{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T20:16:37Z","timestamp":1793218597302,"version":"4.5.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T00:00:00Z","timestamp":1777507200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T00:00:00Z","timestamp":1777507200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["NRF-CRP19-2017-05-00"],"award-info":[{"award-number":["NRF-CRP19-2017-05-00"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["NRF-CRP19-2017-05-00"],"award-info":[{"award-number":["NRF-CRP19-2017-05-00"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","award":["C211917003"],"award-info":[{"award-number":["C211917003"]}],"id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","award":["C233017006"],"award-info":[{"award-number":["C233017006"]}],"id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","award":["C233017006"],"award-info":[{"award-number":["C233017006"]}],"id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","award":["C233017006"],"award-info":[{"award-number":["C233017006"]}],"id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","award":["C211917003"],"award-info":[{"award-number":["C211917003"]}],"id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Antimicrob Resist"],"DOI":"10.1038\/s44259-026-00206-7","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:57:46Z","timestamp":1777568266000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Accelerating natural product discovery with linked MS-genomics and language\/transformer-based models"],"prefix":"10.1038","volume":"4","author":[{"given":"Dillon W. P.","family":"Tay","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Winston","family":"Koh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shi Jun","family":"Ang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zicong Marvin","family":"Wong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi Wee","family":"Lim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elena","family":"Heng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu Hung","family":"Ng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naythan Z. X.","family":"Yeo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Krishnan","family":"Adaikkappan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fong Tian","family":"Wong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yee Hwee","family":"Lim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,30]]},"reference":[{"key":"206_CR1","doi-asserted-by":"publisher","first-page":"2141","DOI":"10.1021\/np040106y","volume":"67","author":"MS Butler","year":"2004","unstructured":"Butler, M. S. The role of natural product chemistry in drug discovery. J. Nat. Prod. 67, 2141\u20132153 (2004).","journal-title":"J. Nat. Prod."},{"key":"206_CR2","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1007\/s10295-013-1353-8","volume":"41","author":"PR Jensen","year":"2014","unstructured":"Jensen, P. R., Chavarria, K. L., Fenical, W., Moore, B. S. & Ziemert, N. Challenges and triumphs to genomics-based natural product discovery. J. Ind. Microbiol. Biotechnol. 41, 203\u2013209 (2014).","journal-title":"J. Ind. Microbiol. Biotechnol."},{"key":"206_CR3","doi-asserted-by":"publisher","first-page":"D691","DOI":"10.1093\/nar\/gkae1093","volume":"53","author":"EF Poynton","year":"2024","unstructured":"Poynton, E. F. et al. The Natural Products Atlas 3.0: extending the database of microbially derived natural products. Nucleic Acids Res. 53, D691\u2013D699 (2024).","journal-title":"Nucleic Acids Res."},{"key":"206_CR4","doi-asserted-by":"publisher","unstructured":"Johnson, S. R. & Lange, B. M. Open-access metabolomics databases for natural product research: present capabilities and future potential. Front. Bioeng. Biotechnol. 3, https:\/\/doi.org\/10.3389\/fbioe.2015.00022 (2015).","DOI":"10.3389\/fbioe.2015.00022"},{"key":"206_CR5","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1038\/nbt.3597","volume":"34","author":"M Wang","year":"2016","unstructured":"Wang, M. et al. Sharing and community curation of mass spectrometry data with Global Natural Products Social Molecular Networking. Nat. Biotechnol. 34, 828\u2013837 (2016).","journal-title":"Nat. Biotechnol."},{"key":"206_CR6","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02207-x","volume":"10","author":"DWP Tay","year":"2023","unstructured":"Tay, D. W. P., Yeo, N. Z. X., Adaikkappan, K., Lim, Y. H. & Ang, S. J. 67 million natural product-like compound database generated via molecular language processing. Sci. Data 10, 296 (2023).","journal-title":"Sci. Data"},{"key":"206_CR7","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1186\/s13321-020-00478-9","volume":"13","author":"M Sorokina","year":"2021","unstructured":"Sorokina, M., Merseburger, P., Rajan, K., Yirik, M. A. & Steinbeck, C. COCONUT online: collection of open natural products database. J. Cheminform. 13, 2 (2021).","journal-title":"J. Cheminform."},{"key":"206_CR8","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1038\/s41589-023-01276-8","volume":"19","author":"LK Caesar","year":"2023","unstructured":"Caesar, L. K. et al. Correlative metabologenomics of 110 fungi reveals metabolite\u2013gene cluster pairs. Nat. Chem. Biol. 19, 846\u2013854 (2023).","journal-title":"Nat. Chem. Biol."},{"key":"206_CR9","doi-asserted-by":"publisher","first-page":"1029","DOI":"10.1021\/acschembio.7b01089","volume":"13","author":"EI Parkinson","year":"2018","unstructured":"Parkinson, E. I. et al. Discovery of the tyrobetaine natural products and their biosynthetic gene cluster via metabologenomics. ACS Chem. Biol. 13, 1029\u20131037 (2018).","journal-title":"ACS Chem. Biol."},{"key":"206_CR10","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1021\/acscentsci.5b00331","volume":"2","author":"AW Goering","year":"2016","unstructured":"Goering, A. W. et al. Metabologenomics: correlation of microbial gene clusters with metabolites drives discovery of a nonribosomal peptide with an unusual amino acid monomer. ACS Cent. Sci. 2, 99\u2013108 (2016).","journal-title":"ACS Cent. Sci."},{"key":"206_CR11","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","volume":"379","author":"Z Lin","year":"2023","unstructured":"Lin, Z. et al. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379, 1123\u20131130 (2023).","journal-title":"Science"},{"key":"206_CR12","doi-asserted-by":"publisher","unstructured":"Chen, J.-Y. et al. Evaluating the advancements in protein language models for encoding strategies in protein function prediction: a comprehensive review. Front. Bioeng. Biotechnol. 13, https:\/\/doi.org\/10.3389\/fbioe.2025.1506508 (2025).","DOI":"10.3389\/fbioe.2025.1506508"},{"key":"206_CR13","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-46808-5","volume":"15","author":"W Liu","year":"2024","unstructured":"Liu, W. et al. PLMSearch: Protein language model powers accurate and fast sequence search for remote homology. Nat. Commun. 15, 2775 (2024).","journal-title":"Nat. Commun."},{"key":"206_CR14","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.91415","volume":"12","author":"SR Johnson","year":"2024","unstructured":"Johnson, S. R., Peshwa, M. & Sun, Z. Sensitive remote homology search by local alignment of small positional embeddings from protein language models. eLife 12, RP91415 (2024).","journal-title":"eLife"},{"key":"206_CR15","doi-asserted-by":"crossref","unstructured":"Douze M. et al. The Faiss Library. In IEEE Transactions on Big Data, 12, 346\u2013361 (2026).","DOI":"10.1109\/TBDATA.2025.3618474"},{"key":"206_CR16","doi-asserted-by":"publisher","first-page":"e1008920","DOI":"10.1371\/journal.pcbi.1008920","volume":"17","author":"G Hj\u00f6rleifsson Eldj\u00e1rn","year":"2021","unstructured":"Hj\u00f6rleifsson Eldj\u00e1rn, G. et al. Ranking microbial metabolomic and genomic links in the NPLinker framework using complementary scoring functions. PLoS Comput. Biol. 17, e1008920 (2021).","journal-title":"PLoS Comput. Biol."},{"key":"206_CR17","doi-asserted-by":"publisher","first-page":"W32","DOI":"10.1093\/nar\/gkaf334","volume":"53","author":"K Blin","year":"2025","unstructured":"Blin, K. et al. antiSMASH 8.0: extended gene cluster detection capabilities and analyses of chemistry, enzymology, and regulation. Nucleic Acids Res. 53, W32\u2013W38 (2025).","journal-title":"Nucleic Acids Res."},{"key":"206_CR18","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-026-68733-5","volume":"17","author":"A Draisma","year":"2026","unstructured":"Draisma, A. et al. BiG-SCAPE 2.0 and BiG-SLiCE 2.0: scalable, accurate and interactive sequence clustering of metabolic gene clusters. Nat. Commun. 17, 2000 (2026).","journal-title":"Nat. Commun."},{"key":"206_CR19","doi-asserted-by":"publisher","first-page":"D678","DOI":"10.1093\/nar\/gkae1115","volume":"53","author":"MM Zdouc","year":"2024","unstructured":"Zdouc, M. M. et al. MIBiG 4.0: advancing biosynthetic gene cluster curation through global collaboration. Nucleic Acids Res. 53, D678\u2013D690 (2024).","journal-title":"Nucleic Acids Res."},{"key":"206_CR20","doi-asserted-by":"publisher","first-page":"3419","DOI":"10.1021\/acs.analchem.3c04654","volume":"96","author":"S Goldman","year":"2024","unstructured":"Goldman, S., Li, J. & Coley, C. W. Generating molecular fragmentation graphs with autoregressive neural networks. Anal. Chem. 96, 3419\u20133428 (2024).","journal-title":"Anal. Chem."},{"key":"206_CR21","doi-asserted-by":"publisher","first-page":"11692","DOI":"10.1021\/acs.analchem.1c01465","volume":"93","author":"F Wang","year":"2021","unstructured":"Wang, F. et al. CFM-ID 4.0: more accurate ESI-MS\/MS spectral prediction and compound identification. Anal. Chem. 93, 11692\u201311700 (2021).","journal-title":"Anal. Chem."},{"key":"206_CR22","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1021\/acscentsci.9b00085","volume":"5","author":"JN Wei","year":"2019","unstructured":"Wei, J. N., Belanger, D., Adams, R. P. & Sculley, D. Rapid prediction of electron\u2013ionization mass spectrometry using neural networks. ACS Cent. Sci. 5, 700\u2013708 (2019).","journal-title":"ACS Cent. Sci."},{"key":"206_CR23","doi-asserted-by":"publisher","first-page":"7946","DOI":"10.1021\/acs.analchem.6b00770","volume":"88","author":"H Tsugawa","year":"2016","unstructured":"Tsugawa, H. et al. Hydrogen rearrangement rules: computational MS\/MS fragmentation and structure elucidation using MS-FINDER software. Anal. Chem. 88, 7946\u20137958 (2016).","journal-title":"Anal. Chem."},{"key":"206_CR24","doi-asserted-by":"publisher","first-page":"2887","DOI":"10.1021\/jm9602928","volume":"39","author":"GW Bemis","year":"1996","unstructured":"Bemis, G. W. & Murcko, M. A. The properties of known drugs. 1. Molecular frameworks. J. Med. Chem. 39, 2887\u20132893 (1996).","journal-title":"J. Med. Chem."},{"key":"206_CR25","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/s11222-005-6203-8","volume":"15","author":"MD Marzio","year":"2005","unstructured":"Marzio, M. D. & Taylor, C. C. Kernel density classification and boosting: an L2 analysis. Stat. Comput. 15, 113\u2013123 (2005).","journal-title":"Stat. Comput."},{"key":"206_CR26","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-024-03833-9","volume":"11","author":"DWP Tay","year":"2024","unstructured":"Tay, D. W. P. et al. Tandem mass spectral metabolic profiling of 54 actinobacterial strains and their 459 mutants. Sci. Data 11, 977 (2024).","journal-title":"Sci. Data"},{"key":"206_CR27","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1038\/s42003-023-05648-7","volume":"7","author":"DWP Tay","year":"2024","unstructured":"Tay, D. W. P. et al. Exploring a general multi-pronged activation strategy for natural product discovery in Actinomycetes. Commun. Biol. 7, 50 (2024).","journal-title":"Commun. Biol."},{"key":"206_CR28","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1038\/nbt.4187","volume":"36","author":"SB Ng","year":"2018","unstructured":"Ng, S. B. et al. The 160K Natural Organism Library, a unique resource for natural products research. Nat. Biotechnol. 36, 570\u2013573 (2018).","journal-title":"Nat. Biotechnol."},{"key":"206_CR29","doi-asserted-by":"publisher","first-page":"1410","DOI":"10.1039\/b501199j","volume":"3","author":"F Huang","year":"2005","unstructured":"Huang, F. et al. The neomycin biosynthetic gene cluster of Streptomyces fradiae NCIMB 8233: characterisation of an aminotransferase involved in the formation of 2-deoxystreptamine. Org. Biomol. Chem. 3, 1410\u20131418 (2005).","journal-title":"Org. Biomol. Chem."},{"key":"206_CR30","doi-asserted-by":"publisher","first-page":"2114","DOI":"10.1093\/bioinformatics\/btu170","volume":"30","author":"AM Bolger","year":"2014","unstructured":"Bolger, A. M., Lohse, M. & Usadel, B. Trimmomatic: a flexible trimmer for Illumina sequence data. Bioinformatics 30, 2114\u20132120 (2014).","journal-title":"Bioinformatics"},{"key":"206_CR31","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-11-119","volume":"11","author":"D Hyatt","year":"2010","unstructured":"Hyatt, D. et al. Prodigal: prokaryotic gene recognition and translation initiation site identification. BMC Bioinform. 11, 119 (2010).","journal-title":"BMC Bioinform."},{"key":"206_CR32","doi-asserted-by":"publisher","unstructured":"Nicolescu, T. O. Interpretation of mass spectra. In Mass Spectrometry (ed. Aliofkhazraei, M.) 23\u201378 https:\/\/doi.org\/10.5772\/intechopen.68595 (IntechOpen, 2017).","DOI":"10.5772\/intechopen.68595"}],"container-title":["npj Antimicrobials and Resistance"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s44259-026-00206-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s44259-026-00206-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s44259-026-00206-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:57:48Z","timestamp":1777568268000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s44259-026-00206-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,30]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["206"],"URL":"https:\/\/doi.org\/10.1038\/s44259-026-00206-7","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2025.01.20.633932","asserted-by":"object"}]},"ISSN":["2731-8745"],"issn-type":[{"value":"2731-8745","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,30]]},"assertion":[{"value":"28 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Two provisional patent applications have been filed by some of the authors wherein some of the data are disclosed in this manuscript. The authors (Y.H.L., D.T., S.J.A. and Z.M.W.) are inventors to SG Patent 10202400652R, and the authors (Y.H.L., D.T., S.J.A., N.Z.X.Y. and K.A.) are inventors to SG Patent 10202403057W.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"31"}}