Precious1GPT: multimodal transformer-based transfer learning for aging clock development and feature importance analysis for aging and age-related disease target discovery.

Autor:	Urban A; Insilico Medicine, Pak Shek Kok, New Territories, Hong Kong., Sidorenko D; Insilico Medicine, Pak Shek Kok, New Territories, Hong Kong., Zagirova D; Insilico Medicine, Pak Shek Kok, New Territories, Hong Kong., Kozlova E; Insilico Medicine, Pak Shek Kok, New Territories, Hong Kong., Kalashnikov A; Insilico Medicine, Masdar City, United Arab Emirates., Pushkov S; Insilico Medicine, Pak Shek Kok, New Territories, Hong Kong., Naumov V; Insilico Medicine, Pak Shek Kok, New Territories, Hong Kong., Sarkisova V; Insilico Medicine, Pak Shek Kok, New Territories, Hong Kong., Leung GHD; Insilico Medicine, Pak Shek Kok, New Territories, Hong Kong., Leung HW; Insilico Medicine, Pak Shek Kok, New Territories, Hong Kong., Pun FW; Insilico Medicine, Pak Shek Kok, New Territories, Hong Kong., Ozerov IV; Insilico Medicine, Pak Shek Kok, New Territories, Hong Kong., Aliper A; Insilico Medicine, Pak Shek Kok, New Territories, Hong Kong.; Insilico Medicine, Masdar City, United Arab Emirates., Ren F; Insilico Medicine, Shanghai, China., Zhavoronkov A; Insilico Medicine, Pak Shek Kok, New Territories, Hong Kong.; Insilico Medicine, Masdar City, United Arab Emirates.
Jazyk:	angličtina
Zdroj:	Aging [Aging (Albany NY)] 2023 Jun 13; Vol. 15 (11), pp. 4649-4666. Date of Electronic Publication: 2023 Jun 13.
DOI:	10.18632/aging.204788
Abstrakt:	Aging is a complex and multifactorial process that increases the risk of various age-related diseases and there are many aging clocks that can accurately predict chronological age, mortality, and health status. These clocks are disconnected and are rarely fit for therapeutic target discovery. In this study, we propose a novel approach to multimodal aging clock we call Precious1GPT utilizing methylation and transcriptomic data for interpretable age prediction and target discovery developed using a transformer-based model and transfer learning for case-control classification. While the accuracy of the multimodal transformer is lower within each individual data type compared to the state of art specialized aging clocks based on methylation or transcriptomic data separately it may have higher practical utility for target discovery. This method provides the ability to discover novel therapeutic targets that hypothetically may be able to reverse or accelerate biological age providing a pathway for therapeutic drug discovery and validation using the aging clock. In addition, we provide a list of promising targets annotated using the PandaOmics industrial target discovery platform.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu