Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/
[en] Abstract Structural annotation of small molecules in biological samples remains a key bottleneck in untargeted metabolomics, despite rapid progress in predictive methods and tools during the past decade. Liquid chromatography–tandem mass spectrometry, one of the most widely used analysis platforms, can detect thousands of molecules in a sample, the vast majority of which remain unidentified even with best-of-class methods. Here we present LC-MS2Struct, a machine learning framework for structural annotation of small-molecule data arising from liquid chromatography–tandem mass spectrometry (LC-MS2) measurements. LC-MS2Struct jointly predicts the annotations for a set of mass spectrometry features in a sample, using a novel structured prediction model trained to optimally combine the output of state-of-the-art MS2 scorers and observed retention orders. We evaluate our method on a dataset covering all publicly available reversed-phase LC-MS2 data in the MassBank reference database, including 4,327 molecules measured using 18 different LC conditions from 16 contributors, greatly expanding the chemical analytical space covered in previous multi-MSscorer evaluations. LC-MS2Struct obtains significantly higher annotation accuracy than earlier methods and improves the annotation accuracy of state-of-the-art MS2 scorers by up to 106\%. The use of stereochemistry-aware molecular fingerprints improves prediction performance, which highlights limitations in existing approaches and has strong implications for future computational LC-MS2 developments.
Disciplines :
Life sciences: Multidisciplinary, general & others
Author, co-author :
Bach, Eric
SCHYMANSKI, Emma ; University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
Rousu, Juho
External co-authors :
yes
Language :
English
Title :
Joint structural annotation of small molecules using liquid chromatography retention order and tandem mass spectrometry data
da Silva, R. R., Dorrestein, P. C. & Quinn, R. A. Illuminating the dark matter in metabolomics. Proc. Natl Acad. Sci. USA 112, 12549–12550 (2015).
Aksenov, A. A., da Silva, R., Knight, R., Lopes, N. P. & Dorrestein, P. C. Global chemical analysis of biology by mass spectrometry. Nat. Rev. Chem. 1, 0054 (2017).
Blaženović, I. et al. Structure annotation of all mass spectra in untargeted metabolomics. Anal. Chem. 91, 2155–2162 (2019).
Blaženović, I., Kind, T., Ji, J. & Fiehn, O. Software tools and approaches for compound identification of LC-MS/MS data in metabolomics. Metabolites 8, 31 (2018).
Schymanski, E. L. et al. Critical assessment of small molecule identification 2016: automated methods. J. Cheminform. 9, 22 (2017).
Nguyen, D. H., Nguyen, C. H. & Mamitsuka, H. Recent advances and prospects of computational methods for metabolite identification: a review with emphasis on machine learning approaches. Brief. Bioinform. 20, 2028–2043 (2019).
Wolf, S., Schmidt, S., Müller-Hannemann, M. & Neumann, S. In silico fragmentation for computer assisted identification of metabolite mass spectra. BMC Bioinform. 11, 1–12 (2010).
Dührkop, K., Shen, H., Meusel, M., Rousu, J. & Böcker, S. Searching molecular structure databases with tandem mass spectra using CSI:FingerID. Proc. Natl Acad. Sci. USA 112, 12580–12585 (2015).
Allen, F., Greiner, R. & Wishart, D. Competitive fragmentation modeling of ESI-MS/MS spectra for putative metabolite identification. Metabolomics 11, 98–110 (2015).
Brouard, C. et al. Fast metabolite identification with input output kernel regression. Bioinformatics 32, i28–i36 (2016).
Ruttkies, C., Schymanski, E. L., Wolf, S., Hollender, J. & Neumann, S. MetFrag relaunched: incorporating strategies beyond in silico fragmentation. J. Cheminform. 8, 3 (2016).
Brouard, C., Bach, E., Böcker, S. & Rousu, J. Magnitude-preserving ranking for structured outputs. In Proc. Ninth Asian Conference on Machine Learning, Proc. Machine Learning Research Vol. 77 (eds Zhang, M.-L. & Noh, Y.-K.) 407–422 (PMLR, 2017); http://proceedings.mlr.press/v77/brouard17a.html
Nguyen, D. H., Nguyen, C. H. & Mamitsuka, H. Simple: sparse interaction model over peaks of molecules for fast, interpretable metabolite identification from tandem mass spectra. Bioinformatics 34, i323–i332 (2018).
Li, Y., Kuhn, M., Gavin, A.-C. & Bork, P. Identification of metabolites from tandem mass spectra with a machine learning approach utilizing structural features. Bioinformatics 36, 1213–1218 (2019).
Ruttkies, C., Neumann, S. & Posch, S. Improving MetFrag with statistical learning of fragment annotations. BMC Bioinform. 20, 376 (2019).
Nguyen, D. H., Nguyen, C. H. & Mamitsuka, H. ADAPTIVE: learning data-dependent, concIse molecular vectors for fast, accurate metabolite identification from tandem mass spectra. Bioinformatics 35, i164–i172 (2019).
Dührkop, K. et al. SIRIUS 4: a rapid tool for turning tandem mass spectra into metabolite structure information. Nat. Methods 10.1038/s41592-019-0344-8 (2019).
Wang, F. et al. CFM-ID 4.0: nore accurate ESI-MS/MS spectral prediction and compound identification. Anal. Chem. 10.1021/acs.analchem.1c01465 (2021).
Wishart, D. S. et al. HMDB 4.0: the Human Metabolome Database for 2018. Nucleic Acids Res. 46, D608–D617 (2017).
Kim, S. et al. PubChem in 2021: new data content and improved web interfaces. Nucleic Acids Res. 49, D1388–D1395 (2020).
Stanstrup, J., Neumann, S. & Vrhovšek, U. PredRet: prediction of retention time by direct mapping between multiple chromatographic systems. Anal. Chem. 87, 9421–9428 (2015).
Low, D. Y. et al. Data sharing in predret for accurate prediction of retention time: application to plant food bioactive compounds. Food Chem. 357, 129757 (2021).
Fanali, S., Haddad, P., Poole, C. & Lloyd, D. Liquid Chromatography: Fundamentals and Instrumentation (Handbooks in Separation Science, Elsevier Science, 2013).
Witting, M. & Böcker, S. Current status of retention time prediction in metabolite identification. J. Sep. Sci. 43, 1746–1754 (2020).
Bouwmeester, R., Martens, L. & Degroeve, S. Comprehensive and empirical evaluation of machine learning algorithms for small molecule LC retention time prediction. Anal. Chem. 91, 3694–3703 (2019).
Aicheler, F. et al. Retention time prediction improves identification in nontargeted lipidomics approaches. Anal. Chem. 87, 7698–7704 (2015).
Samaraweera, M. A., Hall, L. M., Hill, D. W. & Grant, D. F. Evaluation of an artificial neural network retention index model for chemical structure identification in nontargeted metabolomics. Anal. Chem. 90, 12752–12760 (2018).
Bonini, P., Kind, T., Tsugawa, H., Barupal, D. K. & Fiehn, O. Retip: retention time prediction for compound annotation in untargeted metabolomics. Anal. Chem. https://doi.org/10.1021/acs.analchem.9b05765 (2020).
Yang, Q., Ji, H., Lu, H. & Zhang, Z. Prediction of liquid chromatographic retention time with graph neural networks to assist in small molecule identification. Anal. Chem. https://doi.org/10.1021/acs.analchem.0c04071 (2021).
Bouwmeester, R., Martens, L. & Degroeve, S. Generalized calibration across liquid chromatography setups for generic prediction of small-molecule retention times. Anal. Chem. 92, 6571–6578 (2020).
Bach, E., Szedmak, S., Brouard, C., Böcker, S. & Rousu, J. Liquid-chromatography retention order prediction for metabolite identification. Bioinformatics 34, i875–i883 (2018).
Liu, J. J., Alipuly, A., Baczek, T., Wong, M. W. & Žuvela, P. Quantitative structure–retention relationships with non-linear programming for prediction of chromatographic elution order. Int. J. Mol. Sci. 20, 3443 (2019).
Žuvela, P., Liu, J. J., Wong, M. W. & Baczek, T. Prediction of chromatographic elution order of analytical mixtures based on quantitative structure–retention relationships and multi-objective optimization. Molecules 25, 3085 (2020).
Bach, E., Rogers, S., Williamson, J. & Rousu, J. Probabilistic framework for integration of mass spectrum and retention time information in small molecule identification. Bioinformatics 37, 1724–1731 (2021).
Tsochantaridis, I., Joachims, T., Hofmann, T. & Altun, Y. Large margin methods for structured and interdependent output variables. J. Mach. Learn. Res. 6, 1453–1484 (2005).
Taskar, B., Guestrin, C. & Koller, D. Max-margin Markov networks. Adv. Neural Inf. Process. Syst. 16, 25–32 (MIT, 2004).
Horai, H. et al. MassBank: a public repository for sharing mass spectral data for life sciences. J. Mass Spectrom. 45, 703–714 (2010).
Rogers, D. & Hahn, M. Extended-connectivity fingerprints. J. Chem. Inf. Model. 50, 742–754 (2010).
Pence, H. & Williams, A. ChemSpider: an online chemical information resource. J. Chem. Educ. 87, 1123–1124 (2010).
Schymanski, E. L. et al. Empowering large chemical knowledge bases for exposomics: PubChemLite meets MetFrag. J. Cheminform. 10.21203/rs.3.rs-107432/v1 (2021).
Schüller, A., Schneider, G. & Byvatov, E. SmiLib: rapid assembly of combinatorial libraries in smiles notation. QSAR Comb. Sci. 22, 719–721 (2003).
Schüller, A., Hähnke, V. & Schneider, G. SmiLib v2.0: a Java-based tool for rapid combinatorial library enumeration. QSAR Comb. Sci. 26, 407–410 (2007).
Wainwright, M., Jaakkola, T. & Willsky, A. Tree consistency and bounds on the performance of the max-product algorithm and its generalizations. Stat. Comput. 14, 143–166 (2004).
MacKay, D. J. Information Theory, Inference and Learning Algorithms (Cambridge Univ. Press, 2005).
Pletscher, P., Ong, C. S. & Buhmann, J. Spanning tree approximations for conditional random fields. In Proc. Twelth International Conference on Artificial Intelligence and Statistics, Proc. Machine Learning Research Vol. 5 (eds van Dyk, D. & Welling, M.) 408–415 (PMLR, 2009); http://proceedings.mlr.press/v5/pletscher09a.html
Su, H. & Rousu, J. Multilabel classification through random graph ensembles. Mach. Learn. 99, 231–256 (2015).
Rousu, J., Saunders, C., Szedmak, S. & Shawe-Taylor, J. Kernel-based learning of hierarchical multilabel classification models. J. Mach. Learn. Res. 7, 1601–1626 (2006).
Elisseeff, A. & Weston, J. A kernel method for multi-labelled classification. Adv. Neural Inf. Process. Syst. 14, 681–687 (2002).
Joachims, T. Optimizing search engines using clickthrough data. In Proc. Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 133–142 (ACM, 2002); https://doi.org/10.1145/775047.775067
Cheng, T. et al. Computation of octanol-water partition coefficients by guiding an additive model with knowledge. J. Chem. Inf. Model. 47, 2140–2148 (2007).
Feunang, Y. D. et al. ClassyFire: automated chemical classification with a comprehensive, computable taxonomy. J. Cheminform. 8, 61 (2016).
Bach, E. massbank2db: build a machine learning ready SQLite database from MassBank. GitHub https://github.com/bachi55/massbank2db (2022).
Gärtner, T. & Vembu, S. On structured output training: hard cases and an efficient alternative. Mach. Learn. 76, 227–242 (2009).
Xue, Y., Li, Z., Ermon, S., Gomes, C. P. & Selman, B. Solving marginal map problems with NP oracles and parity constraints. Adv. Neural Inf. Process. Syst. 29, 1135–1143 (2016).
Lacoste-Julien, S., Jaggi, M., Schmidt, M. & Pletscher, P. Block-coordinate Frank–Wolfe optimization for structural svms. In International Conference on Machine Learning 53–61 (PMLR, 2013).
Frank, M. & Wolfe, P. An algorithm for quadratic programming. Nav. Res. Logist. Q. 3, 95–110 (1956).
Ralaivola, L., Swamidass, S. J., Saigo, H. & Baldi, P. Graph kernels for chemical informatics. Neural Netw. 18, 1093–1110 (2005).
Heller, S. R., McNaught, A., Pletnev, I., Stein, S. & Tchekhovskoi, D. InChI, the IUPAC international chemical identifier. J. Cheminform. 7, 23 (2015).
Weininger, D. SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. J. Chem. Inf. Comput. Sci. 28, 31–36 (1988).
Benton, H. P., Wong, D. M., Trauger, S. A. & Siuzdak, G. XCMS2: processing tandem mass spectrometry data for metabolite identification and structural characterization. Anal. Chem. 80, 6382–6389 (2008).
Watrous, J. et al. Mass spectral molecular networking of living microbial colonies. Proc. Natl Acad. Sci. USA 109, E1743–E1752 (2012).
Huber, F. et al. matchms—processing and similarity evaluation of mass spectrometry data. J. Open Source Softw. 5, 2411 (2020).
Dolan, J. W. Column Dead Time as a Diagnostic Tool. LCGC North America 32, 24–29 (2014).
Järvelin, K. & Kekäläinen, J. Cumulated gain-based evaluation of ir techniques. ACM Trans. Inf. Syst. 20, 422–446 (2002).
Pedregosa, F. et al. scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
Drucker, H., Burges, C. J., Kaufman, L., Smola, A. J. & Vapnik, V. Support vector regression machines. Adv. Neural Inf. Process. Syst. 9, 155–161 (1997).
Bach, E. Retention order support vector machine (ROSVM) GitHub https://github.com/bachi55/rosvm (2022).
Willighagen, E. L. et al. The chemistry development kit (CDK) v2.0: atom typing, depiction, molecular formulas, and substructure searching. J. Cheminform. 9, 33 (2017).
Bach, E. msmsrt_scorer: probabilistic framework for integration of mass spectrum and retention order information. GitHub https://github.com/aalto-ics-kepaco/msms_rt_score_integration (2021).
Platt, J. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv. Large Margin Classifiers 10, 61–74 (2000).
Bach, E. Dataset: ‘Joint structural annotation of small molecules using liquid chromatography retention order and tandem mass spectrometry data’. Zenodo 10.5281/zenodo.5854661 (2022).
Bach, E. Result files (ALLDATA): ‘Joint structural annotation of small molecules using liquid chromatography retention order and tandem mass spectrometry data with LC-MS2Struct’. Zenodo https://doi.org/10.5281/zenodo.6451016 (2022).
Bach, E. Result files (ONLYSTEREO): ‘Joint structural annotation of small molecules using liquid chromatography retention order and tandem mass spectrometry data’. Zenodo 10.5281/zenodo.6037629 (2022).
Bach, E. msms_rt_ssvm: implementation of the LC-MS2Struct algorithm. GitHub https://github.com/aalto-ics-kepaco/msms_rt_ssvm (2022).
Bach, E. Experiments and figure generation for the LC-MS2Struct evaluation. GitHub https://github.com/aalto-ics-kepaco/lcms2struct_exp (2022).