Related Experiment Video
Updated: Aug 16, 2026
13:35
Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos
Published on: March 21, 2021
Machine Learning-Derived Sarcopenia Signature Identifies High-Risk Molecular State in T2D Skeletal Muscle
Qiyao Zhao1, Qiwang He2, Sining Wang1
1Tongde Hospital of Zhejiang Province Affiliated to Zhejiang Chinese Medical University (College of Integrated Traditional Chinese and Western Medicine Clinical Medicine), Hangzhou, 310012, China.
Cell Biochemistry and Biophysics
|August 14, 2026
Summary
Sarcopenia is common in type 2 diabetes (T2D). This study developed a machine-learning model to identify a high-risk molecular state in T2D skeletal muscle, associated with impaired physical performance.
Area of Science:
- Molecular biology
- Genomics
- Biomedical research
Background:
- Sarcopenia, a common condition in type 2 diabetes (T2D), presents challenges in understanding its molecular underpinnings in skeletal muscle.
- Detecting sarcopenia-associated transcriptomic features within diabetic skeletal muscle is crucial for targeted interventions.
Purpose of the Study:
- To develop and validate a machine-learning signature for identifying a high-risk molecular state in skeletal muscle of individuals with T2D.
- To investigate the association of this molecular signature with physical performance and explore underlying cellular mechanisms.
Main Methods:
- A machine-learning signature was created using 26 gene-expression features and one ssGSEA-derived feature from transcriptomic datasets (GSE111016, GSE226151).
- The signature was validated in independent cohorts (GSE111010) and applied to bulk and single-nucleus RNA-sequencing data from T2D skeletal muscle.
- Association with lower-extremity physical performance was assessed using the Short Physical Performance Battery (SPPB) in GSE144304.
Main Results:
- The machine-learning model demonstrated strong performance with AUCs of 0.906 (training) and 0.762 (validation).
- A high-risk molecular state in T2D skeletal muscle was linked to inflammatory, extracellular-matrix, adhesion, and stress-response pathways, with SESN3 and VCAM1 identified as key genes.
- A higher signature score correlated with lower SPPB scores, indicating poorer physical performance, independent of age, sex, and BMI.
Conclusions:
- A robust molecular signature can effectively identify a high-risk molecular state in T2D skeletal muscle.
- This signature is associated with detrimental molecular programs and impaired physical function, offering potential for early detection and therapeutic strategies in T2D sarcopenia.
