A Multitask Active Learning Framework with Probabilistic Modeling for Multi-Species Acute Toxicity Prediction

Read full text Summarise with VIRAT
Authors: Tianyu Han, Jingjing Wang, Yanpeng Zhao, Ying Lin, Lu Yu, Song He, Peng Zan, Xiaochen Bo
Cited by: 0
References: 38

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Predicting acute toxicity across species is essential for early-stage drug safety evaluation. While recent efforts have primarily focused on improving predictive accuracy, they often fail to address two critical issues: the substantial divergence in toxicity mechanisms among different species, and the inherent noise present in experimental data. To bridge this gap, we introduce a Probabilistic Multitask Active Learning (PMAL) framework for multi-species acute toxicity prediction. Our framework integrates two key modules: a Probabilistic Multitask Learning (PML) component which jointly models the predictive distributions of multiple toxicity endpoints from a probabilistic viewpoint, and an Uncertainty-based Active Learning (UAL) component which strategically selects the most informative compounds for experimental annotation based on predictive uncertainty. Empirical evaluations demonstrate that PMAL surpasses state-of-the-art methods and is capable of providing well-calibrated uncertainty estimates for small molecules across diverse toxicity endpoints. Beyond advancing multi-species toxicity prediction, the core design principles of PMAL offer a generalizable paradigm for learning in noisy multi-task environments.

Fields of Study & Subjects

Computational Drug Discovery Methods Animal testing and alternatives Machine Learning in Materials Science

Publication details

Journal / source
Molecules
Volume
31
Issue
7
Pages
1144–1144
Publication date
30 March 2026
Language
EN