In a living being, proteins make up roughly everything: from the molecular machines running every cell’s metabolism, to the tip of your hair. Encoded in the DNA, a protein may be represented as ...

However, it presents a complex challenge since protein function is dependent not only on the sequence of amino acids but also on the three-dimensional (3D) protein structure, which needs to be ...

On Thursday, Google's sister company, DeepMind, announced it has successfully used artificial intelligence to predict the 3D structures of nearly every catalogued protein known to science.

The prediction of protein structure is difficult for a few reasons. First, there is a huge search space — every possible 3D position for each atom in each amino acid.

Protein Pfs48/45, a crucial part of the malaria parasite that eluded scientists until DeepMind’s AlphaFold was able to predict its 3D structure DeepMind By Billy Perrigo July 28, 2022 7:01 AM EDT ...

The tip of rotavirus B spike protein is not only totally different from the corresponding structure in rotavirus A and C, but also no other protein before had been reported to have this structure.

Researchers from the Göttingen Cluster of Excellence Multiscale Bioimaging (MBExC) have uncovered the 3D structure of the membrane proteins myoferlin and dysferlin using high-resolution cryo ...

In a recent study by the team, they discovered the 3D structure of a protein called TnpB, a probable precursor to the CRISPR-Cas12 enzyme. Their findings appeared in the journal Nature.

Once it was fully trained, ESM-2 was able to ingest a raw string of amino acids and output a 3D protein structure, along with a score that represents its confidence in the accuracy of that structure.

Mask-prior-guided denoising diffusion (MapDiff) for inverse protein folding. Credit: Nature Machine Intelligence (2025). DOI: 10.1038/s42256-025-01042-6 ...