{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T10:50:04Z","timestamp":1782298204558,"version":"3.54.5"},"reference-count":78,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T00:00:00Z","timestamp":1780099200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T00:00:00Z","timestamp":1782259200000},"content-version":"vor","delay-in-days":25,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Structure-based drug discovery (SBDD) aims to identify novel molecules that bind to therapeutic protein targets. The vast chemical space and limitations of traditional approaches make this task challenging. Recent advances in AI-generative models, such as flow matching, can produce novel, pocket-conditioned molecular structures directly in three-dimensional space. However, most pocket conditioned models in the literature are trained on structures derived from the Protein Data Bank (PDB), which contains structures with varying quality and inconsistent annotation. Moreover, the PDB is enriched with cofactors and natural products, thereby poorly representing real world SBDD scenarios. The relatively limited number of ligand series within the same pockets also hinder the model\u2019s ability to learn protein-ligand interactions effectively. Here for the first time we report the results of training pocket-conditioned generative models on internal crystallography data from a large pharmaceutical company. We also investigate other key determinants of model performance, such as inclusion of hydrogens and pretraining on unconditional data. We evaluate how each factor affects the generative quality of the ligands across the diverse training settings. Our results provide practical guidelines for the development of more effective 3D generative models for SBDD and highlight key directions for future research toward reliable, pocket-aware molecular design. \u00a0<\/jats:p>","DOI":"10.1186\/s13321-026-01230-5","type":"journal-article","created":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T15:03:04Z","timestamp":1780153384000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Assessing the factors influencing the quality of pocket-conditioned 3D generative models"],"prefix":"10.1186","volume":"18","author":[{"given":"Kunyu","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helen","family":"Lai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ross","family":"Irwin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jon Paul","family":"Janet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro","family":"Tibo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,30]]},"reference":[{"key":"1230_CR1","unstructured":"Adams K, Abeywardane K, Fromer J, Coley CW (2025) ShEPhERD: Diffusing shape, electrostatics, and pharmacophores for bioisosteric drug design. http:\/\/arxiv.org\/abs\/2411.04130"},{"key":"1230_CR2","unstructured":"Albergo MS, Vanden-Eijnden E (2023) Building normalizing flows with stochastic interpolants. arXiv:2209.15571"},{"issue":"9","key":"1230_CR3","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1016\/j.chembiol.2003.09.002","volume":"10","author":"AC Anderson","year":"2003","unstructured":"Anderson AC (2003) The process of structure-based drug design. Chem Biol 10(9):787\u2013797. https:\/\/doi.org\/10.1016\/j.chembiol.2003.09.002","journal-title":"Chem Biol"},{"issue":"1","key":"1230_CR4","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-019-0341-z","volume":"11","author":"J Ar\u00fas-Pous","year":"2019","unstructured":"Ar\u00fas-Pous J, Blaschke T, Ulander S et al (2019) Exploring the GDB-13 chemical space using deep generative models. J Cheminform 11(1):20. https:\/\/doi.org\/10.1186\/s13321-019-0341-z","journal-title":"J Cheminform"},{"issue":"1","key":"1230_CR5","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1038\/s41597-022-01288-4","volume":"9","author":"S Axelrod","year":"2022","unstructured":"Axelrod S, G\u00f3mez-Bombarelli R (2022) Geom, energy-annotated molecular conformations for property prediction and molecular generation. Sci Data 9(1):185. https:\/\/doi.org\/10.1038\/s41597-022-01288-4","journal-title":"Sci Data"},{"key":"1230_CR6","unstructured":"Baillif B, Cole J, McCabe P et\u00a0al (2024a) Benchmarking structure-based three-dimensional molecular generative models using GenBench3D: Ligand conformation quality matters. arXiv:2407.04424"},{"key":"1230_CR7","unstructured":"Baillif B, Cole J, McCabe P et\u00a0al (2024b) Benchmarking structure-based three-dimensional molecular generative models using genbench3d: ligand conformation quality matters. arXiv:2407.04424"},{"issue":"2","key":"1230_CR8","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1038\/nchem.1243","volume":"4","author":"GR Bickerton","year":"2012","unstructured":"Bickerton GR, Paolini GV, Besnard J et al (2012) Quantifying the chemical beauty of drugs. Nat Chem 4(2):90\u201398. https:\/\/doi.org\/10.1038\/nchem.1243","journal-title":"Nat Chem"},{"issue":"1","key":"1230_CR9","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1002\/(SICI)1098-1128(199601)16:1<3::AID-MED1>3.0.CO;2-6","volume":"16","author":"RS Bohacek","year":"1996","unstructured":"Bohacek RS, McMartin C, Guida WC (1996) The art and practice of structure-based drug design: a molecular modeling perspective. Med Res Rev 16(1):3\u201350","journal-title":"Med Res Rev"},{"key":"1230_CR10","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-021-00548-6","author":"C Bouysset","year":"2021","unstructured":"Bouysset C, Fiorucci S (2021) ProLIF: a library to encode molecular interactions as fingerprints. J Cheminform. https:\/\/doi.org\/10.1186\/s13321-021-00548-6","journal-title":"J Cheminform"},{"key":"1230_CR11","doi-asserted-by":"publisher","DOI":"10.1039\/D3SC04185A","author":"M Buttenschoen","year":"2024","unstructured":"Buttenschoen M, Morris GM, Deane CM (2024) Posebusters: AI-based docking methods fail to generate physically valid poses or generalise to novel sequences. Chem Sci. https:\/\/doi.org\/10.1039\/D3SC04185A","journal-title":"Chem Sci"},{"issue":"4","key":"1230_CR12","doi-asserted-by":"publisher","first-page":"1449","DOI":"10.1039\/D3SC05552C","volume":"15","author":"H Cai","year":"2024","unstructured":"Cai H, Shen C, Jian T et al (2024) CarsiDock: a deep learning paradigm for accurate protein-ligand docking and screening based on large-scale pre-training. Chem Sci 15(4):1449\u20131471. https:\/\/doi.org\/10.1039\/D3SC05552C","journal-title":"Chem Sci"},{"key":"1230_CR13","doi-asserted-by":"publisher","first-page":"28266","DOI":"10.52202\/068431-2049","volume":"35","author":"A Campbell","year":"2022","unstructured":"Campbell A, Benton J, De Bortoli V et al (2022) A continuous time framework for discrete denoising models. Adv Neural Inf Process Syst 35:28266\u201328279","journal-title":"Adv Neural Inf Process Syst"},{"key":"1230_CR14","unstructured":"Campbell A, Yim J, Barzilay R et al (2024) Generative flows on discrete state-spaces: Enabling multimodal flows with applications to protein co-design. arXiv:2402.04997"},{"key":"1230_CR15","unstructured":"Chen RT, Rubanova Y, Bettencourt J (2018) Neural ordinary differential equations. Advances in neural information processing systems. p 31"},{"key":"1230_CR16","unstructured":"Corso G, St\u00e4rk H, Jing B (2023) DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking. arXiv:2210.01776"},{"key":"1230_CR17","doi-asserted-by":"crossref","unstructured":"Cremer J, Le T, No\u00e9 F (2024) Pilot: equivariant diffusion for pocket conditioned de novo ligand generation with multi-objective guidance via importance sampling. arXiv preprint arXiv:2405.14925","DOI":"10.1039\/D4SC03523B"},{"key":"1230_CR18","doi-asserted-by":"crossref","unstructured":"Cremer J, Irwin R, Tibo A (2025) Flowr: flow matching for structure-aware de novo, interaction-and fragment-based ligand generation. arXiv preprint arXiv:2504.10564","DOI":"10.1038\/s43588-026-00998-8"},{"issue":"9","key":"1230_CR19","doi-asserted-by":"publisher","first-page":"4035","DOI":"10.1021\/acs.jmedchem.5b01684","volume":"59","author":"M De Vivo","year":"2016","unstructured":"De Vivo M, Masetti M, Bottegoni G et al (2016) Role of molecular dynamics and related methods in drug discovery. J Med Chem 59(9):4035\u20134061. https:\/\/doi.org\/10.1021\/acs.jmedchem.5b01684","journal-title":"J Med Chem"},{"key":"1230_CR20","unstructured":"Dunn I, Koes DR (2024) Mixed continuous and categorical flow matching for 3d de novo molecule generation. arXiv:2404.19739"},{"key":"1230_CR21","doi-asserted-by":"publisher","DOI":"10.1101\/2024.07.17.603955","author":"J Durairaj","year":"2024","unstructured":"Durairaj J, Adeshina Y, Cao Z et al (2024) Plinder: the protein-ligand interactions dataset and evaluation resource. bioRxiv. https:\/\/doi.org\/10.1101\/2024.07.17.603955","journal-title":"bioRxiv"},{"issue":"1","key":"1230_CR22","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1038\/s42256-023-00775-6","volume":"6","author":"W Feng","year":"2024","unstructured":"Feng W, Wang L, Lin Z et al (2024) Generation of 3d molecules in pockets via a language model. Nat Mach Intell 6(1):62\u201373","journal-title":"Nat Mach Intell"},{"issue":"15","key":"1230_CR23","doi-asserted-by":"publisher","first-page":"3486","DOI":"10.1021\/acs.jcim.1c01334","volume":"62","author":"M Garc\u00eda-Orteg\u00f3n","year":"2022","unstructured":"Garc\u00eda-Orteg\u00f3n M, Simm GNC, Tripp AJ et al (2022) DOCKSTRING: easy molecular docking yields better benchmarks for ligand design. J Chem Inf Model 62(15):3486\u20133502. https:\/\/doi.org\/10.1021\/acs.jcim.1c01334","journal-title":"J Chem Inf Model"},{"key":"1230_CR24","doi-asserted-by":"crossref","unstructured":"Gat I, Remez T, Shaul N (2024) Discrete flow matching. arXiv preprint arXiv:2407.15595","DOI":"10.52202\/079017-4239"},{"issue":"1","key":"1230_CR25","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-020-00472-1","volume":"12","author":"S Genheden","year":"2020","unstructured":"Genheden S, Thakkar A, Chadimov\u00e1 V et al (2020) Aizynthfinder: a fast, robust and flexible open-source software for retrosynthetic planning. J Cheminform 12(1):70","journal-title":"J Cheminform"},{"issue":"1","key":"1230_CR26","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1021\/cc9800071","volume":"1","author":"AK Ghose","year":"1999","unstructured":"Ghose AK, Viswanadhan VN, Wendoloski JJ (1999) A knowledge-based approach in designing combinatorial or medicinal chemistry libraries for drug discovery. 1. A qualitative and quantitative characterization of known drug databases. J Comb Chem 1(1):55\u201368. https:\/\/doi.org\/10.1021\/cc9800071","journal-title":"J Comb Chem"},{"issue":"11","key":"1230_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2020.101681","volume":"23","author":"OO Grygorenko","year":"2020","unstructured":"Grygorenko OO, Radchenko DS, Dziuba I et al (2020) Generating multibillion chemical space of readily accessible screening compounds. iScience 23(11):101681. https:\/\/doi.org\/10.1016\/j.isci.2020.101681","journal-title":"iScience"},{"key":"1230_CR28","unstructured":"Guan J, Qian WW, Peng X et al (2023) 3d equivariant diffusion for target-aware molecule generation and affinity prediction. arXiv:2303.03543"},{"issue":"1","key":"1230_CR29","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-021-00563-7","volume":"13","author":"J Guo","year":"2021","unstructured":"Guo J, Janet JP, Bauer MR et al (2021) DockStream: a docking wrapper to enhance de novo molecular design. J Cheminform 13(1):89. https:\/\/doi.org\/10.1186\/s13321-021-00563-7","journal-title":"J Cheminform"},{"issue":"7","key":"1230_CR30","doi-asserted-by":"publisher","first-page":"1750","DOI":"10.1021\/jm030644s","volume":"47","author":"TA Halgren","year":"2004","unstructured":"Halgren TA, Murphy RB, Friesner RA et al (2004) Glide: a new approach for rapid, accurate docking and scoring. 2. Enrichment factors in database screening. J Med Chem 47(7):1750\u20131759. https:\/\/doi.org\/10.1021\/jm030644s","journal-title":"J Med Chem"},{"key":"1230_CR31","unstructured":"Harris C, Didi K, Jamasb AR et\u00a0al (2023) Benchmarking generated poses: How rational is structure-based drug design with generative models? arXiv preprint arXiv:2308.07413"},{"key":"1230_CR32","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho J, Jain A, Abbeel P (2020) Denoising diffusion probabilistic models. Adv Neural Inf Process Syst 33:6840\u20136851","journal-title":"Adv Neural Inf Process Syst"},{"key":"1230_CR33","unstructured":"Hoogeboom E, Satorras VG, Vignac C (2022) Equivariant diffusion for molecule generation in 3d. International conference on machine learning. PMLR, p 8867\u20138887"},{"issue":"1","key":"1230_CR34","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-63245-0","volume":"16","author":"Q Hu","year":"2025","unstructured":"Hu Q, Sun C, He H et al (2025) Target-aware 3D molecular generation based on guided equivariant diffusion. Nat Commun 16(1):7928. https:\/\/doi.org\/10.1038\/s41467-025-63245-0","journal-title":"Nat Commun"},{"issue":"1","key":"1230_CR35","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-46569-1","volume":"15","author":"L Huang","year":"2024","unstructured":"Huang L, Xu T, Yu Y et al (2024) A dual diffusion model enables 3D molecule generation and lead optimization based on target pockets. Nat Commun 15(1):2657. https:\/\/doi.org\/10.1038\/s41467-024-46569-1","journal-title":"Nat Commun"},{"key":"1230_CR36","unstructured":"Irwin R, Tibo A, Janet JP (2025) Semlaflow-efficient 3d molecular generation with latent attention and equivariant flow matching. International Conference on Artificial Intelligence and Statistics. PMLR, p 3772\u20133780"},{"issue":"1","key":"1230_CR37","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-78537-2","volume":"10","author":"W Jeon","year":"2020","unstructured":"Jeon W, Kim D (2020) Autonomous molecule generation using reinforcement learning and docking to develop potential novel inhibitors. Sci Rep 10(1):22104. https:\/\/doi.org\/10.1038\/s41598-020-78537-2","journal-title":"Sci Rep"},{"issue":"7873","key":"1230_CR38","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","volume":"596","author":"J Jumper","year":"2021","unstructured":"Jumper J, Evans R, Pritzel A (2021) Highly accurate protein structure prediction with alphafold. Nature 596(7873):583\u2013589","journal-title":"Nature"},{"issue":"D1","key":"1230_CR39","doi-asserted-by":"publisher","first-page":"D1388","DOI":"10.1093\/nar\/gkaa971","volume":"49","author":"S Kim","year":"2021","unstructured":"Kim S, Chen J, Cheng T et al (2021) PubChem in 2021: new data content and improved web interfaces. Nucleic Acids Res 49(D1):D1388\u2013D1395. https:\/\/doi.org\/10.1093\/nar\/gkaa971","journal-title":"Nucleic Acids Res"},{"issue":"13","key":"1230_CR40","doi-asserted-by":"publisher","first-page":"6644","DOI":"10.1021\/acs.jcim.5c00665","volume":"65","author":"Z Koczor-Benda","year":"2025","unstructured":"Koczor-Benda Z, Gilkes J, Bartucca F et al (2025) Structural bias in three-dimensional autoregressive generative machine learning of organic molecules. J Chem Inf Model 65(13):6644\u20136654. https:\/\/doi.org\/10.1021\/acs.jcim.5c00665","journal-title":"J Chem Inf Model"},{"key":"1230_CR41","unstructured":"Le T, Cremer J, No\u00e9 F (2023) Navigating the design space of equivariant diffusion-based generative models for de novo 3d molecule generation. arXiv"},{"issue":"35","key":"1230_CR42","doi-asserted-by":"publisher","first-page":"e02702","DOI":"10.1002\/advs.202502702","volume":"12","author":"J Lee","year":"2025","unstructured":"Lee J, Zhung W, Seo J et al (2025) Bind: bond and interaction-generating diffusion model for multi-objective structure-based drug design. Adv Sci 12(35):e02702","journal-title":"Adv Sci"},{"key":"1230_CR43","unstructured":"Lipman Y, Chen R, Ben-Hamu H (2023) Flow matching for generative modeling. arXiv"},{"issue":"24","key":"1230_CR44","doi-asserted-by":"publisher","first-page":"9260","DOI":"10.1021\/acs.jcim.4c01598","volume":"64","author":"H Liu","year":"2024","unstructured":"Liu H, Qin Y, Niu Z et al (2024) How good are current pocket-based 3D generative models?: The benchmark set and evaluation of protein pocket-based 3D molecular generative models. J Chem Inf Model 64(24):9260\u20139275. https:\/\/doi.org\/10.1021\/acs.jcim.4c01598","journal-title":"J Chem Inf Model"},{"key":"1230_CR45","unstructured":"Liu M, Luo Y, Uchino K (2022) Generating 3d molecules for target protein binding. International Conference on Machine Learning. PMLR, p 13912\u201313924"},{"key":"1230_CR46","unstructured":"Liu X, Gong C, Qiang L (2023) Flow straight and fast: Learning to generate and transfer data with rectified flow. arXiv:2209.03003"},{"issue":"3","key":"1230_CR47","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1093\/bioinformatics\/btu626","volume":"31","author":"Z Liu","year":"2015","unstructured":"Liu Z, Li Y, Han L et al (2015) PDB-wide collection of binding data: current status of the PDBbind database. Bioinformatics 31(3):405\u2013412. https:\/\/doi.org\/10.1093\/bioinformatics\/btu626","journal-title":"Bioinformatics"},{"issue":"1","key":"1230_CR48","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 et al (2024) Reinvent 4: modern AI-driven generative molecule design. J Cheminform 16(1):20. https:\/\/doi.org\/10.1186\/s13321-024-00812-5","journal-title":"J Cheminform"},{"key":"1230_CR49","unstructured":"Luo S, Guan J, Ma J (2021) A 3d generative model for structure-based drug design. Advances in Neural Information Processing Systems. p 6229\u20136239"},{"issue":"7743","key":"1230_CR50","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1038\/s41586-019-0917-9","volume":"566","author":"J Lyu","year":"2019","unstructured":"Lyu J, Wang S, Balius TE et al (2019) Ultra-large library docking for discovering new chemotypes. Nature 566(7743):224\u2013229. https:\/\/doi.org\/10.1038\/s41586-019-0917-9","journal-title":"Nature"},{"issue":"1","key":"1230_CR51","doi-asserted-by":"publisher","first-page":"6398","DOI":"10.1038\/s41598-017-04905-0","volume":"7","author":"P Matricon","year":"2017","unstructured":"Matricon P, Ranganathan A, Warnick E et al (2017) Fragment optimization for GPCRs by molecular dynamics free energy calculations: probing druggable subpockets of the A 2A adenosine receptor binding site. Sci Rep 7(1):6398. https:\/\/doi.org\/10.1038\/s41598-017-04905-0","journal-title":"Sci Rep"},{"key":"1230_CR52","doi-asserted-by":"publisher","unstructured":"McInnes L, Healy J, Melville J (2020) UMAP: uniform manifold approximation and projection for dimension reduction. arXiv. https:\/\/doi.org\/10.48550\/arXiv.1802.03426","DOI":"10.48550\/arXiv.1802.03426"},{"key":"1230_CR53","doi-asserted-by":"publisher","DOI":"10.1101\/2025.06.14.659707","author":"S Passaro","year":"2025","unstructured":"Passaro S, Corso G, Wohlwend J et al (2025) Boltz-2: towards accurate and efficient binding affinity prediction. bioRxiv. https:\/\/doi.org\/10.1101\/2025.06.14.659707","journal-title":"bioRxiv"},{"key":"1230_CR54","unstructured":"Peng X, Luo S, Guan J et al (2022) Pocket2Mol: Efficient molecular sampling based on 3D protein pockets. In: Proceedings of the 39th International Conference on Machine Learning, Proceedings of Machine Learning Research, vol 162. PMLR, p 17644\u201317655, arXiv:2205.07249"},{"key":"1230_CR55","unstructured":"Qu Y, Qiu K, Song Y (2024) Molcraft: Structure-based drug design in continuous parameter space. arxiv:2404.12141"},{"issue":"9","key":"1230_CR56","doi-asserted-by":"publisher","first-page":"2701","DOI":"10.1039\/D1SC05976A","volume":"13","author":"M Ragoza","year":"2022","unstructured":"Ragoza M, Masuda T, Koes DR (2022) Generating 3D molecules conditional on receptor binding sites with deep generative models. Chem Sci 13(9):2701\u20132713. https:\/\/doi.org\/10.1039\/D1SC05976A","journal-title":"Chem Sci"},{"key":"1230_CR57","unstructured":"Rekesh A, Cretu M, Shevchuk D (2025) Syncogen: Synthesizable 3d molecule generation via joint reaction and coordinate modeling. arXiv preprint arXiv:2507.11818"},{"key":"1230_CR58","doi-asserted-by":"publisher","DOI":"10.64898\/2025.12.09.693161","author":"UF R\u00f6hrig","year":"2025","unstructured":"R\u00f6hrig UF, Mathieu-Bugnon M, Zoete V (2025) Comparative assessment of the utility of co-folding and docking for small-molecule drug design. bioRxiv. https:\/\/doi.org\/10.64898\/2025.12.09.693161","journal-title":"bioRxiv"},{"issue":"15","key":"1230_CR59","doi-asserted-by":"publisher","first-page":"8006","DOI":"10.1021\/acs.jcim.5c01020","volume":"65","author":"N Sanjrani","year":"2025","unstructured":"Sanjrani N, Coupry DE, Pog\u00e1ny P et al (2025) Benchmarking 3D structure-based molecule generators. J Chem Inf Model 65(15):8006\u20138021. https:\/\/doi.org\/10.1021\/acs.jcim.5c01020","journal-title":"J Chem Inf Model"},{"key":"1230_CR60","unstructured":"Schneuing A, Du Y, Harris C (2023) Structure-based drug design with equivariant diffusion models. arXiv:2210.13695"},{"key":"1230_CR61","unstructured":"Schneuing A, Igashov I, Dobbelstein AW et al (2025) Multi-domain distribution learning for de novo drug design. arXiv:2508.17815"},{"key":"1230_CR62","volume-title":"Schr\u00f6dinger release 2025\u20132: maestro","author":"Schr\u00f6dinger LLC","year":"2025","unstructured":"Schr\u00f6dinger LLC (2025) Schr\u00f6dinger release 2025\u20132: maestro. Schr\u00f6dinger, LLC, New York"},{"key":"1230_CR63","unstructured":"Shen T, Seo S, Irwin R (2025) Compositional flows for 3d molecule and synthesis pathway co-design In: Forty-second International Conference on Machine Learning"},{"key":"1230_CR64","doi-asserted-by":"publisher","DOI":"10.1101\/2025.02.03.636309","author":"P \u0160krinjar","year":"2025","unstructured":"\u0160krinjar P, Eberhardt J, Durairaj J (2025) Have protein-ligand co-folding methods moved beyond memorisation? bioRxiv. https:\/\/doi.org\/10.1101\/2025.02.03.636309","journal-title":"bioRxiv"},{"key":"1230_CR65","unstructured":"Sohl-Dickstein J, Weiss E, Maheswaranathan N (2015) Deep unsupervised learning using nonequilibrium thermodynamics. International conference on machine learning. PMLR, p 2256\u20132265"},{"issue":"23","key":"1230_CR66","doi-asserted-by":"publisher","first-page":"12752","DOI":"10.1021\/acs.jcim.5c02053","volume":"65","author":"M Thomas","year":"2025","unstructured":"Thomas M, Bou A, G\u00f3mez-Tamayo JC et al (2025) Reinforce-ing chemical language models for drug discovery. J Chem Inf Model 65(23):12752\u201312763. https:\/\/doi.org\/10.1021\/acs.jcim.5c02053","journal-title":"J Chem Inf Model"},{"issue":"4","key":"1230_CR67","doi-asserted-by":"publisher","first-page":"1166","DOI":"10.1021\/acs.jcim.2c01253","volume":"63","author":"BI Tingle","year":"2023","unstructured":"Tingle BI, Tang KG, Castanon M et al (2023) ZINC-22-A free multi-billion-scale database of tangible compounds for ligand discovery. J Chem Inf Model 63(4):1166\u20131176. https:\/\/doi.org\/10.1021\/acs.jcim.2c01253","journal-title":"J Chem Inf Model"},{"issue":"2","key":"1230_CR68","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1002\/jcc.21334","volume":"31","author":"O Trott","year":"2010","unstructured":"Trott O, Olson AJ (2010) AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading. J Comput Chem 31(2):455\u2013461. https:\/\/doi.org\/10.1002\/jcc.21334","journal-title":"J Comput Chem"},{"key":"1230_CR69","doi-asserted-by":"publisher","unstructured":"Vignac C, Osman N, Toni L et\u00a0al (2023) Midi: Mixed graph and 3d denoising diffusion for molecule generation. In: Machine Learning and Knowledge Discovery in Databases: Research Track - European Conference, ECML PKDD 2023, Turin, Italy, September 18-22, 2023, Proceedings, Part II, Lecture Notes in Computer Science, vol 14170. Springer, p 560\u2013576, https:\/\/doi.org\/10.1007\/978-3-031-43415-0_33","DOI":"10.1007\/978-3-031-43415-0_33"},{"issue":"7","key":"1230_CR70","doi-asserted-by":"publisher","first-page":"2695","DOI":"10.1021\/ja512751q","volume":"137","author":"L Wang","year":"2015","unstructured":"Wang L, Wu Y, Deng Y et al (2015) Accurate and reliable prediction of relative ligand binding potency in prospective drug discovery by way of a modern free-energy calculation protocol and force field. J Am Chem Soc 137(7):2695\u20132703. https:\/\/doi.org\/10.1021\/ja512751q","journal-title":"J Am Chem Soc"},{"issue":"12","key":"1230_CR71","doi-asserted-by":"publisher","first-page":"4111","DOI":"10.1021\/jm048957q","volume":"48","author":"R Wang","year":"2005","unstructured":"Wang R, Fang X, Lu Y et al (2005) The PDBbind database: methodologies and updates. J Med Chem 48(12):4111\u20134119","journal-title":"J Med Chem"},{"issue":"1","key":"1230_CR72","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad451","volume":"25","author":"J Yan","year":"2024","unstructured":"Yan J, Ye Z, Yang Z et al (2024) Multi-task bioassay pre-training for protein-ligand binding affinity prediction. Brief Bioinform 25(1):bbad451. https:\/\/doi.org\/10.1093\/bib\/bbad451","journal-title":"Brief Bioinform"},{"key":"1230_CR73","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.5c01706","author":"B Yang","year":"2025","unstructured":"Yang B, Xiang C, Li T et al (2025) Structure-based generation of 3D small-molecule drugs: are we there yet? J Med Chem. https:\/\/doi.org\/10.1021\/acs.jmedchem.5c01706","journal-title":"J Med Chem"},{"issue":"6","key":"1230_CR74","doi-asserted-by":"publisher","first-page":"2572","DOI":"10.1021\/acs.jcim.0c01328","volume":"61","author":"J Zhang","year":"2021","unstructured":"Zhang J, Mercado R, Engkvist O et al (2021) Comparative study of deep generative models on chemical space coverage. J Chem Inf Model 61(6):2572\u20132581. https:\/\/doi.org\/10.1021\/acs.jcim.0c01328","journal-title":"J Chem Inf Model"},{"key":"1230_CR75","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00920-9","author":"Z Zhang","year":"2024","unstructured":"Zhang Z, Shen WX, Liu Q et al (2024) Efficient generation of protein pockets with Pocketgen. Nat Mach Intell. https:\/\/doi.org\/10.1038\/s42256-024-00920-9","journal-title":"Nat Mach Intell"},{"key":"1230_CR76","doi-asserted-by":"publisher","first-page":"53918","DOI":"10.52202\/079017-1707","volume":"37","author":"Z Zhang","year":"2024","unstructured":"Zhang Z, Wang M, Liu Q (2024) Flexsbdd: structure-based drug design with flexible protein modeling. Adv Neural Inf Process Syst 37:53918\u201353944","journal-title":"Adv Neural Inf Process Syst"},{"key":"1230_CR77","doi-asserted-by":"publisher","unstructured":"Zhou G, Gao Z, Ding Q (2022) Uni-Mol: a universal 3D molecular representation learning framework. https:\/\/doi.org\/10.26434\/chemrxiv-2022-jjm0j","DOI":"10.26434\/chemrxiv-2022-jjm0j"},{"issue":"1","key":"1230_CR78","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-47011-2","volume":"15","author":"W Zhung","year":"2024","unstructured":"Zhung W, Kim H, Kim WY (2024) 3D molecular generative framework for interaction-guided drug design. Nat Commun 15(1):2688","journal-title":"Nat Commun"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-026-01230-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-026-01230-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-026-01230-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T10:39:00Z","timestamp":1782297540000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13321-026-01230-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,30]]},"references-count":78,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1230"],"URL":"https:\/\/doi.org\/10.1186\/s13321-026-01230-5","relation":{},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,30]]},"assertion":[{"value":"14 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 May 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":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"82"}}