牛津大学Shabaz Mohammed课题组的研究显示，使用单一深度学习模型将可选择的碎片化技术集成到标准LC-MS工作流程中，增强了蛋白质组的覆盖范围。这一研究成果于2026年3月23日发表在国际顶尖学术期刊《自然—方法学》上。

在这里，课题组研究人员开发了一个集成的质谱平台，可以实现自动碰撞，电子和光子破碎技术。使用多酶深度蛋白质组学工作流程，该课题组人员生成了全面的数据集，以训练统一的Prosit深度学习模型，预测所有解离方法的光谱。这个公开可用的模型现在集成到FragPipe的MSBooster模块中，在所有片段化技术中，无论是数据依赖还是数据独立的获取，蛋白质鉴定平均提高了10%。研究组证明了替代方法，特别是电子诱导和紫外光解，可以产生更丰富，更信息的光谱，实现与CID竞争的识别效率，同时提供更好的序列覆盖。这项工作建立了一个框架，使先进的碎片技术在标准蛋白质组学管道的常规应用。

据介绍，自下而上的蛋白质组学主要依赖于碰撞诱导解离（CID）进行肽测序，该方法已经取得了显著的灵敏度和效率，现在可以进行单细胞分析。然而，CID在描述翻译后修饰和复杂的蛋白质形态方面显示出局限性。

附：英文原文

Title: Integration of alternative fragmentation techniques into standard LC-MS workflows using a single deep learning model enhances proteome coverage

Author: Levin, Nikita, Saylan, Cemil Can, Lapin, Joel, Demyanenko, Yana, Yang, Kevin L., Sidda, John, Nesvizhskii, Alexey I., Wilhelm, Mathias, Mohammed, Shabaz

Issue&Volume: 2026-03-23

Abstract: Bottom-up proteomics relies predominantly on collision-induced dissociation (CID) for peptide sequencing, which has achieved remarkable sensitivity and efficiency now enabling single-cell analysis. However, CID shows limitations in characterizing post-translational modifications and complex proteoforms. Here we have developed an integrated mass spectrometry platform enabling automated collision-, electron- and photon-based fragmentation techniques. Using multi-enzyme deep proteomics workflows, we generated comprehensive datasets to train a unified Prosit deep learning model predicting spectra across all dissociation methods. This publicly available model, now integrated into FragPipe’s MSBooster module, increased protein identifications by >10% on average for both data-dependent and data-independent acquisition across all fragmentation techniques. We demonstrate that alternative approaches, particularly electron-induced and ultraviolet photodissociation, which generate richer, more informative spectra, achieve identification efficiency competitive with CID while providing superior sequence coverage. This work establishes a framework enabling routine application of advanced fragmentation techniques in standard proteomics pipelines.

DOI: 10.1038/s41592-026-03042-9

Source: https://www.nature.com/articles/s41592-026-03042-9