Geometric Deep Learning for Biomolecules
Recent advancements in machine learning offer a promising pathway to deeper insights into biological phenomena. This manuscript explores the integration of geometric deep learning techniques to model biological structures. By embedding inductive biases based on geometry and physical laws, we aim to...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2024
|
| Online Access: | https://hdl.handle.net/1721.1/156606 |
| _version_ | 1826192142773518336 |
|---|---|
| author | Mitnikov, Ilan |
| author2 | Jacobson, Joseph M. |
| author_facet | Jacobson, Joseph M. Mitnikov, Ilan |
| author_sort | Mitnikov, Ilan |
| collection | MIT |
| description | Recent advancements in machine learning offer a promising pathway to deeper insights into biological phenomena. This manuscript explores the integration of geometric deep learning techniques to model biological structures. By embedding inductive biases based on geometry and physical laws, we aim to enhance our understanding and predictive capabilities in biomolecular systems. We present methods using equivariant neural networks for geometrical protein representation learning, molecular representation learning for electron density prediction, and scalable molecular dynamics simulations using stochastic interpolants. |
| first_indexed | 2024-09-23T09:06:54Z |
| format | Thesis |
| id | mit-1721.1/156606 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T09:06:54Z |
| publishDate | 2024 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1566062024-09-04T03:56:40Z Geometric Deep Learning for Biomolecules Mitnikov, Ilan Jacobson, Joseph M. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Recent advancements in machine learning offer a promising pathway to deeper insights into biological phenomena. This manuscript explores the integration of geometric deep learning techniques to model biological structures. By embedding inductive biases based on geometry and physical laws, we aim to enhance our understanding and predictive capabilities in biomolecular systems. We present methods using equivariant neural networks for geometrical protein representation learning, molecular representation learning for electron density prediction, and scalable molecular dynamics simulations using stochastic interpolants. M.Eng. 2024-09-03T21:11:07Z 2024-09-03T21:11:07Z 2024-05 2024-07-11T15:31:03.679Z Thesis https://hdl.handle.net/1721.1/156606 Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) Copyright retained by author(s) https://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf Massachusetts Institute of Technology |
| spellingShingle | Mitnikov, Ilan Geometric Deep Learning for Biomolecules |
| title | Geometric Deep Learning for Biomolecules |
| title_full | Geometric Deep Learning for Biomolecules |
| title_fullStr | Geometric Deep Learning for Biomolecules |
| title_full_unstemmed | Geometric Deep Learning for Biomolecules |
| title_short | Geometric Deep Learning for Biomolecules |
| title_sort | geometric deep learning for biomolecules |
| url | https://hdl.handle.net/1721.1/156606 |
| work_keys_str_mv | AT mitnikovilan geometricdeeplearningforbiomolecules |