A Siamese neural network model for the prioritization of metabolic disorders by integrating real and simulated data.
KAUST DepartmentComputational Bioscience Research Center (CBRC)
Computer Science Program
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Structural and Functional Bioinformatics Group
KAUST Grant NumberFCC/1/1976-04
Embargo End Date2021-12-31
Permanent link to this recordhttp://hdl.handle.net/10754/666798
MetadataShow full item record
AbstractMotivationUntargeted metabolomic approaches hold a great promise as a diagnostic tool for inborn errors of metabolisms (IEMs) in the near future. However, the complexity of the involved data makes its application difficult and time consuming. Computational approaches, such as metabolic network simulations and machine learning, could significantly help to exploit metabolomic data to aid the diagnostic process. While the former suffers from limited predictive accuracy, the latter is normally able to generalize only to IEMs for which sufficient data are available. Here, we propose a hybrid approach that exploits the best of both worlds by building a mapping between simulated and real metabolic data through a novel method based on Siamese neural networks (SNN).ResultsThe proposed SNN model is able to perform disease prioritization for the metabolic profiles of IEM patients even for diseases that it was not trained to identify. To the best of our knowledge, this has not been attempted before. The developed model is able to significantly outperform a baseline model that relies on metabolic simulations only. The prioritization performances demonstrate the feasibility of the method, suggesting that the integration of metabolic models and data could significantly aid the IEM diagnosis process in the near future.Availability and implementationMetabolic datasets used in this study are publicly available from the cited sources. The original data produced in this study, including the trained models and the simulated metabolic profiles, are also publicly available (Messa et al., 2020).
CitationMessa, G. M., Napolitano, F., Elsea, S. H., di Bernardo, D., & Gao, X. (2020). A Siamese neural network model for the prioritization of metabolic disorders by integrating real and simulated data. Bioinformatics, 36(Supplement_2), i787–i794. doi:10.1093/bioinformatics/btaa841
SponsorsThe research reported in this publication was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) [FCC/1/1976-04, FCC/1/1976-06, FCC/1/1976-17, FCC/1/1976-18, FCC/1/1976-23, FCC/1/1976-25, FCC/1/1976-26, URF/1/3450-01, URF/1/4098-01-01 and REI/1/0018-01-01].
PublisherOxford University Press (OUP)
JournalBioinformatics (Oxford, England)
- Translational Metabolomics of Head Injury: Exploring Dysfunctional Cerebral Metabolism with Ex Vivo NMR Spectroscopy-Based Metabolite Quantification
- Authors: Wolahan SM, Hirt D, Glenn TC, Kobeissy FH
- Issue date: 2015
- The role of the Human Metabolome Database in inborn errors of metabolism.
- Authors: Mandal R, Chamot D, Wishart DS
- Issue date: 2018 May
- Next-generation metabolic screening: targeted and untargeted metabolomics for the diagnosis of inborn errors of metabolism in individual patients.
- Authors: Coene KLM, Kluijtmans LAJ, van der Heeft E, Engelke UFH, de Boer S, Hoegen B, Kwast HJT, van de Vorst M, Huigen MCDG, Keularts IMLW, Schreuder MF, van Karnebeek CDM, Wortmann SB, de Vries MC, Janssen MCH, Gilissen C, Engel J, Wevers RA
- Issue date: 2018 May
- Metabolomics: a challenge for detecting and monitoring inborn errors of metabolism.
- Authors: Mussap M, Zaffanello M, Fanos V
- Issue date: 2018 Sep
- Untargeted Metabolomics for Metabolic Diagnostic Screening with Automated Data Interpretation Using a Knowledge-Based Algorithm.
- Authors: Haijes HA, van der Ham M, Prinsen HCMT, Broeks MH, van Hasselt PM, de Sain-van der Velden MGM, Verhoeven-Duif NM, Jans JJM
- Issue date: 2020 Feb 1