Dynamicasome—a molecular dynamics-guided and AI-driven pathogenicity prediction catalogue for all genetic mutations
Abstract Advances in genomic medicine accelerate the identification of mutations in disease-associated genes, but the pathogenicity of many mutations remains unknown, hindering their use in diagnostics and clinical decision-making. Predictive AI models are generated to combat this issue, but current...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Communications Biology |
| Online Access: | https://doi.org/10.1038/s42003-025-08334-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849761453237600256 |
|---|---|
| author | Naeyma N. Islam Mathew A. Coban Jessica M. Fuller Caleb Weber Rohit Chitale Benjamin Jussila Trisha J. Brock Cui Tao Thomas R. Caulfield |
| author_facet | Naeyma N. Islam Mathew A. Coban Jessica M. Fuller Caleb Weber Rohit Chitale Benjamin Jussila Trisha J. Brock Cui Tao Thomas R. Caulfield |
| author_sort | Naeyma N. Islam |
| collection | DOAJ |
| description | Abstract Advances in genomic medicine accelerate the identification of mutations in disease-associated genes, but the pathogenicity of many mutations remains unknown, hindering their use in diagnostics and clinical decision-making. Predictive AI models are generated to combat this issue, but current tools display low accuracy when tested against functionally validated datasets. We show that integrating detailed conformational data extracted from molecular dynamics simulations (MDS) into advanced AI-based models increases their predictive power. We carry out an exhaustive mutational analysis of the disease gene PMM2 and subject structural models of each variant to MDS. AI models trained on this dataset outperform existing tools when predicting the known pathogenicity of mutations. Our best performing model, a neuronal networks model, also predicts the pathogenicity of several PMM2 mutations currently considered of unknown significance. We believe this model helps alleviate the burden of unknown variants in genomic medicine. |
| format | Article |
| id | doaj-art-328700c89ddc4e979e735b9086013621 |
| institution | DOAJ |
| issn | 2399-3642 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Communications Biology |
| spelling | doaj-art-328700c89ddc4e979e735b90860136212025-08-20T03:06:01ZengNature PortfolioCommunications Biology2399-36422025-07-018111410.1038/s42003-025-08334-yDynamicasome—a molecular dynamics-guided and AI-driven pathogenicity prediction catalogue for all genetic mutationsNaeyma N. Islam0Mathew A. Coban1Jessica M. Fuller2Caleb Weber3Rohit Chitale4Benjamin Jussila5Trisha J. Brock6Cui Tao7Thomas R. Caulfield8Department of Neuroscience, Mayo ClinicDepartment of Neuroscience, Mayo ClinicDepartment of Neuroscience, Mayo ClinicDepartment of Neuroscience, Mayo ClinicDepartment of Infectious Disease, Mayo ClinicInVivo Biosystems, Inc.InVivo Biosystems, Inc.Department of Artificial Intelligence and Informatics, Mayo ClinicDepartment of Neuroscience, Mayo ClinicAbstract Advances in genomic medicine accelerate the identification of mutations in disease-associated genes, but the pathogenicity of many mutations remains unknown, hindering their use in diagnostics and clinical decision-making. Predictive AI models are generated to combat this issue, but current tools display low accuracy when tested against functionally validated datasets. We show that integrating detailed conformational data extracted from molecular dynamics simulations (MDS) into advanced AI-based models increases their predictive power. We carry out an exhaustive mutational analysis of the disease gene PMM2 and subject structural models of each variant to MDS. AI models trained on this dataset outperform existing tools when predicting the known pathogenicity of mutations. Our best performing model, a neuronal networks model, also predicts the pathogenicity of several PMM2 mutations currently considered of unknown significance. We believe this model helps alleviate the burden of unknown variants in genomic medicine.https://doi.org/10.1038/s42003-025-08334-y |
| spellingShingle | Naeyma N. Islam Mathew A. Coban Jessica M. Fuller Caleb Weber Rohit Chitale Benjamin Jussila Trisha J. Brock Cui Tao Thomas R. Caulfield Dynamicasome—a molecular dynamics-guided and AI-driven pathogenicity prediction catalogue for all genetic mutations Communications Biology |
| title | Dynamicasome—a molecular dynamics-guided and AI-driven pathogenicity prediction catalogue for all genetic mutations |
| title_full | Dynamicasome—a molecular dynamics-guided and AI-driven pathogenicity prediction catalogue for all genetic mutations |
| title_fullStr | Dynamicasome—a molecular dynamics-guided and AI-driven pathogenicity prediction catalogue for all genetic mutations |
| title_full_unstemmed | Dynamicasome—a molecular dynamics-guided and AI-driven pathogenicity prediction catalogue for all genetic mutations |
| title_short | Dynamicasome—a molecular dynamics-guided and AI-driven pathogenicity prediction catalogue for all genetic mutations |
| title_sort | dynamicasome a molecular dynamics guided and ai driven pathogenicity prediction catalogue for all genetic mutations |
| url | https://doi.org/10.1038/s42003-025-08334-y |
| work_keys_str_mv | AT naeymanislam dynamicasomeamoleculardynamicsguidedandaidrivenpathogenicitypredictioncatalogueforallgeneticmutations AT mathewacoban dynamicasomeamoleculardynamicsguidedandaidrivenpathogenicitypredictioncatalogueforallgeneticmutations AT jessicamfuller dynamicasomeamoleculardynamicsguidedandaidrivenpathogenicitypredictioncatalogueforallgeneticmutations AT calebweber dynamicasomeamoleculardynamicsguidedandaidrivenpathogenicitypredictioncatalogueforallgeneticmutations AT rohitchitale dynamicasomeamoleculardynamicsguidedandaidrivenpathogenicitypredictioncatalogueforallgeneticmutations AT benjaminjussila dynamicasomeamoleculardynamicsguidedandaidrivenpathogenicitypredictioncatalogueforallgeneticmutations AT trishajbrock dynamicasomeamoleculardynamicsguidedandaidrivenpathogenicitypredictioncatalogueforallgeneticmutations AT cuitao dynamicasomeamoleculardynamicsguidedandaidrivenpathogenicitypredictioncatalogueforallgeneticmutations AT thomasrcaulfield dynamicasomeamoleculardynamicsguidedandaidrivenpathogenicitypredictioncatalogueforallgeneticmutations |