Genetics

This blog post explores a recent scientific study investigating how machine learning models classify multiple sclerosis and Alzheimer’s disease using genomic data from the UK Biobank. It highlights the surprising robustness of logistic regression, compares machine learning with polygenic risk scores, and explains how the results revealed distinct genetic architectures for the two diseases—one dominated by a major risk variant in APOE, the other shaped by a broad immune-related polygenic landscape.