Virtual Screening of Nrf2 Dietary-Derived Agonists and Safety by a New Deep-Learning Model and Verified In Vitro and In Vivo.
J Agric Food Chem
; 71(21): 8038-8049, 2023 May 31.
Article
en En
| MEDLINE
| ID: mdl-37196215
ABSTRACT
Nuclear factor (erythroid-derived 2)-like 2 (Nrf2) is an essential regulatory target of antioxidants, but the lack of Nrf2 active site information has hindered discovery of new Nrf2 agonists from food-derived compounds by large-scale virtual screening. Two deep-learning models were separately trained to screen for Nrf2-agonists and safety. The trained models screened potentially active chemicals from approximately 70,000 dietary compounds within 5 min. Of the 169 potential Nrf2 agonists identified via deep-learning screening, 137 had not been reported before. Six compounds selected from the new Nrf2 agonists significantly increased (p < 0.05) the activity of Nrf2 on carbon tetrachloride (CCl4)-intoxicated HepG2 cells (nicotiflorin (99.44 ± 18.5%), artemetin (97.91 ± 8.22%), daidzin (87.73 ± 3.77%), linonin (74.27 ± 5.73%), sinensetin (72.74 ± 10.41%), and tectoridin (77.78 ± 4.80%)), and their safety were demonstrated by an MTT assay. The safety and Nrf2 agonistic activity of nicotiflorin, artemetin, and daidzin were also reconfirm by a single-dose acute oral toxicity study and CCl4-intoxicated rat assay.
Palabras clave
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Asunto principal:
Factor 2 Relacionado con NF-E2
/
Aprendizaje Profundo
Tipo de estudio:
Diagnostic_studies
/
Prognostic_studies
/
Screening_studies
Límite:
Animals
Idioma:
En
Revista:
J Agric Food Chem
Año:
2023
Tipo del documento:
Article
País de afiliación:
China