Nanobody–antigen interaction prediction with ensemble deep learning and prompt-based protein language models

Abstract

Nanobodies can provide specific binding to divergent antigens, leading to many promising therapeutic and detection applications in recent years. Traditional technologies of nanobody discovery based on alpaca immunization and phage display are very time-consuming and labour-intensive. Despite recent progress in the study of nanobodies, developing fast and accurate computational tools for nanobody–antigen interaction (NAI) prediction is urgently desirable. Here we propose an ensemble deep learning-based framework named DeepNano-seq to predict general protein–protein interaction (PPI) containing NAI from pure sequence information. Quantitative comparison results show that DeepNano-seq possesses the best cross-species generalization ability among existing PPI algorithms. Nevertheless, several of the most effective PPI methods, including DeepNano-seq, demonstrate suboptimal performance for NAI prediction due to the distinction between NAI and PPI at both the pattern and data levels. Therefore, we organize NAI data from the public database for dedicated NAI modelling. Furthermore, we enhance the prediction pipeline of DeepNano-seq by directing the model’s attention to the antigen-binding sites through a prompt-based approach to present the final DeepNano. The comprehensive evaluation demonstrates that DeepNano performs superiorly in NAI prediction and virtual screening of nanobodies. Overall, DeepNano-seq and DeepNano can offer powerful tools for nanobody discovery. Predicting nanobody–antigen interactions is crucial for advancing nanobody development in drug discovery, but it remains a challenging task. Deng et al. propose DeepNano to enhance the prediction of nanobody–antigen interactions, facilitating virtual screening of target nanobodies.