美国普渡大学Daisuke Kihara研究小组开发出新技术，使用扩散模型对冷冻电镜图进行大分子结构建模。该研究于2024年10月21日在线发表于国际一流学术期刊《自然—方法学》。

研究人员介绍了DiffModeler，这是一种用于建模大型蛋白质复合物结构的全自动方法。DiffModeler采用扩散模型进行主链追踪，并整合AlphaFold2预测的单链结构进行结构拟合。

DiffModeler在两组0–5 Å分辨率的冷冻电镜图谱中显示出平均模板建模评分为0.88和0.91，而在5–10 Å的中等分辨率图谱中为0.92，显著优于现有方法。在低分辨率（10–20 Å）下的进一步基准测试证实了其多功能性，展示了合理的性能。

据了解，冷冻电镜（cryo-EM）现已广泛用于确定多链蛋白复合物。然而，建模大型复合结构（例如，具有十条以上链的结构）具有挑战性，特别是在图谱分辨率降低时。

附：英文原文

Title: DiffModeler: large macromolecular structure modeling for cryo-EM maps using a diffusion model

Author: Wang, Xiao, Zhu, Han, Terashi, Genki, Taluja, Manav, Kihara, Daisuke

Issue&Volume: 2024-10-21

Abstract: Cryogenic electron microscopy (cryo-EM) has now been widely used for determining multichain protein complexes. However, modeling a large complex structure, such as those with more than ten chains, is challenging, particularly when the map resolution decreases. Here we present DiffModeler, a fully automated method for modeling large protein complex structures. DiffModeler employs a diffusion model for backbone tracing and integrates AlphaFold2-predicted single-chain structures for structure fitting. DiffModeler showed an average template modeling score of 0.88 and 0.91 for two datasets of cryo-EM maps of 0–5 resolution and 0.92 for intermediate resolution maps (5–10), substantially outperforming existing methodologies. Further benchmarking at low resolutions (10–20) confirms its versatility, demonstrating plausible performance.

DOI: 10.1038/s41592-024-02479-0

Source: https://www.nature.com/articles/s41592-024-02479-0