Causality-integrated graph learning for multi-endpoint toxicity prediction

Toxicity prediction remains a longstanding challenge in the safety assessment of numerous artificial chemicals. While conventional single-endpoint models are effective for predicting many molecular properties, they fail to capture the complex mechanisms underlying toxicity, which involve multiple molecular targets, interconnected pathways, and diverse outcomes. We present a causality-integrated graph learning framework that embeds toxicological mechanisms extracted from large-scale literature mining as directed graphs within deep learning (DL) models. By using chemical structure as input, the framework generates compound-specific perturbation profiles within a fixed causal space, enabling system-level classification, quantitative prioritization, and mechanistic interpretation across multiple outcomes. Focusing on endocrine-disrupting chemicals, we constructed a large-scale, causally organized knowledge graph (EDKG) and implemented the framework as EDKG-DL, a predictive model that incorporates mechanism-aware graph reasoning. Through extensive external validations, EDKG-DL outperforms structure-driven state-of-the-art approaches in both stability and cross-scenario generalization. This work establishes a mechanism-constrained, causality-informed learning paradigm that is highly relevant for multi-endpoint toxicity assessment and regulatory decision-making.

Authors

Institutions

Publication Details

Journal
Proceedings of the National Academy of Sciences
Published
2026-10-05
DOI
https://doi.org/10.1073/pnas.2608919123
Primary Topic
Computational Drug Discovery Methods
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Causality-integrated graph learning for multi-endpoint toxicity prediction

Tadahaya Mizuno, Wei Feng Shi, Changsheng Qu, Haoyue Tan et al.
Proceedings of the National Academy of Sciences
Computational Drug Discovery Methods
article

Causality-integrated graph learning for multi-endpoint toxicity prediction

Tadahaya Mizuno, Wei Feng Shi, Changsheng Qu, Haoyue Tan, Emilio Benfenati, Xuezhi Xiao, Huan Zhong, Jingfan Qiu, Qing Zhou, Jinsha Jin, Xiaowei Zhang, Dan Xu, Jing Guo, Huixiao Hong, Yan Mao, Yin Fang, Xiangyi Yu, Rong Zhang, Tong Bao, Lan Xie, Hongxia Yu
article en

Abstract

Toxicity prediction remains a longstanding challenge in the safety assessment of numerous artificial chemicals. While conventional single-endpoint models are effective for predicting many molecular properties, they fail to capture the complex mechanisms underlying toxicity, which involve multiple molecular targets, interconnected pathways, and diverse outcomes. We present a causality-integrated graph learning framework that embeds toxicological mechanisms extracted from large-scale literature mining as directed graphs within deep learning (DL) models. By using chemical structure as input, the framework generates compound-specific perturbation profiles within a fixed causal space, enabling system-level classification, quantitative prioritization, and mechanistic interpretation across multiple outcomes. Focusing on endocrine-disrupting chemicals, we constructed a large-scale, causally organized knowledge graph (EDKG) and implemented the framework as EDKG-DL, a predictive model that incorporates mechanism-aware graph reasoning. Through extensive external validations, EDKG-DL outperforms structure-driven state-of-the-art approaches in both stability and cross-scenario generalization. This work establishes a mechanism-constrained, causality-informed learning paradigm that is highly relevant for multi-endpoint toxicity assessment and regulatory decision-making.

Proceedings of the National Academy of SciencesVol. 123(41)
National Center for Toxicological Research (US), United States Food and Drug Administration (US), Mario Negri Institute for Pharmacological Research (IT), Ministry of Ecology and Environment (CN), The Institute of Statistical Mathematics (JP), Statistical Service (CY), Statistical Research (United States) (US), The University of Tokyo (JP), Zhejiang University (CN), Nanjing University (CN), Ministry of Industry and Information Technology (CN)
Openalex Percentile: Top 12%
Computational Drug Discovery Methods
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.