Google’s DeepMind launches AlphaGenome AI tool for DNA analysis

Investing.com -- Google (NASDAQ:GOOGL)’s DeepMind has unveiled AlphaGenome, a new artificial intelligence tool designed to predict how genetic variations in human DNA impact biological processes regulating genes.

The AI model can analyze up to 1 million DNA base pairs and predict thousands of molecular properties related to regulatory activity. It can also evaluate the effects of genetic variants by comparing predictions between mutated and unmutated sequences.

DeepMind is making AlphaGenome available in preview through an API for non-commercial research, with plans to release the full model in the future.

The new tool builds upon DeepMind’s previous genomics model, Enformer, and complements AlphaMissense, which focuses on protein-coding regions that make up just 2% of the genome. AlphaGenome aims to interpret the remaining 98% of non-coding regions that orchestrate gene activity and contain many disease-linked variants.

According to DeepMind, AlphaGenome offers several advantages over existing DNA sequence models, including long sequence analysis with high resolution, comprehensive prediction across multiple biological processes, efficient variant scoring, and novel splice-junction modeling.

The company reports that AlphaGenome outperformed the best external models on 22 out of 24 evaluations when producing predictions for single DNA sequences. When predicting regulatory effects of variants, it matched or exceeded top-performing external models on 24 out of 26 evaluations.

"AlphaGenome will be a powerful tool for the field. Determining the relevance of different non-coding variants can be extremely challenging, particularly to do at scale," said Professor Marc Mansour from University College London. "This tool will provide a crucial piece of the puzzle, allowing us to make better connections to understand diseases like cancer."

Dr. Caleb Lareau from Memorial Sloan Kettering Cancer Center called it "a milestone for the field," noting that "for the first time, we have a single model that unifies long-range context, base-level precision and state-of-the-art performance across a whole spectrum of genomic tasks."

DeepMind suggests AlphaGenome could advance disease understanding, synthetic biology, and fundamental genomic research. The company demonstrated its potential by using the tool to investigate cancer-associated mutations in T-cell acute lymphoblastic leukemia, successfully replicating a known disease mechanism.

Despite its capabilities, DeepMind acknowledges current limitations, including challenges in capturing the influence of very distant regulatory elements and increasing cell-specific pattern recognition. The company emphasizes that AlphaGenome is intended for research purposes only and has not been validated for clinical applications.

This article was generated with the support of AI and reviewed by an editor. For more information see our T&C.