Xu Da, Ando Nozomi
Department of Chemistry and Chemical Biology, Cornell University, Ithaca, NY 14850, USA.
bioRxiv. 2024 Feb 27:2023.12.08.570849. doi: 10.1101/2023.12.08.570849.
Efficient and high-accuracy filtering of cryo-electron microscopy (cryo-EM) micrographs is an emerging challenge with the growing speed of data collection and sizes of datasets. Convolutional neural networks (CNNs) are machine learning models that have been proven successful in many computer vision tasks, and have been previously applied to cryo-EM micrograph filtering. In this work, we demonstrate that two strategies, fine-tuning models from pretrained weights and including the power spectrum of micrographs as input, can greatly improve the attainable prediction accuracy of CNN models. The resulting software package, Miffi, is open-source and freely available for public use (https://github.com/ando-lab/miffi).
随着低温电子显微镜（cryo-EM）显微照片数据收集速度的加快和数据集规模的增大，高效且高精度地过滤这些显微照片成为了一项新出现的挑战。卷积神经网络（CNNs）是已在许多计算机视觉任务中被证明成功的机器学习模型，并且此前已应用于低温电子显微镜显微照片过滤。在这项工作中，我们证明了两种策略，即从预训练权重微调模型以及将显微照片的功率谱作为输入，可以极大地提高卷积神经网络模型可达到的预测精度。由此产生的软件包Miffi是开源的，可供公众免费使用（https://github.com/ando-lab/miffi）。
