# ccgnet

**Repository Path**: xugitee2021/ccgnet

## Basic Information

- **Project Name**: ccgnet
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: add-license-1
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2021-10-17
- **Last Updated**: 2021-10-17

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# ccgnet
CCGNet (Co-Crystal Graph Network) is a deep learning framework for virtual screening of organic cocrystals, which integrates the priori knowledge into the feature learning on molecular graph and achieves a great improvement of performance for data-driven cocrystal screening.

Requirements:
* Python 3.7
* Tensorflow (>=1.6)
* RDKit
* Openbabel 2.4.1
* CCDC Python API
* Scikit-learn

The ccgnet module could be used to build CCGNet models. In ccgnet, the message passing is implement by Graph-CNN, where the code of this part we borrow from https://github.com/fps7806/Graph-CNN. The Featurize module represents the combination of two molecules as the input of CCGNet models.

# usage