New CALM framework links brain imaging and genetics from separate datasets

Researchers have developed a new framework called CALM, designed to uncover interpretable associations between brain imaging data and genetic information, even when these datasets come from entirely separate populations. CALM achieves this by aligning the two modalities into a shared latent space using linear projections. These projections not only match the distributions of the data but also ensure group separability, yielding interpretable links between genetic pathways and brain regions. When applied to autism spectrum disorder, CALM identified connections between specific cortical regions and immune/metabolic pathways, aligning with existing scientific literature. AI

IMPACT Enables cross-modal analysis of biological data from disparate sources, potentially accelerating biomarker discovery for complex diseases.

RANK_REASON The cluster contains a research paper detailing a new computational framework for analyzing biological data. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• CALM

• paper
• other

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