An Active Learning Framework for PFAS-Free Surfactant Discovery in Firefighting Foams
- 1Virginia Tech , 635 Prices Fork Road , , ,
- 2The Chinese University of Hong Kong , Ma Liu Shui, New Territories , ,
Abstract
The growing concerns over the environmental and health impacts of per- and polyfluoroalkyl substances (PFAS) in firefighting foams have necessitated the development of efficient discovery frameworks for eco-friendly alternatives. In this work, we demonstrate an integrated pipeline leveraging active learning and coarse-grained (CG) molecular dynamics simulations to explore the design space of single-tail hydrocarbon surfactants for inhibiting fuel transport across interfaces. We design a targeted chemical space of 12,124 CG surfactants, represented by latent vectors learned from molecular graphs using a GNN-based autoencoder. Through four rounds of active learning, simulating only 2.5% of this space, we identify top-performing candidates with calculated interfacial transport resistance (Rint) reaching 1641.5 s/m, representing a significant improvement over the commercial DTAB benchmark. Furthermore, we evaluate the effectiveness of constant and adaptive sampling strategies in Bayesian Optimization during the discovery process. Overall, this work establishes an active-learning-driven computational paradigm for accelerating the discovery of PFAS-free surfactants, providing both chemical design insights and an open-access data set to guide future experimental synthesis and validation. All data and source code used in this study are publicly available at https://github.com/elliewang21/Active_Learning.
Related
- Active Learning for Fragment-Based Kinase Inhibitor Discovery using Docking
- MLIP Detective: Active Failure Mode Discovery Beyond Benchmark Scores for Machine-Learning Interatomic Potentials
- Linear inductive bias boosts extrapolative molecular discovery by Bayesian active learning in the small-data limit
- Accelerated Discovery of BPA-Free Dental Resin Candidates through Active Learning of Network-Emergent Properties
- GastroDL-Fusion: A Dual-Modal Deep Learning Framework Integrating Protein–Ligand Complexes and Gene Sequences for Gastrointestinal Disease Drug Discovery
BibTeX
@article{wang2026active,
title = {{An Active Learning Framework for PFAS-Free Surfactant Discovery in Firefighting Foams}},
author = {Xin Wang and Hongwei Zhang and Xingtong Yu and Seokgyun Ham and Brian Lattimer and Rui Qiao},
journal = {ACS omega},
year = {2026},
month = sep,
doi = {10.1021/acsomega.6c07702},
url = {https://europepmc.org/article/PMC/PMC13670300},
note = {CC BY},
}
RIS
TY - JOUR
TI - An Active Learning Framework for PFAS-Free Surfactant Discovery in Firefighting Foams
AU - Xin Wang
AU - Hongwei Zhang
AU - Xingtong Yu
AU - Seokgyun Ham
AU - Brian Lattimer
AU - Rui Qiao
PY - 2026
DA - 2026/09/30
JO - ACS omega
DO - 10.1021/acsomega.6c07702
UR - https://europepmc.org/article/PMC/PMC13670300
AB - The growing concerns over the environmental and health impacts of per- and polyfluoroalkyl substances (PFAS) in firefighting foams have necessitated the development of efficient discovery frameworks for eco-friendly alternatives. In this work, we demonstrate an integrated pipeline leveraging active learning and coarse-grained (CG) molecular dynamics simulations to explore the design space of single-tail hydrocarbon surfactants for inhibiting fuel transport across interfaces. We design a targeted chemical space of 12,124 CG surfactants, represented by latent vectors learned from molecular graphs using a GNN-based autoencoder. Through four rounds of active learning, simulating only 2.5% of this space, we identify top-performing candidates with calculated interfacial transport resistance (Rint) reaching 1641.5 s/m, representing a significant improvement over the commercial DTAB benchmark. Furthermore, we evaluate the effectiveness of constant and adaptive sampling strategies in Bayesian Optimization during the discovery process. Overall, this work establishes an active-learning-driven computational paradigm for accelerating the discovery of PFAS-free surfactants, providing both chemical design insights and an open-access data set to guide future experimental synthesis and validation. All data and source code used in this study are publicly available at https://github.com/elliewang21/Active_Learning.
SN - 2470-1343
ER -