Identifying pathogenetic variants and inferring their impact on protein-protein interactions sheds light on their functional consequences on diseases.Limited by the availability of experimental data on the consequence...Identifying pathogenetic variants and inferring their impact on protein-protein interactions sheds light on their functional consequences on diseases.Limited by the availability of experimental data on the consequences of protein interaction,most existing methods focus on building models to predict changes in protein binding affinity.Here,we introduced MIPPI,an end-to-end,interpretable transformer-based deep learning model that learns features directly from sequences by leveraging the interaction data from IMEx.MIPPI was specifically trained to determine the types of variant impact(increasing,decreasing,disrupting,and no effect)on protein-protein interactions.We demonstrate the accuracy of MIPPI and provide interpretation through the analysis of learned attention weights,which exhibit correlations with the amino acids interacting with the variant.Moreover,we showed the practicality of MIPPI in prioritizing de novo mutations associated with complex neurodevelopmental disorders and the potential to determine the pathogenic and driving mutations.Finally,we experimentally validated the functional impact of several variants identified in patients with such disorders.Overall,MIPPI emerges as a versatile,robust,and interpretable model,capable of effectively predicting mutation impacts on protein-protein interactions and facilitating the discovery of clinically actionable variants.展开更多
基金supported by grants from STI 2030-Major Projects(no.2022ZD0209100)the National Natural Science Foundation of China(nos.81971292 and 82150610506)+3 种基金the Natural Science Foundation of Shanghai(no.21ZR1428600)the Medical-Engineering Cross Foundation of Shanghai Jiao Tong University(nos.YG2022ZD026 and YG2023ZD27)SJTU Trans-med Awards Research(no.20220103)the Paul K.and Diane Shumaker Endowment Fund at University of Missouri.
文摘Identifying pathogenetic variants and inferring their impact on protein-protein interactions sheds light on their functional consequences on diseases.Limited by the availability of experimental data on the consequences of protein interaction,most existing methods focus on building models to predict changes in protein binding affinity.Here,we introduced MIPPI,an end-to-end,interpretable transformer-based deep learning model that learns features directly from sequences by leveraging the interaction data from IMEx.MIPPI was specifically trained to determine the types of variant impact(increasing,decreasing,disrupting,and no effect)on protein-protein interactions.We demonstrate the accuracy of MIPPI and provide interpretation through the analysis of learned attention weights,which exhibit correlations with the amino acids interacting with the variant.Moreover,we showed the practicality of MIPPI in prioritizing de novo mutations associated with complex neurodevelopmental disorders and the potential to determine the pathogenic and driving mutations.Finally,we experimentally validated the functional impact of several variants identified in patients with such disorders.Overall,MIPPI emerges as a versatile,robust,and interpretable model,capable of effectively predicting mutation impacts on protein-protein interactions and facilitating the discovery of clinically actionable variants.
