Predicting Bioconcentration Factors of Per- and Polyfluoroalkyl Substances Using a Directed Message Passing Neural Network with Multimodal Feature Fusion
- 20 May 2025
- journal article
- Published by American Chemical Society (ACS) in Environmental Science & Technology
- Vol. 59 (21) , 10286-10298
Abstract
Amid growing concerns regarding the ecological risks posed by emerging contaminants, per- and polyfluoroalkyl substances (PFASs) present significant challenges for risk assessment due to their structural diversity and the paucity of experimental data on their bioaccumulation. This study investigated the bioconcentration factors (BCFs) of 18 emerging and legacy PFASs using zebrafish in a flow-through exposure system and constructed a robust BCF prediction model to address the data gaps associated with numerous novel PFASs. Experimental results indicated that perfluoro(3,5,7,9,11-pentaoxadodecanoic) acid (PFO5DoDA) and perfluoro-2,5-dimethyl-3,6-dioxanonanoic acid (C9 HFPO-TA) exhibited higher bioaccumulation potential than perfluorooctanoic acid (PFOA). A multimodal feature-fused directed message passing neural network (FF-DMPNN) model was constructed, integrating molecular graph representations, physicochemical descriptors, and bioassay data reflecting absorption, distribution, metabolism, and excretion characteristics. The FF-DMPNN model demonstrated superior predictive performance compared to conventional machine learning approaches by providing a more complete representation of molecular structures and physicochemical properties, achieving higher accuracy (R2 = 0.742) and robustness in predicting BCF values for PFASs. Application of the model to a comprehensive PFAS database identified 2.45% of chemicals as bioaccumulative, highlighting the need for regulatory attention. Overall, this study provides critical insights into the bioconcentration risks associated with PFASs and offers a reliable framework for prioritizing regulatory actions for these emerging contaminants, addressing a pressing need for their effective environmental management.Keywords
Funding Information
- China Postdoctoral Science Foundation (2023M740656, GZB20240161)
- National Natural Science Foundation of China (22406025, U22A20618)
This publication has 59 references indexed in Scilit:
- Comparative in vitro hepatic clearances of commonly used antidepressants, antipsychotics, and anti-inflammatory agents in rainbow trout liver S9 fractionsAquatic Toxicology, 2024
- Cyanotoxin cylindrospermopsin disrupts lipid homeostasis and metabolism in a 3D in vitro model of the human liverChemico-Biological Interactions, 2024
- Immunomodulation and exposure to per- and polyfluoroalkyl substances: an overview of the current evidence from animal and human studiesArchives of Toxicology, 2022
- Machine learning in drug design: Use of artificial intelligence to explore the chemical structure–biological activity relationshipWIREs Computational Molecular Science, 2021
- Evaluation of Published Bioconcentration Factor (BCF) and Bioaccumulation Factor (BAF) Data for Per- and Polyfluoroalkyl Substances Across Aquatic SpeciesEnvironmental Toxicology and Chemistry, 2021
- Per- and Polyfluoroalkyl Substance Toxicity and Human Health Review: Current State of Knowledge and Strategies for Informing Future ResearchEnvironmental Toxicology and Chemistry, 2020
- Triphenyl phosphate is a selective PPARγ modulator that does not induce brite adipogenesis in vitro and in vivoArchives of Toxicology, 2020
- Comprehensive kinetic and modeling analyses revealed CYP2C9 and 3A4 determine terbinafine metabolic clearance and bioactivationBiochemical Pharmacology, 2019
- The responses of Oncorhynchus mykiss coping with BDE-47 stress via PXR-mediated detoxification and Nrf2-mediated antioxidation systemAquatic Toxicology, 2019
- An approach for classification of highly imbalanced data using weighting and undersamplingAmino Acids, 2010