Generative Adversarial Learning of Protein Tertiary Structures
Protein molecules are inherently dynamic and modulate their interactions with different molecular partners by accessing different tertiary structures under physiological conditions. Elucidating such structures remains challenging. Current momentum in deep learning and the powerful performance of gen...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Molecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1420-3049/26/5/1209 |
| _version_ | 1797395422793170944 |
|---|---|
| author | Taseef Rahman Yuanqi Du Liang Zhao Amarda Shehu |
| author_facet | Taseef Rahman Yuanqi Du Liang Zhao Amarda Shehu |
| author_sort | Taseef Rahman |
| collection | DOAJ |
| description | Protein molecules are inherently dynamic and modulate their interactions with different molecular partners by accessing different tertiary structures under physiological conditions. Elucidating such structures remains challenging. Current momentum in deep learning and the powerful performance of generative adversarial networks (GANs) in complex domains, such as computer vision, inspires us to investigate GANs on their ability to generate physically-realistic protein tertiary structures. The analysis presented here shows that several GAN models fail to capture complex, distal structural patterns present in protein tertiary structures. The study additionally reveals that mechanisms touted as effective in stabilizing the training of a GAN model are not all effective, and that performance based on loss alone may be orthogonal to performance based on the quality of generated datasets. A novel contribution in this study is the demonstration that Wasserstein GAN strikes a good balance and manages to capture both local and distal patterns, thus presenting a first step towards more powerful deep generative models for exploring a possibly very diverse set of structures supporting diverse activities of a protein molecule in the cell. |
| first_indexed | 2024-03-09T00:34:21Z |
| format | Article |
| id | doaj.art-321b3c608ced44fbafa0a98419722629 |
| institution | Directory Open Access Journal |
| issn | 1420-3049 |
| language | English |
| last_indexed | 2024-03-09T00:34:21Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Molecules |
| spelling | doaj.art-321b3c608ced44fbafa0a984197226292023-12-11T18:15:10ZengMDPI AGMolecules1420-30492021-02-01265120910.3390/molecules26051209Generative Adversarial Learning of Protein Tertiary StructuresTaseef Rahman0Yuanqi Du1Liang Zhao2Amarda Shehu3Department of Computer Science, George Mason University, Fairfax, VA 22030, USADepartment of Computer Science, George Mason University, Fairfax, VA 22030, USADepartment of Computer Science, Emory University, Atlanta, GA 30322, USADepartment of Computer Science, George Mason University, Fairfax, VA 22030, USAProtein molecules are inherently dynamic and modulate their interactions with different molecular partners by accessing different tertiary structures under physiological conditions. Elucidating such structures remains challenging. Current momentum in deep learning and the powerful performance of generative adversarial networks (GANs) in complex domains, such as computer vision, inspires us to investigate GANs on their ability to generate physically-realistic protein tertiary structures. The analysis presented here shows that several GAN models fail to capture complex, distal structural patterns present in protein tertiary structures. The study additionally reveals that mechanisms touted as effective in stabilizing the training of a GAN model are not all effective, and that performance based on loss alone may be orthogonal to performance based on the quality of generated datasets. A novel contribution in this study is the demonstration that Wasserstein GAN strikes a good balance and manages to capture both local and distal patterns, thus presenting a first step towards more powerful deep generative models for exploring a possibly very diverse set of structures supporting diverse activities of a protein molecule in the cell.https://www.mdpi.com/1420-3049/26/5/1209protein modelingtertiary structuregenerative adversarial learningdeep learning |
| spellingShingle | Taseef Rahman Yuanqi Du Liang Zhao Amarda Shehu Generative Adversarial Learning of Protein Tertiary Structures Molecules protein modeling tertiary structure generative adversarial learning deep learning |
| title | Generative Adversarial Learning of Protein Tertiary Structures |
| title_full | Generative Adversarial Learning of Protein Tertiary Structures |
| title_fullStr | Generative Adversarial Learning of Protein Tertiary Structures |
| title_full_unstemmed | Generative Adversarial Learning of Protein Tertiary Structures |
| title_short | Generative Adversarial Learning of Protein Tertiary Structures |
| title_sort | generative adversarial learning of protein tertiary structures |
| topic | protein modeling tertiary structure generative adversarial learning deep learning |
| url | https://www.mdpi.com/1420-3049/26/5/1209 |
| work_keys_str_mv | AT taseefrahman generativeadversariallearningofproteintertiarystructures AT yuanqidu generativeadversariallearningofproteintertiarystructures AT liangzhao generativeadversariallearningofproteintertiarystructures AT amardashehu generativeadversariallearningofproteintertiarystructures |