Protein structure predictions articles from across Nature Portfolio

Amyloid fibrils are ordered protein assemblies implicated in neurodegenerative disease. Here the authors show that hairpin trimers can be transition states of fibril nucleation, explaining how different fibril isoforms may arise from alternative nucleation sites.

Protein dynamics, crucial for life, are difficult and expensive to predict. This study shows that AI-based structure prediction methods can be modified for rapidly predicting the conformational landscapes of proteins, with strong correlations with experimentally-measured relative state populations.

The inside surface of microtubules contains so-called microtubule inner proteins, but little is known about their identity. Here the authors use bioinformatics to identify structural motifs within this class of proteins and potential new members.

AlphaFold is a breakthrough in protein structure prediction, but limitations in its application to computation- and structure-guided drug discovery remain. As with structure prediction, public-domain data and benchmarking initiatives will be essential to advance the field of computational drug design.

Intrinsically disordered regions of proteins are prevalent across the kingdoms of life; however, biophysical characterization is expensive, requiring specialized expertise and equipment and time-consuming sample preparation. By combining simulations and deep learning, we have developed a method to predict their average ensemble properties directly from sequence.

How accurate is the prediction of protein structure by AlphaFold? Terwilliger et al. address this question with a rigorous assessment of the accuracy of AlphaFold-predicted structures by comparing them with experimentally determined X-ray crystallographic data.

Large language models are learning the language of genomics.