Deep Learning for MS2 Feature Detection in Liquid Chromatography Mass Spectrometry
DOI:
https://doi.org/10.47611/jsrhs.v11i3.2964Keywords:
Deep Learning, Feature detection, liquid-chromatography mass spectrometryAbstract
Accuracy of peptide identification is crucial for LC-MS analysis to reveal information regarding many different aspects of proteins that aid in the discovery of biomarkers and profiling of complex proteomes. Preprocessing steps such as feature detection are crucial yet challenging; current feature detection tools are not robust enough to detect low-abundance, low-peak fragments of peptides found in MS2 data from tandem mass spectrometry. In this study, we developed a deep learning-based model with an innovative sliding window process that enables high-resolution processing of quantitative MS/MS data to conduct accurate feature detection on MS2 data. Experimental results show that our model is able to produce more accurate values and identifications than existing feature detection tools. Therefore, we believe that our model can realize the full potential of neural networks in the field of bioinformatics and yields long-term benefits in the advancement of proteomic inquiry.
Downloads
References or Bibliography
Ren, Shaoqing, et al. “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6,2016, pp. 1137-1149, doi:10.1109/TPAMI.2016.2577031
Zohora, Fatema Tuz, et al. “DeepIso: A Deep Learning model for Peptide Feature Detection from LC-MS Map.” Scientific Reports, vol. 9, no. 17168, 2019. https://doi.org/10.1038/s41598-019-52954-4.
Sellers, K. & Miecznikowski, J. “Feature Detection Techniques for Preprocessing Proteomic Data.” International Journal of Biomedical Imaging, vol. 2010, 2010, 896718. doi: 10.1155/2010/896718.
Ma, Chunwei, et al. “Improved Peptide Retention Time Prediction in Liquid Chromatography through Deep Learning.” Analytical Chemistry, vol. 90, no. 18, 2018, pp. 10881-10888, https://doi.org/10.1021/acs.analchem.8b02386.
Nicolescu, Teodor Octavian. “Interpretation of Mass Spectra.” Mass Spectrometry, edited by Mahmood Aliofkhazraei, IntechOpen, 2017. doi: 10.5772/intechopen.68595.
Cox, J & Mann, M. “MaxQuant enables high peptide identification rates, individualized p.p.b.-range mass accuracies and proteome-wide quantification.” Nature Biotechnology, vol. 26, 2008, pp. 1367-1372. https://doi.org/10.1038/nbt.1511.
Teleman, John, et al. “Dinosaur: A Refined Open-Source Peptide MS Feature Detector.” Journal of Proteome Research, vol. 15, no. 7, 2016, pp. 2143-2151. https://doi.org/10.1021/acs.jproteome.6b00016.
Cappadona, S., Baker, P. R., Cutillas, P. R., Heck, A. J. & van Breukelen, B. “Current challenges in software solutions for mass spectrometry-based quantitative proteomics.” Amino acids, vol. 43, 2012, pp. 1087–1108. https://doi.org/10.1007/s00726-012-1289-8
Savojardo, Castrense, et al. “DeepSig: deep learning improves signal peptide detection in proteins.” Bioinformatics, vol. 34, no. 10, 2018, pp. 1690-1696. https://doi.org/10.1093/bioinformatics/btx818.
Tran, Ngoc Hieu, et al. “De novo peptide sequencing by deep learning.” Proceedings of the National Academy of Sciences, vol. 114, no. 31, 2017, pp. 8247-8252. https://doi.org/10.1073/pnas.1705691114.
Yang, X., Mochanov, P., Kautz, J. “Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification.” Proceedings of the 24th ACM International Conference on Multimedia, 2016, pp. 978-987, doi: 10.1145/2964284.2964297.
Rost, H., Sachsenberg, T., Aiche, S. et al. “OpenMS: a flexible open-source software platform for mass spectrometry data analysis.” Nature Methods, vol 13, 2016, pp. 741-748. https://doi.org/10.1038/nmeth.3959.
Hoffman, Melissa A et al. “Comparison of Quantitative Mass Spectrometry Platforms for Monitoring Kinase ATP Probe Uptake in Lung Cancer.” Journal of Proteome Research, vol. 17, no. 1, 2018, pp. 63-75. doi:10.1021/acs.jproteome.7b00329.
McLafferty, F. W. “Tandem mass spectrometry (MS/MS): a promising new analytical technique for specific component determination in complex mixtures.” Accounts of Chemical Research, vol. 13, no. 2, 1980, pp. 33-39. Doi: 10.1021/ar50146a001.
Kessner, D., Chambers, M., Burke, R., Agus, D. & Mallick, P. “ProteoWizard: open source software for rapid proteomics tool development.” Bioinformatics, vol. 24, no. 21, 2008, pp. 2534-2536. https://doi.org/10.1093/bioinformatics/btn323
Adusumilli, R. & Mallick, P. “Data Conversion with ProteoWizard msConvert.” Proteomics, Methods in Molecular Biology, vol. 1550, 2017. https://doi.org/10.1007/978-1-4939-6747-6_23.
Stewart, P. A., Welsh, E. A., Slebos, R. J. C. et al. “Proteogenomic landscape of squamous cell lung cancer.” Nature Communications, vol. 10, no. 3578, 2019. https://doi.org/10.1038/s41467-019-11452-x.
Stewart, P. et al. “Relative protein quantification and accessible biology in lung tumor proteomes from four LC-MS/MS discovery platforms.” Proteomics, vol. 17, no. 6, 2017. Doi: 10.1002/pmic.201600300.
Hu, A. et al. “Technical Advances in proteomics: new developments in data-independent acquisition.” F1000Research, vol. 5, 2016. doi: 10.12688/f1000research.7042.1.
Tada, I. et al. “Correlation-Based Deconvolution (CorrDec) To Generate High-Quality MS2 Spectra from Data-Independent Acquisition in Multisample Studies.” Analytical Chemistry, vol. 92, no. 16, 2020, pp. 11310-11317. Doi: 10.1021/acs.analchem.0c01980.
Virreira Winter, S., Meier, F., Wichmann, C. et al. “EASI-tag enables accurate multiplexed and interference-free MS2-based proteome quantification.” Nature Methods, vol. 15, 2018, pp. 527–530. https://doi.org/10.1038/s41592-018-0037-8.
Weissert, H. & Choudhary, J. S. “Targeted Feature Detection for Data-Dependent Shotgun Proteomics.” Journal of Proteome Research, vol. 16, no. 8, 2017, pp. 2964-2974. doi: 10.1021/acs.jproteome.7b00248.
Wang, X., Shen, S., Rasam, S. S. & Qu, J. “MS1 ion current-based quantitative proteomics: A promising solution for reliable analysis of large biological cohorts.” Mass Spectrometry Reviews, vol. 38, no. 6, 2019, pp. 461-482. doi: 10.1002/mas.21595.
Bodla, N., Singh, B., Chellappa, R. & Daivs, L. “Soft-NMS – Improving Object Detection with One Line of Code.” IEEE International Conference on Computer Vision, 2017, pp. 5562-5570. https://doi.org/10.48550/arXiv.1704.04503.
Zhang, G. et al. “Overview of peptide and protein analysis by mass spectrometry.” Current protocols in protein science, vol. 16, no. 1, 2010. doi:10.1002/0471140864.ps1601s62.
Published
How to Cite
Issue
Section
Copyright (c) 2022 Jonathan He, Olivia Liu; Xuan Guo
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright holder(s) granted JSR a perpetual, non-exclusive license to distriute & display this article.
