{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:32:39Z","timestamp":1777984359782,"version":"3.51.4"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T00:00:00Z","timestamp":1776211200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T00:00:00Z","timestamp":1777334400000},"content-version":"vor","delay-in-days":13,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000268","name":"Biotechnology and Biological Sciences Research Council","doi-asserted-by":"publisher","award":["BB\/X511778\/1"],"award-info":[{"award-number":["BB\/X511778\/1"]}],"id":[{"id":"10.13039\/501100000268","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Generative deep learning models have demonstrated significant potential in designing drug-like molecules. However, medicinal chemistry typically requires generating analogues that combine structural similarity with scaffold hopping, which is the replacement of molecular scaffolds while retaining biological relevance. To address this, we introduce ANNalog, a transformer-based sequence-to-sequence generative model trained on pairs of molecules extracted from the same bioactivity assay in a paper as recorded in ChEMBL33. The dataset was constructed based on the idea that molecules tested within the same assay can be considered analogues in medicinal chemistry space. Paired molecules were encoded as Simplified Molecular Input Line Entry System strings, and Levenshtein distance-guided alignment was applied to maximise intrapair string similarity; this preprocessing step was found to markedly enhance model performance. ANNalog has the ability to produce structurally similar analogues involving minor modifications, such as substituent replacements, as well as the ability to perform scaffold hopping, generating structurally distinct yet chemically relevant analogues. Scaffold-hopping capability was validated using manually curated molecule pairs and further confirmed through a case study involving orexin-2 receptor antagonists from patent literature. When the generation process was constrained using ANNalog\u2019s prefix control feature, approximately 25% of the known scaffolds from the patent set were successfully recovered by the model, illustrating enhanced performance under user-guided conditions. Scientific Contribution: This study introduces ANNalog, a generative model trained using pairs of molecules synthesised and tested together within the same medicinal chemistry project. Unlike previous models trained on pairs of molecules selected according to similarity measures, ANNalog successfully generates not only structurally similar molecules but also diverse scaffold-hopping transformations that have precedent in the medicinal chemistry literature.<\/jats:p>","DOI":"10.1186\/s13321-026-01186-6","type":"journal-article","created":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T10:45:26Z","timestamp":1776249926000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ANNalog: generation of MedChem-similar molecules"],"prefix":"10.1186","volume":"18","author":[{"given":"Wei","family":"Dai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan D.","family":"Tyzack","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arianna","family":"Fornili","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chris","family":"de Graaf","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noel M.","family":"O\u2019Boyle","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,15]]},"reference":[{"key":"1186_CR1","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1021\/acscentsci.7b00572","volume":"4","author":"R G\u00f3mez-Bombarelli","year":"2018","unstructured":"G\u00f3mez-Bombarelli R, Wei JN, Duvenaud D, Hern\u00e1ndez-Lobato JM, S\u00e1nchez-Lengeling B, Sheberla D et al (2018) Automatic chemical design using a data-driven continuous representation of molecules. ACS Cent Sci 4:268\u2013276","journal-title":"ACS Cent Sci"},{"key":"1186_CR2","doi-asserted-by":"crossref","unstructured":"Ma C, Zhang X (2021) GF-VAE: a flow-based variational autoencoder for molecule generation. In: Proceedings of the 30th ACM international conference on information & knowledge management. Association for Computing Machinery, New York, pp 1181\u20131190","DOI":"10.1145\/3459637.3482260"},{"key":"1186_CR3","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac814","volume":"39","author":"Z Liao","year":"2023","unstructured":"Liao Z, Xie L, Mamitsuka H, Zhu S (2023) Sc2Mol: a scaffold-based two-step molecule generator with variational autoencoder and transformer. Bioinformatics 39:btac814","journal-title":"Bioinformatics"},{"key":"1186_CR4","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1186\/s13321-019-0393-0","volume":"11","author":"J Ar\u00fas-Pous","year":"2019","unstructured":"Ar\u00fas-Pous J, Johansson SV, Prykhodko O, Bjerrum EJ, Tyrchan C, Reymond J-L et al (2019) Randomized SMILES strings improve the quality of molecular generative models. J Cheminform 11:71","journal-title":"J Cheminform"},{"key":"1186_CR5","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1021\/acscentsci.7b00512","volume":"4","author":"MHS Segler","year":"2018","unstructured":"Segler MHS, Kogej T, Tyrchan C, Waller MP (2018) Generating focused molecule libraries for drug discovery with recurrent neural networks. ACS Cent Sci 4:120\u2013131","journal-title":"ACS Cent Sci"},{"key":"1186_CR6","doi-asserted-by":"publisher","first-page":"972","DOI":"10.1080\/14686996.2017.1401424","volume":"18","author":"X Yang","year":"2017","unstructured":"Yang X, Zhang J, Yoshizoe K, Terayama K, Tsuda K (2017) ChemTS: an efficient Python library for de novo molecular generation. Sci Technol Adv Mater 18:972\u2013976","journal-title":"Sci Technol Adv Mater"},{"key":"1186_CR7","unstructured":"Honda S, Shi S, Ueda HR (2019) SMILES transformer: pre-trained molecular fingerprint for low-data drug discovery. 2019 [cited 2025 Sep 03]. https:\/\/arxiv.org\/abs\/1911.04738"},{"key":"1186_CR8","doi-asserted-by":"publisher","first-page":"2064","DOI":"10.1021\/acs.jcim.1c00600","volume":"62","author":"V Bagal","year":"2022","unstructured":"Bagal V, Aggarwal R, Vinod PK, Priyakumar UD (2022) MolGPT: molecular generation using a transformer-decoder model. J Chem Inf Model 62:2064\u20132076","journal-title":"J Chem Inf Model"},{"key":"1186_CR9","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac3ffb","volume":"3","author":"R Irwin","year":"2022","unstructured":"Irwin R, Dimitriadis S, He J, Bjerrum EJ (2022) Chemformer: a pre-trained transformer for computational chemistry. Mach Learn Sci Technol 3:015022","journal-title":"Mach Learn Sci Technol"},{"key":"1186_CR10","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s13321-024-00812-5","volume":"16","author":"HH Loeffler","year":"2024","unstructured":"Loeffler HH, He J, Tibo A, Janet JP, Voronov A, Mervin LH et al (2024) REINVENT 4: modern AI-driven generative molecule design. J Cheminform 16:20","journal-title":"J Cheminform"},{"key":"1186_CR11","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-024-00861-w","volume":"16","author":"M Thomas","year":"2024","unstructured":"Thomas M, O\u2019Boyle NM, Bender A, De Graaf C (2024) MolScore: a scoring, evaluation and benchmarking framework for generative models in de novo drug design. J Cheminform 16:64","journal-title":"J Cheminform"},{"key":"1186_CR12","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1007\/s10822-016-9938-8","volume":"30","author":"S Kearnes","year":"2016","unstructured":"Kearnes S, McCloskey K, Berndl M, Pande V, Riley P (2016) Molecular graph convolutions: moving beyond fingerprints. J Comput Aided Mol Des 30:595\u2013608","journal-title":"J Comput Aided Mol Des"},{"key":"1186_CR13","doi-asserted-by":"publisher","first-page":"1146","DOI":"10.3390\/ijms24021146","volume":"24","author":"X Wang","year":"2023","unstructured":"Wang X, Gao C, Han P, Li X, Chen W, Rodr\u00edguez Pat\u00f3n A et al (2023) PETrans: de novo drug design with protein-specific encoding based on transfer learning. Int J Mol Sci 24:1146","journal-title":"Int J Mol Sci"},{"key":"1186_CR14","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1186\/s13321-020-00430-x","volume":"12","author":"X Li","year":"2020","unstructured":"Li X, Fourches D (2020) Inductive transfer learning for molecular activity prediction: next-gen QSAR models with MolPMoFiT. J Cheminform 12:27","journal-title":"J Cheminform"},{"key":"1186_CR15","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1021\/acs.jcim.8b00902","volume":"59","author":"M Awale","year":"2019","unstructured":"Awale M, Sirockin F, Stiefl N, Reymond J-L (2019) Drug analogs from fragment-based long short-term memory generative neural networks. J Chem Inf Model 59:1347\u20131356","journal-title":"J Chem Inf Model"},{"key":"1186_CR16","doi-asserted-by":"publisher","first-page":"7315","DOI":"10.1038\/s41467-024-51672-4","volume":"15","author":"A Tibo","year":"2024","unstructured":"Tibo A, He J, Janet JP, Nittinger E, Engkvist O (2024) Exhaustive local chemical space exploration using a transformer model. Nat Commun 15:7315","journal-title":"Nat Commun"},{"key":"1186_CR17","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1002\/9783527665143.ch16","volume-title":"Scaffold hopping in medicinal chemistry","author":"LC Konkol","year":"2013","unstructured":"Konkol LC, Senter TJ, Lindsley CW (2013) Case study 1: scaffold hopping for T-type calcium channel and glycine transporter type 1 inhibitors. In: Brown N (ed) Scaffold hopping in medicinal chemistry. Wiley, Weinheim, pp 245\u2013258"},{"key":"1186_CR18","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1016\/j.drudis.2011.10.024","volume":"17","author":"H Sun","year":"2012","unstructured":"Sun H, Tawa G, Wallqvist A (2012) Classification of scaffold-hopping approaches. Drug Discov Today 17:310\u2013324","journal-title":"Drug Discov Today"},{"key":"1186_CR19","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.ejmech.2013.12.033","volume":"74","author":"J-F Renard","year":"2014","unstructured":"Renard J-F, Lecomte F, Hubert P, de Leval X, Pirotte B (2014) N-(3-arylaminopyridin-4-yl)alkanesulfonamides as pyridine analogs of nimesulide: cyclooxygenases inhibition, anti-inflammatory studies and insight on metabolism. Eur J Med Chem 74:12\u201322","journal-title":"Eur J Med Chem"},{"key":"1186_CR20","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1186\/s13321-016-0148-0","volume":"8","author":"NM O\u2019Boyle","year":"2016","unstructured":"O\u2019Boyle NM, Sayle RA (2016) Comparing structural fingerprints using a literature-based similarity benchmark. J Cheminform 8:36","journal-title":"J Cheminform"},{"key":"1186_CR21","doi-asserted-by":"publisher","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","volume":"40","author":"A Gaulton","year":"2012","unstructured":"Gaulton A, Bellis LJ, Bento AP, Chambers J, Davies M, Hersey A et al (2012) ChEMBL: a large-scale bioactivity database for drug discovery. Nucleic Acids Res 40:D1100\u2013D1107","journal-title":"Nucleic Acids Res"},{"key":"1186_CR22","first-page":"707","volume":"10","author":"VI Levenshtein","year":"1966","unstructured":"Levenshtein VI (1966) Binary codes capable of correcting deletions, insertions, and reversals. Sov Phys Dokl 10:707\u2013710","journal-title":"Sov Phys Dokl"},{"key":"#cr-split#-1186_CR23.1","unstructured":"Trevett B (2025) pytorch-seq2seq: tutorials on implementing sequence-to-sequence (seq2seq) models using PyTorch [Internet]. GitHub"},{"key":"#cr-split#-1186_CR23.2","unstructured":"cited 2025 Sep 23. https:\/\/github.com\/bentrevett\/pytorch-seq2seq\/tree\/main\/legacy"},{"key":"1186_CR24","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1186\/s13321-023-00696-x","volume":"15","author":"L Schoenmaker","year":"2023","unstructured":"Schoenmaker L, B\u00e9quignon OJM, Jespers W, van Westen GJP (2023) UnCorrupt SMILES: a novel approach to de novo design. J Cheminform 15:22","journal-title":"J Cheminform"},{"key":"1186_CR25","doi-asserted-by":"crossref","unstructured":"Wilt C, Thayer J, Ruml W (2010) A comparison of greedy search algorithms. In: Proceedings of the international symposium on combinatorial search, vol 1, pp 129\u201336","DOI":"10.1609\/socs.v1i1.18182"},{"key":"1186_CR26","doi-asserted-by":"crossref","unstructured":"Freitag M, Al-Onaizan Y (2017) Beam search strategies for neural machine translation. In: Proceedings of the first workshop on neural machine translation. Association for Computational Linguistics, pp 56\u201360","DOI":"10.18653\/v1\/W17-3207"},{"key":"1186_CR27","doi-asserted-by":"crossref","unstructured":"Meister C, Vieira T, Cotterell R (2020) If beam search is the answer, what was the question? In: Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP). Association for Computational Linguistics, pp 2173\u20132185","DOI":"10.18653\/v1\/2020.emnlp-main.170"},{"key":"1186_CR28","unstructured":"O\u2019Boyle NM (2025) partialsmiles [Internet]. [cited 2025 Mar 15]. https:\/\/github.com\/baoilleach\/partialsmiles"},{"key":"1186_CR29","unstructured":"Landrum G (2024) RDKit: open-source cheminformatics [Internet] [cited 2024 Sep 03]. https:\/\/www.rdkit.org\/"},{"key":"1186_CR30","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1021\/c160017a018","volume":"5","author":"HL Morgan","year":"1965","unstructured":"Morgan HL (1965) The generation of a unique machine description for chemical structures\u2014a technique developed at Chemical Abstracts Service. J Chem Doc 5:107\u2013113","journal-title":"J Chem Doc"},{"key":"1186_CR31","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1186\/s13321-017-0225-z","volume":"9","author":"P Ertl","year":"2017","unstructured":"Ertl P (2017) An algorithm to identify functional groups in organic molecules. J Cheminform 9:36","journal-title":"J Cheminform"},{"key":"1186_CR32","unstructured":"O\u2019Boyle N (2018) When all you want is a ring: Part II. Noel O\u2019Blog [Internet]. 2018 May [cited 2025 Aug 13]. https:\/\/baoilleach.blogspot.com\/2018\/05\/when-all-you-want-is-ring-part-ii.html"},{"key":"1186_CR33","doi-asserted-by":"publisher","first-page":"5620","DOI":"10.1021\/acs.jmedchem.5b00742","volume":"58","author":"MA Letavic","year":"2015","unstructured":"Letavic MA, Bonaventure P, Carruthers NI, Dugovic C, Koudriakova T, Lord B et al (2015) Novel octahydropyrrolo[3,4-c]pyrroles are selective orexin-2 antagonists: SAR leading to a clinical candidate. J Med Chem 58:5620\u20135636","journal-title":"J Med Chem"},{"key":"1186_CR34","doi-asserted-by":"publisher","first-page":"1528","DOI":"10.1021\/acs.jmedchem.9b01787","volume":"63","author":"M Rappas","year":"2020","unstructured":"Rappas M, Ali AAE, Bennett KA, Brown JD, Bucknell SJ, Congreve M et al (2020) Comparison of orexin 1 and orexin 2 ligand binding modes using X-ray crystallography and computational analysis. J Med Chem 63:1528\u20131543","journal-title":"J Med Chem"},{"key":"1186_CR35","unstructured":"Chai W, Letavic MA, Ly KS, Pippel DJ, Rudolph DA, Sappey KC et al (2021) Disubstituted octahydropyrrolo[3,4-c]pyrroles as orexin receptor modulators. United States patent US 11059828 B2"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-026-01186-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-026-01186-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-026-01186-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T20:53:21Z","timestamp":1777409601000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13321-026-01186-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,15]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1186"],"URL":"https:\/\/doi.org\/10.1186\/s13321-026-01186-6","relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv-2025-9c1v6","asserted-by":"object"}]},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,15]]},"assertion":[{"value":"23 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"J.T., N.O. and C.D.G. are employees of, or have previously been employed by, Nxera Pharma Co., Ltd. (also known as Nxera Pharma Corporation). C.D.G\u00a0is currently employed by Structure Therapeutics. W.D. receives research funding from Nxera Pharma Co., Ltd.. All other authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"53"}}