A single mutation in the HBB gene causes sickle cell disease by changing the shape and function of red blood cells. This article explores the biology behind the disease, its connection to malaria, and how CRISPR gene editing therapies such as Casgevy and India’s Birsa‑101 aim to correct the mutation at its source.
Every human genome contains millions of genetic variants. Most are harmless but occasionally a single change can cause a serious disease. Finding that one variant is a needle‑in‑the‑haystack problem and increasingly a challenge tackled with machine learning.
A personal recap from the Microsoft AI Tour 2026 in Munich, covering Satya Nadella’s keynote, multimodal AI research in healthcare, sovereign cloud architectures, and emerging trends around AI agents, Power Platform, and the revival of Excel as an AI‑driven data interface.
Missense variants, that is, single amino acid substitutions in proteins, are often difficult to assess. Our machine learning workflow uses protein structure-based graph embeddings to predict the pathogenicity of such variants. In doing so, the structural information enhances existing approaches like the CADD score and provides new insights for genomic medical diagnostics.