MEMO-stab: Sequence-based Annotation of Mutation Effect on Transmembrane Protein Stability with Protein Language Model-Driven Machine Learning

Transmembrane proteins are pivotal drug targets. Accurately predicting the impact of mutations on their stability can serve as an early indicator of alterations in protein function. Existing prediction methods based on protein crystal structures lack the capability for large-scale annotation of mutation effects on transmembrane proteins. In this study, we present a sequence-based protein language model-driven machine learning framework, MEMO-stab, to predict the effect of mutations on the stability of transmembrane proteins. MEMO-stab is an end-to-end binary classifier capable of rapidly and extensively annotating whether a mutation is destabilizing. We evaluated the integrative capability of MEMO-stab with eight diverse protein language models and conducted a performance comparison against alternative existing methods. We also designed case studies to further illustrate the advantage of our methods. MEMO-stab is the first sequence-based transmembrane protein-specific prediction tool capable of achieving reasonable results for destabilizing mutation prediction.