Research map / Probabilistic and scientific modeling / Molecules and proteins
CryoAtlas: A Large Curated Dataset and Unified Benchmark for Cryo-EM Atomic Model Building
Mingrui Li, Minzhang Li, Weichen Qin, Yufan Xie, Zhangzhi Xiong, Sixian Shen, Jiakai Zhang, Yuan Pei, Jingyi Yu
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Introduces CryoAtlas, a curated dataset and unified benchmark built from EMDB and PDB entries for density-guided cryo-EM atomic model building.
Problem
Deep learning progress on automated atomic model building from cryo-EM maps is limited by the lack of large, high-quality datasets and standardized evaluation benchmarks.
Approach
A rigorously filtered dataset integrating EMDB maps with PDB atomic models (entries up to March 2026), paired with a unified benchmark for density-guided model building.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| train ModelAngelo CNN on CryoAtlas instead of Cryo2StructData (ablation) | ModelAngelo (retrained CNN) · CryoAtlas benchmark (618 targets) | Ca RMSD (A): 1.108 -> 0.769 | Improved |
| train ModelAngelo CNN on CryoAtlas instead of Cryo2StructData (ablation) | ModelAngelo (retrained CNN) · CryoAtlas benchmark (618 targets) | GT Score: 0.697 -> 0.755 | Improved |
| retrain ModelAngelo CNN on CryoAtlas vs released checkpoint | ModelAngelo · CryoAtlas benchmark (618 targets) | GT Score: 0.723 -> 0.755 | Improved |
| restore discarded entries to CryoAtlas training set (ablation) | ModelAngelo CNN training · CNN training, first 5,000 steps | EMA loss: 0.0898 -> 0.1140 | Hurt |
| apply CryoAtlas filters to raw Cryo2StructData (ablation) | ModelAngelo CNN training · CNN training, first 5,000 steps | EMA loss: 0.1127 -> 0.0865 | Improved |
| use released normalized Cryo2StructData maps instead of raw (ablation) | ModelAngelo CNN training · CNN training, first 5,000 steps | EMA loss: 0.1127 -> 0.1475 | Hurt |
| lower map resolution (stratification) | all benchmarked methods · CryoAtlas benchmark (618 targets) | GT Score | Hurt |
| lower map resolution (stratification) | all benchmarked methods · CryoAtlas benchmark (618 targets) | Geom Score | No clear effect |
| longer sequence length (stratification) | AlphaFold 3 · CryoAtlas benchmark (618 targets) | GT Score and Map Score | Hurt |
| longer sequence length (stratification) | density-guided methods · CryoAtlas benchmark (618 targets) | Map Score | No clear effect |
| higher train-test sequence identity (stratification) | density-guided methods · CryoAtlas benchmark (618 targets) | GT Score | No clear effect |
| use sequence-only AlphaFold 3 instead of density-guided methods | model building · CryoAtlas benchmark (618 targets) | Geom Score vs GT Score: Geom 0.598 vs 0.537; GT 0.552 vs 0.787 (CryoAtom2) | Mixed |
Experimental setup
Datasets: EMDB PDB
Benchmarks: CryoAtlas
Closest papers by meaning
- Multiscale guidance of protein structure prediction with heterogeneous cryo-EM data (NeurIPS 2025 · similarity 0.90)
- CryoFM: A Flow-based Foundation Model for Cryo-EM Densities (ICLR 2025 · similarity 0.90)
- cryoSPHERE: Single-Particle HEterogeneous REconstruction from cryo EM (ICLR 2025 · similarity 0.89)
- CryoBench: Diverse and challenging datasets for the heterogeneity problem in cryo-EM (NeurIPS 2024 · similarity 0.88)
- CryoSPIN: Improving Ab-Initio Cryo-EM Reconstruction with Semi-Amortized Pose Inference (NeurIPS 2024 · similarity 0.86)
- CryoDomain: Sequence-free Protein Domain Identification from Low-resolution Cryo-EM Density Maps (AAAI 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
