Fingerprint-enhanced graph attention network (FinGAT) model for antibiotic discovery
Artificial Intelligence (AI) techniques are of great potential to fundamentally change antibiotic discovery industries. Efficient and effective molecular featurization is key to all highly accurate learning models for antibiotic discovery. In this paper, we propose a fingerprint-enhanced graph atten...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/170327 |
| _version_ | 1811689051558772736 |
|---|---|
| author | Choo, Hou Yee Wee, Junjie Shen, Cong Xia, Kelin |
| author2 | School of Physical and Mathematical Sciences |
| author_facet | School of Physical and Mathematical Sciences Choo, Hou Yee Wee, Junjie Shen, Cong Xia, Kelin |
| author_sort | Choo, Hou Yee |
| collection | NTU |
| description | Artificial Intelligence (AI) techniques are of great potential to fundamentally change antibiotic discovery industries. Efficient and effective molecular featurization is key to all highly accurate learning models for antibiotic discovery. In this paper, we propose a fingerprint-enhanced graph attention network (FinGAT) model by the combination of sequence-based 2D fingerprints and structure-based graph representation. In our feature learning process, sequence information is transformed into a fingerprint vector, and structural information is encoded through a GAT module into another vector. These two vectors are concatenated and input into a multilayer perceptron (MLP) for antibiotic activity classification. Our model is extensively tested and compared with existing models. It has been found that our FinGAT can outperform various state-of-the-art GNN models in antibiotic discovery. |
| first_indexed | 2024-10-01T05:41:57Z |
| format | Journal Article |
| id | ntu-10356/170327 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:41:57Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1703272023-09-07T03:25:19Z Fingerprint-enhanced graph attention network (FinGAT) model for antibiotic discovery Choo, Hou Yee Wee, Junjie Shen, Cong Xia, Kelin School of Physical and Mathematical Sciences Science::Mathematics Anti-bacterial Agents Artificial Intelligence Artificial Intelligence (AI) techniques are of great potential to fundamentally change antibiotic discovery industries. Efficient and effective molecular featurization is key to all highly accurate learning models for antibiotic discovery. In this paper, we propose a fingerprint-enhanced graph attention network (FinGAT) model by the combination of sequence-based 2D fingerprints and structure-based graph representation. In our feature learning process, sequence information is transformed into a fingerprint vector, and structural information is encoded through a GAT module into another vector. These two vectors are concatenated and input into a multilayer perceptron (MLP) for antibiotic activity classification. Our model is extensively tested and compared with existing models. It has been found that our FinGAT can outperform various state-of-the-art GNN models in antibiotic discovery. Ministry of Education (MOE) Nanyang Technological University This work was supported in part by Nanyang Technological University Startup Grant M4081842.110, Singapore Ministry of Education Academic Research fund Tier 1 RG109/19 and Tier 2 MOE-T2EP20120-0013, MOE-T2EP20220-0010, and MOE-T2EP20221-0003. 2023-09-07T03:25:19Z 2023-09-07T03:25:19Z 2023 Journal Article Choo, H. Y., Wee, J., Shen, C. & Xia, K. (2023). Fingerprint-enhanced graph attention network (FinGAT) model for antibiotic discovery. Journal of Chemical Information and Modeling, 63(10), 2928-2935. https://dx.doi.org/10.1021/acs.jcim.3c00045 1549-9596 https://hdl.handle.net/10356/170327 10.1021/acs.jcim.3c00045 37167016 2-s2.0-85159773173 10 63 2928 2935 en M4081842.110 RG109/19 MOE-T2EP20120-0013 MOE-T2EP20220-0010 MOE-T2EP20221-0003 Journal of Chemical Information and Modeling © 2023 American Chemical Society. All rights reserved. |
| spellingShingle | Science::Mathematics Anti-bacterial Agents Artificial Intelligence Choo, Hou Yee Wee, Junjie Shen, Cong Xia, Kelin Fingerprint-enhanced graph attention network (FinGAT) model for antibiotic discovery |
| title | Fingerprint-enhanced graph attention network (FinGAT) model for antibiotic discovery |
| title_full | Fingerprint-enhanced graph attention network (FinGAT) model for antibiotic discovery |
| title_fullStr | Fingerprint-enhanced graph attention network (FinGAT) model for antibiotic discovery |
| title_full_unstemmed | Fingerprint-enhanced graph attention network (FinGAT) model for antibiotic discovery |
| title_short | Fingerprint-enhanced graph attention network (FinGAT) model for antibiotic discovery |
| title_sort | fingerprint enhanced graph attention network fingat model for antibiotic discovery |
| topic | Science::Mathematics Anti-bacterial Agents Artificial Intelligence |
| url | https://hdl.handle.net/10356/170327 |
| work_keys_str_mv | AT choohouyee fingerprintenhancedgraphattentionnetworkfingatmodelforantibioticdiscovery AT weejunjie fingerprintenhancedgraphattentionnetworkfingatmodelforantibioticdiscovery AT shencong fingerprintenhancedgraphattentionnetworkfingatmodelforantibioticdiscovery AT xiakelin fingerprintenhancedgraphattentionnetworkfingatmodelforantibioticdiscovery |