Molecular Generation and Optimization of Molecular Properties Using a Transformer Model
Generating novel molecules to satisfy specific properties is a challenging task in modern drug discovery, which requires the optimization of a specific objective based on satisfying chemical rules. Herein, we aim to optimize the properties of a specific molecule to satisfy the specific properties of...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2024-03-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2023.9020009 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832544230746095616 |
|---|---|
| author | Zhongyin Xu Xiujuan Lei Mei Ma Yi Pan |
| author_facet | Zhongyin Xu Xiujuan Lei Mei Ma Yi Pan |
| author_sort | Zhongyin Xu |
| collection | DOAJ |
| description | Generating novel molecules to satisfy specific properties is a challenging task in modern drug discovery, which requires the optimization of a specific objective based on satisfying chemical rules. Herein, we aim to optimize the properties of a specific molecule to satisfy the specific properties of the generated molecule. The Matched Molecular Pairs (MMPs), which contain the source and target molecules, are used herein, and logD and solubility are selected as the optimization properties. The main innovative work lies in the calculation related to a specific transformer from the perspective of a matrix dimension. Threshold intervals and state changes are then used to encode logD and solubility for subsequent tests. During the experiments, we screen the data based on the proportion of heavy atoms to all atoms in the groups and select 12365, 1503, and 1570 MMPs as the training, validation, and test sets, respectively. Transformer models are compared with the baseline models with respect to their abilities to generate molecules with specific properties. Results show that the transformer model can accurately optimize the source molecules to satisfy specific properties. |
| format | Article |
| id | doaj-art-d8b0e9f8a84f4fd4aa2e1221577e300a |
| institution | Kabale University |
| issn | 2096-0654 |
| language | English |
| publishDate | 2024-03-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj-art-d8b0e9f8a84f4fd4aa2e1221577e300a2025-02-03T10:49:41ZengTsinghua University PressBig Data Mining and Analytics2096-06542024-03-017114215510.26599/BDMA.2023.9020009Molecular Generation and Optimization of Molecular Properties Using a Transformer ModelZhongyin Xu0Xiujuan Lei1Mei Ma2Yi Pan3School of Computer Science, Shaanxi Normal University, Xi’an 710119, ChinaSchool of Computer Science, Shaanxi Normal University, Xi’an 710119, ChinaSchool of Computer Science, Shaanxi Normal University, Xi’an 710119, ChinaFaculty of Computer Science and Control Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaGenerating novel molecules to satisfy specific properties is a challenging task in modern drug discovery, which requires the optimization of a specific objective based on satisfying chemical rules. Herein, we aim to optimize the properties of a specific molecule to satisfy the specific properties of the generated molecule. The Matched Molecular Pairs (MMPs), which contain the source and target molecules, are used herein, and logD and solubility are selected as the optimization properties. The main innovative work lies in the calculation related to a specific transformer from the perspective of a matrix dimension. Threshold intervals and state changes are then used to encode logD and solubility for subsequent tests. During the experiments, we screen the data based on the proportion of heavy atoms to all atoms in the groups and select 12365, 1503, and 1570 MMPs as the training, validation, and test sets, respectively. Transformer models are compared with the baseline models with respect to their abilities to generate molecules with specific properties. Results show that the transformer model can accurately optimize the source molecules to satisfy specific properties.https://www.sciopen.com/article/10.26599/BDMA.2023.9020009molecular optimizationtransformermatched molecular pairs (mmps)logdsolubility |
| spellingShingle | Zhongyin Xu Xiujuan Lei Mei Ma Yi Pan Molecular Generation and Optimization of Molecular Properties Using a Transformer Model Big Data Mining and Analytics molecular optimization transformer matched molecular pairs (mmps) logd solubility |
| title | Molecular Generation and Optimization of Molecular Properties Using a Transformer Model |
| title_full | Molecular Generation and Optimization of Molecular Properties Using a Transformer Model |
| title_fullStr | Molecular Generation and Optimization of Molecular Properties Using a Transformer Model |
| title_full_unstemmed | Molecular Generation and Optimization of Molecular Properties Using a Transformer Model |
| title_short | Molecular Generation and Optimization of Molecular Properties Using a Transformer Model |
| title_sort | molecular generation and optimization of molecular properties using a transformer model |
| topic | molecular optimization transformer matched molecular pairs (mmps) logd solubility |
| url | https://www.sciopen.com/article/10.26599/BDMA.2023.9020009 |
| work_keys_str_mv | AT zhongyinxu moleculargenerationandoptimizationofmolecularpropertiesusingatransformermodel AT xiujuanlei moleculargenerationandoptimizationofmolecularpropertiesusingatransformermodel AT meima moleculargenerationandoptimizationofmolecularpropertiesusingatransformermodel AT yipan moleculargenerationandoptimizationofmolecularpropertiesusingatransformermodel |