ResearchHigh importance
Google DeepMind's AlphaGenome 2 predicts how DNA mutations act in each cell type and finds almost twice as many causal variants
On Wednesday (11/11) Google DeepMind presented AlphaGenome 2, a new version of its DNA sequence model. Instead of predicting the effect of a mutation on average across a tissue, it makes the prediction for a specific cell type or state, such as a heart muscle cell or an activated immune cell. It was trained on more than 107 million profiles of human and mouse cells and also predicts DNA methylation. In a set of 28 immune system cell types, it found almost twice as many causal variants as the previous model (30% versus 16%), and it can work with data from new cells without being retrained. It is available through the AlphaGenome API for non-commercial research and in closed preview for commercial use.
Published in edition no. 24 of Noticiário do Joãozinho ·
Translated by Joãozinho AI from the original Brazilian Portuguese edition. Facts, numbers and sources are the same as in the original; quotes, video titles and source names stay in their original language. Read the original in Portuguese
Original source
https://deepmind.google/blog/alphagenome-2-deciphering-how-cells-read-dna-to-better-understand-disease/