苏黎世联邦理工学院Nicola Zamboni小组开发出MSNovelist，可从质谱数据中从头产生新的结构。这一研究成果于2022年5月30日发表在国际顶尖学术期刊《自然—方法学》上。

研究人员提出了MSNovelist，它将指纹预测与编码器-解码器神经网络相结合，仅从串联质谱（MS²）谱图中从头产生新的结构。在对来自Global Natural Product Social Molecular Networking网站的3,863个MS²谱图的评估中，MSNovelist在第一等级中预测了25%的结构是正确的，总体上检索了45%的结构，再现了61%的正确数据库注释，而在训练阶段从未见过该结构。同样，对于CASMI 2016挑战，MSNovelist正确预测了26%的结构，检索了57%的结构，恢复了64%的正确数据库注释。

最后，研究人员演示了MSNovelist在苔藓植物MS²数据集中的应用，在该数据集中，新的结构预测大大超过了七个谱图的最佳数据库候选。MSNovelist非常适合在分析物类别和新化合物代表性差的情况下补充基于库的注释。

据了解，目前的小分子结构阐释方法依赖于寻找与已知化合物谱图的相似性，但不能预测未知化合物类别的从头结构。

附：英文原文

Title: MSNovelist: de novo structure generation from mass spectra

Author: Stravs, Michael A., Dhrkop, Kai, Bcker, Sebastian, Zamboni, Nicola

Issue&Volume: 2022-05-30

Abstract: Current methods for structure elucidation of small molecules rely on finding similarity with spectra of known compounds, but do not predict structures de novo for unknown compound classes. We present MSNovelist, which combines fingerprint prediction with an encoder–decoder neural network to generate structures de novo solely from tandem mass spectrometry (MS2) spectra. In an evaluation with 3,863 MS2 spectra from the Global Natural Product Social Molecular Networking site, MSNovelist predicted 25% of structures correctly on first rank, retrieved 45% of structures overall and reproduced 61% of correct database annotations, without having ever seen the structure in the training phase. Similarly, for the CASMI 2016 challenge, MSNovelist correctly predicted 26% and retrieved 57% of structures, recovering 64% of correct database annotations. Finally, we illustrate the application of MSNovelist in a bryophyte MS2 dataset, in which de novo structure prediction substantially outscored the best database candidate for seven spectra. MSNovelist is ideally suited to complement library-based annotation in the case of poorly represented analyte classes and novel compounds.

DOI: 10.1038/s41592-022-01486-3

Source: https://www.nature.com/articles/s41592-022-01486-3