Novel machine learning approaches for improving structural discrimination in cryo-electron tomography

用于改善冷冻电子断层扫描结构辨别的新型机器学习方法

• 批准号: 10454131
• 负责人: Min Xu
• 金额: $ 32.74万
• 依托单位: CARNEGIE-MELLON UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-06-10 至 2024-05-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10454131
• 关键词: 3-Dimensional; Algorithmic Software; Algorithms; Back; Benchmarking; Biological Process; Cells; Communities; Computer Analysis; Computer software; Cryo-electron tomography; Data; Data Analyses; Data Set; Detection; Discrimination; Evaluation; Future; Gaussian model; Hour; Image; In Situ; Knowledge; Laplacian; Literature; Machine Learning; Macromolecular Complexes; Manuals; Methods; Mitochondria; Modeling; Molecular Conformation; Monitor; Neurophysiology - biologic function; Noise; Organelles; Performance; Process; Publishing; Reporting; Resolution; Series; Signal Transduction; Structure; System; Techniques; Testing; Time; Tomogram; Weight; Work; autoencoder; automated algorithm; base; deep learning; design; falls; feature detection; graphical user interface; improved; innovation; insight; machine learning algorithm; nano; nanometer resolution; novel; novel strategies; open source; particle; pi-Mesons; programs; reconstruction; success; user-friendly

Project Summary Cellular cryo-electron tomography (Cryo-ET) has made possible the observation of cellular organelles and macromolecular complexes at nanometer resolution with native conformations. The rapid increasing amount of Cryo-ET data available however brings along some major challenges for analysis which we will timely ad- dress in this proposal. We will design novel data-driven machine learning algorithms for improving structural discrimination and resolution. In particular, we have the following specific aims: (1) We will develop a novel Autoencoder and Iterative region Matching (AIM) algorithm for marker-free alignment of image tilt-series to re- construct tomograms with improved resolution; (2) We will develop a saliency-based auto-picking algorithm for better detecting macromolecular complexes, and combine it with an innovative 2D-to-3D framework to further improve structure detection accuracy; (3) We will design an end-to-end convolutional model for pose-invariant clustering of subtomograms. This model will produce an initial clustering which will be refined by a new subto- mogram averaging algorithm that automatically down-weights subtomograms of noise and little contribution; (4) We will perform experimental evaluations by using previously reported bacterial secretion systems and mito- chondrial ultrastructures datasets to improve the final resolution. Implementing algorithms in Aims 1-3, we will develop a user-friendly open-source graphical user interface -tom to directly benefit the scientific community. -tom will be systematically compared with existing software including IMOD, EMAN2, and Relion on simulated and benchmark datasets. To facilitate distribution, -tom will be integrated into existing software platforms Sci- pion and TomoMiner. Our data-driven algorithms and software not only will facilitate and accelerate the future use of Cryo-ET, but also can be readily used on analyzing the existing large amounts of Cryo-ET data to im- prove our understanding of the structure, function, and spatial organization of macromolecular complexes in situ.

项目概要 细胞冷冻电子断层扫描 (Cryo-ET) 使观察细胞器和 具有天然构象的纳米分辨率的大分子复合物数量迅速增加。 然而，可用的 Cryo-ET 数据给分析带来了一些重大挑战，我们将及时调整这些挑战 我们将设计新颖的数据驱动机器学习算法来改进结构。 具体而言，我们有以下具体目标：（1）我们将开发一部小说。 自动编码器和迭代区域匹配（AIM）算法，用于图像倾斜系列的无标记对齐，以重新 构建分辨率更高的断层图；（2）我们将开发一种基于显着性的自动拾取算法 更好地检测大分子复合物，并将其与创新的 2D 到 3D 框架相结合，进一步 (3)我们将设计一个端到端的姿态不变卷积模型 该模型将产生一个初始聚类，该聚类将通过新的子断层图进行细化。 (4) 断层图平均算法，自动降低噪声和贡献较小的子断层图的权重； 我们将通过使用先前报道的细菌分泌系统和线粒体来进行实验评估 实现目标 1-3 中的算法，我们将使用球粒超微结构数据集来提高最终分辨率。 开发一个用户友好的开源图形用户界面-tom，直接造福科学界。 -tom将在模拟上与现有软件（包括IMOD、EMAN2和Relion）进行系统比较 和基准数据集，为了便于分发，-tom 将集成到现有的软件平台 Sci- 中。 pion 和 TomoMiner 我们的数据驱动算法和软件不仅将促进和加速未来。 Cryo-ET 的使用，而且还可以轻松用于分析现有的大量 Cryo-ET 数据，以改进 证明我们对大分子复合物的结构、功能和空间组织的理解 情况。