{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T17:20:39Z","timestamp":1785864039250,"version":"3.56.0"},"reference-count":42,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:00:00Z","timestamp":1758672000000},"content-version":"vor","delay-in-days":24,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Iktos"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,31]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In the present work, two reaction-based generative models for molecular design are presented: growing optimizer and linking optimizer. These models are designed to emulate real-life chemical synthesis by sequentially selecting building blocks and simulating the reactions between them to form new compounds. By focusing on the feasibility of the generated molecules, growing optimizer and linking optimizer offer several advantages, including the ability to restrict chemistry to specific building blocks, reaction types, and synthesis pathways, a crucial requirement in drug design. Unlike text-based models, which construct molecules by iteratively forming a textual representation of the molecular structure, and graph-based models, which assemble molecules atom by atom or fragment by fragment, our approach incorporates a more comprehensive understanding of chemical knowledge, making it relevant for drug discovery projects. Comparative analysis with REINVENT 4, a state-of-the-art molecular generative model, shows that growing optimizer and linking optimizer are more likely to produce synthetically accessible molecules while reaching molecules of interest with the desired properties.<\/jats:p>","DOI":"10.1093\/bib\/bbaf482","type":"journal-article","created":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T11:41:14Z","timestamp":1756467674000},"source":"Crossref","is-referenced-by-count":8,"title":["Growing and linking optimizers: synthesis-driven molecule design"],"prefix":"10.1093","volume":"26","author":[{"given":"Clarisse","family":"Descamps","sequence":"first","affiliation":[{"name":"Iktos , 65 Rue de Prony, 75017 Paris, \u00cele-de-France,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vincent","family":"Bouttier","sequence":"additional","affiliation":[{"name":"Iktos , 65 Rue de Prony, 75017 Paris, \u00cele-de-France,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Sanz Garc\u00eda","sequence":"additional","affiliation":[{"name":"Iktos , 65 Rue de Prony, 75017 Paris, \u00cele-de-France,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maoussi","family":"Lhuillier-Akakpo","sequence":"additional","affiliation":[{"name":"Iktos , 65 Rue de Prony, 75017 Paris, \u00cele-de-France,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quentin","family":"Perron","sequence":"additional","affiliation":[{"name":"Iktos , 65 Rue de Prony, 75017 Paris, \u00cele-de-France,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamza","family":"Tajmouati","sequence":"additional","affiliation":[{"name":"Iktos , 65 Rue de Prony, 75017 Paris, \u00cele-de-France,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,9,24]]},"reference":[{"key":"2025092410471497600_ref1","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/nrd3078","article-title":"How to improve R&D productivity: the pharmaceutical industry\u2019s grand challenge","volume":"9","author":"Paul","year":"2010","journal-title":"Nat Rev Drug Discov"},{"key":"2025092410471497600_ref2","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.2174\/1381612829666230412084137","article-title":"A review on deep learning-driven drug discovery: strategies, tools and applications","volume":"29","author":"Sumathi","year":"2023","journal-title":"Curr Pharm Des"},{"key":"2025092410471497600_ref3","doi-asserted-by":"publisher","first-page":"102658.","DOI":"10.1016\/j.sbi.2023.102658","article-title":"Fake it until you make it? Generative de novo design and virtual screening of synthesizable molecules","volume":"82","author":"Stanley","year":"2023","journal-title":"Curr Opin Struct Biol"},{"key":"2025092410471497600_ref4","doi-asserted-by":"publisher","first-page":"e427","DOI":"10.1016\/j.ddtec.2013.02.001","article-title":"Multi-objective optimization methods in drug design","volume":"10","author":"Nicolaou","year":"2013","journal-title":"Drug Discov Today Technol"},{"key":"2025092410471497600_ref5","doi-asserted-by":"publisher","first-page":"1239","DOI":"10.1111\/j.1476-5381.2010.01127.x","article-title":"Principles of early drug discovery","volume":"162","author":"Hughes","year":"2011","journal-title":"Br J Pharmacol"},{"key":"2025092410471497600_ref6","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s13321-024-00812-5","article-title":"Reinvent 4: modern AI\u2013driven generative molecule design","volume":"16","author":"Loeffler","year":"2024","journal-title":"J Chem"},{"key":"2025092410471497600_ref7","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules","volume":"28","author":"Weininger","year":"1988","journal-title":"J Chem Inf Comput Sci"},{"key":"2025092410471497600_ref8","article-title":"Automatic chemical design using a data-driven continuous representation of molecules","volume-title":"CoRR","author":"G\u00f3mez-Bombarelli","year":"2016."},{"key":"2025092410471497600_ref9","article-title":"Generating sequences with recurrent neural networks","volume-title":"CoRR","author":"Graves","year":"2013."},{"key":"2025092410471497600_ref10","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1021\/acscentsci.7b00512","article-title":"Generating focused molecule libraries for drug discovery with recurrent neural networks","volume":"4","author":"Segler","year":"2018","journal-title":"ACS Central Sci"},{"key":"2025092410471497600_ref11","volume-title":"PrefixMol: Target- and Chemistry-Aware Molecule Design Via Prefix Embedding","author":"Gao","year":"2023"},{"key":"2025092410471497600_ref12","article-title":"Learning deep generative models of graphs","volume-title":"CoRR","author":"Li","year":"2018"},{"key":"2025092410471497600_ref13","doi-asserted-by":"crossref","DOI":"10.1186\/s13321-018-0287-6","volume-title":"Multi-Objective De Novo Drug Design with Conditional Graph Generative Model","author":"Li","year":"2018"},{"key":"2025092410471497600_ref14","volume-title":"A Deep Generative Model for Fragment-Based Molecule Generation","author":"Podda","year":"2020"},{"key":"2025092410471497600_ref15","volume-title":"Hit and Lead Discovery with Explorative RL and Fragment-Based Molecule Generation","year":"2021"},{"key":"2025092410471497600_ref16","doi-asserted-by":"publisher","first-page":"5714","DOI":"10.1021\/acs.jcim.0c00174","article-title":"The synthesizability of molecules proposed by generative models","volume":"60","author":"Gao","year":"2020","journal-title":"J Chem Inf Model"},{"key":"2025092410471497600_ref17","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/1758-2946-1-8","article-title":"Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions","volume":"1","author":"Ertl","year":"2009","journal-title":"J Chem"},{"key":"2025092410471497600_ref18","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1021\/acs.jcim.7b00622","article-title":"SCScore: synthetic complexity learned from a reaction corpus","volume":"58","author":"Coley","year":"2018","journal-title":"J Chem Inf Model"},{"key":"2025092410471497600_ref19","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1186\/s13321-023-00742-8","article-title":"Integrating synthetic accessibility with AI-based generative drug design","volume":"15","author":"Parrot","year":"2023","journal-title":"J Chem"},{"key":"2025092410471497600_ref20","article-title":"Barking up the right tree: an approach to search over molecule synthesis DAGs","author":"Bradshaw","year":"2020","journal-title":"arXiv NeurIPS"},{"key":"2025092410471497600_ref21","volume-title":"SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraints","year":"2024"},{"key":"2025092410471497600_ref22","volume-title":"RGFN: Synthesizable Molecular Generation Using GFlowNets","author":"Koziarski","year":"2024"},{"key":"2025092410471497600_ref23","volume-title":"Generative Flows on Synthetic Pathway for Drug Design","author":"Seo","year":"2024"},{"key":"2025092410471497600_ref24","volume-title":"Smarts","author":"Inc. Daylight Chemical Information Systems"},{"key":"2025092410471497600_ref25","doi-asserted-by":"publisher","first-page":"1572","DOI":"10.1021\/acscentsci.9b00576","article-title":"Molecular transformer: a model for uncertainty-calibrated chemical reaction prediction","volume":"5","author":"Schwaller","year":"2019","journal-title":"ACS Central Sci"},{"key":"2025092410471497600_ref26","volume-title":"REAL Space Navigator.","author":"Ltd","year":"2025"},{"key":"2025092410471497600_ref27","article-title":"Spaya retrosynthesis tool.","author":"Iktos"},{"key":"2025092410471497600_ref28","volume-title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","author":"Cho","year":"2014"},{"key":"2025092410471497600_ref29","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"2025092410471497600_ref30","article-title":"Neural-symbolic machine learning for retrosynthesis and reaction prediction","volume":"23","author":"Segler","year":"2017","journal-title":"Chemistry (Weinheim an der Bergstrasse, Germany)"},{"key":"2025092410471497600_ref31","volume-title":"Pistachio.","author":"NextMove Software"},{"key":"2025092410471497600_ref32","volume-title":"ChEMBL","author":"ChEMBL"},{"key":"2025092410471497600_ref33","volume-title":"Exploring Deep Recurrent Models with Reinforcement Learning for Molecule Design","author":"Neil","year":"2018"},{"key":"2025092410471497600_ref34","volume-title":"Understanding the Impact of Entropy on Policy Optimization","author":"Ahmed","year":"2019"},{"key":"2025092410471497600_ref35","article-title":"Differentiable scaffolding tree for molecule optimization","volume-title":"International Conference on Learning Representations","year":"2022."},{"key":"2025092410471497600_ref36","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1021\/acs.jcim.8b00839","article-title":"GuacaMol: benchmarking models for de novo molecular design","volume":"59","author":"Brown","year":"2019","journal-title":"J Chem Inf Model"},{"key":"2025092410471497600_ref37","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1186\/s13321-020-00472-1","article-title":"AiZynthFinder: a fast, robust and flexible open-source software for retrosynthetic planning","volume":"12","author":"Genheden","year":"2020","journal-title":"J Chem"},{"key":"2025092410471497600_ref38","volume-title":"Sample Efficiency Matters: A Benchmark for Practical Molecular Optimization","author":"Gao","year":"2022"},{"key":"2025092410471497600_ref39","doi-asserted-by":"publisher","first-page":"3238","DOI":"10.1021\/acs.jcim.2c01355","article-title":"Generative models should at least be able to design molecules that dock well: a new benchmark","volume":"63","author":"Ciepli\u0144ski","year":"2023","journal-title":"J Chem Inf Model"},{"key":"2025092410471497600_ref40","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-connectivity fingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J Chem Inf Model"},{"key":"2025092410471497600_ref41","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1038\/nchem.1243","article-title":"Quantifying the chemical beauty of drugs","volume":"4","author":"Bickerton","year":"2012","journal-title":"Nat Chem"},{"key":"2025092410471497600_ref42","doi-asserted-by":"publisher","volume-title":"ChemRxiv","author":"Medcalf","DOI":"10.26434\/chemrxiv-2024-0z7g6-v2"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/5\/bbaf482\/64373017\/bbaf482.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/5\/bbaf482\/64373017\/bbaf482.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T14:47:30Z","timestamp":1758725250000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf482\/8262889"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,31]]},"references-count":42,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,8,31]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf482","relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv-2025-64bhb","asserted-by":"object"},{"id-type":"doi","id":"10.26434\/chemrxiv-2025-64bhb-v2","asserted-by":"object"}]},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,9]]},"published":{"date-parts":[[2025,8,31]]},"article-number":"bbaf482"}}