Google's AI Company DeepMind launches gene prediction tool | Statistics

Machine Learning


Katie Palmer covers Telehealth, clinical artificial intelligence, and the health data economy with an emphasis on the impact of digital healthcare for patients, health providers and businesses. You can contact Katie via Palmer.01 Signal.

In the biology circle, Google's AI research company DeepMind is best known for its folding proteins. Its deep learning model, which predicts protein structure from amino acid sequences, shared the Nobel Prize in Chemistry with David Baker of the University of Washington last year.

However, DeepMind has recently tackled the issue of many gnarlier precursors that predict how DNA encodes gene regulation. In a preprint and blog post released on Wednesday, the company unveiled its latest Stab at the Challenge with a new model called Alphagenome, an early step towards possible applications in therapeutic development.

Compared to the well-defined problem of protein structure prediction, “genomics is a more ambiguous field,” says Natasha Latysheva, a research engineer at Deepmind. “There's no one metric for success.” So, deep mind is chasing as many people as possible.

Statistics + Exclusive Stories

Statistics+

This article is for stat+ subscribers only

In addition to unlocking this article, we also provide in-depth analysis, newsletters, premium events and news alerts.

Do you already have an account? Login

View all plans

To read the rest of this story, subscribe to stat+.

Subscribe



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *