EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Benchmarking deep learning methods for C α atom prediction in cryo-EM density maps

Tian Zhang, Zhe Liu, Yiqing Ma, Chenjie Feng, Renmin Han iD

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btag350 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Tian Zhang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Research Center for Mathematics and Interdisciplinary Sciences; Cheeloo College of Medicine, Qilu Hospital (Qingdao), Shandong University, Qingdao 26…. Hauptthemen laut MEDLINE: Cryoelectron Microscopy, Deep Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, Fundamental Research Funds for the Central Universities, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation With the advancement of cryo-electron microscopy (cryo-EM) into the atomic resolution era, accurate Cα atom modeling has become essential for macromolecular structure determination. However, existing evaluation systems overly rely on full-atom metrics and lack a dedicated, comprehensive benchmark for assessing Cα prediction modules within automated modeling tools. Results To address this gap, we establish a rigorous benchmark to evaluate the Cα prediction performance of four prominent deep learning-based methods (ModelAngelo, DeepMainMast, EModelX, and CryoAtom) across multiple dimensions. We construct a diverse dataset covering a wide range of resolutions (1–8 Å), molecular weights, and noise levels. A novel evaluation framework is introduced, incorporating multi-threshold RMSD-based metrics (1–3 Å) alongside advanced point-cloud similarity measures (Chamfer Distance, Earth Mover’s Distance) for quantitative and nuanced assessment. Our results reveal that method performance is highly dependent on the chosen evaluation criteria and intrinsic data characteristics. ModelAngelo excels under loose thresholds with high-quality data but shows sensitivity to resolution degradation; CryoAtom demonstrates notable computational efficiency, however, its completeness-oriented design leads to a certain loss of precision; EModelX demonstrates balanced generalization across varied conditions; DeepMainMast achieves high localization accuracy under stringent criteria but incurs a high computational cost. Availability and implementation This work provides a reproducible, Cα-centric evaluation framework to guide method development and advance automated cryo-EM structure determination. The source code for the benchmark and evaluation metrics is freely available at https://github.com/zhtianz/Benchmarking\_CA.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cryoelectron MicroscopyDeep LearningBenchmarkingModels, Molecular

Autor:innen und Institutionen

  • Research Center for Mathematics and Interdisciplinary Sciences; Cheeloo College of Medicine, Qilu Hospital (Qingdao), Shandong University, Qingdao 266237, China.
  • College of Medical Information and Engineering, Ningxia Medical University, Yinchuan 750004, China.

ORCID-Profile: Renmin Han

Förderung

  • National Key Research and Development Program of China
  • Fundamental Research Funds for the Central Universities
  • National Natural Science Foundation of China
  • Foundation of Ningxia Province

Zitieren

APA

Zhang, T., Liu, Z., Ma, Y., Feng, C., & Han, R. (2026). Benchmarking deep learning methods for C α atom prediction in cryo-EM density maps. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag350

Vancouver

Zhang T, Liu Z, Ma Y, Feng C, Han R. Benchmarking deep learning methods for C α atom prediction in cryo-EM density maps. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag350

BibTeX
@article{Zhang2026,
  author = {Zhang, Tian and Liu, Zhe and Ma, Yiqing and Feng, Chenjie and Han, Renmin},
  title = {Benchmarking deep learning methods for C α atom prediction in cryo-EM density maps},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag350}
}
Kostenlos starten →