Data-driven learning models for protein folding analysis
In this paper, the protein folding prediction problem is modelled and solved using reinforcement learning. Deep learning methods have been commonly used to predict protein structure and folding in recent years. However, it has been found that this method may not take into account the energy function...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/148523 |
| _version_ | 1811684245681209344 |
|---|---|
| author | Tedja, Erika |
| author2 | Xia Kelin |
| author_facet | Xia Kelin Tedja, Erika |
| author_sort | Tedja, Erika |
| collection | NTU |
| description | In this paper, the protein folding prediction problem is modelled and solved using reinforcement learning. Deep learning methods have been commonly used to predict protein structure and folding in recent years. However, it has been found that this method may not take into account the energy function and hydrophobic-polar nature of proteins. This paper attempted to use the Q-learning approach using ℇ-greedy policy to predict the secondary structure of protein given its amino acid sequence and optimal energy. This paper can be improved by incorporating pretraining of the agent or using more advanced deep Q-learning algorithm. |
| first_indexed | 2024-10-01T04:25:34Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/148523 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:25:34Z |
| publishDate | 2021 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1485232023-02-28T23:13:42Z Data-driven learning models for protein folding analysis Tedja, Erika Xia Kelin School of Physical and Mathematical Sciences xiakelin@ntu.edu.sg Science::Mathematics In this paper, the protein folding prediction problem is modelled and solved using reinforcement learning. Deep learning methods have been commonly used to predict protein structure and folding in recent years. However, it has been found that this method may not take into account the energy function and hydrophobic-polar nature of proteins. This paper attempted to use the Q-learning approach using ℇ-greedy policy to predict the secondary structure of protein given its amino acid sequence and optimal energy. This paper can be improved by incorporating pretraining of the agent or using more advanced deep Q-learning algorithm. Bachelor of Science in Mathematical Sciences and Economics 2021-04-29T03:07:55Z 2021-04-29T03:07:55Z 2021 Final Year Project (FYP) Tedja, E. (2021). Data-driven learning models for protein folding analysis. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/148523 https://hdl.handle.net/10356/148523 en application/pdf Nanyang Technological University |
| spellingShingle | Science::Mathematics Tedja, Erika Data-driven learning models for protein folding analysis |
| title | Data-driven learning models for protein folding analysis |
| title_full | Data-driven learning models for protein folding analysis |
| title_fullStr | Data-driven learning models for protein folding analysis |
| title_full_unstemmed | Data-driven learning models for protein folding analysis |
| title_short | Data-driven learning models for protein folding analysis |
| title_sort | data driven learning models for protein folding analysis |
| topic | Science::Mathematics |
| url | https://hdl.handle.net/10356/148523 |
| work_keys_str_mv | AT tedjaerika datadrivenlearningmodelsforproteinfoldinganalysis |