A Machine Learning Pipeline for estimating Binding Affinity to Serum Albumin and Half-Lives of Per- and Polyfluoroalkyl Substances in Humans

Per- and Polyfluoroalkyl substances (PFAS) are synthetic chemicals that pose environmental concerns due to their long half-lives and strong protein binding properties that have been reported. A decisive role is played by their binding to human serum albumin (HSA), which is the most abundant protein in human blood. This study focuses on developing an in silico tool that predicts both the binding affinity of PFAS to HSA and their half-lives in humans. We propose a linear computational pipeline consisting of two QSAR models: the first predicts PFAS-albumin association constants, while the second uses these predictions along with additional molecular features to estimate half-lives, enabling identification of structural characteristics that influence retention time in organisms.