Positive-unlabeled convolutional neural networks for particle picking in cryo-electron micrographs
Positive-unlabeled convolutional neural networks for particle picking in cryo-electron micrographs
复制标题
DOI：
10.1038/s41592-019-0575-8
复制
发表时间：
2019-11-01
期刊：
影响因子：
48
通讯作者：
Berger, Bonnie
中科院分区：
文献类型：
--
作者：
Bepler, Tristan;Morin, Andrew;Berger, Bonnie
冷冻电子显微镜是一种用于确定蛋白质结构的流行方法;然而，识别足够数量的颗粒进行分析可能需要数月的人工努力。目前的计算方法发现许多假阳性，需要特别的后处理，特别是对于形状不寻常的颗粒。为了解决这些缺点，我们开发了黄玉，这是一种高效准确的粒子拾取管道，使用通用的正未标记学习方法训练神经网络。该框架使粒子检测模型能够用很少的稀疏标记粒子和没有标记的负粒子进行训练。黄玉检索更多的真实的颗粒比传统的采摘方法，同时保持低的假阳性率，是能够采摘具有挑战性的异常形状的蛋白质（例如，小，非球形和不对称的颗粒），产生更多的代表性颗粒集，不需要事后策划。我们证明了性能的黄玉两个困难的数据集和三个传统的数据集。黄玉是模块化的、独立的、免费的和开源的（http：topaz.csail.mit.edu）。
Cryo-electron microscopy is a popular method for the determination of protein structures; however, identifying a sufficient number of particles for analysis can take months of manual effort. Current computational approaches find many false positives and require ad hoc postprocessing, especially for unusually shaped particles. To address these shortcomings, we develop Topaz, an efficient and accurate particle-picking pipeline using neural networks trained with a general-purpose positive-unlabeled learning method. This framework enables particle detection models to be trained with few sparsely labeled particles and no labeled negatives. Topaz retrieves many more real particles than conventional picking methods while maintaining low false-positive rates, is capable of picking challenging unusually shaped proteins (for example, small, non-globular and asymmetric particles), produces more representative particle sets and does not require post hoc curation. We demonstrate the performance of Topaz on two difficult datasets and three conventional datasets. Topaz is modular, standalone, free and open source (http://topaz.csail.mit.edu).