Next Article in Journal
Comprehensive Analysis of Soybean Mosaic Virus P3 Protein Interactors and Hypersensitive Response-Like Lesion-Inducing Protein Function
Next Article in Special Issue
Targeting HIV/HCV Coinfection Using a Machine Learning-Based Multiple Quantitative Structure-Activity Relationships (Multiple QSAR) Method
Previous Article in Journal
“Biological Adhesion” is a Significantly Regulated Molecular Process during Long-Term Primary In Vitro Culture of Oviductal Epithelial Cells (Oecs): A Transcriptomic and Proteomic Study
Previous Article in Special Issue
Predicting Apoptosis Protein Subcellular Locations based on the Protein Overlapping Property Matrix and Tri-Gram Encoding
Article Menu

Export Article

Open AccessArticle

Chemi-Net: A Molecular Graph Convolutional Network for Accurate Drug Property Prediction

Accutar Biotechnology Inc., 760 Parkside Ave., Brooklyn, NY 11226, USA
Amgen Inc., 1 Amgen Center Dr., Thousand Oaks, CA 91320, USA
Amgen Inc., 360 Binney St., Cambridge, MA 02141, USA
Authors to whom correspondence should be addressed.
These authors contributed equally to this work.
Int. J. Mol. Sci. 2019, 20(14), 3389;
Received: 22 March 2019 / Revised: 10 June 2019 / Accepted: 2 July 2019 / Published: 10 July 2019
(This article belongs to the Special Issue Artificial Intelligence and Computer Aided Drug Design)
PDF [4748 KB, uploaded 10 July 2019]


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. For all 13 data sets, Chemi-Net resulted in higher R2 values compared with the Cubist benchmark. The median R2 increase rate over Cubist was 26.7%. We expect that the significantly increased accuracy of ADME prediction seen with Chemi-Net over Cubist will greatly accelerate drug discovery. View Full-Text
Keywords: deep learning; ADME prediction; drug discovery deep learning; ADME prediction; drug discovery

Graphical abstract

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

Supplementary material


Share & Cite This Article

MDPI and ACS Style

Liu, K.; Sun, X.; Jia, L.; Ma, J.; Xing, H.; Wu, J.; Gao, H.; Sun, Y.; Boulnois, F.; Fan, J. Chemi-Net: A Molecular Graph Convolutional Network for Accurate Drug Property Prediction. Int. J. Mol. Sci. 2019, 20, 3389.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics



[Return to top]
Int. J. Mol. Sci. EISSN 1422-0067 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top