An Attention‐Aware Multi‐Task Learning Framework Identifies Candidate Targets for Drug Repurposing in Sarcopenia

作者：Md. Selim Reza, Chuan Qiu, Lin Xu, Kuan‐Jui Su, Anqi Liu, Xiao Zhang, Yun Gong, Zhe Luo, Qing Tian, Martin C. Nwadiugwu, Shun‐Xing Liang, Hui Shen, Hong‐Wen Deng · 发表于：Journal of Cachexia Sarcopenia and Muscle · 年份：2025 · DOI：10.1002/jcsm.13661 · 被引用次数：8 · 研究领域：Nutrition and Health in Aging、Muscle metabolism and nutrition、Nutrition, Genetics, and Disease

BACKGROUND: Sarcopenia presents a pressing public health concern due to its association with age-related muscle mass decline, strength loss and reduced physical performance, particularly in the growing older population. Given the absence of approved pharmacological therapies for sarcopenia, the need to discover effective pharmacological interventions has become critical. METHODS: To address this challenge and discover new therapies, we developed a novel Multi-Task Attention-aware method for Multi-Omics data (MTA-MO) to extract complex biological insights from various biomedical data sources, including transcriptome, methylome and genome data to identify drug targets and discover new therapies. Additionally, MTA-MO integrates human protein-protein interaction (PPI) networks and drug-target networks to improve target identification. The novel method is applied to a multi-omics dataset that included 1055 participants aged 20-50 (mean (± SD) age 36.88 (± 8.64)), comprising 37.82% African-American and 62.18% Caucasian/White individuals. Physical activity levels were self-reported and categorized into three groups: ≥ 3 times/week, < 3 times/week and no regular exercise. Mean (± SD) measures for grip strength, appendicular lean mass (ALM), exercise frequency and smoking status (no/yes, n (%)) were 38.72 (± 8.93) kg, 28.65 (± 4.63) kg, 4.31 (± 1.79) and 30.81%/69.19%, respectively. Significant differences (p < 0.05) were found between groups in age, ALM, smoking, and consumption of m...