Unknown Metabolite Identification Using Machine Learning Collision Cross-Section Prediction and Tandem Mass Spectrometry.
Unknown Metabolite Identification Using Machine Learning Collision Cross-Section Prediction and Tandem Mass Spectrometry.
复制标题
DOI：
10.1021/acs.analchem.2c03749
复制
发表时间：
2023-01-17
影响因子：
7.4
通讯作者：
Fernández FM
中科院分区：
文献类型：
--
作者：
Asef CK;Rainey MA;Garcia BM;Gouveia GJ;Shaver AO;Leach FE 3rd;Morse AM;Edison AS;McIntyre LM;Fernández FM
离子迁移率（IM）光谱法为质谱法（MS）提供了半正交数据，显示出在复杂的非靶向代谢组学数据集中识别未知代谢物的前景。虽然目前的文献已经展示了IM-MS用于在接近理想的情况下识别未知物，但在涉及具有困难基质的高度复杂样品的代谢组学研究中评估这种方法的性能的工作较少。在这里，我们提出了一个工作流程，将从头分子式注释和MS/MS结构阐明使用SIRIUS 4与实验IM碰撞截面（CCS）测量和机器学习CCS预测，以确定秀丽隐杆线虫突变株中的差异未知代谢物。对于其中许多离子特征，该工作流程能够成功过滤通过计算机模拟MS/MS预测生成的候选结构，尽管在某些情况下，注释受到仪器性能和数据分析方面的重大障碍的挑战。虽然对于37%的差异特征，我们能够成功收集MS/MS和CCS数据，但由于机器学习训练集匹配不良，实验和预测CCS值的准确性有限，以及缺乏MS/MS数据产生的候选结构，因此使用CCS过滤减少了可能的候选结构数量，这些特征中只有不到一半受益。当使用± 3%的CCS误差截止值时，平均可以成功过滤28%的候选结构。在此，我们确定并描述了与使用IM-MS识别非靶向代谢组学中的未知物相关的瓶颈和限制，以关注并提供对需要进一步改进的领域的见解。
Ion mobility (IM) spectrometry provides semiorthogonal data to mass spectrometry (MS), showing promise for identifying unknown metabolites in complex non-targeted metabolomics data sets. While current literature has showcased IM–MS for identifying unknowns under near ideal circumstances, less work has been conducted to evaluate the performance of this approach in metabolomics studies involving highly complex samples with difficult matrices. Here, we present a workflow incorporating de novo molecular formula annotation and MS/MS structure elucidation using SIRIUS 4 with experimental IM collision cross-section (CCS) measurements and machine learning CCS predictions to identify differential unknown metabolites in mutant strains of Caenorhabditis elegans. For many of those ion features, this workflow enabled the successful filtering of candidate structures generated by in silico MS/MS predictions, though in some cases, annotations were challenged by significant hurdles in instrumentation performance and data analysis. While for 37% of differential features we were able to successfully collect both MS/MS and CCS data, fewer than half of these features benefited from a reduction in the number of possible candidate structures using CCS filtering due to poor matching of the machine learning training sets, limited accuracy of experimental and predicted CCS values, and lack of candidate structures resulting from the MS/MS data. When using a CCS error cutoff of ±3%, on average, 28% of candidate structures could be successfully filtered. Herein, we identify and describe the bottlenecks and limitations associated with the identification of unknowns in non-targeted metabolomics using IM–MS to focus and provide insights into areas requiring further improvement.
登录
查看更多内容
影响因子：
7.4
作者：
Rainey, Markace A.;Watson, Chandler A.;Asef, Carter K.;Foster, Makayla R.;Baker, Erin S.;Fernandez, Facundo M.
通讯作者：
Fernandez, Facundo M.
影响因子：
7.4
作者：
Hines KM;Ross DH;Davidson KL;Bush MF;Xu L
通讯作者：
Xu L
影响因子：
7.4
作者：
Paglia, Giuseppe;Williams, Jonathan P.;Menikarachchi, Lochana;Thompson, J. Will;Tyldesley-Worster, Richard;Halldorsson, Skarphedinn;Rolfsson, Ottar;Moseley, Arthur;Grant, David;Langridge, James;Palsson, Bernhard O.;Astarita, Giuseppe
通讯作者：
Astarita, Giuseppe
影响因子：
7.4
作者：
Richardson, K.;Langridge, D.;Ruotolo, B. T.
通讯作者：
Ruotolo, B. T.
影响因子：
7.4
作者：
Li A;Conant CR;Zheng X;Bloodsworth KJ;Orton DJ;Garimella SVB;Attah IK;Nagy G;Smith RD;Ibrahim YM
通讯作者：
Ibrahim YM