2026-10-14T07:26:31Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34036617 2026-09-30T18:18:55Z category_4 category_146 category_13 category_873 category_734 portal_63 item_type_6 month_year_09_2026

An Active Learning Framework for PFAS-Free Surfactant Discovery in Firefighting Foams Xin Wang (91924) Hongwei Zhang (28335) Xingtong Yu (25145562) Seokgyun Ham (8575374) Brian Lattimer (16504424) Rui Qiao (458542) Biochemistry Space Science Genetics Chemical Sciences not elsewhere classified Biological Sciences not elsewhere classified source code used molecular graphs using molecular dynamics simulations latent vectors learned https :// github driven computational paradigm commercial dtab benchmark adaptive sampling strategies tail hydrocarbon surfactants efficient discovery frameworks targeted chemical space chemical design insights access data set free surfactant discovery 124 cg surfactants active learning framework free surfactants discovery process significant improvement r </ publicly available polyfluoroalkyl substances performing candidates identify top health impacts growing concerns friendly alternatives four rounds firefighting foams design space bayesian optimization based autoencoder active learning >< sub 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 (<i>R</i>_int) 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. 2026-09-30T00:00:00Z Text Journal contribution 10.1021/acsomega.6c07702.s001 https://figshare.com/articles/journal_contribution/An_Active_Learning_Framework_for_PFAS-Free_Surfactant_Discovery_in_Firefighting_Foams/34036617 CC BY-NC 4.0