MpbPPI: a multi-task pre-training-based equivariant approach for the prediction of the effect of amino acid mutations on protein–protein interactions

The accurate prediction of the effect of amino acid mutations for protein–protein interactions (PPI [Formula: see text]) is a crucial task in protein engineering, as it provides insight into the relevant biological processes underpinning protein binding and provides a basis for further drug discovery. In this study, we propose MpbPPI, a novel multi-task pre-training-based geometric equivariance-preserving framework to predict PPI [Formula: see text]. Pre-training on a strictly screened pre-training dataset is employed to address the scarcity of protein–protein complex structures annotated with PPI [Formula: see text] values. MpbPPI employs a multi-task pre-training technique, forcing the framework to learn comprehensive backbone and side chain geometric regulations of protein–protein complexes at different scales. After pre-training, MpbPPI can generate high-quality representations capturing the effective geometric characteristics of labeled protein–protein complexes for downstream [Formula: see text] predictions. MpbPPI serves as a scalable framework supporting different sources of mutant-type (MT) protein–protein complexes for flexible application. Experimental results on four benchmark datasets demonstrate that MpbPPI is a state-of-the-art framework for PPI [Formula: see text] predictions. The data and source code are available at https://github.com/arantir123/MpbPPI.