Artificial intelligence-driven rational design of ionizable lipids for mRNA delivery
Abstract Lipid nanoparticles (LNPs) have proven effective in mRNA delivery, as evidenced by COVID-19 vaccines. Its key ingredient, ionizable lipids, is traditionally optimized by inefficient and costly experimental screening. This study leverages artificial intelligence (AI) and virtual screening to...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-55072-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559381846523904 |
|---|---|
| author | Wei Wang Kepan Chen Ting Jiang Yiyang Wu Zheng Wu Hang Ying Hang Yu Jing Lu Jinzhong Lin Defang Ouyang |
| author_facet | Wei Wang Kepan Chen Ting Jiang Yiyang Wu Zheng Wu Hang Ying Hang Yu Jing Lu Jinzhong Lin Defang Ouyang |
| author_sort | Wei Wang |
| collection | DOAJ |
| description | Abstract Lipid nanoparticles (LNPs) have proven effective in mRNA delivery, as evidenced by COVID-19 vaccines. Its key ingredient, ionizable lipids, is traditionally optimized by inefficient and costly experimental screening. This study leverages artificial intelligence (AI) and virtual screening to facilitate the rational design of ionizable lipids by predicting two key properties of LNPs, apparent pKa and mRNA delivery efficiency. Nearly 20 million ionizable lipids were evaluated through two iterations of AI-driven generation and screening, yielding three and six new molecules, respectively. In mouse test validation, one lipid from the initial iteration, featuring a benzene ring, demonstrated performance comparable to the control DLin-MC3-DMA (MC3). Notably, all six lipids from the second iteration equaled or outperformed MC3, with one exhibiting efficacy akin to a superior control lipid SM-102. Furthermore, the AI model is interpretable in structure-activity relationships. |
| format | Article |
| id | doaj-art-a35c1bde5a3f4141be73397d74b5f359 |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-a35c1bde5a3f4141be73397d74b5f3592025-01-05T12:34:36ZengNature PortfolioNature Communications2041-17232024-12-0115111710.1038/s41467-024-55072-6Artificial intelligence-driven rational design of ionizable lipids for mRNA deliveryWei Wang0Kepan Chen1Ting Jiang2Yiyang Wu3Zheng Wu4Hang Ying5Hang Yu6Jing Lu7Jinzhong Lin8Defang Ouyang9State Key Laboratory of Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences, University of MacauState Key Laboratory of Genetic Engineering, School of Life Sciences, Zhongshan Hospital, Fudan UniversityCenter for mRNA Translational Research, Fudan UniversityState Key Laboratory of Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences, University of MacauState Key Laboratory of Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences, University of MacauCenter for mRNA Translational Research, Fudan UniversityCenter for mRNA Translational Research, Fudan UniversityCenter for mRNA Translational Research, Fudan UniversityState Key Laboratory of Genetic Engineering, School of Life Sciences, Zhongshan Hospital, Fudan UniversityState Key Laboratory of Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences, University of MacauAbstract Lipid nanoparticles (LNPs) have proven effective in mRNA delivery, as evidenced by COVID-19 vaccines. Its key ingredient, ionizable lipids, is traditionally optimized by inefficient and costly experimental screening. This study leverages artificial intelligence (AI) and virtual screening to facilitate the rational design of ionizable lipids by predicting two key properties of LNPs, apparent pKa and mRNA delivery efficiency. Nearly 20 million ionizable lipids were evaluated through two iterations of AI-driven generation and screening, yielding three and six new molecules, respectively. In mouse test validation, one lipid from the initial iteration, featuring a benzene ring, demonstrated performance comparable to the control DLin-MC3-DMA (MC3). Notably, all six lipids from the second iteration equaled or outperformed MC3, with one exhibiting efficacy akin to a superior control lipid SM-102. Furthermore, the AI model is interpretable in structure-activity relationships.https://doi.org/10.1038/s41467-024-55072-6 |
| spellingShingle | Wei Wang Kepan Chen Ting Jiang Yiyang Wu Zheng Wu Hang Ying Hang Yu Jing Lu Jinzhong Lin Defang Ouyang Artificial intelligence-driven rational design of ionizable lipids for mRNA delivery Nature Communications |
| title | Artificial intelligence-driven rational design of ionizable lipids for mRNA delivery |
| title_full | Artificial intelligence-driven rational design of ionizable lipids for mRNA delivery |
| title_fullStr | Artificial intelligence-driven rational design of ionizable lipids for mRNA delivery |
| title_full_unstemmed | Artificial intelligence-driven rational design of ionizable lipids for mRNA delivery |
| title_short | Artificial intelligence-driven rational design of ionizable lipids for mRNA delivery |
| title_sort | artificial intelligence driven rational design of ionizable lipids for mrna delivery |
| url | https://doi.org/10.1038/s41467-024-55072-6 |
| work_keys_str_mv | AT weiwang artificialintelligencedrivenrationaldesignofionizablelipidsformrnadelivery AT kepanchen artificialintelligencedrivenrationaldesignofionizablelipidsformrnadelivery AT tingjiang artificialintelligencedrivenrationaldesignofionizablelipidsformrnadelivery AT yiyangwu artificialintelligencedrivenrationaldesignofionizablelipidsformrnadelivery AT zhengwu artificialintelligencedrivenrationaldesignofionizablelipidsformrnadelivery AT hangying artificialintelligencedrivenrationaldesignofionizablelipidsformrnadelivery AT hangyu artificialintelligencedrivenrationaldesignofionizablelipidsformrnadelivery AT jinglu artificialintelligencedrivenrationaldesignofionizablelipidsformrnadelivery AT jinzhonglin artificialintelligencedrivenrationaldesignofionizablelipidsformrnadelivery AT defangouyang artificialintelligencedrivenrationaldesignofionizablelipidsformrnadelivery |