Exploring Fragment Adding Strategies to Enhance Molecule Pretraining in AI-Driven Drug Discovery
The effectiveness of AI-driven drug discovery can be enhanced by pretraining on small molecules. However, the conventional masked language model pretraining techniques are not suitable for molecule pretraining due to the limited vocabulary size and the non-sequential structure of molecules. To overc...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2024-09-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2024.9020003 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832568849837326336 |
|---|---|
| author | Zhaoxu Meng Cheng Chen Xuan Zhang Wei Zhao Xuefeng Cui |
| author_facet | Zhaoxu Meng Cheng Chen Xuan Zhang Wei Zhao Xuefeng Cui |
| author_sort | Zhaoxu Meng |
| collection | DOAJ |
| description | The effectiveness of AI-driven drug discovery can be enhanced by pretraining on small molecules. However, the conventional masked language model pretraining techniques are not suitable for molecule pretraining due to the limited vocabulary size and the non-sequential structure of molecules. To overcome these challenges, we propose FragAdd, a strategy that involves adding a chemically implausible molecular fragment to the input molecule. This approach allows for the incorporation of rich local information and the generation of a high-quality graph representation, which is advantageous for tasks like virtual screening. Consequently, we have developed a virtual screening protocol that focuses on identifying estrogen receptor alpha binders on a nucleus receptor. Our results demonstrate a significant improvement in the binding capacity of the retrieved molecules. Additionally, we demonstrate that the FragAdd strategy can be combined with other self-supervised methods to further expedite the drug discovery process. |
| format | Article |
| id | doaj-art-75dbf0c867db4ba6bab24df45ec47c91 |
| institution | Kabale University |
| issn | 2096-0654 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj-art-75dbf0c867db4ba6bab24df45ec47c912025-02-03T00:12:56ZengTsinghua University PressBig Data Mining and Analytics2096-06542024-09-017356557610.26599/BDMA.2024.9020003Exploring Fragment Adding Strategies to Enhance Molecule Pretraining in AI-Driven Drug DiscoveryZhaoxu Meng0Cheng Chen1Xuan Zhang2Wei Zhao3Xuefeng Cui4School of Life Sciences, Shandong University, Qingdao 266237, ChinaSchool of Computer Science and Technology, Shandong University, Qingdao 266237, ChinaSchool of Computer Science and Technology, Shandong University, Qingdao 266237, ChinaState Key Laboratory of Microbiology Technology, Shandong University, Qingdao 266237, ChinaSchool of Computer Science and Technology, Shandong University, Qingdao 266237, ChinaThe effectiveness of AI-driven drug discovery can be enhanced by pretraining on small molecules. However, the conventional masked language model pretraining techniques are not suitable for molecule pretraining due to the limited vocabulary size and the non-sequential structure of molecules. To overcome these challenges, we propose FragAdd, a strategy that involves adding a chemically implausible molecular fragment to the input molecule. This approach allows for the incorporation of rich local information and the generation of a high-quality graph representation, which is advantageous for tasks like virtual screening. Consequently, we have developed a virtual screening protocol that focuses on identifying estrogen receptor alpha binders on a nucleus receptor. Our results demonstrate a significant improvement in the binding capacity of the retrieved molecules. Additionally, we demonstrate that the FragAdd strategy can be combined with other self-supervised methods to further expedite the drug discovery process.https://www.sciopen.com/article/10.26599/BDMA.2024.9020003pretraininginformation retrievaldrug discoveryvirtual screeningmolecule property prediction |
| spellingShingle | Zhaoxu Meng Cheng Chen Xuan Zhang Wei Zhao Xuefeng Cui Exploring Fragment Adding Strategies to Enhance Molecule Pretraining in AI-Driven Drug Discovery Big Data Mining and Analytics pretraining information retrieval drug discovery virtual screening molecule property prediction |
| title | Exploring Fragment Adding Strategies to Enhance Molecule Pretraining in AI-Driven Drug Discovery |
| title_full | Exploring Fragment Adding Strategies to Enhance Molecule Pretraining in AI-Driven Drug Discovery |
| title_fullStr | Exploring Fragment Adding Strategies to Enhance Molecule Pretraining in AI-Driven Drug Discovery |
| title_full_unstemmed | Exploring Fragment Adding Strategies to Enhance Molecule Pretraining in AI-Driven Drug Discovery |
| title_short | Exploring Fragment Adding Strategies to Enhance Molecule Pretraining in AI-Driven Drug Discovery |
| title_sort | exploring fragment adding strategies to enhance molecule pretraining in ai driven drug discovery |
| topic | pretraining information retrieval drug discovery virtual screening molecule property prediction |
| url | https://www.sciopen.com/article/10.26599/BDMA.2024.9020003 |
| work_keys_str_mv | AT zhaoxumeng exploringfragmentaddingstrategiestoenhancemoleculepretraininginaidrivendrugdiscovery AT chengchen exploringfragmentaddingstrategiestoenhancemoleculepretraininginaidrivendrugdiscovery AT xuanzhang exploringfragmentaddingstrategiestoenhancemoleculepretraininginaidrivendrugdiscovery AT weizhao exploringfragmentaddingstrategiestoenhancemoleculepretraininginaidrivendrugdiscovery AT xuefengcui exploringfragmentaddingstrategiestoenhancemoleculepretraininginaidrivendrugdiscovery |