Home

Awesome

GEOM-CVAE

Geometry-based Molecular Generation with Deep Constrained Variational Autoencoder. <br> This is the official code implementation of GEOM-CVAE paper.

<P> <b>Acknowledgements</b> <br> We thank the authors of Shape-Based Generative Modeling for de Novo Drug Design[1] for releasing their code. The code in this repository is based on their source code release. If you find this code useful, please consider citing their work. <P> <b>Requirements</b> <br> This code was tested in Python 3.6.8 with torch 1.7.1, torch-geometric 1.6.3, torch-scatter 2.0.6 and torch-sparse 0.6.9. <P> <b>Datasets</b> <br> The AID1706 Bioassay data for COVID-19 in PubChem database (https://pubchem.ncbi.nlm.nih.gov/bioassay/1706). <P> <b>Reference:</b> <br> [1]. @article{Miha2019Shapebased,<br> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; author = {Skalic, Miha and Jim\'{e}nez, Jos\'{e} and Sabbadin, Davide and Fabritiis, Gianni De},<br> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; title = {Shape-Based Generative Modeling for de Novo Drug Design},<br> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; journal = {Journal of Chemical Information and Modeling},<br> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; volume = {59},<br> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; number = {3},<br> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; pages = {1205-1214},<br> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; year = {2019}<br> &nbsp;&nbsp;&nbsp; }