{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T23:25:40Z","timestamp":1792797940258,"version":"4.5.0"},"reference-count":72,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:00:00Z","timestamp":1784332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:00:00Z","timestamp":1792022400000},"content-version":"vor","delay-in-days":89,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR\u201018\u2010IdEx\u20100001"],"award-info":[{"award-number":["ANR\u201018\u2010IdEx\u20100001"]}],"id":[{"id":"10.13039\/501100001665","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>Cystathionine \u03b2-synthase (CBS) has emerged as an important therapeutic target implicated in cancer and Down syndrome, yet the discovery of selective CBS inhibitors remains challenging due to limited structural diversity of known ligands and the scarcity of target-focused virtual screening (VS) benchmarks. In this study, we present the first comprehensive evaluation of CBS-specific artificial intelligence (AI) models for structure-based VS, supported by a carefully curated and up-to-date data set of experimentally validated CBS inhibitors, true inactives and decoys. Using this data set, we developed CBS-specific binary classification models trained on docking-derived features and evaluated them in a rigorous five-fold cross-validation framework that employed similarity-controlled splits, ensuring structural independence between training and test sets while minimizing intra-fold class bias. Predictive performance was assessed primarily using the normalized enrichment factor of true actives at 1% (NEF1%) alongside balanced accuracy. Across all folds, the CBS-specific AI models demonstrated consistently high screening power and robust classification performance. Importantly, we benchmarked their performance against a diverse panel of 16 established VS pipelines, including widely adopted docking-based scoring schemes, modern deep-learning (DL) docking tools, and recent co-folding approaches for protein\u2013ligand binding prediction. The CBS-specific AI classifiers substantially outperformed these state-of-the-art (SOTA) methods in early enrichment (NEF1%\u2009=\u20090.764\u2009\u00b1\u20090.191), highlighting the advantage of target-focused training for VS tasks. Our results further reveal that generic DL docking and co-folding approaches struggle to achieve reliable screening performance when applied to targets under-represented in or entirely absent from their training data, as appears to be the case for CBS. This finding underscores a key limitation of broadly trained foundation-style models in prospective drug discovery campaigns involving less-studied proteins. Overall, this work reinforces the benefits of target-specific AI scoring models tailored to individual proteins, highlights the value of high-quality curated data sets for such efforts, and provides practical guidance for selecting VS strategies in case of data-limited targets. To promote transparency and reproducibility, all input and output files, curated data sets and source code are freely available via GitHub and Zenodo.<\/jats:p>","DOI":"10.1186\/s13321-026-01262-x","type":"journal-article","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:25:11Z","timestamp":1784391911000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing virtual screening of cystathionine \u03b2-synthase inhibitors: benchmarking target-specific machine-learning scoring functions against state-of-the-art AI docking and co-folding approaches"],"prefix":"10.1186","volume":"18","author":[{"given":"Cao-Minh","family":"Truong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Van-Thinh","family":"To","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nathalie","family":"Janel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julien","family":"Dairou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pedro J.","family":"Ballester","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olivier","family":"Taboureau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7497-333X","authenticated-orcid":false,"given":"Viet-Khoa","family":"Tran-Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,18]]},"reference":[{"key":"1262_CR1","doi-asserted-by":"publisher","first-page":"1336","DOI":"10.1038\/ejhg.2008.122","volume":"16","author":"C Irving","year":"2008","unstructured":"Irving C, Basu A, Richmond S et al (2008) Twenty-year trends in prevalence and survival of Down syndrome. Eur J Hum Genet 16:1336\u20131340","journal-title":"Eur J Hum Genet"},{"key":"1262_CR2","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1089\/ars.2005.7.547","volume":"7","author":"C-G Zou","year":"2005","unstructured":"Zou C-G, Banerjee R (2005) Homocysteine and redox signaling. Antioxid Redox Signal 7:547\u2013559","journal-title":"Antioxid Redox Signal"},{"key":"1262_CR3","doi-asserted-by":"publisher","first-page":"52082","DOI":"10.1074\/jbc.C400481200","volume":"279","author":"X Chen","year":"2004","unstructured":"Chen X, Jhee K-H, Kruger WD (2004) Production of the neuromodulator H2S by cystathionine \u03b2-synthase via the condensation of cysteine and homocysteine. J Biol Chem 279:52082\u201352086","journal-title":"J Biol Chem"},{"key":"1262_CR4","doi-asserted-by":"publisher","first-page":"10548","DOI":"10.1021\/bi001020g","volume":"39","author":"K-H Jhee","year":"2000","unstructured":"Jhee K-H, McPhie P, Miles EW (2000) Domain architecture of the heme-independent yeast cystathionine \u03b2-synthase provides insights into mechanisms of catalysis and regulation. Biochemistry 39:10548\u201310556","journal-title":"Biochemistry"},{"key":"1262_CR5","doi-asserted-by":"publisher","first-page":"36018","DOI":"10.1074\/jbc.M114.610782","volume":"289","author":"TJ McCorvie","year":"2014","unstructured":"McCorvie TJ, Kopec J, Hyung S-J et al (2014) Inter-domain communication of human cystathionine \u03b2-synthase. J Biol Chem 289:36018\u201336030","journal-title":"J Biol Chem"},{"key":"1262_CR6","doi-asserted-by":"publisher","first-page":"3958","DOI":"10.1007\/s12035-018-1323-2","volume":"56","author":"J London","year":"2019","unstructured":"London J, Ndiaye FK, Bui LC et al (2019) Alterations in the serotonin and dopamine pathways by cystathionine beta synthase overexpression in murine brain. Mol Neurobiol 56:3958\u20133971","journal-title":"Mol Neurobiol"},{"key":"1262_CR7","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1177\/002215540305100311","volume":"51","author":"K Robert","year":"2003","unstructured":"Robert K, Vialard F, Thiery E et al (2003) Expression of the cystathionine \u03b2 synthase (CBS) gene during mouse development and immunolocalization in adult brain. J Histochem Cytochem 51:363\u2013371","journal-title":"J Histochem Cytochem"},{"key":"1262_CR8","doi-asserted-by":"publisher","first-page":"1547","DOI":"10.1016\/j.bbrc.2005.10.118","volume":"338","author":"A Ichinohe","year":"2005","unstructured":"Ichinohe A, Kanaumi T, Takashima S et al (2005) Cystathionine \u03b2-synthase is enriched in the brains of Down\u2019s patients. Biochem Biophys Res Commun 338:1547\u20131550","journal-title":"Biochem Biophys Res Commun"},{"key":"1262_CR9","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/0006-291X(85)91641-9","volume":"128","author":"B Chadefaux","year":"1985","unstructured":"Chadefaux B, Rethor\u00e9 MO, Raoul O et al (1985) Cystathionine beta synthase: gene dosage effect in trisomy 21. Biochem Biophys Res Commun 128:40\u201344","journal-title":"Biochem Biophys Res Commun"},{"key":"1262_CR10","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1002\/ajmg.a.10847","volume":"116A","author":"P Kamoun","year":"2003","unstructured":"Kamoun P, Belardinelli M, Chabli A et al (2003) Endogenous hydrogen sulfide overproduction in Down syndrome. Am J Med Genet A 116A:310\u2013311","journal-title":"Am J Med Genet A"},{"key":"1262_CR11","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/s00726-004-0072-x","volume":"26","author":"P Kamoun","year":"2004","unstructured":"Kamoun P (2004) Endogenous production of hydrogen sulfide in mammals. Amino Acids 26:243\u2013254","journal-title":"Amino Acids"},{"key":"1262_CR12","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.neuint.2007.05.016","volume":"52","author":"K Qu","year":"2008","unstructured":"Qu K, Lee SW, Bian JS et al (2008) Hydrogen sulfide: neurochemistry and neurobiology. Neurochem Int 52:155\u2013165","journal-title":"Neurochem Int"},{"key":"1262_CR13","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1089\/ars.2010.3517","volume":"15","author":"L-F Hu","year":"2011","unstructured":"Hu L-F, Lu M, Hon Wong PT, Bian J-S (2011) Hydrogen sulfide: neurophysiology and neuropathology. Antioxid Redox Signal 15:405\u2013419","journal-title":"Antioxid Redox Signal"},{"key":"1262_CR14","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1039\/C6MD00493H","volume":"8","author":"W Niu","year":"2017","unstructured":"Niu W, Wu P, Chen F et al (2017) Discovery of selective cystathionine \u03b2-synthase inhibitors by high-throughput screening with a fluorescent thiol probe. MedChemComm 8:198\u2013201","journal-title":"MedChemComm"},{"key":"1262_CR15","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1007\/s00018-022-04479-9","volume":"79","author":"M Petrosino","year":"2022","unstructured":"Petrosino M, Zuhra K, Kopec J et al (2022) H2S biogenesis by cystathionine beta-synthase: mechanism of inhibition by aminooxyacetic acid and unexpected role of serine. Cell Mol Life Sci 79:438","journal-title":"Cell Mol Life Sci"},{"key":"1262_CR16","doi-asserted-by":"publisher","first-page":"697","DOI":"10.3390\/biom10050697","volume":"10","author":"K Zuhra","year":"2020","unstructured":"Zuhra K, Augsburger F, Majtan T, Szabo C (2020) Cystathionine-\u03b2-synthase: molecular regulation and pharmacological inhibition. Biomolecules 10:697","journal-title":"Biomolecules"},{"key":"1262_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.redox.2022.102331","volume":"53","author":"K Ascen\u00e7\u00e3o","year":"2022","unstructured":"Ascen\u00e7\u00e3o K, Szabo C (2022) Emerging roles of cystathionine \u03b2-synthase in various forms of cancer. Redox Biol 53:102331","journal-title":"Redox Biol"},{"key":"1262_CR18","doi-asserted-by":"publisher","first-page":"D1516","DOI":"10.1093\/nar\/gkae1059","volume":"53","author":"S Kim","year":"2025","unstructured":"Kim S, Chen J, Cheng T et al (2025) PubChem 2025 update. Nucleic Acids Res 53:D1516\u2013D1525","journal-title":"Nucleic Acids Res"},{"key":"1262_CR19","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 et al (2012) ChEMBL: a large-scale bioactivity database for drug discovery. Nucleic Acids Res 40:D1100\u2013D1107","journal-title":"Nucleic Acids Res"},{"key":"1262_CR20","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1109\/I2CACIS65476.2025.11100436","volume-title":"2025 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","author":"HN Chua","year":"2025","unstructured":"Chua HN, Jasser MB, Issa B, Wong RTK (2025) Differentiating Artificial Intelligence, Machine Learning, Deep Learning, and Data Mining. 2025 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS). IEEE, Kuala Lumpur, Malaysia, pp 250\u2013255"},{"key":"1262_CR21","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-025-01063-8","volume":"17","author":"V-K Tran-Nguyen","year":"2025","unstructured":"Tran-Nguyen V-K, Randriharimanamizara UF, Taboureau O (2025) HERGAI: an artificial intelligence tool for structure-based prediction of hERG inhibitors. J Cheminform 17:110","journal-title":"J Cheminform"},{"key":"1262_CR22","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/j.jare.2024.01.024","volume":"67","author":"P G\u00f3mez-Sacrist\u00e1n","year":"2025","unstructured":"G\u00f3mez-Sacrist\u00e1n P, Simeon S, Tran-Nguyen V-K et al (2025) Inactive-enriched machine-learning models exploiting patent data improve structure-based virtual screening for PDL1 dimerizers. J Adv Res 67:185\u2013196","journal-title":"J Adv Res"},{"key":"1262_CR23","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1186\/s13321-024-00832-1","volume":"16","author":"K Caba","year":"2024","unstructured":"Caba K, Tran-Nguyen V-K, Rahman T, Ballester PJ (2024) Comprehensive machine learning boosts structure-based virtual screening for PARP1 inhibitors. J Cheminform 16:40","journal-title":"J Cheminform"},{"key":"1262_CR24","doi-asserted-by":"crossref","unstructured":"Castillo Tarazona MY, Miscione GP 2026 Enhancing structure-based virtual screening of MDM2\u2013p53 inhibitors: a benchmark of machine learning vs. traditional docking scoring functions. Front Drug Discov 5 1731262.","DOI":"10.3389\/fddsv.2025.1731262"},{"key":"1262_CR25","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1021\/acs.jcim.5c01677","volume":"66","author":"A Serghini","year":"2026","unstructured":"Serghini A, Zhou Y, Myung Y et al (2026) KinCSM-RTK: machine learning-based screening of receptor tyrosine kinase inhibitors in drug discovery. J Chem Inf Model 66:61\u201373","journal-title":"J Chem Inf Model"},{"key":"1262_CR26","doi-asserted-by":"publisher","first-page":"2400238","DOI":"10.1002\/aisy.202400238","volume":"6","author":"V-K Tran-Nguyen","year":"2024","unstructured":"Tran-Nguyen V-K, Camproux A-C, Taboureau O (2024) ClassyPose: A Machine-Learning Classification Model for Ligand Pose Selection Applied to Virtual Screening in Drug Discovery. Adv Intell Syst 6:2400238","journal-title":"Adv Intell Syst"},{"key":"1262_CR27","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-025-01107-z","volume":"17","author":"F Victoria-Mu\u00f1oz","year":"2025","unstructured":"Victoria-Mu\u00f1oz F, Menke J, Sanchez-Cruz N, Koch O (2025) Efficient decoy selection to improve virtual screening using machine learning models. J Cheminform 17:165","journal-title":"J Cheminform"},{"key":"1262_CR28","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1186\/s13321-025-01039-8","volume":"17","author":"Q Guo","year":"2025","unstructured":"Guo Q, Hernandez-Hernandez S, Ballester PJ (2025) UMAP-based clustering split for rigorous evaluation of AI models for virtual screening on cancer cell lines*. J Cheminform 17:94","journal-title":"J Cheminform"},{"key":"1262_CR29","doi-asserted-by":"publisher","first-page":"1893","DOI":"10.1021\/ci300604z","volume":"53","author":"DR Koes","year":"2013","unstructured":"Koes DR, Baumgartner MP, Camacho CJ (2013) Lessons learned in empirical scoring with smina from the CSAR 2011 benchmarking exercise. J Chem Inf Model 53:1893\u20131904","journal-title":"J Chem Inf Model"},{"key":"1262_CR30","doi-asserted-by":"publisher","first-page":"1334","DOI":"10.1093\/bioinformatics\/bty757","volume":"35","author":"M W\u00f3jcikowski","year":"2019","unstructured":"W\u00f3jcikowski M, Kukie\u0142ka M, Stepniewska-Dziubinska MM et al (2019) Development of a protein\u2013ligand extended connectivity (PLEC) fingerprint and its application for binding affinity predictions. Bioinformatics 35:1334\u20131341","journal-title":"Bioinformatics"},{"key":"1262_CR31","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.1038\/s42256-021-00409-9","volume":"3","author":"O M\u00e9ndez-Lucio","year":"2021","unstructured":"M\u00e9ndez-Lucio O, Ahmad M, Del Rio-Chanona EA, Wegner JK (2021) A geometric deep learning approach to predict binding conformations of bioactive molecules. Nat Mach Intell 3:1033\u20131039","journal-title":"Nat Mach Intell"},{"key":"1262_CR32","doi-asserted-by":"publisher","first-page":"10223","DOI":"10.1038\/s41467-024-54440-6","volume":"15","author":"H Lai","year":"2024","unstructured":"Lai H, Wang L, Qian R et al (2024) Interformer: an interaction-aware model for protein-ligand docking and affinity prediction. Nat Commun 15:10223","journal-title":"Nat Commun"},{"key":"1262_CR33","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1038\/s41592-024-02516-y","volume":"22","author":"D Cao","year":"2025","unstructured":"Cao D, Chen M, Zhang R et al (2025) SurfDock is a surface-informed diffusion generative model for reliable and accurate protein\u2013ligand complex prediction. Nat Methods 22:310\u2013322","journal-title":"Nat Methods"},{"key":"1262_CR34","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1038\/s43588-023-00511-5","volume":"3","author":"X Zhang","year":"2023","unstructured":"Zhang X, Zhang O, Shen C et al (2023) Efficient and accurate large library ligand docking with KarmaDock. Nat Comput Sci 3:789\u2013804","journal-title":"Nat Comput Sci"},{"key":"1262_CR35","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. Preprint at bioRxiv. https:\/\/doi.org\/10.1101\/2025.06.14.659707","journal-title":"Preprint at bioRxiv"},{"key":"1262_CR36","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","volume":"630","author":"J Abramson","year":"2024","unstructured":"Abramson J, Adler J, Dunger J et al (2024) Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature 630:493\u2013500","journal-title":"Nature"},{"key":"1262_CR37","doi-asserted-by":"publisher","DOI":"10.1038\/srep46710","volume":"7","author":"M W\u00f3jcikowski","year":"2017","unstructured":"W\u00f3jcikowski M, Ballester PJ, Siedlecki P (2017) Performance of machine-learning scoring functions in structure-based virtual screening. Sci Rep 7:46710","journal-title":"Sci Rep"},{"key":"1262_CR38","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-025-00973-x","volume":"17","author":"AT McNutt","year":"2025","unstructured":"McNutt AT, Li Y, Meli R et al (2025) GNINA 1.3: the next increment in molecular docking with deep learning. J Cheminform 17:28","journal-title":"J Cheminform"},{"key":"1262_CR39","unstructured":"Blehaut H, Bellamy F, Matt C, Giraud S, Charre D (2010) Inhibitors of cystathionine beta synthase to reduce the neurotoxic overproduction of endogenous hydrogen sulfide. WO2010072807A2, 1 Jul 2010."},{"key":"1262_CR40","unstructured":"Blehaut H, Bellamy F, Matt C, Giraud S, Charre D (2010) Inhibitors of cystathionine beta synthase for preventing or treating neurotoxic or cognitive disorders. WO2010072807A3"},{"key":"1262_CR41","unstructured":"Charre D, Blehaut H, Bellamy F 2013 Inhibitors of cystathionine beta synthase to reduce the neurotoxic overproduction of endogenous hydrogen sulfide. WO2013068592A1"},{"key":"1262_CR42","doi-asserted-by":"publisher","first-page":"3460","DOI":"10.1038\/s41596-023-00885-w","volume":"18","author":"V-K Tran-Nguyen","year":"2023","unstructured":"Tran-Nguyen V-K, Junaid M, Simeon S, Ballester PJ (2023) A practical guide to machine-learning scoring for structure-based virtual screening. Nat Protoc 18:3460\u20133511","journal-title":"Nat Protoc"},{"key":"1262_CR43","doi-asserted-by":"publisher","first-page":"4263","DOI":"10.1021\/acs.jcim.0c00155","volume":"60","author":"V-K Tran-Nguyen","year":"2020","unstructured":"Tran-Nguyen V-K, Jacquemard C, Rognan D (2020) LIT-PCBA: an unbiased data set for machine learning and virtual screening. J Chem Inf Model 60:4263\u20134273","journal-title":"J Chem Inf Model"},{"key":"1262_CR44","doi-asserted-by":"publisher","first-page":"498","DOI":"10.3390\/biom13030498","volume":"13","author":"S Hern\u00e1ndez-Hern\u00e1ndez","year":"2023","unstructured":"Hern\u00e1ndez-Hern\u00e1ndez S, Ballester PJ (2023) On the best way to cluster NCI-60 molecules. Biomolecules 13:498","journal-title":"Biomolecules"},{"key":"1262_CR45","doi-asserted-by":"publisher","first-page":"1851","DOI":"10.1021\/acs.chemrestox.4c00169","volume":"37","author":"F Camilleri","year":"2024","unstructured":"Camilleri F, Wenda JM, Pecoraro-Mercier C et al (2024) Cell painting and chemical structure read-across can complement each other for rat acute oral toxicity prediction in chemical early derisking. Chem Res Toxicol 37:1851\u20131866","journal-title":"Chem Res Toxicol"},{"key":"1262_CR46","doi-asserted-by":"publisher","first-page":"6410","DOI":"10.1021\/acs.jcim.4c01102","volume":"64","author":"I Arab","year":"2024","unstructured":"Arab I, Laukens K, Bittremieux W (2024) Semisupervised learning to boost hERG, Nav1.5, and Cav1.2 cardiac ion channel toxicity prediction by mining a large unlabeled small molecule data set. J Chem Inf Model 64:6410\u20136420","journal-title":"J Chem Inf Model"},{"key":"1262_CR47","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1333\/s00897112344a","volume":"16","author":"A Kumar","year":"2011","unstructured":"Kumar A (2011) Chemical similarity methods- a tutorial review. Chem Educator 16:46\u201350","journal-title":"Chem Educator"},{"key":"1262_CR48","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/s13321-025-00948-y","volume":"17","author":"J Wellnitz","year":"2025","unstructured":"Wellnitz J, Jain S, Hochuli JE et al (2025) One size does not fit all: revising traditional paradigms for assessing accuracy of QSAR models used for virtual screening. J Cheminform 17:7","journal-title":"J Cheminform"},{"key":"1262_CR49","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2023.120253","volume":"277","author":"P Th\u00f6lke","year":"2023","unstructured":"Th\u00f6lke P, Mantilla-Ramos Y-J, Abdelhedi H et al (2023) Class imbalance should not throw you off balance: choosing the right classifiers and performance metrics for brain decoding with imbalanced data. Neuroimage 277:120253","journal-title":"Neuroimage"},{"key":"1262_CR50","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.ddtec.2020.09.001","volume":"32\u201333","author":"PJ Ballester","year":"2019","unstructured":"Ballester PJ (2019) Selecting machine-learning scoring functions for structure-based virtual screening. Drug Discov Today Technol 32\u201333:81\u201387","journal-title":"Drug Discov Today Technol"},{"key":"1262_CR51","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.cbpa.2021.04.009","volume":"65","author":"G Ghislat","year":"2021","unstructured":"Ghislat G, Rahman T, Ballester PJ (2021) Recent progress on the prospective application of machine learning to structure-based virtual screening. Curr Opin Chem Biol 65:28\u201334","journal-title":"Curr Opin Chem Biol"},{"key":"1262_CR52","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1021\/ci600426e","volume":"47","author":"J-F Truchon","year":"2007","unstructured":"Truchon J-F, Bayly CI (2007) Evaluating virtual screening methods: good and bad metrics for the \u201cearly recognition\u201d problem. J Chem Inf Model 47:488\u2013508","journal-title":"J Chem Inf Model"},{"key":"1262_CR53","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1186\/s12859-016-1169-4","volume":"17","author":"H Li","year":"2016","unstructured":"Li H, Leung K-S, Wong M-H, Ballester PJ (2016) Correcting the impact of docking pose generation error on binding affinity prediction. BMC Bioinformatics 17:308","journal-title":"BMC Bioinformatics"},{"key":"1262_CR54","doi-asserted-by":"publisher","first-page":"2858","DOI":"10.1039\/D5SC06481C","volume":"17","author":"C Shen","year":"2026","unstructured":"Shen C, Zhang X, Gu S et al (2026) Unlocking the application potential of AlphaFold3-like approaches in virtual screening. Chem Sci 17:2858\u20132879","journal-title":"Chem Sci"},{"key":"1262_CR55","doi-asserted-by":"publisher","first-page":"17374","DOI":"10.1039\/D5SC05395A","volume":"16","author":"Y Li","year":"2025","unstructured":"Li Y, Yi J, Li H et al (2025) Decoding the limits of deep learning in molecular docking for drug discovery. Chem Sci 16:17374\u201317390","journal-title":"Chem Sci"},{"key":"1262_CR56","doi-asserted-by":"publisher","first-page":"3130","DOI":"10.1039\/D3SC04185A","volume":"15","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 15:3130\u20133139","journal-title":"Chem Sci"},{"key":"1262_CR57","doi-asserted-by":"publisher","first-page":"1427","DOI":"10.1038\/s42256-023-00756-9","volume":"5","author":"A Mastropietro","year":"2023","unstructured":"Mastropietro A, Pasculli G, Bajorath J (2023) Learning characteristics of graph neural networks predicting protein\u2013ligand affinities. Nat Mach Intell 5:1427\u20131436","journal-title":"Nat Mach Intell"},{"key":"1262_CR58","doi-asserted-by":"publisher","unstructured":"Jain AN, Cleves AE, Walters WP 2024 Deep-Learning Based Docking Methods: Fair Comparisons to Conventional Docking Workflows. Preprint at arXiv. https:\/\/doi.org\/10.48550\/arXiv.2412.02889.","DOI":"10.48550\/arXiv.2412.02889"},{"key":"1262_CR59","doi-asserted-by":"publisher","unstructured":"Truong C-M, Ballester PJ, Taboureau O, Tran-Nguyen V-K (2026) NextTopDocker: the largest-to-date docking power benchmark reveals that deep learning performs generally much worse than logistic regression models. Preprint at ChemRxiv. https:\/\/doi.org\/10.26434\/chemrxiv.10001776\/v2.","DOI":"10.26434\/chemrxiv.10001776\/v2"},{"key":"1262_CR60","doi-asserted-by":"publisher","first-page":"8854","DOI":"10.1038\/s41467-025-63947-5","volume":"16","author":"MR Masters","year":"2025","unstructured":"Masters MR, Mahmoud AH, Lill MA (2025) Investigating whether deep learning models for co-folding learn the physics of protein-ligand interactions. Nat Commun 16:8854","journal-title":"Nat Commun"},{"key":"1262_CR61","volume":"8","author":"E Nittinger","year":"2025","unstructured":"Nittinger E, Yoluk \u00d6, Tibo A et al (2025) Co-folding, the future of docking \u2013 prediction of allosteric and orthosteric ligands. Artif Intell Life Sci 8:100136","journal-title":"Artif Intell Life Sci"},{"key":"1262_CR62","doi-asserted-by":"publisher","unstructured":"Grieswelle M, Homberg S, Janssen P, et al (2026) A new benchmark for deep learning based affinity prediction: Solving the inter-protein scoring noise problem. Preprint at ChemRxiv. https:\/\/doi.org\/10.26434\/chemrxiv-2025-sf3cs\/v2.","DOI":"10.26434\/chemrxiv-2025-sf3cs\/v2"},{"key":"1262_CR63","doi-asserted-by":"publisher","first-page":"1401","DOI":"10.1021\/acs.jcim.3c00218","volume":"63","author":"V-K Tran-Nguyen","year":"2023","unstructured":"Tran-Nguyen V-K, Ballester PJ (2023) Beware of simple methods for structure-based virtual screening: the critical importance of broader comparisons. J Chem Inf Model 63:1401\u20131405","journal-title":"J Chem Inf Model"},{"key":"1262_CR64","doi-asserted-by":"publisher","first-page":"5433","DOI":"10.1039\/D5CS00146C","volume":"54","author":"AM Mroz","year":"2025","unstructured":"Mroz AM, Basford AR, Hastedt F et al (2025) Cross-disciplinary perspectives on the potential for artificial intelligence across chemistry. Chem Soc Rev 54:5433\u20135469","journal-title":"Chem Soc Rev"},{"key":"1262_CR65","unstructured":"Dark Chemical Matter Library, ChemDiv. https:\/\/www.chemdiv.com\/catalog\/focused-and-targeted-libraries\/dark-chemical-matter-library\/. Accessed 19 Jan 2026."},{"key":"1262_CR66","doi-asserted-by":"publisher","first-page":"958","DOI":"10.1038\/nchembio.1936","volume":"11","author":"AM Wassermann","year":"2015","unstructured":"Wassermann AM, Lounkine E, Hoepfner D et al (2015) Dark chemical matter as a promising starting point for drug lead discovery. Nat Chem Biol 11:958\u2013966","journal-title":"Nat Chem Biol"},{"key":"1262_CR67","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/1758-2946-3-33","volume":"3","author":"NM O\u2019Boyle","year":"2011","unstructured":"O\u2019Boyle NM, Banck M, James CA et al (2011) Open babel: an open chemical toolbox. J Cheminform 3:33","journal-title":"J Cheminform"},{"key":"1262_CR68","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1038\/msb.2011.75","volume":"7","author":"F Sievers","year":"2011","unstructured":"Sievers F, Wilm A, Dineen D et al (2011) Fast, scalable generation of high-quality protein multiple sequence alignments using Clustal Omega. Mol Syst Biol 7:539","journal-title":"Mol Syst Biol"},{"key":"1262_CR69","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/978-1-4939-7756-7_3","volume-title":"Computational drug discovery and design","author":"RN Dos Santos","year":"2018","unstructured":"Dos Santos RN, Ferreira LG, Andricopulo AD (2018) Practices in molecular docking and structure-based virtual screening. In: Gore M, Jagtap UB (eds) Computational drug discovery and design. Springer, New York, pp 31\u201350"},{"key":"1262_CR70","unstructured":"Boltz-2 GitHub page. https:\/\/github.com\/jwohlwend\/boltz\/blob\/main\/docs\/prediction.md. Accessed 12 February 2026."},{"key":"1262_CR71","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1021\/acs.jcim.8b00363","volume":"59","author":"S Liu","year":"2019","unstructured":"Liu S, Alnammi M, Ericksen SS et al (2019) Practical model selection for prospective virtual screening. J Chem Inf Model 59:282\u2013293","journal-title":"J Chem Inf Model"},{"key":"1262_CR72","doi-asserted-by":"crossref","unstructured":"Fresnais L, Ballester PJ (2021) The impact of compound library size on the performance of scoring functions for structure-based virtual screening. Brief Bioinform 22:bbaa095.","DOI":"10.1093\/bib\/bbaa095"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-026-01262-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-026-01262-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-026-01262-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T10:57:46Z","timestamp":1792061866000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-026-01262-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,18]]},"references-count":72,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1262"],"URL":"https:\/\/doi.org\/10.1186\/s13321-026-01262-x","relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv.15000891\/v1","asserted-by":"object"}]},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,18]]},"assertion":[{"value":"9 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"141"}}