Machine Learning on Human Muscle Transcriptomic Data for Biomarker Discovery and Tissue-Specific Drug Target Identification.

摘要: For the past several decades, research in understanding molecular basis of human muscle aging has progressed significantly. However, development accessible tissue-specific biomarkers that may be measured to evaluate effectiveness therapeutic interventions is still a major challenge. Here we present method for tracking age-related changes skeletal muscle. We analyzed publicly available gene expression profiles young and old tissue from healthy donors. Differential pathway analysis were performed compare signatures preprocess resulting data set machine learning algorithms. Our study confirms established mechanisms aging, including dysregulation cytosolic Ca2+ homeostasis, PPAR signaling neurotransmitter recycling along with IGFR PI3K-Akt-mTOR signaling. Applying supervised techniques, neural networks, built panel aging. predictive model achieved 0.91 Pearson correlation respect actual age values samples, mean absolute error 6.19 years on test set. The performance models was also evaluated samples muscles Gene Genotype-Tissue Expression (GTEx) project. best accuracy 0.80 bin prediction external validation Furthermore, demonstrated can used identify new targets anti-aging therapies.