Prediction of Liquid-Liquid Phase Separation Proteins Using Machine Learning

The liquid-liquid phase separation (LLPS) of biomolecules in cell underpins the formation of membraneless organelles, which are the condensates of protein, nucleic acid, or both, and play critical roles in cellular function. Dysregulation of LLPS is implicated in a number of diseases. Although the LLPS of biomolecules has been investigated intensively in recent years, the knowledge of the prevalence and distribution of phase separation proteins (PSPs) is still lag behind. Development of computational methods to predict PSPs is therefore of great importance for comprehensive understanding of the biological function of LLPS. Based on the PSPs collected in LLPSDB, we developed a sequence-based prediction tool for LLPS proteins (PSPredictor). This tool is the first attempt at general purpose PSP prediction that does not depend on specific protein types. Our model achieves a 10-fold cross-validation accuracy of 94.71%, and outperforms previously reported PSP prediction tools. PSPredictor identifies novel scaffold proteins for stress granules and predicts PSPs candidates in the human genome for further study. We also built an user-friendly PSPredictor web server (http://www.pkumdl.cn/PSPredictor) that predicts potential PSPs.