发表机构
Keio University; Keio AI Research Center; Carnegie Mellon University（庆应义塾大学; 庆应AI研究中心; 卡内基梅隆大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究将冷冻电镜颗粒挑选、污染去除、二维分类选择整合为感知重构的单一流程，采用CryoTransformer等组件，实现更优三维分辨率，指出颗粒选择应基于重构效果判断。
AI 中文摘要
冷冻电镜（cryo-EM）可在近原子分辨率下测定蛋白质及大分子复合物的结构，最终的三维重构依赖于从含噪显微图中提取纯净的颗粒栈。该提取过程可分解为三个子任务，即颗粒挑选、污染去除和二维分类选择。然而，每个子任务均是单独训练和评估的，且 none 是针对重构进行优化的。我们将这三个子任务整合为一个针对下游重构质量的单一流程。我们为每个子任务采用最先进的组件实例化该流程：CryoTransformer 进行宽松的颗粒挑选，MicrographCleaner 对污染进行掩蔽，CryoSift 通过连续质量分数选择二维分类，并通过微调步骤形成闭环，该步骤将存活的颗粒反馈给挑选器。该流程实现了比我们对比的每个挑选器都更好的三维分辨率。我们还表明，最佳的二维 F1 值并非最佳分辨率，因此颗粒选择更适合被视为一个由其生成的图谱判断的感知重构流程。
英文摘要
Cryo-electron microscopy (cryo-EM) determines the structures of proteins and macromolecular assemblies at near-atomic resolution, and the final 3D reconstruction depends on extracting a clean particle stack from noisy micrographs. This extraction decomposes into three sub-tasks, namely particle picking, contamination removal, and 2D class selection. Each of them, however, is trained and evaluated in isolation, and none is optimized for the reconstruction. We instead integrate the three sub-tasks into a single pipeline posed against downstream reconstruction quality. We instantiate the pipeline with a state-of-the-art component for each sub-task, CryoTransformer picking permissively, MicrographCleaner masking contamination, and CryoSift selecting 2D classes by a continuous quality score, and close the loop with a fine-tuning step that returns the surviving particles to the picker. The pipeline achieves a better 3D resolution than every picker we compare. We also show that the best 2D F1 is not the best resolution, so particle selection is better treated as one reconstruction-aware pipeline judged by the map it delivers.
