Zhang Chenwei, Condon Anne, Dao Duc Khanh
Department of Computer Science, University of British Columbia, Vancouver, BC V6T 1Z4, Canada.
Department of Mathematics, University of British Columbia, Vancouver, BC V6T 1Z2, Canada.
Bioinform Adv. 2025 Aug 4;5(1):vbaf179. doi: 10.1093/bioadv/vbaf179. eCollection 2025.
Generating synthetic cryogenic electron microscopy 3D density maps from molecular structures has potential important applications in structural biology. Yet existing simulation-based methods cannot mimic all the complex features present in experimental maps, such as secondary structure elements. As an alternative, we propose
is a novel data-driven method that employs a generative adversarial network to produce improved experimental-like density maps from molecular structures. More specifically, uses a nested U-Net architecture as the generator, with an additional L1 loss term and further processing of raw training experimental maps to enhance learning efficiency. While can promptly generate maps after training, we demonstrate that it outperforms existing simulation-based methods for a wide array of tested maps and across various evaluation metrics.
The is publicly accessible via https://github.com/chenwei-zhang/struc2mapGAN.
从分子结构生成合成低温电子显微镜3D密度图在结构生物学中具有潜在的重要应用。然而，现有的基于模拟的方法无法模拟实验图中存在的所有复杂特征，例如二级结构元件。作为一种替代方法，我们提出
是一种新颖的数据驱动方法，它采用生成对抗网络从分子结构生成改进的类似实验的密度图。更具体地说，使用嵌套U-Net架构作为生成器，带有额外的L1损失项，并对原始训练实验图进行进一步处理以提高学习效率。虽然在训练后可以迅速生成图，但我们证明，在各种测试图和不同评估指标上，它优于现有的基于模拟的方法。
