Leveraging a large language model to predict protein phase transition: a physical, multiscale and interpretable approach

Abstract

AbstractProtein phase transitions (PPTs) from the soluble state to a dense liquid phase (forming droplets via liquid-liquid phase separation) or solid aggregates (such as amyloid) play key roles in pathological processes associated with age-related diseases such as Alzheimer’s disease (AD). Several computational frameworks are capable of separately predicting the formation of protein droplets or amyloid aggregates based on protein sequences, yet none have tackled the prediction of both within a unified framework. Recently, large language models (LLMs) have exhibited great success in protein structure prediction; however, they have not yet been used for PPTs. Here, we fine-tune a LLM for predicting PPTs and demonstrate its superior performance compared to suitable classical benchmarks. Due to the “black-box” nature of the LLM, we also employ a classical random forest model along with biophysical features to facilitate interpretation. Finally, focusing on AD-related proteins, we demonstrate that greater aggregation is associated with reduced gene expression in AD, suggesting a natural defense mechanism.Significance StatementThe protein phase transition is a physical mechanism associated with both physiological processes and age-related diseases. Here, we present a modeling approach for predicting a specific protein sequence’s propensity to undergo phase transitions directly from its sequence. Our methodology involves utilizing a large language model to analyze the likelihood of a given protein sequence existing in a particular material state. Additionally, for enhanced interpretability, we incorporate a classical knowledge-based model. Our results suggest the potential for accurately predicting the propensity to form either liquid or solid condensates. Furthermore, our findings indicate the potential regulation of this propensity by gene expression under pathological conditions to prevent aggregation.