Document Type
Article
Publication Date
2024
DOI
10.1093/bioadv/vbae169
Publication Title
Bioinformatics Advances
Volume
4
Issue
1
Pages
vbae169 (1-15)
Abstract
Although multiple neural networks have been proposed for detecting secondary structures from medium-resolution (5–10 Å) cryo-electron microscopy (cryo-EM) maps, the loss functions used in the existing deep learning networks are primarily based on cross-entropy loss, which is known to be sensitive to class imbalances. To monitor and tune the performance of various loss functions for the secondary structure detection problem, we investigated five loss functions: cross-entropy, Focal loss, Dice loss, and two combined loss functions. Using a U-Net architecture in our DeepSSETracer method and a dataset composed of 1,355 box-cropped atomic-structure/density-map pairs, we found that a newly designed loss function that combines Focal loss and Dice loss provides the best overall detection accuracy for secondary structures. For β-sheet voxels, which are generally much harder to detect than helix voxels, the combined loss function achieved a significant improvement (an 8.8% increase in the F₁ score) compared to the cross-entropy loss function and a noticeable improvement from the Dice loss function. This study demonstrates the potential for designing more effective loss functions for hard cases in the segmentation of secondary structures. The newly trained model was incorporated into DeepSSETracer 1.1 for the segmentation of protein secondary structures in medium-resolution cryo-EM map components. DeepSSETracer 1.1 can be integrated into ChimeraX, a popular molecular visualization software.
Rights
© The Authors 2024.
This is an Open Access article distributed under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) License, which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
Data Availability
Article states: "Testing data used in this work are available on request to the corresponding author. DeepSSETracer 1.1. is downloadable at https://www.cs.odu.edu/~bioinfo/B2I_Tools/."
Original Publication Citation
Mu, Y., Nguyen, T., Hawickhorst, B., Wriggers, W., Sun, J., & He, J. (2024). The combined focal loss and dice loss function improves the segmentation of beta-sheets in medium-resolution cryo-electron-microscopy density maps. Bioinformatics Advances, 4(1), 1-15, Article vbae169. https://doi.org/10.1093/bioadv/vbae169
Repository Citation
Mu, Y., Nguyen, T., Hawickhorst, B., Wriggers, W., Sun, J., & He, J. (2024). The combined focal loss and dice loss function improves the segmentation of beta-sheets in medium-resolution cryo-electron-microscopy density maps. Bioinformatics Advances, 4(1), 1-15, Article vbae169. https://doi.org/10.1093/bioadv/vbae169
ORCID
0009-0005-7058-2979 (Mu), 0000-0001-5326-3152 (Wriggers), 0009-0000-8905-7553 (Sun), 0000-0002-7249-4746 (He)