Researchers at $Alphabet-C (GOOG.US)$$Alphabet-A (GOOGL.US)$ Google DeepMind have developed AlphaFold 3, an new artificial intelligence (AI) model.

AlphaFold 3 can predict the structure and interactions of biological molecules. This includes proteins, DNA and RNA, and small molecules that could function as drugs.

Google DeepMind will make the model available for non-commercial use through the AlphaFold server.

The details were published in the journal Nature on May 8.

The company adds that AlphaFold 3 can predict the structure and interactions of all life's molecules. For the interactions of proteins with other molecule types, researchers saw a 50% improvement compared with existing prediction methods. For some important categories of interaction, that's double the prediction accuracy.

To build on AlphaFold 3's potential for drug design, Isomorphic Labs is already collaborating with pharmaceutical companies to apply it to real-world drug design challenges.

The new model builds on the foundations of AlphaFold 2, released in 2020, significantly improved on the first's protein structure accuracy predictions.

The company adds that millions of researchers have used AlphaFold 2 to make discoveries in malaria vaccines, cancer treatments and enzyme design. AlphaFold has been cited more than 20,000 times and its scientific impact.

AlphaFold 3 generates a joint 3D structure with an input list of molecules, revealing how they all fit together.

It models large biomolecules such as proteins, DN, and RNA, as well as small molecules, also known as ligands — a category encompassing many drugs.

Furthermore, AlphaFold 3 can model chemical modifications to these molecules, which control the healthy functioning of cells that, when disrupted, can lead to disease.

In January, Isomorphic Labs announced its two commercial partners, Eli Lilly And Co (NYSE:LLY) and Novartis AG (NYSE:NVS). Both the deals are multi-target and focused on small molecules.