Deep Learning Enable Untargeted Metabolite Extraction from High Throughput Coverage Data-Independent Acquisition

The sequential window acquisition of all theoretical spectra (SWATH) technique is a specific variant of data-independent acquisition (DIA), which is supposed to increase the metabolite coverage and the reproducibility compared to data-dependent acquisition (DDA). However, SWATH technique lost the direct link between the precursor ion and the fragments. Here, we propose a deep-learning-based approach (DeepSWATH) to reconstruct the association between the MS/MS spectra and their precursors. Comparing with MS-DIAL, the proposed method can extract more accurate spectra with less noise to improve the identification accuracy of metabolites. Besides, DeepSWATH can also handle severe coelution conditions.

[1]  Christoph B. Messner,et al.  DIA-NN: Neural networks and interference correction enable deep proteome coverage in high throughput , 2019, Nature Methods.

[2]  Juho Rousu,et al.  SIRIUS 4: a rapid tool for turning tandem mass spectra into metabolite structure information , 2019, Nature Methods.

[3]  Samuel H Payne,et al.  PECAN: Library Free Peptide Detection for Data-Independent Acquisition Tandem Mass Spectrometry Data , 2017, Nature Methods.

[4]  Ben C. Collins,et al.  OpenSWATH enables automated, targeted analysis of data-independent acquisition MS data , 2014, Nature Biotechnology.

[5]  Romà Tauler,et al.  A graphical user-friendly interface for MCR-ALS: a new tool for multivariate curve resolution in MATLAB , 2005 .

[6]  Marc Litaudon,et al.  MetGem Software for the Generation of Molecular Networks Based on the t-SNE Algorithm. , 2018, Analytical chemistry.

[7]  Michael J MacCoss,et al.  Specter: linear deconvolution for targeted analysis of data-independent acquisition mass spectrometry proteomics , 2018, Nature Methods.

[8]  Zhimin Zhang,et al.  KPIC2: An Effective Framework for Mass Spectrometry-Based Metabolomics Using Pure Ion Chromatograms. , 2017, Analytical chemistry.

[9]  R. Abagyan,et al.  XCMS: processing mass spectrometry data for metabolite profiling using nonlinear peak alignment, matching, and identification. , 2006, Analytical chemistry.

[10]  Yuanyue Li,et al.  Group-DIA: analyzing multiple data-independent acquisition mass spectrometry data files , 2015, Nature Methods.

[11]  K. Reinert,et al.  OpenMS: a flexible open-source software platform for mass spectrometry data analysis , 2016, Nature Methods.

[12]  Masanori Arita,et al.  MS-DIAL: Data Independent MS/MS Deconvolution for Comprehensive Metabolome Analysis , 2015, Nature Methods.

[13]  Zhuozhong Wang,et al.  DecoMetDIA: Deconvolution of Multiplexed MS/MS Spectra for Metabolite Identification in SWATH-MS based Untargeted Metabolomics. , 2019, Analytical chemistry.

[14]  Yuping Cai,et al.  MetDIA: Targeted Metabolite Extraction of Multiplexed MS/MS Spectra Generated by Data-Independent Acquisition. , 2016, Analytical chemistry.

[15]  Xiaohui Liu,et al.  In silico spectral libraries by deep learning facilitate data-independent acquisition proteomics , 2020, Nature Communications.

[16]  Chih-Chiang Tsou,et al.  DIA-Umpire: comprehensive computational framework for data-independent acquisition proteomics , 2015, Nature Methods.

[17]  S. Böcker,et al.  Searching molecular structure databases with tandem mass spectra using CSI:FingerID , 2015, Proceedings of the National Academy of Sciences of the United States of America.

[18]  Hyungwon Choi,et al.  Customized Consensus Spectral Library Building for Untargeted Quantitative Metabolomics Analysis with Data Independent Acquisition Mass Spectrometry and MetaboDIA Workflow. , 2017, Analytical chemistry.

[19]  Mathias Wilhelm,et al.  Prosit: proteome-wide prediction of peptide tandem mass spectra by deep learning , 2019, Nature Methods.

[20]  Marc Litaudon,et al.  MZmine 2 Data-Preprocessing To Enhance Molecular Networking Reliability. , 2017, Analytical chemistry.

[21]  Jürgen Cox,et al.  High-quality MS/MS spectrum prediction for data-dependent and data-independent acquisition data analysis , 2019, Nature Methods.