Google's AI genome system evaluates every possible one-base change
Most one-base changes to the human genome do nothing, but a few are significant.
On Tuesday, Google unveiled AlphaGenome Atlas, a tool designed to predict the effects of every single one-base alteration within the human genome. The human genome consists of approximately 3 billion bases, which necessitates the exploration of all alternative DNA bases, leading to a total of 9 billion bases being processed through the AlphaGenome software.
AlphaGenome's primary objective is to determine the potential functions of non-coding DNA, the majority of which does not encode proteins but plays a crucial role in regulating the activity of the protein-coding genome. Certain non-coding DNA segments are vital for controlling protein-coding elements, regulating the production of messenger RNAs, processing them into mature protein-coding forms, and other related functions.
However, a significant portion of non-coding DNA appears to be remnants of viruses and other molecular parasites. The ability to identify functional components of this non-coding DNA is highly beneficial, and having all the analysis executed by a single software package is advantageous. Nevertheless, without widespread adoption by biologists (assuming this occurs), it remains uncertain what additional value AlphaGenome provides beyond what could have been achieved through its training data.
Written by urgent.news from Ars Technica Science's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
