ACS Editors' Choice® is a collection designed to feature scientific articles of broad public interest. Read the latest articles
Consensus Modeling for Predicting Chemical Binding to Transthyretin as the Winning Solution of the Tox24 ChallengeClick to copy article linkArticle link copied!
- Dmitriy M. Makarov*Dmitriy M. Makarov*Email: [email protected]G. A. Krestov Institute of Solution Chemistry of the Russian Academy of Sciences, Ivanovo 153045, RussiaMore by Dmitriy M. Makarov
- Alexander A. KsenofontovAlexander A. KsenofontovG. A. Krestov Institute of Solution Chemistry of the Russian Academy of Sciences, Ivanovo 153045, RussiaMore by Alexander A. Ksenofontov
- Yury A. BudkovYury A. BudkovG. A. Krestov Institute of Solution Chemistry of the Russian Academy of Sciences, Ivanovo 153045, RussiaLaboratory of Computational Physics, HSE University, Tallinskaya st. 34, Moscow 123458, RussiaSchool of Applied Mathematics, HSE University, Tallinskaya st. 34, Moscow 123458, RussiaMore by Yury A. Budkov
Abstract
The utilization of predictive methodologies for the assessment of toxicological properties represents an alternative approach that facilitates the identification of safe compounds while concurrently reducing the financial costs associated with the process. The objective of the Tox24 Challenge was to assess the progress in computational methods for predicting the activity of chemical binding to transthyretin (TTR). In order to fulfill the requirements of this task, the data set, measured by the Environmental Protection Agency, consisted of 1512 chemical substances of diverse nature. This paper describes the model that won the Tox24 Challenge and the steps taken for its further improvement. The Transformer convolutional neural network (CNN) model achieved the best performance as a standalone solution. Meanwhile, a multitask model built on a graph CNN, trained using 11 additional acute systemic toxicity data sets with increased weighting on the TTR binding activity, showed comparable results on the blind test set. The winning solution was a consensus model consisting of two catBoost models with OEstate and Mold2 descriptor sets, as well as two transformer-based models. The improvement of this solution involved adding a fifth model based on multitask learning using the graph CNN method, which led to a reduction in RMSE on the blind test set to 20.3%. The winning model was developed using the OCHEM web platform and is available online at https://ochem.eu/article/162082.
Cited By
This article is cited by 7 publications.
- Stephanie A. Eytcheson, Igor V. Tetko. Which Modern AI Methods Provide Accurate Predictions of Toxicological End Points? Analysis of Tox24 Challenge Results. Chemical Research in Toxicology 2025, 38
(9)
, 1443-1451. https://doi.org/10.1021/acs.chemrestox.5c00273
- Thalita Cirino, Luis Pinto, Mateusz Iwan, Alexis Dougha, Bono Lučić, Antonija Kraljević, Zaven Navoyan, Ani Tevosyan, Hrach Yeghiazaryan, Lusine Khondkaryan, Narek Abelyan, Vahe Atoyan, Nelly Babayan, Yuma Iwashita, Kyosuke Kimura, Tomoya Komasaka, Koki Shishido, Taichi Nakamura, Mizuho Asada, Sankalp Jain, Alexey V. Zakharov, Haobo Wang, Wenjia Liu, Vladimir Chupakhin, Yoshihiro Uesawa. Consensus Modeling Strategies for Predicting Transthyretin Binding Affinity from Tox24 Challenge Data. Chemical Research in Toxicology 2025, 38
(6)
, 1061-1071. https://doi.org/10.1021/acs.chemrestox.5c00018
- Dmitriy M. Makarov, Nikolai N. Kalikin, Yury A. Budkov, Pavel Gurikov, Sergey E. Kruchinin, Abolghasem Jouyban, Michael G. Kiselev. Improved Solubility Predictions in scCO2 Using Thermodynamics-Informed Machine Learning Models. Journal of Chemical Information and Modeling 2025, 65
(8)
, 4043-4056. https://doi.org/10.1021/acs.jcim.5c00432
- Igor V. Tetko, Guillaume Godin, Kevin M. Jablonka, Adrian Mirza, Luc Patiny. Consensus Prediction of Chemical Reactions with OCHEM-R Platform. 2026, 45-52. https://doi.org/10.1007/978-3-032-04552-2_7
- Daan A. Jiskoot, Jeroen L.A. Pennings, Willie J.G.M. Peijnenburg, Gerard J.P. van Westen, Willem Jespers, Pim N.H. Wassenaar. In silico prediction of endocrine activity. Trends in Endocrinology & Metabolism 2025, 16 https://doi.org/10.1016/j.tem.2025.09.011
- Siwen Li, Haojie Xu, Fengxi Liu, Rong Ni, Yinping Shi, Xiao Li. In silico prediction of drug-induced cardiotoxicity with ensemble machine learning and structural pattern recognition. Molecular Diversity 2025, 59 https://doi.org/10.1007/s11030-025-11266-8
- Yuanyuan Dan, Junhao Ruan, Zhenghua Zhu, Hualong Yu. Predicting the Toxicity of Drug Molecules with Selecting Effective Descriptors Using a Binary Ant Colony Optimization (BACO) Feature Selection Approach. Molecules 2025, 30
(7)
, 1548. https://doi.org/10.3390/molecules30071548
Article Views are the COUNTER-compliant sum of full text article downloads since November 2008 (both PDF and HTML) across all institutions and individuals. These metrics are regularly updated to reflect usage leading up to the last few days.
Citations are the number of other articles citing this article, calculated by Crossref and updated daily. Find more information about Crossref citation counts.
The Altmetric Attention Score is a quantitative measure of the attention that a research article has received online. Clicking on the donut icon will load a page at altmetric.com with additional details about the score and the social media presence for the given article. Find more information on the Altmetric Attention Score and how the score is calculated.