Google DeepMind has launched AlphaGenome, an advanced artificial intelligence model designed to predict the effects of single nucleotide variants or mutations across the entire human genome, including both protein-coding and non-coding regions. The model processes up to one million DNA base pairs at once, enabling high-resolution analysis of how genetic changes impact gene regulation, RNA splicing, protein production, and other molecular functions. AlphaGenome is accessible via an API for non-commercial research and outperforms or matches existing genomics models in accuracy and scope. By decoding the so-called "junk DNA" or non-protein-coding genome, which constitutes approximately 98% of human DNA, AlphaGenome aims to enhance understanding of gene function, accelerate biological discoveries, and support research into disease mechanisms such as cancer. The AI tool is expected to contribute to advances in synthetic biology and precision medicine by providing rapid, lab-free insights into the functional consequences of genetic mutations.
How far away is AI from being a biotech fund manager? Read @PeterKolchinsky's post in @rapport_bio. Th link to the post is in the reply: https://t.co/1DgzH2KSHe
ai is generationally important technology today @profluentbio's work building frontier ai models to write the language of functional genome editors is published in @nature! they produce a synthetic crispr system that edits human dna and sharply reduces off-target effects 🧵 https://t.co/B28RfM4wV1
Profluent’s AI-Designed Gene Editor Provides Glimpse Into Generalizable Platform https://t.co/9cHVVGFfvl #news #biotech