Artificial intelligence (AI) is rapidly transforming structural biology, enabling increasingly accurate modeling of protein structures and molecular interactions. In this talk, I will present our recent work on developing and evaluating AI methods for several important problems in structural biology.
I will first discuss MULTICOM, our protein structure prediction system that integrates large-scale AlphaFold-based model generation with deep learning-based model quality assessment.
Dr. Jianlin Cheng
I will then describe our work on protein–ligand modeling, including PoseBench, a comprehensive benchmark of protein–ligand structure prediction methods, and FlowDock, a generative AI method based on flow matching for predicting protein–ligand structures and binding affinities.
Finally, I will present Cryo2Struct, a 3D transformer-based method for de novo protein structure building from cryo-electron microscopy (cryo-EM) density maps, and MICA, a multimodal deep learning method that integrates experimental cryo-EM density maps with AlphaFold3 predictions to build high-accuracy protein structures. Together, these advances demonstrate the growing potential of AI to address challenging problems in structural biology and accelerate drug discovery.
Dr. Jianlin Cheng is a Curators’ Distinguished Professor and Paul & Diane Shumaker Professor in the David L. Payne Department of Electrical Engineering and Computer Science at the University of Missouri–Columbia (MU) and an investigator with MU’s NextGen Precision Health Initiative. He earned his PhD in computer science from the University of California, Irvine, in 2006. His research spans bioinformatics, machine learning, and artificial intelligence (AI). Dr. Cheng has authored or co-authored more than 290 publications, which have received more than 28,000 citations, with an h-index of 75. His AI methods for protein structure prediction have consistently ranked among the top performers in 10 consecutive rounds of the biennial worldwide Critical Assessment of Structure Prediction (CASP7–16), from 2006 to 2024.
His research has been supported by the National Institutes of Health (NIH), National Science Foundation(NSF), Department of Energy (DOE), and Department of Agriculture (USDA). Dr. Cheng is a Fellow of the American Association for the Advancement of Science (AAAS) and the American Institute for Medical and Biological Engineering (AIMBE). He serves as an Associate Editor for Bioinformatics and served as an Area Chair for NeurIPS from 2024 to 2026.