Beyond peptide targeting sequences: machine learning of cellular condensate localization

Abstract

Proteins within cells must navigate complex intracellular environments to co-localize with partners and regulate functional cellular organization. In a recentScience paper, Kilgore et al. report the development of ProtGPS, a machine learning-trained predictor of protein localization within biomolecular condensates in cells that can be used to predict the ability of disease-linked mutations to dysregulate protein localization to biomolecular condensates.