Graph neural networks
Molecular property predictions are crucial for drug discovery and development. Predicting the properties of molecular compounds could essentially speed up the research process in areas such as drug designing and chemical substance discovery. In recent years, Graph Neural Networks (GNNs) have b...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/169974 |
| _version_ | 1826124590652325888 |
|---|---|
| author | Lian, Ran |
| author2 | Luu Anh Tuan |
| author_facet | Luu Anh Tuan Lian, Ran |
| author_sort | Lian, Ran |
| collection | NTU |
| description | Molecular property predictions are crucial for drug discovery and development. Predicting the
properties of molecular compounds could essentially speed up the research process in areas such
as drug designing and chemical substance discovery. In recent years, Graph Neural Networks
(GNNs) have become increasingly attractive methods for molecular property prediction due to their
abilities to analyze graph structural data with chemical structures being easily displayed as graphs.
In this paper, I will perform a comparative study on some of the state-of-the-arts architectures used
today, including Graph Convolutional Networks (GCNs), Graph Attention Networks (GATs),
Attentive FP and Path-Augmented Graph Transformer Networks (GATNs) for molecular property
prediction on 5 benchmark datasets (HIV, Tox21, BBBP, ClinTox and BACE). With fixed
hyperparameters choices on different deep learning architectures, the experimental results showed
that the PAGTN model outperformed other GNN architectures on several datasets. Finally, to
simplify the drug discovery process for pharmaceutical scientists, I proposed one possible
application using the best model which could be adopted by them in the development and testing
of new drugs. |
| first_indexed | 2024-10-01T06:22:52Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/169974 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:22:52Z |
| publishDate | 2023 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1699742023-09-12T07:47:58Z Graph neural networks Lian, Ran Luu Anh Tuan School of Computer Science and Engineering anhtuan.luu@ntu.edu.sg Engineering::Computer science and engineering Molecular property predictions are crucial for drug discovery and development. Predicting the properties of molecular compounds could essentially speed up the research process in areas such as drug designing and chemical substance discovery. In recent years, Graph Neural Networks (GNNs) have become increasingly attractive methods for molecular property prediction due to their abilities to analyze graph structural data with chemical structures being easily displayed as graphs. In this paper, I will perform a comparative study on some of the state-of-the-arts architectures used today, including Graph Convolutional Networks (GCNs), Graph Attention Networks (GATs), Attentive FP and Path-Augmented Graph Transformer Networks (GATNs) for molecular property prediction on 5 benchmark datasets (HIV, Tox21, BBBP, ClinTox and BACE). With fixed hyperparameters choices on different deep learning architectures, the experimental results showed that the PAGTN model outperformed other GNN architectures on several datasets. Finally, to simplify the drug discovery process for pharmaceutical scientists, I proposed one possible application using the best model which could be adopted by them in the development and testing of new drugs. Bachelor of Science in Data Science and Artificial Intelligence 2023-08-18T05:53:16Z 2023-08-18T05:53:16Z 2023 Final Year Project (FYP) Lian, R. (2023). Graph neural networks. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/169974 https://hdl.handle.net/10356/169974 en SCSE22-0479 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering Lian, Ran Graph neural networks |
| title | Graph neural networks |
| title_full | Graph neural networks |
| title_fullStr | Graph neural networks |
| title_full_unstemmed | Graph neural networks |
| title_short | Graph neural networks |
| title_sort | graph neural networks |
| topic | Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/169974 |
| work_keys_str_mv | AT lianran graphneuralnetworks |