Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Uncovering the Mechanism of Hepatotoxiciy of PFAS Targeting L-FABP Using GCN and Computational Modeling

Lucas Jividen, Tibo Duran, Xi-Zhi Niu, Jun Bai

TL;DR

A novel approach to enhance the prediction of PFAS binding affinities by isolating molecular fingerprints to construct graphs where then descriptors are set as the node features and unsupervised clustering identifies representative compounds for detailed binding studies.

Abstract

Per- and polyfluoroalkyl substances (PFAS) are persistent environmental pollutants with known toxicity and bioaccumulation issues. Their widespread industrial use and resistance to degradation have led to global environmental contamination and significant health concerns. While a minority of PFAS have been extensively studied, the toxicity of many PFAS remains poorly understood due to limited direct toxicological data. This study advances the predictive modeling of PFAS toxicity by combining semi-supervised graph convolutional networks (GCNs) with molecular descriptors and fingerprints. We propose a novel approach to enhance the prediction of PFAS binding affinities by isolating molecular fingerprints to construct graphs where then descriptors are set as the node features. This approach specifically captures the structural, physicochemical, and topological features of PFAS without overfitting due to an abundance of features. Unsupervised clustering then identifies representative compounds for detailed binding studies. Our results provide a more accurate ability to estimate PFAS hepatotoxicity to provide guidance in chemical discovery of new PFAS and the development of new safety regulations.

Uncovering the Mechanism of Hepatotoxiciy of PFAS Targeting L-FABP Using GCN and Computational Modeling

TL;DR

A novel approach to enhance the prediction of PFAS binding affinities by isolating molecular fingerprints to construct graphs where then descriptors are set as the node features and unsupervised clustering identifies representative compounds for detailed binding studies.

Abstract

Per- and polyfluoroalkyl substances (PFAS) are persistent environmental pollutants with known toxicity and bioaccumulation issues. Their widespread industrial use and resistance to degradation have led to global environmental contamination and significant health concerns. While a minority of PFAS have been extensively studied, the toxicity of many PFAS remains poorly understood due to limited direct toxicological data. This study advances the predictive modeling of PFAS toxicity by combining semi-supervised graph convolutional networks (GCNs) with molecular descriptors and fingerprints. We propose a novel approach to enhance the prediction of PFAS binding affinities by isolating molecular fingerprints to construct graphs where then descriptors are set as the node features. This approach specifically captures the structural, physicochemical, and topological features of PFAS without overfitting due to an abundance of features. Unsupervised clustering then identifies representative compounds for detailed binding studies. Our results provide a more accurate ability to estimate PFAS hepatotoxicity to provide guidance in chemical discovery of new PFAS and the development of new safety regulations.
Paper Structure (21 sections, 5 equations, 9 figures, 1 table)

This paper contains 21 sections, 5 equations, 9 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methods
  3. Graph Convolutional Network
  4. Definition
  5. Graph representation
  6. Message Passing
  7. Feature Propagation and Layer Stacking
  8. Uncovering of Binding Mechanisms
  9. Clustering
  10. MD simulation
  11. Experimental Setup
  12. Data
  13. Molecular Fingerprint and Descriptor Calculation
  14. Baseline Models
  15. MD setup
  16. ...and 6 more sections

Figures (9)

  • Figure 1: Method Flow Chart
  • Figure 2: Performance of binding affinity prediction models of PFAS docking into LFABP.
  • Figure 3: Unsupervised scoring function comparison to determine $K$ optimal clusters for the Ward algorithm.
  • Figure 4: Global PFAS Ward cluster visualization utilizing t-SNE.
  • Figure 5: Presence of functional groups in PFAS distributed among clusters.
  • ...and 4 more figures