Deep Learning for Protein Secondary-Structure Segmentation in Intermediate-Resolution Cryo-EM Maps: A Resolution-Stratified Benchmark Dataset and Controlled Evaluation
- 1Georgia Southern University , , , ,
Abstract
Accurate segmentation of protein secondary structures in cryo-electron microscopy (cryo-EM) maps is crucial for protein tracing and atomic model building, yet remains challenging at intermediate resolutions. Although deep learning architectures have recently been applied to this task, there remains a lack of standardized evaluation protocols and systematic resolution-stratified analyses. Consequently, it remains unclear how segmentation performance varies across finer resolution ranges within the intermediate-resolution regime and how different volumetric segmentation architectures compare under controlled experimental conditions. To address these gaps, we present a nonredundant, resolution-stratified benchmark dataset and a controlled evaluation framework for protein secondary-structure segmentation in intermediate-resolution cryo-EM maps. The dataset comprises 972 nonredundant protein-chain samples from 495 cryo-EM protein structures resolved at 4.5–8.0 Å, with voxel-level annotations for helices, sheets, and non-periodic secondary-structure (NPSS) regions. The dataset is stratified into three resolution ranges─4.5–5.5, 5.5–6.5, and 6.5–8.0 Å─to enable systematic analysis of resolution-dependent segmentation performance. Using this benchmark, we evaluate five representative convolutional and transformer-based volumetric segmentation architectures─U-Net, Residual U-Net, Attention U-Net, UNETR, and Swin-UNETR─under standardized preprocessing, training, and evaluation protocols. Residual U-Net achieves the highest macro-averaged foreground (Macro-FG) F1 score in all three resolution bins, while helices are segmented more accurately than sheets and NPSS regions. All five architectures achieve their highest Macro-FG F1 scores in the highest-resolution bin, whereas performance varies between the two lower-resolution bins across architectures and secondary-structure classes. Overall, this benchmark enables fine-grained analysis of resolution-dependent segmentation performance, supports reproducible method development, and facilitates controlled comparison of future cryo-EM secondary-structure segmentation approaches.
Related
- A unified intermediate-resolution framework for modeling biomolecular condensates at near-cellular complexity
- Intermediate-Resolution Modeling of Dynamic DNAs and Their Phase Separation
- ErrorRoute: Budgeted Utility-Aware Resolution Routingfor 3D Medical Image Segmentation
- Structure of a sparsely populated chimeric intermediate that facilitates fold-switching of a metamorphic protein
- Starship transposons mobilise via a circular intermediate with potential biotechnological applications
BibTeX
@article{pial2026deep,
title = {{Deep Learning for Protein Secondary-Structure Segmentation in Intermediate-Resolution Cryo-EM Maps: A Resolution-Stratified Benchmark Dataset and Controlled Evaluation}},
author = {Md Ehashan Rabbi Pial and Farhan Noor Dehan and Salim Sazzed},
journal = {ACS Omega},
year = {2026},
month = oct,
doi = {10.1021/acsomega.6c06887},
url = {https://pubs.acs.org/acsodf/article/11/42/65152/5452270/Deep-Learning-for-Protein-Secondary-Structure},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Deep Learning for Protein Secondary-Structure Segmentation in Intermediate-Resolution Cryo-EM Maps: A Resolution-Stratified Benchmark Dataset and Controlled Evaluation
AU - Md Ehashan Rabbi Pial
AU - Farhan Noor Dehan
AU - Salim Sazzed
PY - 2026
DA - 2026/10/15
JO - ACS Omega
DO - 10.1021/acsomega.6c06887
UR - https://pubs.acs.org/acsodf/article/11/42/65152/5452270/Deep-Learning-for-Protein-Secondary-Structure
AB - Accurate segmentation of protein secondary structures in cryo-electron microscopy (cryo-EM) maps is crucial for protein tracing and atomic model building, yet remains challenging at intermediate resolutions. Although deep learning architectures have recently been applied to this task, there remains a lack of standardized evaluation protocols and systematic resolution-stratified analyses. Consequently, it remains unclear how segmentation performance varies across finer resolution ranges within the intermediate-resolution regime and how different volumetric segmentation architectures compare under controlled experimental conditions. To address these gaps, we present a nonredundant, resolution-stratified benchmark dataset and a controlled evaluation framework for protein secondary-structure segmentation in intermediate-resolution cryo-EM maps. The dataset comprises 972 nonredundant protein-chain samples from 495 cryo-EM protein structures resolved at 4.5–8.0 Å, with voxel-level annotations for helices, sheets, and non-periodic secondary-structure (NPSS) regions. The dataset is stratified into three resolution ranges─4.5–5.5, 5.5–6.5, and 6.5–8.0 Å─to enable systematic analysis of resolution-dependent segmentation performance. Using this benchmark, we evaluate five representative convolutional and transformer-based volumetric segmentation architectures─U-Net, Residual U-Net, Attention U-Net, UNETR, and Swin-UNETR─under standardized preprocessing, training, and evaluation protocols. Residual U-Net achieves the highest macro-averaged foreground (Macro-FG) F1 score in all three resolution bins, while helices are segmented more accurately than sheets and NPSS regions. All five architectures achieve their highest Macro-FG F1 scores in the highest-resolution bin, whereas performance varies between the two lower-resolution bins across architectures and secondary-structure classes. Overall, this benchmark enables fine-grained analysis of resolution-dependent segmentation performance, supports reproducible method development, and facilitates controlled comparison of future cryo-EM secondary-structure segmentation approaches.
SN - 2470-1343
ER -