Ensemble Machine learning model identified citrusinol as functional food candidate for improving myotube differentiation and controlling CT26-Induced myotube atrophy. (May 2023)

• Record Type: Journal Article
• Authors: Jaesuk Lee, Justin; Min Ahn, Byeong; Kim, Nara; Noh, Yuran; Ju Ahn, Hee; Sol Hwang, Eun; Shim, Jaewon; Won Lee, Ki; Jin Jang, Young
• Is Part Of: Journal of functional foods. Volume 104(2023)
• Publication Date: 2023-05
• Subjects: Functional food -- Muscle atrophy -- Machine learning -- Citrusinol -- TGF-β pathway -- PGC-1α pathway; CCM CT26 conditioned medium -- CMap connectivity mapping -- CTD comparative toxicogenomics database -- DAPI 4′, 6-diamidino-2-phenylindole -- DNN deep neural network -- DMEM dulbecco's modified eagle's medium -- DMSO dimethyl sulfoxide -- DT decision tree -- ERRα estrogen-related receptor alpha -- FBS fetal bovine serum -- HS horse serum -- IL-6 interleukin-6 -- KNN k-nearest neighbor -- NRF-1 nuclear respiratory factor 1 -- MAFbx muscle atrophy F-box -- MEF2 myocyte enhancer factor 2 -- MHC myosin heavy chain -- MLP Multi-layered perceptron -- MTT 3-(4, 5-Dimethyl-2-thiazolyl)-2, 5-diphenyl-2H-tetrazolium bromide -- mTORC1 mammalian target of rapamycin complex 1 -- MuRF1 muscle RING-finger protein-1 -- NOX4 NAPDH oxidase 4 -- PGC-1α peroxisome proliferator-activated receptor-gamma coactivator-1 alpha -- PPARδ peroxisome proliferator-activated receptor delta -- PVDF polyvinylidene difluoride -- RF random forest -- SMILES simplified molecular-input line-entry system -- SUnSET surface sensing of translation -- SVM support vector machine -- S6K1 ribosomal protein S6 kinase beta-1 -- TFAM transcription factor A, mitochondrial -- TGF- β transforming growth factor-β -- TNF- α tumor necrosis factor α -- 4EBP1 eukaryotic translation initiation factor 4E-binding protein 1; Functional foods -- Analysis -- Periodicals; Food -- Biotechnology -- Periodicals; Nutrition -- Periodicals; 613.2
• DOI: 10.1016/j.jff.2023.105542
• Languages: English
• ISSNs: 1756-4646

Abstract

Graphical abstract: Highlights: Machine learning is designed to find phytochemicals regulating PGC-1α and TGF-β. Citrusinol was derived by machine learning to prevent muscle atrophy. Citrusinol enhances protein synthesis and myogenic differentiation in C2C12 cells. Citrusinol regulates PGC-1α and TGF-β, validated results of machine learning. Abstract: Skeletal muscle loss leads to decreased quality of life, increased incidence of chronic disease and mortality. To identify functional food materials to alleviate muscle atrophy, we built a multitarget-based machine learning system to identify novel phytochemicals that can inhibit TGF-β, which induce muscle weakness, and increase PGC-1α, a target of exercise mimetics. The multitarget-based machine learning system is built as an ensemble model of four algorithms with each optimal input representation. Citrusinol was identified by our model, and its anti-atrophy effects were validated using C2C12 cells. Citrusinol enhanced protein synthesis via AKT/mTORC1 pathway, increased myogenic differentiation, and increased PGC-1α and its downstream regulators, MEF2A and TFAM. Citrusinol attenuated CT26–induced myotube atrophy by blocking TGF-β, p-SMAD3, MAFbx, and TGF-β-induced MuRF1 and p-SMAD3. These results suggest that the proposed model can effectively identify functional foods to manage muscle atrophy; additionally, citrusinol was demonstrated as a promising candidate for future animal experiments.