Inferring the Effects of Protein Variants on Protein–Protein Interactions with Interpretable Transformer Representations

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 predic...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu, Zhe, Qian, Wei, Cai, Wenxiang, Song, Weichen, Wang, Weidi, Maharjan, Dhruba Tara, Cheng, Wenhong, Chen, Jue, Wang, Han, Xu, Dong, Lin, Guan Ning
Formato: Online Artículo Texto
Lenguaje:English
Publicado: AAAS 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10494974/
https://www.ncbi.nlm.nih.gov/pubmed/37701056
http://dx.doi.org/10.34133/research.0219
_version_ 1785104805155307520
author Liu, Zhe
Qian, Wei
Cai, Wenxiang
Song, Weichen
Wang, Weidi
Maharjan, Dhruba Tara
Cheng, Wenhong
Chen, Jue
Wang, Han
Xu, Dong
Lin, Guan Ning
author_facet Liu, Zhe
Qian, Wei
Cai, Wenxiang
Song, Weichen
Wang, Weidi
Maharjan, Dhruba Tara
Cheng, Wenhong
Chen, Jue
Wang, Han
Xu, Dong
Lin, Guan Ning
author_sort Liu, Zhe
collection PubMed
description 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.
format Online
Article
Text
id pubmed-10494974
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher AAAS
record_format MEDLINE/PubMed
spelling pubmed-104949742023-09-12 Inferring the Effects of Protein Variants on Protein–Protein Interactions with Interpretable Transformer Representations Liu, Zhe Qian, Wei Cai, Wenxiang Song, Weichen Wang, Weidi Maharjan, Dhruba Tara Cheng, Wenhong Chen, Jue Wang, Han Xu, Dong Lin, Guan Ning Research (Wash D C) Research Article 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. AAAS 2023-09-11 /pmc/articles/PMC10494974/ /pubmed/37701056 http://dx.doi.org/10.34133/research.0219 Text en Copyright © 2023 Zhe Liu et al. https://creativecommons.org/licenses/by/4.0/Exclusive licensee Science and Technology Review Publishing House. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution License 4.0 (CC BY 4.0) (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Research Article
Liu, Zhe
Qian, Wei
Cai, Wenxiang
Song, Weichen
Wang, Weidi
Maharjan, Dhruba Tara
Cheng, Wenhong
Chen, Jue
Wang, Han
Xu, Dong
Lin, Guan Ning
Inferring the Effects of Protein Variants on Protein–Protein Interactions with Interpretable Transformer Representations
title Inferring the Effects of Protein Variants on Protein–Protein Interactions with Interpretable Transformer Representations
title_full Inferring the Effects of Protein Variants on Protein–Protein Interactions with Interpretable Transformer Representations
title_fullStr Inferring the Effects of Protein Variants on Protein–Protein Interactions with Interpretable Transformer Representations
title_full_unstemmed Inferring the Effects of Protein Variants on Protein–Protein Interactions with Interpretable Transformer Representations
title_short Inferring the Effects of Protein Variants on Protein–Protein Interactions with Interpretable Transformer Representations
title_sort inferring the effects of protein variants on protein–protein interactions with interpretable transformer representations
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10494974/
https://www.ncbi.nlm.nih.gov/pubmed/37701056
http://dx.doi.org/10.34133/research.0219
work_keys_str_mv AT liuzhe inferringtheeffectsofproteinvariantsonproteinproteininteractionswithinterpretabletransformerrepresentations
AT qianwei inferringtheeffectsofproteinvariantsonproteinproteininteractionswithinterpretabletransformerrepresentations
AT caiwenxiang inferringtheeffectsofproteinvariantsonproteinproteininteractionswithinterpretabletransformerrepresentations
AT songweichen inferringtheeffectsofproteinvariantsonproteinproteininteractionswithinterpretabletransformerrepresentations
AT wangweidi inferringtheeffectsofproteinvariantsonproteinproteininteractionswithinterpretabletransformerrepresentations
AT maharjandhrubatara inferringtheeffectsofproteinvariantsonproteinproteininteractionswithinterpretabletransformerrepresentations
AT chengwenhong inferringtheeffectsofproteinvariantsonproteinproteininteractionswithinterpretabletransformerrepresentations
AT chenjue inferringtheeffectsofproteinvariantsonproteinproteininteractionswithinterpretabletransformerrepresentations
AT wanghan inferringtheeffectsofproteinvariantsonproteinproteininteractionswithinterpretabletransformerrepresentations
AT xudong inferringtheeffectsofproteinvariantsonproteinproteininteractionswithinterpretabletransformerrepresentations
AT linguanning inferringtheeffectsofproteinvariantsonproteinproteininteractionswithinterpretabletransformerrepresentations