Prof. Yu LI’s group, together with their collaborators from Zelixir and Fudan University, won first place in the CASP15-RNA structure prediction competition. The joint team tried to model the RNA 3D structure using AI and physical force field methods, leading to the AICHEMY-RNA and AICHEMY-RNA2 submissions. Among all the worldwide participants, AICHEMY-RNA2 won first place regarding overall performance, and AICHEMY-RNA won first place in fully automatic modeling. Two Ph.D. students, Zhihang Hu and Liang Hong, and one RA, Jiayang Chen, from Prof. Yu LI’s group contributed to the competition participation.
CASP (Critical Assessment of Structure Prediction) is a community-wide experiment to determine and advance state of the art in modeling macromolecular structures from sequences. Every two years, participants are invited to submit models for a set of macromolecules for which the experimental structures are not yet public. In the latest CASP round, CASP15, nearly 100 groups from around the world submitted more than 53,000 models on 127 modeling targets in 5 prediction categories. Independent assessors then compare the models with the experiment. Noticeably, AlphaFold, developed by DeepMind, won first place in CASP13-Protein and CASP14-Protein competitions. It has been proven to advance the field profoundly.
