{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T08:27:46Z","timestamp":1787646466431,"version":"build-2736575974"},"reference-count":34,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T00:00:00Z","timestamp":1787270400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52273299"],"award-info":[{"award-number":["52273299"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52573336"],"award-info":[{"award-number":["52573336"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["52273299"],"award-info":[{"award-number":["52273299"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"award":["52573336"],"award-info":[{"award-number":["52573336"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["KCXFZ20230731092802004"],"award-info":[{"award-number":["KCXFZ20230731092802004"]}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20220818100804009"],"award-info":[{"award-number":["JCYJ20220818100804009"]}]},{"name":"Shenzhen AI-Driven Public Service Platform for Pharmaceutical R&D","award":["XMHT20251128002"],"award-info":[{"award-number":["XMHT20251128002"]}]},{"name":"Shenzhen Medical Research Fund","award":["D2403008"],"award-info":[{"award-number":["D2403008"]}]},{"name":"Shenzhen Medical Research Fund","award":["B2404003"],"award-info":[{"award-number":["B2404003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Pharmaceuticals"],"abstract":"<jats:p>Background\/Objectives: Blood\u2013brain barrier (BBB) permeability is a major practical obstacle in central nervous system (CNS) drug discovery, because only a small fraction of drug-like molecules achieve sufficient brain exposure. Methods: We present DeepBBB, a graph-based, data-composition-aware screening workflow for predicting BBB permeability and for constructing BBB-focused screening libraries from commercial chemical space. Rather than introducing a new graph-learning architecture, the workflow combines standard graph convolutional and graph-transformer models with deliberate control of training-set composition, commercial-library filtering, chemical-space profiling, and prospective experimental evaluation. Three model variants were trained on the Blood\u2013Brain Barrier Database (B3DB): a baseline classifier\/regressor pair (DeepBBB_V1_BC\/RG), a variant trained with a more strongly negative-enriched configuration (DeepBBB_V2_BC), and a graph-transformer counterpart (DeepBBB_trans_BC\/RG). Because the sample-level split assignments and per-compound predictions from the original runs were not recoverable, the archived summary metrics are reported descriptively in the main text and are not used to support calibration, scaffold-level validity, or generalization. Applying the workflow to the ChemDiv collection (~1.5 million compounds) and the Enamine REAL lead-like space (~1.7 billion compounds) produced three progressively more stringently filtered BBB-focused libraries (21,991; 4,808,885; and 151,790 compounds). Results: Analysis of available processed data indicated that the predicted BBB-permeable set occupies a compact, BBB-compatible property region. Physicochemical, fragment, and scaffold summaries were interpreted descriptively at the constructed-library level. In a first prospective campaign, one of 12 tested candidate compounds was PAMPA-BBB-positive (all-tested molecular-level positive fraction 8.3%; exact 95% CI 0.2\u201338.5%). In a second campaign, five of 35 tested candidate compounds were PAMPA-BBB-positive (14.3%; exact 95% CI 4.8\u201330.3%); 13 compounds were not quantifiable and were not treated as ordinary CNS-negative measurements, and the two campaigns differed in compound source, selection strategy, and assay setting, so the numerical difference is reported descriptively rather than causally. Conclusions: Together, these results support the feasibility of BBB-focused computational filtering and a PAMPA-BBB evaluation workflow for CNS-oriented discovery.<\/jats:p>","DOI":"10.3390\/ph19081319","type":"journal-article","created":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T09:31:59Z","timestamp":1787304719000},"page":"1319","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DeepBBB: A Data-Composition-Aware Graph Screening Workflow for BBB-Focused CNS Library Construction and Prospective PAMPA-BBB Evaluation"],"prefix":"10.3390","volume":"19","author":[{"given":"Ziying","family":"Xu","sequence":"first","affiliation":[{"name":"School of Pharmacy, Shenzhen University Medical School, Shenzhen University, Shenzhen 518055, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6735-8701","authenticated-orcid":false,"given":"Wei","family":"Xia","sequence":"additional","affiliation":[{"name":"Department of Chemistry, New York University, New York, NY 10003, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3979-7304","authenticated-orcid":false,"given":"Haiqiang","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Pharmacy, Shenzhen University Medical School, Shenzhen University, Shenzhen 518055, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2133-1768","authenticated-orcid":false,"given":"Haiping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Faculty of Pharmaceutical Sciences, Shenzhen University of Advanced Technology, Shenzhen 518055, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.neuropharm.2016.03.021","article-title":"The need for new approaches in CNS drug discovery: Why drugs have failed, and what can be done to improve outcomes","volume":"120","author":"Gribkoff","year":"2017","journal-title":"Neuropharmacology"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Bhunia, S., Kolishetti, N., Vashist, A., Yndart Arias, A., Brooks, D., and Nair, M. (2023). Drug Delivery to the Brain: Recent Advances and Unmet Challenges. Pharmaceutics, 15.","DOI":"10.3390\/pharmaceutics15122658"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1398","DOI":"10.1038\/nn.2946","article-title":"Central nervous system pericytes in health and disease","volume":"14","author":"Winkler","year":"2011","journal-title":"Nat. Neurosci."},{"key":"ref_4","first-page":"1","article-title":"Blood-Brain Barrier: A Comprehensive Review of Its Structure, Function and Role in CNS Diseases","volume":"7","author":"Tajne","year":"2025","journal-title":"Int. J. Multidiscip. Res."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1499","DOI":"10.2174\/13816128113199990458","article-title":"Transporter-Based Delivery of Anticancer Drugs to the Brain: Improving Brain Penetration by Minimizing Drug Efflux at the Blood-Brain Barrier","volume":"20","author":"On","year":"2014","journal-title":"Curr. Pharm. Des."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1002\/bdd.2331","article-title":"The role of the efflux transporter, P-glycoprotein, at the blood\u2013brain barrier in drug discovery","volume":"44","author":"Cox","year":"2023","journal-title":"Biopharm. Drug Dispos."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1602\/neurorx.2.1.3","article-title":"The blood-brain barrier: Bottleneck in brain drug development","volume":"2","author":"Pardridge","year":"2005","journal-title":"NeuroRx"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"10429","DOI":"10.3390\/molecules170910429","article-title":"Computational prediction of blood-brain barrier permeability using decision tree induction","volume":"17","author":"Suenderhauf","year":"2012","journal-title":"Molecules"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1177","DOI":"10.2174\/1381612822666151221150733","article-title":"Evolving Drug Delivery Strategies to Overcome the Blood Brain Barrier","volume":"22","author":"Hersh","year":"2016","journal-title":"Curr. Pharm. Des."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1250","DOI":"10.52711\/0974-360X.2025.00181","article-title":"Physicochemical determinants of blood brain barrier penetrating molecules","volume":"18","author":"Pandey","year":"2025","journal-title":"Res. J. Pharm. Technol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1002\/minf.201500109","article-title":"CNS Multiparameter Optimization Approach: Is it in Accordance with Occam\u2019s Razor Principle?","volume":"35","author":"Raevsky","year":"2016","journal-title":"Mol. Inform."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1602\/neurorx.2.4.541","article-title":"Medicinal chemical properties of successful central nervous system drugs","volume":"2","author":"Pajouhesh","year":"2005","journal-title":"NeuroRx"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1980","DOI":"10.1002\/jps.21580","article-title":"Comparison of blood\u2013brain barrier permeability assays: In situ brain perfusion, MDR1-MDCKII and PAMPA-BBB","volume":"98","author":"Di","year":"2009","journal-title":"J. Pharm. Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/S0223-5234(03)00012-6","article-title":"High throughput artificial membrane permeability assay for blood\u2013brain barrier","volume":"38","author":"Di","year":"2003","journal-title":"Eur. J. Med. Chem."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1016\/j.ejpb.2014.03.012","article-title":"Blood\u2013brain barrier models and their relevance for a successful development of CNS drug delivery systems: A review","volume":"87","author":"Bicker","year":"2014","journal-title":"Eur. J. Pharm. Biopharm."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1208\/s12248-008-9009-8","article-title":"Prodrug Approaches for CNS Delivery","volume":"10","author":"Rautio","year":"2008","journal-title":"AAPS J."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Hersh, A.M., Alomari, S., and Tyler, B.M. (2022). Crossing the Blood-Brain Barrier: Advances in Nanoparticle Technology for Drug Delivery in Neuro-Oncology. Int. J. Mol. Sci., 23.","DOI":"10.3390\/ijms23084153"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Haqqani, A.S., B\u00e9langer, K., and Stanimirovic, D.B. (2024). Receptor-mediated transcytosis for brain delivery of therapeutics: Receptor classes and criteria. Front. Drug Deliv., 4.","DOI":"10.3389\/fddev.2024.1360302"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"4429","DOI":"10.1002\/jps.21745","article-title":"In vivo, in vitro and in silico methods for small molecule transfer across the BBB","volume":"98","author":"Mensch","year":"2009","journal-title":"J. Pharm. Sci."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Faramarzi, S., Kim, M.T., Volpe, D.A., Cross, K.P., Chakravarti, S., and Stavitskaya, L. (2022). Development of QSAR models to predict blood-brain barrier permeability. Front. Pharmacol., 13.","DOI":"10.3389\/fphar.2022.1040838"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1163","DOI":"10.2174\/1389201020666190821145346","article-title":"Blood Brain Barrier Permeability Prediction Using Machine Learning Techniques: An Update","volume":"20","author":"Saxena","year":"2019","journal-title":"Curr. Pharm. Biotechnol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"292683","DOI":"10.1155\/2015\/292683","article-title":"A Genetic Algorithm Based Support Vector Machine Model for Blood-Brain Barrier Penetration Prediction","volume":"2015","author":"Zhang","year":"2015","journal-title":"BioMed Res. Int."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1208\/s12248-025-01059-0","article-title":"GCN-BBB: Deep Learning Blood-Brain Barrier (BBB) Permeability PharmacoAnalytics with Graph Convolutional Neural (GCN) Network","volume":"27","author":"Jing","year":"2025","journal-title":"AAPS J."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1007\/s44163-025-00494-4","article-title":"Blood brain barrier permeability prediction with artificial intelligence and machine learning: A meta-review and future directions","volume":"5","author":"Grant","year":"2025","journal-title":"Discov. Artif. Intell."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e515","DOI":"10.7717\/peerj-cs.515","article-title":"A Deep Learning Approach to Predict Blood-Brain Barrier Permeability","volume":"7","author":"Alsenan","year":"2021","journal-title":"PeerJ Comput. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhu, B., and Liu, S. (2025). Feature-Guided Machine Learning for Studying Passive Blood\u2013Brain Barrier Permeability to Aid Drug Discovery. Int. J. Mol. Sci., 26.","DOI":"10.3390\/ijms262211228"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1080\/17460441.2024.2403639","article-title":"Data-centric challenges with the application and adoption of artificial intelligence for drug discovery","volume":"19","author":"Ghislat","year":"2024","journal-title":"Expert Opin. Drug Discov."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"D1265","DOI":"10.1093\/nar\/gkad976","article-title":"DrugBank 6.0: The DrugBank Knowledgebase for 2024","volume":"52","author":"Knox","year":"2024","journal-title":"Nucleic Acids Res."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Kato, R., Zeng, W., Siramshetty, V.B., Williams, J., Kabir, M., Hagen, N., Padilha, E.C., Wang, A.Q., Math\u00e9, E.A., and Xu, X. (2023). Development and validation of PAMPA-BBB QSAR model to predict brain penetration potential of novel drug candidates. Front. Pharmacol., 14.","DOI":"10.3389\/fphar.2023.1291246"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1007\/s44163-026-00938-5","article-title":"Graph-based deep learning for blood-brain barrier permeability screening in central nervous system drug discovery","volume":"6","author":"Lahoti","year":"2026","journal-title":"Discov. Artif. Intell."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Chitale, R. (2025). Liquid Adaptive AI: A Theoretical Framework for Continuously Self-Improving Artificial Intelligence. AI, 6.","DOI":"10.3390\/ai6080186"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1038\/s41597-021-01069-5","article-title":"A curated diverse molecular database of blood-brain barrier permeability with chemical descriptors","volume":"8","author":"Meng","year":"2021","journal-title":"Sci. Data"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/j.ymeth.2022.07.009","article-title":"DeepBindBC: A practical deep learning method for identifying native-like protein-ligand complexes in virtual screening","volume":"205","author":"Zhang","year":"2022","journal-title":"Methods"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Zhang, H., Saravanan, K.M., and Zhang, J.Z.H. (2023). DeepBindGCN: Integrating Molecular Vector Representation with Graph Convolutional Neural Networks for Protein\u2013Ligand Interaction Prediction. Molecules, 28.","DOI":"10.1101\/2023.03.16.528593"}],"container-title":["Pharmaceuticals"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8247\/19\/8\/1319\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T08:05:35Z","timestamp":1787645135000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8247\/19\/8\/1319"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,21]]},"references-count":34,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["ph19081319"],"URL":"https:\/\/doi.org\/10.3390\/ph19081319","relation":{},"ISSN":["1424-8247"],"issn-type":[{"value":"1424-8247","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,21]]}}}