org/doi/10.1021/acs.jcim.2c00344) ([Preprint](https://doi.org/10.26434/chemrxiv-2022-bn5nt)) with details.

## Installation

    pip install chython-rxnmap

## Usage

This package is a plugin for [chython](https://github.com/chython/chython). Install it alongside chython to enable attention-based atom-to-atom mapping:

    pip install chython[mapping]

Then use mapping as usual:

    from chython import smiles

    r = smiles('OC(=O)C(=C)C=C.C=CC#N>>OC(=O)C1=CCCC(C1)C#N')
    r.attention_mapping()
    print(format(r, 'm'))
