Protein multi‐level structure feature‐integrated deep learning method for mutational effect prediction

Through iterative rounds of mutation and selection, proteins can be engineered to enhance their desired biological functions. Nevertheless, identifying optimal mutation sites for directed evolution remains challenging due to the vastness of the protein sequence landscape and the epistatic mutational effects across residues. To address this challenge, we introduce MLSmut, a deep learning‐based approach that leverages multi‐level structural features of proteins. MLSmut extracts salient information from protein co‐evolution, sequence semantics, and geometric features to predict the mutational effect. Extensive benchmark evaluations on 10 single‐site and two multi‐site deep mutation scanning datasets demonstrate that MLSmut surpasses existing methods in predicting mutational outcomes. To overcome the limited training data availability, we employ a two‐stage training strategy: initial coarse‐tuning on a large corpus of unlabeled protein data followed by fine‐tuning on a curated dataset of 40−100 experimental measurements. This approach enables our model to achieve satisfactory performance on downstream protein prediction tasks. Importantly, our model holds the potential to predict the mutational effects of any protein sequence. Collectively, these findings suggest that our approach can substantially reduce the reliance on laborious wet lab experiments and deepen our understanding of the intricate relationships between mutations and protein function. Graphical and Lay Summary Identifying optimal mutation sites for directed evolution is challenging due to the complexity of protein sequences and mutational effects. We introduce a model for predicting protein mutation effects that integrates protein co‐evolution, sequence semantics, and geometric features. Using data augmentation, our model performs well with only a few experimental data.