Consensus Modeling Strategies for Predicting Transthyretin Binding Affinity from Tox24 Challenge Data

Transthyretin (TTR) is a key transporter of the thyroid hormone thyroxine, and chemicals that bind to TTR, displacing the hormone, can disrupt the endocrine system, even at low concentrations. This study evaluates computational modeling strategies developed during the Tox24 Challenge, using a data set of 1512 compounds tested for TTR binding affinity. Individual models from nine top-performing teams were analyzed for performance and uncertainty using regression metrics and applicability domains (AD). Consensus models were developed by averaging predictions across these models, with and without consideration of their ADs. While applying AD constraints in individual models generally improved external prediction accuracy (at the expense of reduced chemical space coverage), it had limited additional benefit for consensus models. Results showed that consensus models outperformed individual models, achieving a root-mean-square error (RMSE) of 19.8% on the test set, compared to an average RMSE of 20.9% for the nine individual models. Outliers consistently identified in several of these models indicate potential experimental artifacts and/or activity cliffs, requiring further investigation. Substructure importance analysis revealed that models prioritized different chemical features, and consensus averaging harmonized these divergent perspectives. These findings highlight the value of consensus modeling in improving predictive performance and addressing model limitations. Future work should focus on expanding chemical space coverage and refining experimental data sets to support public health protection.

Authors

Institutions

Publication Details

Journal
Chemical Research in Toxicology
Published
2025-05-15
DOI
https://doi.org/10.1021/acs.chemrestox.5c00018
Citations
6
Primary Topic
Computational Drug Discovery Methods
Type
article
Field-Weighted Citation Impact
9.03

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Consensus Modeling Strategies for Predicting Transthyretin Binding Affinity from Tox24 Challenge Data

Zaven Navoyan, Lusine Khondkaryan, Koki Shishido, Yoshihiro Iwashita et al.
6 citations
Chemical Research in Toxicology
Computational Drug Discovery Methods
9.03
article

Consensus Modeling Strategies for Predicting Transthyretin Binding Affinity from Tox24 Challenge Data

Zaven Navoyan, Lusine Khondkaryan, Koki Shishido, Yoshihiro Iwashita, Narek Abelyan, Nelly Babayan, Ani Tevosyan, Yoshihiro Uesawa, Haobo Wang, Bono Lučić, Vladimir Chupakhin, Alexey Zakharov, Mizuho Asada, L. Masfarre Pinto, Sankalp Jain, Wenjia Liu, K Kimura, Vahe Atoyan, Taichi Nakamura, Alexis Dougha, Hrach Yeghiazaryan, Thalita Cirino, Tomoya Komasaka, Mateusz Iwan, Antonija Kraljević
article en
6 citations

Abstract

Transthyretin (TTR) is a key transporter of the thyroid hormone thyroxine, and chemicals that bind to TTR, displacing the hormone, can disrupt the endocrine system, even at low concentrations. This study evaluates computational modeling strategies developed during the Tox24 Challenge, using a data set of 1512 compounds tested for TTR binding affinity. Individual models from nine top-performing teams were analyzed for performance and uncertainty using regression metrics and applicability domains (AD). Consensus models were developed by averaging predictions across these models, with and without consideration of their ADs. While applying AD constraints in individual models generally improved external prediction accuracy (at the expense of reduced chemical space coverage), it had limited additional benefit for consensus models. Results showed that consensus models outperformed individual models, achieving a root-mean-square error (RMSE) of 19.8% on the test set, compared to an average RMSE of 20.9% for the nine individual models. Outliers consistently identified in several of these models indicate potential experimental artifacts and/or activity cliffs, requiring further investigation. Substructure importance analysis revealed that models prioritized different chemical features, and consensus averaging harmonized these divergent perspectives. These findings highlight the value of consensus modeling in improving predictive performance and addressing model limitations. Future work should focus on expanding chemical space coverage and refining experimental data sets to support public health protection.

Chemical Research in ToxicologyVol. 38(6)
Centre National de la Recherche Scientifique (FR), University of Mostar (BA), Inserm (FR), Biocon (Switzerland) (CH), Mario Negri Institute for Pharmacological Research (IT), Université Paris Cité (FR), Meiji Pharmaceutical University (JP), Dalian University of Technology (CN), Beijing Film Academy (CN), Endometriosis UK (GB), Ruđer Bošković Institute (HR), National Center for Advancing Translational Sciences (US), University of Turin (IT), Simulations Plus (United States) (US)
State Committee of Science, National Center for Advancing Translational Sciences, HORIZON EUROPE Marie Sklodowska-Curie Actions
Zero hunger
Openalex Percentile: Top 2%
Computational Drug Discovery Methods
9.03
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.