2022Hao Picking

From 3DEM-Methods
Revision as of 07:58, 20 January 2023 by WikiSysop (talk | contribs) (Created page with "== Citation == Hao, Yu / Wan, Xiaohua / Yan, Rui / Liu, Zhiyong / Li, Jintao / Zhang, Shihua / Cui, Xuefeng / Zhang, Fa. VP-Detector: A 3D multi-scale dense convolutional neu...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

Citation

Hao, Yu / Wan, Xiaohua / Yan, Rui / Liu, Zhiyong / Li, Jintao / Zhang, Shihua / Cui, Xuefeng / Zhang, Fa. VP-Detector: A 3D multi-scale dense convolutional neural network for macromolecule localization and classification in cryo-electron tomograms. 2022, Computer Methods and Programs in Biomedicine, p. 106871

Abstract

Background and objective: Cryo-electron tomography (cryo-ET) with subtomogram averaging (STA) is in- dispensable when studying macromolecule structures and functions in their native environments. Due to the low signal-to-noise ratio, the missing wedge artifacts in tomographic reconstructions, and multiple macromolecules of varied shapes and sizes, macromolecule localization and classification remain chal- lenging. To tackle this bottleneck problem for structural determination by STA, we design an accurate macromolecule localization and classification method named voxelwise particle detector (VP-Detector). Methods: VP-Detector is a two-stage particle detection method based on a 3D multiscale dense convolu- tional neural network (3D MSDNet). The proposed network uses 3D hybrid dilated convolution (3D HDC) to avoid the resolution loss caused by scaling operations. Meanwhile, it uses 3D dense connectivity to encourage the reuse of feature maps to reduce trainable parameters. In addition, the weighted focal loss is proposed to focus more attention on difficult samples and rare classes, which relieves the class im- balance caused by multiple particles of various sizes. The performance of VP-Detector is evaluated on both simulated and real-world tomograms, and it shows that VP-Detector outperforms state-of-the-art methods. Results: The experiments show that VP-Detector outperforms the state-of-the-art methods on particle lo- calization with an F1-score of 0.951 and a precision of 0.978. In addition, VP-Detector can replace manual particle picking in experiment on the real-world tomograms. Furthermore, it performs well in classifying large-, medium-, and small-weight proteins with accuracies of 1, 0.95, and 0.82, respectively. Finally, ab- lation studies demonstrate the effectiveness of 3D HDC, 3D dense connectivity, weighted focal loss, and training on small training sets. Conclusions: VP-Detector can achieve high accuracy in particle detection with few trainable parameters and support training on small datasets. It can also relieve the class imbalance caused by multiple particles with various shapes and sizes.

Keywords

Links

https://www.sciencedirect.com/science/article/pii/S016926072200253X

Related software

Related methods

Comments