Chemi-net: a graph convolutional network for accurate drug property prediction
This addresses the problem of accurate drug property prediction for drug discovery, with significant improvements over existing methods.
The paper tackled drug property prediction for ADME studies by developing Chemi-Net, a graph convolutional network, which improved current methods by a large margin in a large-scale study at Amgen.
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.