{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T01:47:01Z","timestamp":1778636821760,"version":"3.51.4"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,5,28]],"date-time":"2021-05-28T00:00:00Z","timestamp":1622160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,5,28]],"date-time":"2021-05-28T00:00:00Z","timestamp":1622160000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Direct link between metabolism and cell and organism phenotype in health and disease makes metabolomics, a high throughput study of small molecular metabolites, an essential methodology for understanding and diagnosing disease development and progression. Machine learning methods have seen increasing adoptions in metabolomics thanks to their powerful prediction abilities. However, the \u201cblack-box\u201d nature of many machine learning models remains a major challenge for wide acceptance and utility as it makes the interpretation of decision process difficult. This challenge is particularly predominant in biomedical research where understanding of the underlying decision making mechanism is essential for insuring safety and gaining new knowledge.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>In this article, we proposed a novel computational framework, Systems Metabolomics using Interpretable Learning and Evolution (SMILE), for supervised metabolomics data analysis. Our methodology uses an evolutionary algorithm to learn interpretable predictive models and to identify the most influential metabolites and their interactions in association with disease. Moreover, we have developed a web application with a graphical user interface that can be used for easy analysis, interpretation and visualization of the results. Performance of the method and utilization of the web interface is shown using metabolomics data for Alzheimer\u2019s disease.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>SMILE was able to identify several influential metabolites on AD and to provide interpretable predictive models that can be further used for a better understanding of the metabolic background of AD. SMILE addresses the emerging issue of interpretability and explainability in machine learning, and contributes to more transparent and powerful applications of machine learning in bioinformatics.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12859-021-04209-1","type":"journal-article","created":{"date-parts":[[2021,5,28]],"date-time":"2021-05-28T08:05:59Z","timestamp":1622189159000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["SMILE: systems metabolomics using interpretable learning and evolution"],"prefix":"10.1186","volume":"22","author":[{"given":"Chengyuan","family":"Sha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miroslava","family":"Cuperlovic-Culf","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,5,28]]},"reference":[{"issue":"6","key":"4209_CR1","doi-asserted-by":"publisher","first-page":"243","DOI":"10.3390\/metabo10060243","volume":"10","author":"UW Liebal","year":"2020","unstructured":"Liebal UW, Phan AN, Sudhakar M, Raman K, Blank LM. Machine learning applications for mass spectrometry-based metabolomics. Metabolites. 2020;10(6):243.","journal-title":"Metabolites"},{"issue":"44","key":"4209_CR2","doi-asserted-by":"publisher","first-page":"22071","DOI":"10.1073\/pnas.1900654116","volume":"116","author":"WJ Murdoch","year":"2019","unstructured":"Murdoch WJ, Singh C, Kumbier K, Abbasi-Asl R, Yu B. Definitions, methods, and applications in interpretable machine learning. Proc Natl Acad Sci USA. 2019;116(44):22071\u201380.","journal-title":"Proc Natl Acad Sci USA"},{"key":"4209_CR3","unstructured":"Holzinger A, Biemann C, Pattichis CS, Kell DB. What do we need to build explainable AI systems for the medical domain? arXiv preprint arXiv:1712.09923 (2017)."},{"key":"4209_CR4","unstructured":"Molnar C. Interpretable machine learning: a guide for making black box models explainable. https:\/\/christophm.github.io\/interpretable-ml-book (2019)."},{"key":"4209_CR5","first-page":"14","volume":"213","author":"VR Muddapu","year":"2020","unstructured":"Muddapu VR, Dharshini SAP, Chakravarthy VS, Gromiha MM. Neurodegenerative diseases-is metabolic deficiency the root cause? Front Neurosci. 2020;213:14.","journal-title":"Front Neurosci"},{"issue":"3","key":"4209_CR6","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1080\/17460441.2020.1674808","volume":"15","author":"M Cuperlovic-Culf","year":"2020","unstructured":"Cuperlovic-Culf M, Badhwar A. Recent advances from metabolomics and lipidomics application in Alzheimer\u2019s disease inspiring drug discovery. Expert Opin Drug Discov. 2020;15(3):319\u201331.","journal-title":"Expert Opin Drug Discov"},{"issue":"3","key":"4209_CR7","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1038\/s41583-019-0132-6","volume":"20","author":"DA Butterfield","year":"2019","unstructured":"Butterfield DA, Halliwell B. Oxidative stress, dysfunctional glucose metabolism and Alzheimer\u2019s disease. Nat Rev Neurosci. 2019;20(3):148\u201360.","journal-title":"Nat Rev Neurosci"},{"issue":"12","key":"4209_CR8","doi-asserted-by":"publisher","first-page":"1887","DOI":"10.1093\/hmg\/7.12.1887","volume":"7","author":"M Artiga","year":"1998","unstructured":"Artiga M, Bullido M, Frank A, Sastre I, Recuero M, Garcia M, Lendon C, Han S, Morris J, Vazquez J, et al. Risk for Alzheimer\u2019s disease correlates with transcriptional activity of the APOE gene. Hum Mol Genet. 1998;7(12):1887\u201392.","journal-title":"Hum Mol Genet"},{"issue":"9","key":"4209_CR9","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1038\/s41582-019-0228-7","volume":"15","author":"Y Yamazaki","year":"2019","unstructured":"Yamazaki Y, Zhao N, Caulfield TR, Liu C-C, Bu G. Apolipoprotein E and Alzheimer\u2019s disease: pathobiology and targeting strategies. Nat Rev Neurol. 2019;15(9):501\u201318.","journal-title":"Nat Rev Neurol"},{"key":"4209_CR10","doi-asserted-by":"publisher","first-page":"299","DOI":"10.3389\/fnagi.2020.560865","volume":"12","author":"RJ Johnson","year":"2020","unstructured":"Johnson RJ, Gomez-Pinilla F, Nagel M, Nakagawa T, Rodriguez-Iturbe B, Sanchez-Lozada LG, Tolan DR, Lanaspa MA. Cerebral fructose metabolism as a potential mechanism driving Alzheimer\u2019s disease. Front Aging Neurosci. 2020;12:299.","journal-title":"Front Aging Neurosci"},{"key":"4209_CR11","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1016\/j.nicl.2018.07.016","volume":"20","author":"CM Weise","year":"2018","unstructured":"Weise CM, Chen K, Chen Y, Kuang X, Savage CR, Reiman EM, Initiative ADN, et al. Left lateralized cerebral glucose metabolism declines in amyloid-$$\\beta$$ positive persons with mild cognitive impairment. NeuroImage Clin. 2018;20:286\u201396.","journal-title":"NeuroImage Clin"},{"issue":"3","key":"4209_CR12","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1038\/nrneurol.2017.185","volume":"14","author":"SE Arnold","year":"2018","unstructured":"Arnold SE, Arvanitakis Z, Macauley-Rambach SL, Koenig AM, Wang H-Y, Ahima RS, Craft S, Gandy S, Buettner C, Stoeckel LE, et al. Brain insulin resistance in type 2 diabetes and Alzheimer\u2019s disease: concepts and conundrums. Nat Rev Neurol. 2018;14(3):168\u201381.","journal-title":"Nat Rev Neurol"},{"key":"4209_CR13","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.exger.2017.07.004","volume":"107","author":"E Croteau","year":"2018","unstructured":"Croteau E, Castellano C, Fortier M, Bocti C, Fulop T, Paquet N, Cunnane S. A cross-sectional comparison of brain glucose and ketone metabolism in cognitively healthy older adults, mild cognitive impairment and early Alzheimer\u2019s disease. Exp Gerontol. 2018;107:18\u201326.","journal-title":"Exp Gerontol"},{"key":"4209_CR14","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1016\/j.redox.2017.10.014","volume":"14","author":"C Cheignon","year":"2018","unstructured":"Cheignon C, Tomas M, Bonnefont-Rousselot D, Faller P, Hureau C, Collin F. Oxidative stress and the amyloid beta peptide in Alzheimer\u2019s disease. Redox Biol. 2018;14:450\u201364.","journal-title":"Redox Biol"},{"issue":"3","key":"4209_CR15","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.3233\/JAD-170543","volume":"62","author":"DA Butterfield","year":"2018","unstructured":"Butterfield DA, Boyd-Kimball D. Oxidative stress, amyloid-$$\\beta$$ peptide, and altered key molecular pathways in the pathogenesis and progression of Alzheimer\u2019s disease. J Alzheimers Dis. 2018;62(3):1345\u201367.","journal-title":"J Alzheimers Dis"},{"issue":"2","key":"4209_CR16","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1016\/j.jalz.2018.08.012","volume":"15","author":"K Nho","year":"2019","unstructured":"Nho K, Kueider-Paisley A, MahmoudianDehkordi S, Arnold M, Risacher SL, Louie G, Blach C, Baillie R, Han X, Kastenm\u00fcller G, et al. Altered bile acid profile in mild cognitive impairment and Alzheimer\u2019s disease: relationship to neuroimaging and CSF biomarkers. Alzheimer\u2019s Dementia. 2019;15(2):232\u201344.","journal-title":"Alzheimer\u2019s Dementia"},{"issue":"10","key":"4209_CR17","doi-asserted-by":"publisher","first-page":"920","DOI":"10.1212\/WNL.0000000000000755","volume":"83","author":"TJ Littlejohns","year":"2014","unstructured":"Littlejohns TJ, Henley WE, Lang IA, Annweiler C, Beauchet O, Chaves PH, Fried L, Kestenbaum BR, Kuller LH, Langa KM, et al. Vitamin D and the risk of dementia and Alzheimer\u2019s disease. Neurology. 2014;83(10):920\u20138.","journal-title":"Neurology"},{"issue":"9","key":"4209_CR18","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1016\/j.tem.2010.05.005","volume":"21","author":"S Merlo","year":"2010","unstructured":"Merlo S, Spampinato S, Canonico PL, Copani A, Sortino MA. Alzheimer\u2019s disease: brain expression of a metabolic disorder? Trends Endocrinol Metab. 2010;21(9):537\u201344.","journal-title":"Trends Endocrinol Metab"},{"issue":"5","key":"4209_CR19","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1007\/s12264-012-1272-0","volume":"28","author":"X-H Xu","year":"2012","unstructured":"Xu X-H, Huang Y, Wang G, Chen S-D. Metabolomics: a novel approach to identify potential diagnostic biomarkers and pathogenesis in Alzheimer\u2019s disease. Neurosci Bull. 2012;28(5):641\u20138.","journal-title":"Neurosci Bull"},{"issue":"3","key":"4209_CR20","doi-asserted-by":"publisher","first-page":"1005986","DOI":"10.1371\/journal.pcbi.1005986","volume":"14","author":"T Hu","year":"2018","unstructured":"Hu T, Oksanen K, Zhang W, Randell E, Furey A, Sun G, Zhai G. An evolutionary learning and network approach to identifying key metabolites for osteoarthritis. PLoS Comput Biol. 2018;14(3):1005986.","journal-title":"PLoS Comput Biol"},{"issue":"9","key":"4209_CR21","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1007\/s10072-013-1289-9","volume":"34","author":"MC Gueli","year":"2013","unstructured":"Gueli MC, Taibi G. Alzheimer\u2019s disease: amino acid levels and brain metabolic status. Neurol Sci. 2013;34(9):1575\u20139.","journal-title":"Neurol Sci"},{"issue":"3","key":"4209_CR22","doi-asserted-by":"publisher","first-page":"545","DOI":"10.3233\/JAD-122224","volume":"36","author":"L Iuliano","year":"2013","unstructured":"Iuliano L, Pacelli A, Ciacciarelli M, Zerbinati C, Fagioli S, Piras F, Orfei MD, Bossu P, Pazzelli F, Serviddio G, et al. Plasma fatty acid lipidomics in amnestic mild cognitive impairment and Alzheimer\u2019s disease. J Alzheimers Dis. 2013;36(3):545\u201353.","journal-title":"J Alzheimers Dis"},{"issue":"1","key":"4209_CR23","doi-asserted-by":"publisher","first-page":"4","DOI":"10.3390\/metabo8010004","volume":"8","author":"M Cuperlovic-Culf","year":"2018","unstructured":"Cuperlovic-Culf M. Machine learning methods for analysis of metabolic data and metabolic pathway modeling. Metabolites. 2018;8(1):4.","journal-title":"Metabolites"},{"key":"4209_CR24","doi-asserted-by":"publisher","first-page":"66","DOI":"10.3390\/metabo9040066","volume":"9","author":"MY Lee","year":"2019","unstructured":"Lee MY, Hu T. Computational methods for the discovery of metabolic markers of complex traits. Metabolites. 2019;9:66.","journal-title":"Metabolites"},{"key":"4209_CR25","doi-asserted-by":"crossref","unstructured":"Pomyen Y, Wanichthanarak K, Poungsombat P, Fahrmann J, Grapov D, Khoomrung S. Deep metabolome: applications of deep learning in metabolomics. Comput Struct Biotechnol J. 2020.","DOI":"10.1016\/j.csbj.2020.09.033"},{"issue":"5","key":"4209_CR26","doi-asserted-by":"publisher","first-page":"2649","DOI":"10.1021\/pr5000895","volume":"13","author":"G Wang","year":"2014","unstructured":"Wang G, Zhou Y, Huang F-J, Tang H-D, Xu X-H, Liu J-J, Wang Y, Deng Y-L, Ren R-J, Xu W, et al. Plasma metabolite profiles of Alzheimer\u2019s disease and mild cognitive impairment. J Proteome Res. 2014;13(5):2649\u201358.","journal-title":"J Proteome Res"},{"key":"4209_CR27","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, et al. Scikit-learn: machine learning in Python. J Mach Learn Res. 2011;12:2825\u201330.","journal-title":"J Mach Learn Res"},{"key":"4209_CR28","volume-title":"Multi-objective optimization using evolutionary algorithms","author":"K Deb","year":"2001","unstructured":"Deb K. Multi-objective optimization using evolutionary algorithms. New Jersey: Wiley; 2001."},{"key":"4209_CR29","volume-title":"A field guide to genetic programming","author":"R Poli","year":"2008","unstructured":"Poli R, Langdon WB, McPhee NF, Koza JR. A field guide to genetic programming. Egham: Lulu Enterprises; 2008."},{"key":"4209_CR30","volume-title":"Linear genetic programming","author":"MF Brameier","year":"2007","unstructured":"Brameier MF, Banzhaf W. Linear genetic programming. Berlin: Springer; 2007."},{"key":"4209_CR31","doi-asserted-by":"crossref","unstructured":"Hu T. Can genetic programming perform explainable machine learning for bioinformatics? In: Genetic programming theory and practice, vol XVII, Berlin, Springer; 2020.","DOI":"10.1007\/978-3-030-39958-0_4"},{"issue":"9","key":"4209_CR32","doi-asserted-by":"publisher","first-page":"1414","DOI":"10.2967\/jnumed.107.049619","volume":"49","author":"G Esposito","year":"2008","unstructured":"Esposito G, Giovacchini G, Liow J-S, Bhattacharjee AK, Greenstein D, Schapiro M, Hallett M, Herscovitch P, Eckelman WC, Carson RE, et al. Imaging neuroinflammation in Alzheimer\u2019s disease with radiolabeled arachidonic acid and PET. J Nucl Med. 2008;49(9):1414\u201321.","journal-title":"J Nucl Med"},{"issue":"9","key":"4209_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.29245\/2572.942X\/2016\/9.1086","volume":"1","author":"MH Thomas","year":"2016","unstructured":"Thomas MH, Olivier JL. Arachidonic acid in Alzheimer\u2019s disease. J Neurol Neuromed. 2016;1(9):1\u20136.","journal-title":"J Neurol Neuromed"},{"key":"4209_CR34","doi-asserted-by":"publisher","first-page":"265","DOI":"10.3389\/fnins.2019.00265","volume":"13","author":"HM Melo","year":"2019","unstructured":"Melo HM, Santos LE, Ferreira ST. Diet-derived fatty acids, brain inflammation, and mental health. Front Neurosci. 2019;13:265.","journal-title":"Front Neurosci"},{"key":"4209_CR35","doi-asserted-by":"publisher","first-page":"102883","DOI":"10.1016\/j.ebiom.2020.102883","volume":"59","author":"IC Arellanes","year":"2020","unstructured":"Arellanes IC, Choe N, Solomon V, He X, Kavin B, Martinez AE, Kono N, Buennagel DP, Hazra N, Kim G, et al. Brain delivery of supplemental docosahexaenoic acid (DHA): a randomized placebo-controlled clinical trial. EBioMedicine. 2020;59:102883.","journal-title":"EBioMedicine"},{"issue":"1","key":"4209_CR36","doi-asserted-by":"publisher","first-page":"1003012","DOI":"10.1371\/journal.pmed.1003012","volume":"17","author":"UV Mahajan","year":"2020","unstructured":"Mahajan UV, Varma VR, Griswold ME, Blackshear CT, An Y, Oommen AM, Varma S, Troncoso JC, Pletnikova O, O\u2019Brien R, et al. Dysregulation of multiple metabolic networks related to brain transmethylation and polyamine pathways in Alzheimer\u2019s disease: A targeted metabolomic and transcriptomic study. PLoS Med. 2020;17(1):1003012.","journal-title":"PLoS Med"},{"issue":"1","key":"4209_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12929-016-0310-z","volume":"24","author":"M-Y Lee","year":"2017","unstructured":"Lee M-Y, Lin Y-R, Tu Y-S, Tseng YJ, Chan M-H, Chen H-H. Effects of sarcosine and N, N-dimethylglycine on NMDA receptor-mediated excitatory field potentials. J Biomed Sci. 2017;24(1):1\u201311.","journal-title":"J Biomed Sci"},{"issue":"7\u20138","key":"4209_CR38","doi-asserted-by":"publisher","first-page":"1052","DOI":"10.1016\/j.neuint.2006.10.007","volume":"50","author":"HS Walton","year":"2007","unstructured":"Walton HS, Dodd PR. Glutamate-glutamine cycling in Alzheimer\u2019s disease. Neurochem Int. 2007;50(7\u20138):1052\u201366.","journal-title":"Neurochem Int"},{"key":"4209_CR39","doi-asserted-by":"publisher","first-page":"1986","DOI":"10.1093\/bioinformatics\/btr300","volume":"27","author":"L Tolosi","year":"2011","unstructured":"Tolosi L, Lengauer T. Classification with correlated features: unreliability of feature ranking and solutions. Bioinformatics. 2011;27:1986\u201394.","journal-title":"Bioinformatics"},{"key":"4209_CR40","first-page":"1","volume":"59","author":"Y Tomata","year":"2019","unstructured":"Tomata Y, Larsson SC, H\u00e4gg S. Polyunsaturated fatty acids and risk of Alzheimer\u2019s disease: a Mendelian randomization study. Eur J Nutr. 2019;59:1\u20134.","journal-title":"Eur J Nutr"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-021-04209-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-021-04209-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-021-04209-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,28]],"date-time":"2021-05-28T08:07:15Z","timestamp":1622189235000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-021-04209-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,28]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["4209"],"URL":"https:\/\/doi.org\/10.1186\/s12859-021-04209-1","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,28]]},"assertion":[{"value":"15 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 May 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"284"}}