Development, Evaluation and Application of a Multi-Representation Fusion Model for Accurate Prediction of Per- and Polyfluoroalkyl Substance (PFAS) Binding to Plasma Proteins

Clinical Snapshot

Key Findings

• P Value: Not reported in abstract

• Effect Size: Described as 'optimal comprehensive performance' compared to baseline models (specific metrics not provided)

• Primary Outcome: Prediction accuracy of PFAS-plasma protein binding using MURNet model

• Nnt Or Sensitivity: Tanimoto similarity applicability domain analysis demonstrates reliable prediction capability for PFAS homologues

• Confidence Interval: Not reported in abstract

Clinical Application

High feasibility as computational tool requiring only molecular structure input, cost-effective compared to experimental approaches Highly relevant given Australia's PFAS contamination issues around military bases and industrial sites. Could support TGA chemical assessment processes and inform NHMRC drinking water guidelines Relevant to populations exposed to PFAS contamination, particularly useful for regulatory agencies and toxicologists assessing health risks

Abstract

Per- and polyfluoroalkyl substances (PFAS) constitute a large and structurally diverse class of man-made chemicals. Their strong carbon-fluorine (C-F) bonds confer high environmental persistence, bioaccumulation, and various associated toxicities. As amphiphilic compounds, most PFAS bind to proteins and accumulate in protein-rich tissues, with such bioaccumulation exerting significant adverse impacts on human health. Accurate evaluation of the binding status between PFAS and proteins constitutes an essential step in health risk assessment. Traditional experiments and certain modeling approaches for analyzing PFAS bioaccumulation suffer from drawbacks such as time-consuming processes, high costs, or inadequate capture of molecular structural information, while existing machine learning-based prediction methods rely on single molecular representation, making it difficult to comprehensively encode the structural information on PFAS. Here, we propose MURNet, a multirepresentation fusion network model integrating chemical descriptors, 2D molecular graphs, and molecular fingerprints to predict PFAS-plasma protein binding. Compared with the state-of-the-art baseline models, MURNet achieves the optimal comprehensive performance. The multirepresentation fusion strategy generates higher-quality molecular features. Tanimoto similarity applicability domain analysis demonstrates MURNet's capability to reliably predict PFAS homologues. Case studies reveal the effectiveness of MURNet in screening PFAS with potential binding affinity to human serum albumin (HSA).

References

1. 1.Han, J., Song, X., Yi, D., Zhang, Y., Chu, Y., Wei, Y., He, S., & Bo, X. (2026). Development, evaluation and application of a multi-representation fusion model for accurate prediction of per- and polyfluoroalkyl substance (PFAS) binding to plasma proteins. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.5c03060