Distance-AF is a computational method that enhances AlphaFold2 by integrating user-specified distance constraints, enabling accurate protein structures prediction on different applications. It demonst...

Communications Chemistry, Published online: 30 October 2025; doi:10.1038/s42004-025-01751-4Accurate modeling of atomic coordinates into cryo-electron microscopy maps is challenging for proteins with multiple functional states, especially without suitable templates and at low resolutions. Here, the authors employ a refinement approach combining AlphaFold2, clustering, and density-guided simulations, enhancing model accuracy for membrane proteins undergoing significant conformational changes.

Voltage-gated cation channels are crucial membrane proteins responsible for the electrical activity in excitable nerve, muscle, and cardiac tissue. These channels respond to changes in the membrane…

In the ongoing evolution of proteomics, understanding post-translational modifications (PTMs) has become critical. Among these modifications, malonylation, a less commonly studied yet impactful alteration of lysine residues on proteins, presents intriguing opportunities for further inquiry. Recognizing and mapping these malonylation sites is not merely an academic exercise; it carries implications for deciphering various biological processes and disease mechanisms. In their recent work, researchers Xu, Qian, and Yang propose a novel methodology that combines AlphaFold2, an advanced protein structure prediction tool, with ensemble learning algorithms to enhance the identification of malonylation sites significantly.

BindCraft, an open-source, automated pipeline for de novo protein binder design with experimental success rates of 10–100%, leverages AlphaFold2 weights to generate binders with nanomolar affinity without the need for high-throughput screening.

A Database for Triticeae and Avena