Next Article in Journal
Indole-Containing Phytoalexin-Based Bioisosteres as Antifungals: In Vitro and In Silico Evaluation against Fusarium oxysporum
Next Article in Special Issue
Structure-Based Virtual Screening, Molecular Dynamics and Binding Free Energy Calculations of Hit Candidates as ALK-5 Inhibitors
Previous Article in Journal
Changes in Antioxidant Activity, Profile, and Content of Polyphenols and Tocopherols in Common Hazel Seed (Corylus avellana L.) Depending on Variety and Harvest Date
Previous Article in Special Issue
Modeling the Antileukemia Activity of Ellipticine-Related Compounds: QSAR and Molecular Docking Study
Article

Modeling Physico-Chemical ADMET Endpoints with Multitask Graph Convolutional Networks

Digital Technologies, Bayer AG, 13353 Berlin, Germany
*
Author to whom correspondence should be addressed.
Academic Editor: Giosuè Costa
Molecules 2020, 25(1), 44; https://doi.org/10.3390/molecules25010044
Received: 1 December 2019 / Revised: 19 December 2019 / Accepted: 20 December 2019 / Published: 21 December 2019
(This article belongs to the Special Issue Computational Methods in Drug Design and Food Chemistry)
Simple physico-chemical properties, like logD, solubility, or melting point, can reveal a great deal about how a compound under development might later behave. These data are typically measured for most compounds in drug discovery projects in a medium throughput fashion. Collecting and assembling all the Bayer in-house data related to these properties allowed us to apply powerful machine learning techniques to predict the outcome of those assays for new compounds. In this paper, we report our finding that, especially for predicting physicochemical ADMET endpoints, a multitask graph convolutional approach appears a highly competitive choice. For seven endpoints of interest, we compared the performance of that approach to fully connected neural networks and different single task models. The new model shows increased predictive performance compared to previous modeling methods and will allow early prioritization of compounds even before they are synthesized. In addition, our model follows the generalized solubility equation without being explicitly trained under this constraint. View Full-Text
Keywords: ADMET prediction; multitask learning; graph convolutional networks; solubility; QSAR ADMET prediction; multitask learning; graph convolutional networks; solubility; QSAR
Show Figures

Graphical abstract

MDPI and ACS Style

Montanari, F.; Kuhnke, L.; Ter Laak, A.; Clevert, D.-A. Modeling Physico-Chemical ADMET Endpoints with Multitask Graph Convolutional Networks. Molecules 2020, 25, 44. https://doi.org/10.3390/molecules25010044

AMA Style

Montanari F, Kuhnke L, Ter Laak A, Clevert D-A. Modeling Physico-Chemical ADMET Endpoints with Multitask Graph Convolutional Networks. Molecules. 2020; 25(1):44. https://doi.org/10.3390/molecules25010044

Chicago/Turabian Style

Montanari, Floriane, Lara Kuhnke, Antonius Ter Laak, and Djork-Arné Clevert. 2020. "Modeling Physico-Chemical ADMET Endpoints with Multitask Graph Convolutional Networks" Molecules 25, no. 1: 44. https://doi.org/10.3390/molecules25010044

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

Article Access Map by Country/Region

1
Back to TopTop