Absorption, distribution, metabolism, and excretion (ADME) studies are critical for drug discovery. Conventionally, these tasks, together with other chemical property predictions, rely on domain-specific feature descriptors, or fingerprints. Following the recent success of neural networks, we developed Chemi-Net, a completely data-driven, domain knowledge-free, deep learning method for ADME property prediction. To compare the relative performance of Chemi-Net with Cubist, one of the popular machine learning programs used by Amgen, a large-scale ADME property prediction study was performed on-site at Amgen. The results showed that our deep neural network method improved current methods by a large margin. We foresee that the significantly increased accuracy of ADME prediction seen with Chemi-Net over Cubist will greatly accelerate drug discovery.
@article{arxiv.1803.06236,
title = {Chemi-net: a graph convolutional network for accurate drug property prediction},
author = {Ke Liu and Xiangyan Sun and Lei Jia and Jun Ma and Haoming Xing and Junqiu Wu and Hua Gao and Yax Sun and Florian Boulnois and Jie Fan},
journal= {arXiv preprint arXiv:1803.06236},
year = {2018}
}