Enzyme catalytic residue prediction using deep learning methods
Identification of catalytic residues in enzymes have important applications ranging from drug discovery to protein engineering. However, locating catalytic residues in laboratory is time consuming and costly. Through high throughput computational methods, potential catalytic residues could be elucid...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/171862 |
| _version_ | 1811682808887771136 |
|---|---|
| author | Guan, Jia Sheng |
| author2 | Mu Yuguang |
| author_facet | Mu Yuguang Guan, Jia Sheng |
| author_sort | Guan, Jia Sheng |
| collection | NTU |
| description | Identification of catalytic residues in enzymes have important applications ranging from drug discovery to protein engineering. However, locating catalytic residues in laboratory is time consuming and costly. Through high throughput computational methods, potential catalytic residues could be elucidated. While many models trained to predict catalytic residues were published, there are still unexplored combinations of model features and data preparation methods. In this project, graph neural network (GNN) and multi-layer perceptron (MLP) models were constructed to predict catalytic residues. The choice of edge weight equation was discovered to have huge impact on GNN model performance. Embeddings from a large protein language model, Evolutionary Scale Modeling 2 (ESM-2), were experimented and found suitable as features for MLP and GNN models, rivaling many published models in performance. Atchley factors as features were investigated but results hinted that the information might have already been included in the ESM-2 embeddings. To address knowledge gap, structural information of entire protein complex was considered as GNN model feature but found no benefits as compared to using only monomer structures as in published models. To resolve class imbalance issue, down-sampling of non-catalytic to catalytic residues to a 10:1 ratio was tested but it did not improve models’ performances. |
| first_indexed | 2024-10-01T04:02:44Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/171862 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:02:44Z |
| publishDate | 2023 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1718622023-11-20T15:32:40Z Enzyme catalytic residue prediction using deep learning methods Guan, Jia Sheng Mu Yuguang School of Biological Sciences YGMu@ntu.edu.sg Science::Biological sciences Identification of catalytic residues in enzymes have important applications ranging from drug discovery to protein engineering. However, locating catalytic residues in laboratory is time consuming and costly. Through high throughput computational methods, potential catalytic residues could be elucidated. While many models trained to predict catalytic residues were published, there are still unexplored combinations of model features and data preparation methods. In this project, graph neural network (GNN) and multi-layer perceptron (MLP) models were constructed to predict catalytic residues. The choice of edge weight equation was discovered to have huge impact on GNN model performance. Embeddings from a large protein language model, Evolutionary Scale Modeling 2 (ESM-2), were experimented and found suitable as features for MLP and GNN models, rivaling many published models in performance. Atchley factors as features were investigated but results hinted that the information might have already been included in the ESM-2 embeddings. To address knowledge gap, structural information of entire protein complex was considered as GNN model feature but found no benefits as compared to using only monomer structures as in published models. To resolve class imbalance issue, down-sampling of non-catalytic to catalytic residues to a 10:1 ratio was tested but it did not improve models’ performances. Bachelor of Science in Biological Sciences 2023-11-14T06:42:31Z 2023-11-14T06:42:31Z 2023 Final Year Project (FYP) Guan, J. S. (2023). Enzyme catalytic residue prediction using deep learning methods. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/171862 https://hdl.handle.net/10356/171862 en application/pdf Nanyang Technological University |
| spellingShingle | Science::Biological sciences Guan, Jia Sheng Enzyme catalytic residue prediction using deep learning methods |
| title | Enzyme catalytic residue prediction using deep learning methods |
| title_full | Enzyme catalytic residue prediction using deep learning methods |
| title_fullStr | Enzyme catalytic residue prediction using deep learning methods |
| title_full_unstemmed | Enzyme catalytic residue prediction using deep learning methods |
| title_short | Enzyme catalytic residue prediction using deep learning methods |
| title_sort | enzyme catalytic residue prediction using deep learning methods |
| topic | Science::Biological sciences |
| url | https://hdl.handle.net/10356/171862 |
| work_keys_str_mv | AT guanjiasheng enzymecatalyticresiduepredictionusingdeeplearningmethods |