A Composite Biomarker Signature of Type 1 Diabetes Risk Identified via Augmentation of Parallel Multi-Omics Data from a Small Cohort.

Oscar AlcazarSung-Ting ChuangGang RenMitsunori OgiharaBobbie-Jo M Webb-RobertsonErnesto S Nakayasu Peter BuchwaldMidhat H Abdulreda

Published in: bioRxiv : the preprint server for biology (2024)

Results further highlight the promise of our data augmentation approach in unmasking important patterns and pathologically significant features in parallel multi-omics datasets obtained from small sample cohorts to facilitate the identification of promising candidate T1D biomarkers for downstream validation. They also support the potential utility of a composite biomarker signature of T1D risk characterized by the changes in the above markers.

Keyphrases

type diabetes
big data
electronic health record
single cell
insulin resistance
soft tissue
machine learning
risk assessment
metabolic syndrome
adipose tissue
artificial intelligence
data analysis
weight loss