当前位置: X-MOL 学术IEEE/ACM Trans. Comput. Biol. Bioinform. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Macromolecules Structural Classification With a 3D Dilated Dense Network in Cryo-Electron Tomography
IEEE/ACM Transactions on Computational Biology and Bioinformatics ( IF 3.6 ) Pub Date : 2021-03-17 , DOI: 10.1109/tcbb.2021.3065986
Shan Gao 1, 2 , Renmin Han 3 , Xiangrui Zeng 4 , Zhiyong Liu 1 , Min Xu 4 , Fa Zhang 1
Affiliation  

Cryo-electron tomography, combined with subtomogram averaging (STA), can reveal three-dimensional (3D) macromolecule structures in the near-native state from cells and other biological samples. In STA, to get a high-resolution 3D view of macromolecule structures, diverse macromolecules captured by the cellular tomograms need to be accurately classified. However, due to the poor signal-to-noise-ratio (SNR) and severe ray artifacts in the tomogram, it remains a major challenge to classify macromolecules with high accuracy. In this paper, we propose a new convolutional neural network, named 3D-Dilated-DenseNet, to improve the performance of macromolecule classification. In 3D-Dilated-DenseNet, there are two key strategies to guarantee macromolecule classification accuracy: 1) Using dense connections to enhance feature map utilization (corresponding to the baseline 3D-C-DenseNet); 2) Adopting dilated convolution to enrich multi-level information in feature maps. We tested 3D-Dilated-DenseNet and 3D-C-DenseNet both on synthetic data and experimental data. The results show that, on synthetic data, compared with the state-of-the-art method in the SHREC contest (SHREC-CNN), both 3D-C-DenseNet and 3D-Dilated-DenseNet outperform SHREC-CNN. In particular, 3D-Dilated-DenseNet improves 0.393 of F1 metric on tiny-size macromolecules and 0.213 on small-size macromolecules. On experimental data, compared with 3D-C-DenseNet, 3D-Dilated-DenseNet can increase classification performance by 2.1 percent.

中文翻译:

低温电子断层扫描中使用 3D 扩张密集网络进行大分子结构分类

低温电子断层扫描与子断层图平均 (STA) 相结合,可以揭示细胞和其他生物样本中接近天然状态的三维 (3D) 大分子结构。在 STA 中,为了获得大分子结构的高分辨率 3D 视图,需要对细胞层析成像捕获的各种大分子进行准确分类。然而,由于断层图中较差的信噪比 (SNR) 和严重的射线伪​​影,高精度地对大分子进行分类仍然是一个重大挑战。在本文中,我们提出了一种新的卷积神经网络,名为 3D-Dilated-DenseNet,以提高大分子分类的性能。在3D-Dilated-DenseNet中,保证大分子分类精度的关键策略有两个:1)使用密集连接增强特征图利用率(对应baseline 3D-C-DenseNet);2)采用空洞卷积来丰富特征图中的多层次信息。我们在合成数据和实验数据上测试了 3D-Dilated-DenseNet 和 3D-C-DenseNet。结果表明,在合成数据上,与 SHREC 竞赛中最先进的方法 (SHREC-CNN) 相比,3D-C-DenseNet 和 3D-Dilated-DenseNet 均优于 SHREC-CNN。特别是,3D-Dilated-DenseNet 在微小尺寸的大分子上提高了 0.393 的 F1 指标,在小尺寸的大分子上提高了 0.213。在实验数据上,与3D-C-DenseNet相比,3D-Dilated-DenseNet可以将分类性能提高2.1%。我们在合成数据和实验数据上测试了 3D-Dilated-DenseNet 和 3D-C-DenseNet。结果表明,在合成数据上,与 SHREC 竞赛中最先进的方法 (SHREC-CNN) 相比,3D-C-DenseNet 和 3D-Dilated-DenseNet 均优于 SHREC-CNN。特别是,3D-Dilated-DenseNet 在微小尺寸的大分子上提高了 0.393 的 F1 指标,在小尺寸的大分子上提高了 0.213。在实验数据上,与3D-C-DenseNet相比,3D-Dilated-DenseNet可以将分类性能提高2.1%。我们在合成数据和实验数据上测试了 3D-Dilated-DenseNet 和 3D-C-DenseNet。结果表明,在合成数据上,与 SHREC 竞赛中最先进的方法 (SHREC-CNN) 相比,3D-C-DenseNet 和 3D-Dilated-DenseNet 均优于 SHREC-CNN。特别是,3D-Dilated-DenseNet 在微小尺寸的大分子上提高了 0.393 的 F1 指标,在小尺寸的大分子上提高了 0.213。在实验数据上,与3D-C-DenseNet相比,3D-Dilated-DenseNet可以将分类性能提高2.1%。小尺寸大分子的 F1 度量为 393,小尺寸大分子为 0.213。在实验数据上,与3D-C-DenseNet相比,3D-Dilated-DenseNet可以将分类性能提高2.1%。小尺寸大分子的 F1 度量为 393,小尺寸大分子为 0.213。在实验数据上,与3D-C-DenseNet相比,3D-Dilated-DenseNet可以将分类性能提高2.1%。
更新日期:2021-03-17
down
wechat
bug