Metadata-Version: 2.1
Name: qmdesc
Version: 1.0.4
Summary: A qm descriptor prediction package
Home-page: https://github.com/yanfeiguan/qmdesc
Author: Yanfei Guan
Author-email: yanfeig@mit.edu
License: MIT
Keywords: chemistry,machine learning,QM descriptors
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Requires-Dist: torch (>=1.4.0)
Requires-Dist: numpy (>=1.18.1)

# qmdesc

[![GitHub license](https://img.shields.io/github/license/yanfeiguan/qmdesc)](https://github.com/yanfeiguan/qmdesc/blob/master/LICENSE)
[![Documentation Status](https://readthedocs.org/projects/qmdesc/badge/?version=latest)](https://qmdesc.readthedocs.io/en/latest/?badge=latest)


A trained multitask constraint message passing neural networks 
for QM atomic/bond property predictions as described in the paper 
[Regio-Selectivity Prediction with a Machine-Learned Reaction Representation and On-the-Fly Quantum Mechanical Descriptors](https://doi.org/10.26434/chemrxiv.12907316.v1).

QM descriptors under B3LYP/def2svp level of theory that can be predicted with this model:
1. Hirshfeld partial charge
2. Neucleuphilic Fukui indices
3. Electrophilic Fukui indices
4. NMR shielding constants
5. Bond lengths
6. Bond orders

**Documentation:** Documentation of Chemprop is available at https://qmdesc.readthedocs.io/en/latest/index.html.


