GraphGPT: A Graph Enhanced Generative Pretrained Transformer for Conditioned Molecular Generation
Condition-based molecular generation can generate a large number of molecules with particular properties, expanding the virtual drug screening library, and accelerating the process of drug discovery. In this study, we combined a molecular graph structure and sequential representations using a genera...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | International Journal of Molecular Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1422-0067/24/23/16761 |
| _version_ | 1797400139384487936 |
|---|---|
| author | Hao Lu Zhiqiang Wei Xuze Wang Kun Zhang Hao Liu |
| author_facet | Hao Lu Zhiqiang Wei Xuze Wang Kun Zhang Hao Liu |
| author_sort | Hao Lu |
| collection | DOAJ |
| description | Condition-based molecular generation can generate a large number of molecules with particular properties, expanding the virtual drug screening library, and accelerating the process of drug discovery. In this study, we combined a molecular graph structure and sequential representations using a generative pretrained transformer (GPT) architecture for generating molecules conditionally. The incorporation of graph structure information facilitated a better comprehension of molecular topological features, and the augmentation of a sequential contextual understanding of GPT architecture facilitated molecular generation. The experiments indicate that our model efficiently produces molecules with the desired properties, with valid and unique metrics that are close to 100%. Faced with the typical task of generating molecules based on a scaffold in drug discovery, our model is able to preserve scaffold information and generate molecules with low similarity and specified properties. |
| first_indexed | 2024-03-09T01:50:13Z |
| format | Article |
| id | doaj.art-c3421288e07f4838a6c1fcc9b44f1526 |
| institution | Directory Open Access Journal |
| issn | 1661-6596 1422-0067 |
| language | English |
| last_indexed | 2024-03-09T01:50:13Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Molecular Sciences |
| spelling | doaj.art-c3421288e07f4838a6c1fcc9b44f15262023-12-08T15:17:03ZengMDPI AGInternational Journal of Molecular Sciences1661-65961422-00672023-11-0124231676110.3390/ijms242316761GraphGPT: A Graph Enhanced Generative Pretrained Transformer for Conditioned Molecular GenerationHao Lu0Zhiqiang Wei1Xuze Wang2Kun Zhang3Hao Liu4College of Computer Science and Technology, Ocean University of China, Qingdao 266100, ChinaCollege of Computer Science and Technology, Ocean University of China, Qingdao 266100, ChinaCollege of Computer Science and Technology, Ocean University of China, Qingdao 266100, ChinaCollege of Computer Science and Technology, Ocean University of China, Qingdao 266100, ChinaCollege of Computer Science and Technology, Ocean University of China, Qingdao 266100, ChinaCondition-based molecular generation can generate a large number of molecules with particular properties, expanding the virtual drug screening library, and accelerating the process of drug discovery. In this study, we combined a molecular graph structure and sequential representations using a generative pretrained transformer (GPT) architecture for generating molecules conditionally. The incorporation of graph structure information facilitated a better comprehension of molecular topological features, and the augmentation of a sequential contextual understanding of GPT architecture facilitated molecular generation. The experiments indicate that our model efficiently produces molecules with the desired properties, with valid and unique metrics that are close to 100%. Faced with the typical task of generating molecules based on a scaffold in drug discovery, our model is able to preserve scaffold information and generate molecules with low similarity and specified properties.https://www.mdpi.com/1422-0067/24/23/16761molecular generationgenerative pretrained transformergraph neural networks |
| spellingShingle | Hao Lu Zhiqiang Wei Xuze Wang Kun Zhang Hao Liu GraphGPT: A Graph Enhanced Generative Pretrained Transformer for Conditioned Molecular Generation International Journal of Molecular Sciences molecular generation generative pretrained transformer graph neural networks |
| title | GraphGPT: A Graph Enhanced Generative Pretrained Transformer for Conditioned Molecular Generation |
| title_full | GraphGPT: A Graph Enhanced Generative Pretrained Transformer for Conditioned Molecular Generation |
| title_fullStr | GraphGPT: A Graph Enhanced Generative Pretrained Transformer for Conditioned Molecular Generation |
| title_full_unstemmed | GraphGPT: A Graph Enhanced Generative Pretrained Transformer for Conditioned Molecular Generation |
| title_short | GraphGPT: A Graph Enhanced Generative Pretrained Transformer for Conditioned Molecular Generation |
| title_sort | graphgpt a graph enhanced generative pretrained transformer for conditioned molecular generation |
| topic | molecular generation generative pretrained transformer graph neural networks |
| url | https://www.mdpi.com/1422-0067/24/23/16761 |
| work_keys_str_mv | AT haolu graphgptagraphenhancedgenerativepretrainedtransformerforconditionedmoleculargeneration AT zhiqiangwei graphgptagraphenhancedgenerativepretrainedtransformerforconditionedmoleculargeneration AT xuzewang graphgptagraphenhancedgenerativepretrainedtransformerforconditionedmoleculargeneration AT kunzhang graphgptagraphenhancedgenerativepretrainedtransformerforconditionedmoleculargeneration AT haoliu graphgptagraphenhancedgenerativepretrainedtransformerforconditionedmoleculargeneration |