法国巴黎文理研究大学Charles Kervrann、德国慕尼黑工业大学Benjamin D. Engel等研究人员合作发现，深度学习可提高三维细胞低温电子断层图中的大分子识别能力。相关论文于2021年10月21日在线发表于国际学术期刊《自然—方法学》。

研究人员提出了DeepFinder，一个使用人工神经网络来同时定位多类大分子的计算程序。一旦经过训练，DeepFinder的推理阶段比模板匹配更快，并且在识别合成和实验数据集中各种尺寸的大分子方面比其他有竞争力的深度学习方法表现更好。在细胞低温电子断层扫描（cryo-ET）数据中，DeepFinder定位了膜结合和细胞膜核糖体（大约3.2 MDa）、核酮糖1,5-二磷酸羧化酶（大约560 kDa的可溶性复合物）和光系统II（大约550 kDa的膜复合物），其准确度与专家监督的真实注释相当。因此，DeepFinder是一个很有前途的算法，可以对细胞断层图中的各种分子目标进行半自动化分析。

据介绍，cryo-ET以纳米级的分辨率显示了原生细胞内大分子的三维空间分布。然而，细胞断层图内大分子的自动识别受到了噪音和重建伪影的挑战，以及在拥挤的体积内存在许多分子物种。

附：英文原文

Title: Deep learning improves macromolecule identification in 3D cellular cryo-electron tomograms

Author: Moebel, Emmanuel, Martinez-Sanchez, Antonio, Lamm, Lorenz, Righetto, Ricardo D., Wietrzynski, Wojciech, Albert, Sahradha, Larivire, Damien, Fourmentin, Eric, Pfeffer, Stefan, Ortiz, Julio, Baumeister, Wolfgang, Peng, Tingying, Engel, Benjamin D., Kervrann, Charles

Issue&Volume: 2021-10-21

Abstract: Cryogenic electron tomography (cryo-ET) visualizes the 3D spatial distribution of macromolecules at nanometer resolution inside native cells. However, automated identification of macromolecules inside cellular tomograms is challenged by noise and reconstruction artifacts, as well as the presence of many molecular species in the crowded volumes. Here, we present DeepFinder, a computational procedure that uses artificial neural networks to simultaneously localize multiple classes of macromolecules. Once trained, the inference stage of DeepFinder is faster than template matching and performs better than other competitive deep learning methods at identifying macromolecules of various sizes in both synthetic and experimental datasets. On cellular cryo-ET data, DeepFinder localized membrane-bound and cytosolic ribosomes (roughly 3.2MDa), ribulose 1,5-bisphosphate carboxylase–oxygenase (roughly 560kDa soluble complex) and photosystem II (roughly 550kDa membrane complex) with an accuracy comparable to expert-supervised ground truth annotations. DeepFinder is therefore a promising algorithm for the semiautomated analysis of a wide range of molecular targets in cellular tomograms.

DOI: 10.1038/s41592-021-01275-4

Source: https://www.nature.com/articles/s41592-021-01275-4