Structural Biology in the AI Era

TOPICAL COLLECTIONS

Guest Editor

Qingyu Tang

Vanderbilt University

Dr. Qingyu Tang is a research assistant professor in the Department of Molecular Physiology and Biophysics at Vanderbilt University. Their research focuses on elucidating the structural dynamics of protein complexes that govern essential biological processes, with an emphasis on ATP-binding cassette (ABC) transporters and signaling kinases implicated in human disease, including cancer and inflammation. Dr. Tang employs an integrated approach combining cryo-electron microscopy (cryo-EM), double electron–electron resonance (DEER) spectroscopy, molecular dynamics (MD) simulations, deep learning approaches, and functional assays to define how conformational landscapes regulate protein function. Their recent work has elucidated the conformational space and transport mechanism of a heterodimeric ABC transporter through cryo-EM, DEER, and MD simulations, and they have further incorporated AlphaFold to explore novel conformations and shed light on the code governing conformational transitions. Dr. Tang has published extensively in leading journals, including Science, Nature Chemical Biology, and Nature Communications, and has served as a reviewer for numerous publications in the field. They are passionate about decoding protein conformational dynamics and advancing methodological innovation at the intersection of structural biology and artificial intelligence.

Collection Overview

The field of structural biology has continuously advanced through methodological innovation. While nuclear magnetic resonance (NMR) spectroscopy and X-ray crystallography remain powerful techniques, cryo-electron microscopy (cryo-EM) and cryo-electron tomography (cryo-ET) have become increasingly accessible and transformative. Collectively, these methods have contributed more than 256,000 experimentally determined structures to the Protein Data Bank (PDB). However, the recent emergence of artificial intelligence (AI)-enabled approaches, particularly AlphaFold and related deep learning algorithms, has fundamentally reshaped the field by predicting more than 200 million protein structure models, dramatically expanding access to structural information.

Structural biology is not being replaced by AI; rather, it is being transformed by it. The entire structural biology workflow is rapidly adopting AI, particularly deep learning-based algorithms, to accelerate discovery. Deep learning is improving construct design, cryo-EM image processing and particle picking, conformational heterogeneity analysis, model building, and structure refinement. The integration of AI with experimental structural biology is not only increasing efficiency and accuracy but also enabling researchers to address biological questions that were previously inaccessible.

This Topical Collection aims to showcase the latest methodological advances and biological applications at the interface of structural biology and AI. We welcome contributions spanning experimental structural biology, computational biology, and bioinformatics, including NMR, X-ray crystallography, cryo-EM, and cryo-ET workflows; molecular dynamics simulations; protein structure prediction; protein design; and benchmarking of emerging AI models for protein structure and function research. By bringing together researchers from diverse disciplines, this collection will highlight how AI is redefining structural biology and accelerating discoveries across biology, biotechnology, and biomedicine.