{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:23:30Z","timestamp":1772828610943,"version":"3.50.1"},"reference-count":33,"publisher":"Walter de Gruyter GmbH","issue":"2","license":[{"start":{"date-parts":[[2025,3,20]],"date-time":"2025-03-20T00:00:00Z","timestamp":1742428800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"LABBELS","award":["LA\/P\/0029\/2020"],"award-info":[{"award-number":["LA\/P\/0029\/2020"]}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00c3\u00a7\u00c3\u00a3o para a Ci\u00c3\u00aancia e a Tecnologia","doi-asserted-by":"publisher","award":["10.54499\/CEECIND\/03425\/2018\/CP1581\/CT0020"],"award-info":[{"award-number":["10.54499\/CEECIND\/03425\/2018\/CP1581\/CT0020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00c3\u00a7\u00c3\u00a3o para a Ci\u00c3\u00aancia e a Tecnologia","doi-asserted-by":"publisher","award":["DFA\/BD\/08789\/2021"],"award-info":[{"award-number":["DFA\/BD\/08789\/2021"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Plants produce specialized metabolites, which play critical roles in defending against biotic and abiotic stresses. Due to their chemical diversity and bioactivity, these compounds have significant economic implications, particularly in the pharmaceutical and agrotechnology sectors. Despite their importance, the biosynthetic pathways of these metabolites remain largely unresolved. Automating the prediction of their precursors, derived from primary metabolism, is essential for accelerating pathway discovery. Using DeepMol\u2019s automated machine learning engine, we found that regularized linear classifiers offer optimal, accurate, and interpretable models for this task, outperforming state-of-the-art models while providing chemical insights into their predictions. The pipeline and models are available at the repository:\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/jcapels\/SMPrecursorPredictor\">https:\/\/github.com\/jcapels\/SMPrecursorPredictor<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1515\/jib-2024-0050","type":"journal-article","created":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T01:54:01Z","timestamp":1742349241000},"source":"Crossref","is-referenced-by-count":2,"title":["Predicting precursors of plant specialized metabolites using DeepMol automated machine learning"],"prefix":"10.1515","volume":"22","author":[{"given":"Jo\u00e3o","family":"Capela","sequence":"first","affiliation":[{"name":"Centre of Biological Engineering , University of Minho , 4710-057 , Braga , Portugal"}]},{"given":"Jo\u00e3o","family":"Cheixo","sequence":"additional","affiliation":[{"name":"Centre of Biological Engineering , University of Minho , 4710-057 , Braga , Portugal"}]},{"given":"Dick","family":"de Ridder","sequence":"additional","affiliation":[{"name":"Bioinformatics Group, Department of Plant Sciences , Wageningen University and Research , Wageningen , The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1765-7178","authenticated-orcid":false,"given":"Oscar","family":"Dias","sequence":"additional","affiliation":[{"name":"Centre of Biological Engineering , University of Minho , 4710-057 , Braga , Portugal"},{"name":"LABBELS \u2013 Associate Laboratory , Braga\/Guimar\u00e3es , Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8439-8172","authenticated-orcid":false,"given":"Miguel","family":"Rocha","sequence":"additional","affiliation":[{"name":"Centre of Biological Engineering , University of Minho , 4710-057 , Braga , Portugal"},{"name":"LABBELS \u2013 Associate Laboratory , Braga\/Guimar\u00e3es , Portugal"}]}],"member":"374","published-online":{"date-parts":[[2025,3,20]]},"reference":[{"key":"2025102907580413933_j_jib-2024-0050_ref_001","doi-asserted-by":"crossref","unstructured":"Panchy, N, Lehti-Shiu, M, Shiu, SH. Evolution of gene duplication in plants. Plant Physiol 2016;171:2294\u2013316. https:\/\/doi.org\/10.1104\/pp.16.00523.","DOI":"10.1104\/pp.16.00523"},{"key":"2025102907580413933_j_jib-2024-0050_ref_030","doi-asserted-by":"crossref","unstructured":"Chae, L, Kim, T, Nilo-Poyanco, R, Rhee, SY. Genomic signatures of specialized metabolism in plants. Science 2014;344:510\u201313. https:\/\/doi.org\/10.1126\/science.1252076.","DOI":"10.1126\/science.1252076"},{"key":"2025102907580413933_j_jib-2024-0050_ref_002","doi-asserted-by":"crossref","unstructured":"Moore, BM, Wang, P, Fan, P, Leong, B, Schenck, CA, Lloyd, JP, et al.. Robust predictions of specialized metabolism genes through machine learning. Proc Natl Acad Sci USA 2019;116:2344\u201353. https:\/\/doi.org\/10.1073\/pnas.1817074116.","DOI":"10.1073\/pnas.1817074116"},{"key":"2025102907580413933_j_jib-2024-0050_ref_003","doi-asserted-by":"crossref","unstructured":"Zhou, F, Pichersky, E. More is better: the diversity of terpene metabolism in plants. Curr Opin Plant Biol 2020;55:1\u201310. https:\/\/doi.org\/10.1016\/j.pbi.2020.01.005.","DOI":"10.1016\/j.pbi.2020.01.005"},{"key":"2025102907580413933_j_jib-2024-0050_ref_004","doi-asserted-by":"crossref","unstructured":"Bolger, ME, Arsova, B, Usadel, B. Plant genome and transcriptome annotations: from misconceptions to simple solutions. Briefings Bioinf 2017;1:bbw135. https:\/\/doi.org\/10.1093\/bib\/bbw135.","DOI":"10.1093\/bib\/bbw135"},{"key":"2025102907580413933_j_jib-2024-0050_ref_005","doi-asserted-by":"crossref","unstructured":"Pichersky, E, Lewinsohn, E. Convergent evolution in plant specialized metabolism. Annu Rev Plant Biol 2011;62:549\u201366. https:\/\/doi.org\/10.1146\/annurev-arplant-042110-103814.","DOI":"10.1146\/annurev-arplant-042110-103814"},{"key":"2025102907580413933_j_jib-2024-0050_ref_006","unstructured":"Hussein, RA, El-Anssary, AA. Plants secondary metabolites: the key drivers of the pharmacological actions of medicinal plants. In: Herbal Medicine. London,\u00a0 United Kingdom: IntechOpen; 2019:11\u201330 pp."},{"key":"2025102907580413933_j_jib-2024-0050_ref_007","doi-asserted-by":"crossref","unstructured":"Vogt, T. Phenylpropanoid biosynthesis. Mol Plant 2010;3:2\u201320. https:\/\/doi.org\/10.1093\/mp\/ssp106.","DOI":"10.1093\/mp\/ssp106"},{"key":"2025102907580413933_j_jib-2024-0050_ref_031","unstructured":"Aniszewski, T. Alkaloids: chemistry, biology, ecology, and applications. Amsterdam, The Netherlands: Elsevier; 2015."},{"key":"2025102907580413933_j_jib-2024-0050_ref_009","doi-asserted-by":"crossref","unstructured":"Tholl, D. Biosynthesis and biological functions of terpenoids in plants. Biotechnol Isoprenoids 2015:63\u2013106. https:\/\/doi.org\/10.1007\/10_2014_295.","DOI":"10.1007\/10_2014_295"},{"key":"2025102907580413933_j_jib-2024-0050_ref_032","doi-asserted-by":"crossref","unstructured":"Kubeczka, KH. History and sources of essential oil research. In: Handbook of Essential Oils. FL, USA: CRC Press; 2020:3\u201339 pp.","DOI":"10.1201\/9781351246460-2"},{"key":"2025102907580413933_j_jib-2024-0050_ref_033","doi-asserted-by":"crossref","unstructured":"Henry, LK, Thomas, ST, Widhalm, JR, Lynch, JH, Davis, TC, Kessler, SA, et al.. Contribution of isopentenyl phosphate to plant terpenoid metabolism. Nat Plants 2018;4:721\u20139. https:\/\/doi.org\/10.1038\/s41477-018-0220-z.","DOI":"10.1038\/s41477-018-0220-z"},{"key":"2025102907580413933_j_jib-2024-0050_ref_008","doi-asserted-by":"crossref","unstructured":"Eguchi, R, Ono, N, Hirai Morita, A, Katsuragi, T, Nakamura, Huang, M, et al.. Classification of alkaloids according to the starting substances of their biosynthetic pathways using graph convolutional neural networks. BMC Bioinf 2019;20:1\u201313. https:\/\/doi.org\/10.1186\/s12859-019-2963-6.","DOI":"10.1186\/s12859-019-2963-6"},{"key":"2025102907580413933_j_jib-2024-0050_ref_010","doi-asserted-by":"crossref","unstructured":"Correia, J, Capela, J, Rocha, M. Deepmol: an automated machine and deep learning framework for computational chemistry. J Cheminf 2024;16:1\u201317.","DOI":"10.1186\/s13321-024-00937-7"},{"key":"2025102907580413933_j_jib-2024-0050_ref_011","doi-asserted-by":"crossref","unstructured":"Wang, K, Deng, J, Damaris, RN, Yang, M, Xu, L, Yang, P. LOTUS-DB: an integrative and interactive database for Nelumbo nucifera study. Database 2015;2015:bav023. https:\/\/doi.org\/10.1093\/database\/bav023.","DOI":"10.1093\/database\/bav023"},{"key":"2025102907580413933_j_jib-2024-0050_ref_012","doi-asserted-by":"crossref","unstructured":"Kim, HW, Wang, M, Leber, CA, Nothias, LF, Reher, R, Kang, KB, et al.. NPClassifier: a deep neural network-based structural classification tool for natural products. J Nat Prod 2021;84:2795\u2013807. https:\/\/doi.org\/10.1021\/acs.jnatprod.1c00399.","DOI":"10.1021\/acs.jnatprod.1c00399"},{"key":"2025102907580413933_j_jib-2024-0050_ref_013","doi-asserted-by":"crossref","unstructured":"Boldini, D, Ballabio, D, Consonni, V, Todeschini, R, Grisoni, F, Sieber, SA. Effectiveness of molecular fingerprints for exploring the chemical space of natural products. J Cheminf 2024;16:35. https:\/\/doi.org\/10.1186\/s13321-024-00830-3.","DOI":"10.1186\/s13321-024-00830-3"},{"key":"2025102907580413933_j_jib-2024-0050_ref_014","doi-asserted-by":"crossref","unstructured":"Davis, EM, Croteau, R. Cyclization enzymes in the biosynthesis of monoterpenes, sesquiterpenes, and diterpenes. Biosynthesis. Topics in Current Chemistry, vol 209. Springer, Berlin, Heidelberg; 2000:53\u201395 pp. https:\/\/doi.org\/10.1007\/3-540-48146-X_2.","DOI":"10.1007\/3-540-48146-X_2"},{"key":"2025102907580413933_j_jib-2024-0050_ref_015","doi-asserted-by":"crossref","unstructured":"Shumskaya, M, Wurtzel, ET. The carotenoid biosynthetic pathway: thinking in all dimensions. Plant Sci 2013;208:58\u201363. https:\/\/doi.org\/10.1016\/j.plantsci.2013.03.012.","DOI":"10.1016\/j.plantsci.2013.03.012"},{"key":"2025102907580413933_j_jib-2024-0050_ref_016","doi-asserted-by":"crossref","unstructured":"Zullo, MAT, Bajguz, A. The brassinosteroids family\u2013structural diversity of natural compounds and their precursors. In: Brassinosteroids: plant growth and development. Singapore: Springer; 2019:1\u201344 pp.","DOI":"10.1007\/978-981-13-6058-9_1"},{"key":"2025102907580413933_j_jib-2024-0050_ref_017","doi-asserted-by":"crossref","unstructured":"Liu, W, Feng, Y, Yu, S, Fan, Z, Li, X, Li, J, et al.. The flavonoid biosynthesis network in plants. Int J Mol Sci 2021;22:12824. https:\/\/doi.org\/10.3390\/ijms222312824.","DOI":"10.3390\/ijms222312824"},{"key":"2025102907580413933_j_jib-2024-0050_ref_018","doi-asserted-by":"crossref","unstructured":"S\u00f8nderby, IE, Geu-Flores, F, Halkier, BA. Biosynthesis of glucosinolates\u2013gene discovery and beyond. Trends Plant Sci 2010;15:283\u201390. https:\/\/doi.org\/10.1016\/j.tplants.2010.02.005.","DOI":"10.1016\/j.tplants.2010.02.005"},{"key":"2025102907580413933_j_jib-2024-0050_ref_019","doi-asserted-by":"crossref","unstructured":"Frey, M, Schullehner, K, Dick, R, Fiesselmann, A, Gierl, A. Benzoxazinoid biosynthesis, a model for evolution of secondary metabolic pathways in plants. Phytochemistry 2009;70:1645\u201351. https:\/\/doi.org\/10.1016\/j.phytochem.2009.05.012.","DOI":"10.1016\/j.phytochem.2009.05.012"},{"key":"2025102907580413933_j_jib-2024-0050_ref_020","doi-asserted-by":"crossref","unstructured":"Probst, D, Reymond, JL. A probabilistic molecular fingerprint for big data settings. J Cheminf 2018;10:1\u201312. https:\/\/doi.org\/10.1186\/s13321-018-0321-8.","DOI":"10.1186\/s13321-018-0321-8"},{"key":"2025102907580413933_j_jib-2024-0050_ref_021","doi-asserted-by":"crossref","unstructured":"Menke, J, Massa, J, Koch, O. Natural product scores and fingerprints extracted from artificial neural networks. Comput Struct Biotechnol J 2021;19:4593\u2013602. https:\/\/doi.org\/10.1016\/j.csbj.2021.07.032.","DOI":"10.1016\/j.csbj.2021.07.032"},{"key":"2025102907580413933_j_jib-2024-0050_ref_022","doi-asserted-by":"crossref","unstructured":"Trenti, F, Yamamoto, K, Hong, B, Paetz, C, Nakamura, Y, O\u2019Connor, SE. Early and late steps of quinine biosynthesis. Org Lett 2021;23:1793\u20137. https:\/\/doi.org\/10.1021\/acs.orglett.1c00206.","DOI":"10.1021\/acs.orglett.1c00206"},{"key":"2025102907580413933_j_jib-2024-0050_ref_023","doi-asserted-by":"crossref","unstructured":"Guo, J, Gao, D, Lian, J, Qu, Y. De novo biosynthesis of antiarrhythmic alkaloid ajmaline. Nat Commun 2024;15:457. https:\/\/doi.org\/10.1038\/s41467-024-44797-z.","DOI":"10.1038\/s41467-024-44797-z"},{"key":"2025102907580413933_j_jib-2024-0050_ref_024","doi-asserted-by":"crossref","unstructured":"H\u00f6velmann, Y, Jagels, A, Schmid, R, H\u00fcbner, F, Humpf, HU. Identification of potential human urinary biomarkers for tomato juice intake by mass spectrometry-based metabolomics. Eur J Nutr 2020;59:685\u201397. https:\/\/doi.org\/10.1007\/s00394-019-01935-4.","DOI":"10.1007\/s00394-019-01935-4"},{"key":"2025102907580413933_j_jib-2024-0050_ref_025","doi-asserted-by":"crossref","unstructured":"Herraiz, T. \u03b2-Carboline alkaloids. Bioact Compds Foods 2008:199\u2013223. https:\/\/doi.org\/10.1002\/9781444302288.ch8.","DOI":"10.1002\/9781444302288.ch8"},{"key":"2025102907580413933_j_jib-2024-0050_ref_026","doi-asserted-by":"crossref","unstructured":"Minnaar, P, Van Der Rijst, M, Hunter, J. Grapevine row orientation, vintage and grape ripeness effect on anthocyanins, flavan-3-ols, flavonols and phenolic acids: I. Vitis vinifera L. cv. Syrah grapes. OENO One 2022;56:275\u201393. https:\/\/doi.org\/10.20870\/oeno-one.2022.56.1.4857.","DOI":"10.20870\/oeno-one.2022.56.1.4857"},{"key":"2025102907580413933_j_jib-2024-0050_ref_027","doi-asserted-by":"crossref","unstructured":"Ng, J, Smith, SD. How to make a red flower: the combinatorial effect of pigments. AoB Plants 2015;8:plw013. https:\/\/doi.org\/10.1093\/aobpla\/plw013.","DOI":"10.1093\/aobpla\/plw013"},{"key":"2025102907580413933_j_jib-2024-0050_ref_028","doi-asserted-by":"crossref","unstructured":"Zheng, S, Zeng, T, Li, C, Chen, B, Coley, CW, Yang, Y, et al.. Deep learning driven biosynthetic pathways navigation for natural products with BioNavi-NP. Nat Commun 2022;13:3342. https:\/\/doi.org\/10.1038\/s41467-022-30970-9.","DOI":"10.1038\/s41467-022-30970-9"},{"key":"2025102907580413933_j_jib-2024-0050_ref_029","doi-asserted-by":"crossref","unstructured":"Kim, T, Lee, S, Kwak, Y, Choi, MS, Park, J, Hwang, SJ, et al.. READRetro: natural product biosynthesis predicting with retrieval-augmented dual-view retrosynthesis. New Phytol 2024. https:\/\/doi.org\/10.1111\/nph.20012.","DOI":"10.1111\/nph.20012"}],"container-title":["Journal of Integrative Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/jib-2024-0050\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/jib-2024-0050\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T08:00:17Z","timestamp":1761724817000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/jib-2024-0050\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,20]]},"references-count":33,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,7,14]]},"published-print":{"date-parts":[[2025,10,30]]}},"alternative-id":["10.1515\/jib-2024-0050"],"URL":"https:\/\/doi.org\/10.1515\/jib-2024-0050","relation":{},"ISSN":["1613-4516"],"issn-type":[{"value":"1613-4516","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,20]]},"article-number":"20240050"}}