Reproduce “CryoAtlas: A Large Curated Dataset and Unified Benchmark for Cryo-EM Atomic Model Building” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Mingrui Li, Minzhang Li, Weichen Qin, Yufan Xie, Zhangzhi Xiong, Sixian Shen, Jiakai Zhang, Yuan Pei and 1 more
CryoAtlas provides 17,809 curated cryo-EM map–model–sequence entries and a common 618-target benchmark measuring structural accuracy, map fit, and geometry separately. In benchmark comparisons, density-guided CryoAtom2 leads in GT Score and Map Score, while sequence-only AlphaFold 3 leads in Geom Score and TM-score. CryoAtlas training also improves a ModelAngelo CNN reimplementation under the tested setup, not universally.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.