Machine Learning Generation of Dynamic Protein Conformational Ensembles
Machine learning has achieved remarkable success across a broad range of scientific and engineering disciplines, particularly its use for predicting native protein structures from sequence information alone. However, biomolecules are inherently dynamic, and there is a pressing need for accurate pred...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Molecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1420-3049/28/10/4047 |
| _version_ | 1797598906758987776 |
|---|---|
| author | Li-E Zheng Shrishti Barethiya Erik Nordquist Jianhan Chen |
| author_facet | Li-E Zheng Shrishti Barethiya Erik Nordquist Jianhan Chen |
| author_sort | Li-E Zheng |
| collection | DOAJ |
| description | Machine learning has achieved remarkable success across a broad range of scientific and engineering disciplines, particularly its use for predicting native protein structures from sequence information alone. However, biomolecules are inherently dynamic, and there is a pressing need for accurate predictions of dynamic structural ensembles across multiple functional levels. These problems range from the relatively well-defined task of predicting conformational dynamics around the native state of a protein, which traditional molecular dynamics (MD) simulations are particularly adept at handling, to generating large-scale conformational transitions connecting distinct functional states of structured proteins or numerous marginally stable states within the dynamic ensembles of intrinsically disordered proteins. Machine learning has been increasingly applied to learn low-dimensional representations of protein conformational spaces, which can then be used to drive additional MD sampling or directly generate novel conformations. These methods promise to greatly reduce the computational cost of generating dynamic protein ensembles, compared to traditional MD simulations. In this review, we examine recent progress in machine learning approaches towards generative modeling of dynamic protein ensembles and emphasize the crucial importance of integrating advances in machine learning, structural data, and physical principles to achieve these ambitious goals. |
| first_indexed | 2024-03-11T03:27:14Z |
| format | Article |
| id | doaj.art-4287f4b0687644b48e6d2e9e4cbc66f2 |
| institution | Directory Open Access Journal |
| issn | 1420-3049 |
| language | English |
| last_indexed | 2024-03-11T03:27:14Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Molecules |
| spelling | doaj.art-4287f4b0687644b48e6d2e9e4cbc66f22023-11-18T02:38:31ZengMDPI AGMolecules1420-30492023-05-012810404710.3390/molecules28104047Machine Learning Generation of Dynamic Protein Conformational EnsemblesLi-E Zheng0Shrishti Barethiya1Erik Nordquist2Jianhan Chen3Department of Gynecology, The First Affiliated Hospital of Fujian Medical University, Fuzhou 350005, ChinaDepartment of Chemistry, University of Massachusetts Amherst, Amherst, MA 01003, USADepartment of Chemistry, University of Massachusetts Amherst, Amherst, MA 01003, USADepartment of Chemistry, University of Massachusetts Amherst, Amherst, MA 01003, USAMachine learning has achieved remarkable success across a broad range of scientific and engineering disciplines, particularly its use for predicting native protein structures from sequence information alone. However, biomolecules are inherently dynamic, and there is a pressing need for accurate predictions of dynamic structural ensembles across multiple functional levels. These problems range from the relatively well-defined task of predicting conformational dynamics around the native state of a protein, which traditional molecular dynamics (MD) simulations are particularly adept at handling, to generating large-scale conformational transitions connecting distinct functional states of structured proteins or numerous marginally stable states within the dynamic ensembles of intrinsically disordered proteins. Machine learning has been increasingly applied to learn low-dimensional representations of protein conformational spaces, which can then be used to drive additional MD sampling or directly generate novel conformations. These methods promise to greatly reduce the computational cost of generating dynamic protein ensembles, compared to traditional MD simulations. In this review, we examine recent progress in machine learning approaches towards generative modeling of dynamic protein ensembles and emphasize the crucial importance of integrating advances in machine learning, structural data, and physical principles to achieve these ambitious goals.https://www.mdpi.com/1420-3049/28/10/4047autoencoderBoltzmann generatorcollective variabledimension reductionenhanced samplinggenerative adversarial network |
| spellingShingle | Li-E Zheng Shrishti Barethiya Erik Nordquist Jianhan Chen Machine Learning Generation of Dynamic Protein Conformational Ensembles Molecules autoencoder Boltzmann generator collective variable dimension reduction enhanced sampling generative adversarial network |
| title | Machine Learning Generation of Dynamic Protein Conformational Ensembles |
| title_full | Machine Learning Generation of Dynamic Protein Conformational Ensembles |
| title_fullStr | Machine Learning Generation of Dynamic Protein Conformational Ensembles |
| title_full_unstemmed | Machine Learning Generation of Dynamic Protein Conformational Ensembles |
| title_short | Machine Learning Generation of Dynamic Protein Conformational Ensembles |
| title_sort | machine learning generation of dynamic protein conformational ensembles |
| topic | autoencoder Boltzmann generator collective variable dimension reduction enhanced sampling generative adversarial network |
| url | https://www.mdpi.com/1420-3049/28/10/4047 |
| work_keys_str_mv | AT liezheng machinelearninggenerationofdynamicproteinconformationalensembles AT shrishtibarethiya machinelearninggenerationofdynamicproteinconformationalensembles AT eriknordquist machinelearninggenerationofdynamicproteinconformationalensembles AT jianhanchen machinelearninggenerationofdynamicproteinconformationalensembles |