Efficient learning from 3D molecular structures using equivariant neural networks
Abstract/Contents
- Abstract
- Deep learning methods operating on three-dimensional (3D) molecular structures show promise in addressing vital challenges in biology and chemistry. The scarcity of experimentally determined structures, however, poses a significant hurdle in many machine learning applications. The incorporation of equivariance into deep learning models, leveraging inherent symmetries in structural biology problems, is essential for efficient learning from limited data. This dissertation delves into the utilization of rotationally and translationally equivariant neural networks in various structural biology problems. These include protein model quality assessment, the development of a machine learning--based scoring function for protein-ligand docking that considers protein flexibility, and the implementation of pocket-aware 3D fragment-based ligand optimization.
Description
Type of resource | text |
---|---|
Form | electronic resource; remote; computer; online resource |
Extent | 1 online resource. |
Place | California |
Place | [Stanford, California] |
Publisher | [Stanford University] |
Copyright date | 2024; ©2024 |
Publication date | 2024; 2024 |
Issuance | monographic |
Language | English |
Creators/Contributors
Author | Suriana, Patricia Adriana |
---|---|
Degree supervisor | Dror, Ron, 1975- |
Thesis advisor | Dror, Ron, 1975- |
Thesis advisor | Feng, Liang, 1976- |
Thesis advisor | Kundaje, Anshul, 1980- |
Thesis advisor | Maduke, Merritt C, 1966- |
Degree committee member | Feng, Liang, 1976- |
Degree committee member | Kundaje, Anshul, 1980- |
Degree committee member | Maduke, Merritt C, 1966- |
Associated with | Stanford University, School of Engineering |
Associated with | Stanford University, Computer Science Department |
Subjects
Genre | Theses |
---|---|
Genre | Text |
Bibliographic information
Statement of responsibility | Patricia Suriana. |
---|---|
Note | Submitted to the Computer Science Department. |
Thesis | Thesis Ph.D. Stanford University 2024. |
Location | https://purl.stanford.edu/dc577zq7333 |
Access conditions
- Copyright
- © 2024 by Patricia Adriana Suriana
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...