Machine Learning and Structural Dynamics-Based Approach to Reveal Molecular Mechanism of PTEN Missense Mutations Shared by Cancer and Autism Spectrum Disorder DOI
Miao Yang, Jingran Wang, Ziyun Zhou

и другие.

Journal of Chemical Information and Modeling, Год журнала: 2025, Номер unknown

Опубликована: Апрель 14, 2025

Missense mutations in oncogenic proteins that are concurrently associated with neurodevelopmental disorders have garnered significant attention. Phosphatase and tensin homologue (PTEN) serves as a paradigmatic model for mapping its mutational landscape identifying genotypic predictors of distinct phenotypic outcomes, including cancer autism spectrum disorder (ASD). Despite extensive research into the genotype-phenotype correlations PTEN mutations, mechanisms underlying dual association specific both ASD (PTEN-cancer/ASD mutations) remain elusive. This study introduces an integrative approach combines machine learning (ML) structural dynamics to elucidate molecular effects PTEN-cancer/ASD mutations. Analysis biophysical network-biology-based signatures reveals complex energetic functional landscape. Subsequently, ML corresponding integrated score were developed classify predict underscoring significance protein predicting cellular phenotypes. Further simulations demonstrated induce dynamic alterations characterized by open conformational changes restricted P loop coupled interdomain allosteric regulation. aims enhance understanding through interpretable analysis. By shared between ASD, findings pave way development novel therapeutic strategies.

Язык: Английский

Decoding Mechanisms of PTEN Missense Mutations in Cancer and Autism Spectrum Disorder using Interpretable Machine Learning Approaches DOI Creative Commons
Miao Yang, Jingran Wang, Ziyun Zhou

и другие.

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2025, Номер unknown

Опубликована: Янв. 21, 2025

ABSTRACT Missense mutations in oncogenic proteins that are concurrently associated with neurodevelopmental disorders have garnered significant attention. Phosphatase and tensin homolog (PTEN) serves as a paradigmatic model for mapping its mutational landscape identifying genotypic predictors of distinct phenotypic outcomes, including cancer autism spectrum disorder (ASD). Despite extensive research into the genotype-phenotype correlations PTEN mutations, mechanisms underlying dual association specific both ASD (PTEN-cancer/ASD mutations) remain elusive. This study introduces an integrative approach combines machine learning (ML) structural dynamics to elucidate molecular effects PTEN-cancer/ASD mutations. Analysis biophysical network biology-based signatures reveals complex energetic functional landscape. Subsequently, ML corresponding integrated score were developed classify predict underscoring significance protein predicting cellular phenotypes. Further simulations demonstrated induce dynamic alterations characterized by open conformational changes restricted P loop coupled inter-domain allosteric regulation. aims enhance understanding through interpretable analysis. By shared between ASD, findings pave way development novel therapeutic strategies.

Язык: Английский

Процитировано

0
Machine Learning and Structural Dynamics-Based Approach to Reveal Molecular Mechanism of PTEN Missense Mutations Shared by Cancer and Autism Spectrum Disorder DOI
Miao Yang, Jingran Wang, Ziyun Zhou

и другие.

Journal of Chemical Information and Modeling, Год журнала: 2025, Номер unknown

Опубликована: Апрель 14, 2025

Missense mutations in oncogenic proteins that are concurrently associated with neurodevelopmental disorders have garnered significant attention. Phosphatase and tensin homologue (PTEN) serves as a paradigmatic model for mapping its mutational landscape identifying genotypic predictors of distinct phenotypic outcomes, including cancer autism spectrum disorder (ASD). Despite extensive research into the genotype-phenotype correlations PTEN mutations, mechanisms underlying dual association specific both ASD (PTEN-cancer/ASD mutations) remain elusive. This study introduces an integrative approach combines machine learning (ML) structural dynamics to elucidate molecular effects PTEN-cancer/ASD mutations. Analysis biophysical network-biology-based signatures reveals complex energetic functional landscape. Subsequently, ML corresponding integrated score were developed classify predict underscoring significance protein predicting cellular phenotypes. Further simulations demonstrated induce dynamic alterations characterized by open conformational changes restricted P loop coupled interdomain allosteric regulation. aims enhance understanding through interpretable analysis. By shared between ASD, findings pave way development novel therapeutic strategies.

Язык: Английский

Процитировано

0