New MODIS framework integrates multi-omics data for rare diseases

Researchers have developed MODIS, a novel semi-supervised framework designed to integrate multi-omics data, particularly for small and unpaired datasets common in rare disease studies. The framework addresses challenges such as data scarcity and class imbalance by simultaneously training on a large reference database and a small target dataset. MODIS employs a combination of variational auto-encoders, a class classifier, and an adversarially trained modality classifier, utilizing a regularized relativistic GAN loss for stability. Validation on synthetic data and the TCGA database demonstrated MODIS's high prediction accuracy, robustness with limited supervision, and stability with class imbalance. AI

IMPACT This framework could enable more accurate rare disease studies by improving multi-omics data integration.

RANK_REASON The cluster contains an academic paper detailing a new computational biology framework. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Paul Villoutreix
• The Cancer Genome Atlas

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →