{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T12:08:01Z","timestamp":1792843681857,"version":"4.5.0"},"reference-count":33,"publisher":"American Chemical Society (ACS)","issue":"17","license":[{"start":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:00:00Z","timestamp":1786665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100008968","name":"Istanbul Kalkinma Ajansi","doi-asserted-by":"publisher","award":["TR10\/21\/YEP\/0133"],"award-info":[{"award-number":["TR10\/21\/YEP\/0133"]}],"id":[{"id":"10.13039\/501100008968","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015732","name":"Bah?esehir ?niversitesi","doi-asserted-by":"publisher","award":["BAP.2022-02.59"],"award-info":[{"award-number":["BAP.2022-02.59"]}],"id":[{"id":"10.13039\/501100015732","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015732","name":"Bah?esehir ?niversitesi","doi-asserted-by":"publisher","award":["BAP.2024-01.42"],"award-info":[{"award-number":["BAP.2024-01.42"]}],"id":[{"id":"10.13039\/501100015732","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurate identification of repurposable BCL-2 ligands requires not only plausible bound complex structures but also a dynamic description of how ligand binding reshapes residue-level communication. Here, we present a multimodal BCL-2 repurposing workflow built with diffusion-based generative modeling for ligand-specific complex generation and an extended neural relational inference (NRI) framework for trajectory-level interaction analysis. NeuralPlexer was applied to a library of 3094 FDA-approved drugs to generate BCL-2-ligand complex conformations at scale, yielding 1294 structurally acceptable complexes for downstream prioritization. To complement static scoring, filtered candidates were evaluated by molecular docking, anticancer QSAR classification, all-atom molecular dynamics (MD) simulations, and MM\/GBSA binding free-energy calculations. We then extended NRI to protein\u2013ligand trajectories to quantify residue-ligand and residue\u2013residue dynamic couplings, enabling comparison of candidate-specific interaction signatures against the reference BCL-2 inhibitor Venetoclax. Among the prioritized compounds, Relugolix emerged as one of the most compelling hits, combining favorable binding energetics with an NRI-derived interaction pattern closely resembling that of Venetoclax. In vitro experiments supported BCL-2 inhibition by Relugolix in a TR-FRET assay and reduced viability of LN-18 glioma cells (IC50 = 23.55 \u03bcM). Together, these results establish a strategy that couples generative complex prediction with graph-based dynamic inference for structure-guided drug repurposing and identify Relugolix as a tractable scaffold for future BCL-2 inhibitor design.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c01299","type":"journal-article","created":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T22:01:27Z","timestamp":1786744887000},"page":"11361-11376","source":"Crossref","is-referenced-by-count":1,"title":["Targeting BCL-2\nthrough Deep Learning-Based\nDrug Repurposing: A Multimodal Approach Combining Diffusion-Based\nGenerative Modeling, Neural Relational Inference, and In Vitro Validation"],"prefix":"10.1021","volume":"66","author":[{"given":"Ehsan","family":"Sayyah","sequence":"first","affiliation":[{"name":"Bahc\u0327es\u0327ehir University , , ,","place":["I\u0307stanbul, Tu\u0308rkiye, 34349"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6450-5380","authenticated-orcid":true,"given":"Hu\u0308seyin","family":"Tunc\u0327","sequence":"additional","affiliation":[{"name":"Bahc\u0327es\u0327ehir University , , ,","place":["Istanbul, Tu\u0308rkiye, 34349"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asuman","family":"C\u0327elebi","sequence":"additional","affiliation":[{"name":"Bahc\u0327es\u0327ehir University , , ,","place":["Istanbul, Tu\u0308rkiye, 34349"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9014-3838","authenticated-orcid":true,"given":"Timuc\u0327in","family":"Avs\u0327ar","sequence":"additional","affiliation":[{"name":"Bahc\u0327es\u0327ehir University , , ,","place":["Istanbul, Tu\u0308rkiye, 34349"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0426-0905","authenticated-orcid":true,"given":"Serdar","family":"Durdag\u0306\u0131","sequence":"additional","affiliation":[{"name":"Bahc\u0327es\u0327ehir University , , ,","place":["I\u0307stanbul, Tu\u0308rkiye, 34349"]},{"name":"Bahc\u0327es\u0327ehir University , , ,","place":["Istanbul, Tu\u0308rkiye, 34353"]},{"name":"Biruni University , , ,","place":["I\u0307stanbul, Tu\u0308rkiye, 34010"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,8,14]]},"reference":[{"issue":"9","key":"2026091409071943500_cit1","doi-asserted-by":"publisher","first-page":"1003","DOI":"10.1080\/13543776.2022.2116311","article-title":"Patent Landscape of\nInhibitors and PROTACs of the Anti-Apoptotic BCL-2 Family Proteins","volume":"32","author":"Pal","year":"2022","journal-title":"Expert Opin. Ther. Pat."},{"issue":"3","key":"2026091409071943500_cit2","doi-asserted-by":"publisher","first-page":"1111","DOI":"10.1021\/acsptsci.0c00210","article-title":"Hybrid in\nSilico and\nTR-FRET-Guided Discovery of Novel BCL-2 Inhibitors","volume":"4","author":"Sahin","year":"2021","journal-title":"ACS Pharmacol. Transl. Sci."},{"key":"2026091409071943500_cit3","doi-asserted-by":"publisher","first-page":"122181","DOI":"10.1016\/j.lfs.2023.122181","article-title":"Drug Repurposing\nfor the Identification of New Bcl-2 Inhibitors: In Vitro, STD-NMR,\nMolecular Docking, and Dynamic Simulation Studies","volume":"334","author":"Rahman","year":"2023","journal-title":"Life Sci."},{"issue":"3","key":"2026091409071943500_cit4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41419-019-1407-6","article-title":"BCL-2 Family Isoforms\nin Apoptosis and Cancer","volume":"10","author":"Warren","year":"2019","journal-title":"Cell Death Dis."},{"issue":"1","key":"2026091409071943500_cit5","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/s10495-022-01780-7","article-title":"BCL-2 Protein Family:\nAttractive Targets for Cancer Therapy","volume":"28","author":"Kaloni","year":"2023","journal-title":"Apoptosis"},{"key":"2026091409071943500_cit6","doi-asserted-by":"publisher","first-page":"985363","DOI":"10.3389\/fonc.2022.985363","article-title":"The Role of\nBCL-2 Family Proteins in Regulating Apoptosis and Cancer Therapy","volume":"12","author":"Qian","year":"2022","journal-title":"Front. Oncol."},{"issue":"1","key":"2026091409071943500_cit7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41420-022-01225-9","article-title":"A Novel BH3Mimetic\nBcl-2 Inhibitor Promotes Autophagic Cell Death and Reduces in Vivo\nGlioblastoma Tumor Growth","volume":"8","author":"Calis","year":"2022","journal-title":"Cell Death Discovery"},{"key":"2026091409071943500_cit8","doi-asserted-by":"publisher","first-page":"167","DOI":"10.3389\/fchem.2020.00167","article-title":"Integrating Ligand\nand Target-Driven Based Virtual\nScreening Approaches With in Vitro Human Cell Line Models and Time-Resolved\nFluorescence Resonance Energy Transfer Assay to Identify Novel Hit\nCompounds Against BCL-2","volume":"8","author":"Tutumlu","year":"2020","journal-title":"Front. Chem."},{"issue":"5","key":"2026091409071943500_cit9","doi-asserted-by":"publisher","DOI":"10.1002\/cmdc.202500744","article-title":"Advancing\nAccurate Quantification of Protein-Ligand Interactions: Differential\nScanning Calorimetry as a Precision Screening Tool Using BCL-2 as\na Model System","volume":"21","author":"Dinc","year":"2026","journal-title":"ChemMedChem"},{"issue":"43","key":"2026091409071943500_cit10","doi-asserted-by":"publisher","first-page":"50868","DOI":"10.1021\/acsomega.5c03150","article-title":"Targeting\nUbiquitin-Specific Protease 7 (USP7): A Pharmacophore-Guided Drug\nRepurposing and Physics-Based Molecular Simulation Study","volume":"10","author":"Kanan","year":"2025","journal-title":"ACS Omega"},{"issue":"11","key":"2026091409071943500_cit11","doi-asserted-by":"publisher","first-page":"2199","DOI":"10.1007\/s00018-019-03283-2","article-title":"Drug Repurposing Studies of PARP\nInhibitors as a New Therapy for Inherited Retinal Degeneration","volume":"77","author":"Sahaboglu","year":"2020","journal-title":"Cell. Mol. Life Sci."},{"issue":"2","key":"2026091409071943500_cit12","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1038\/s42256-024-00792-z","article-title":"State-Specific\nProtein\u2013Ligand Complex Structure Prediction with a Multiscale\nDeep Generative Model","volume":"6","author":"Qiao","year":"2024","journal-title":"Nat. Mach. Intell."},{"issue":"18","key":"2026091409071943500_cit13","doi-asserted-by":"publisher","first-page":"3513","DOI":"10.1021\/acschemneuro.5c00201","article-title":"Mathematical\nModeling of A\u03b2-42 Dimerization Dynamics: Integrating Physics-Based\nSimulations, Graph-Based Variational Autoencoder-Driven Neural Relational\nInference, and Chaos Theory","volume":"16","author":"Sayyah","year":"2025","journal-title":"ACS Chem. Neurosci."},{"issue":"7873","key":"2026091409071943500_cit14","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly Accurate Protein\nStructure Prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"2026091409071943500_cit15","unstructured":"Kipf, T.; Fetaya, E.; Wang, K. C.; Welling, M.; Zemel, R.\n          Neural Relational Inference\nfor Interacting Systems. In  35th International\nConference on Machine Learning, ICML; Dy, J., Krause, A.,\nEds. Proceedings of Machine Learning Research; PMLR, 2018; Vol. 6, pp 2688\u20132697."},{"issue":"1","key":"2026091409071943500_cit16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-022-29331-3","article-title":"Neural Relational Inference\nto Learn Long-Range Allosteric Interactions in Proteins from Molecular\nDynamics Simulations","volume":"13","author":"Zhu","year":"2022","journal-title":"Nat. Commun."},{"issue":"1","key":"2026091409071943500_cit17","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1021\/acs.jcim.3c01250","article-title":"Chemprop:\nA Machine Learning Package for Chemical Property Prediction","volume":"64","author":"Heid","year":"2024","journal-title":"J. Chem. Inf. Model."},{"issue":"1","key":"2026091409071943500_cit18","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1186\/s13321-021-00522-2","article-title":"GNINA 1.0:\nMolecular\nDocking with Deep Learning","volume":"13","author":"McNutt","year":"2021","journal-title":"J. Cheminf."},{"issue":"4","key":"2026091409071943500_cit19","doi-asserted-by":"publisher","first-page":"459","DOI":"10.3906\/biy-2106-61","article-title":"Binary-QSAR Guided Virtual Screening\nof FDA Approved Drugs and Compounds in Clinical Investigation against\nSARS-CoV-2 Main Protease","volume":"45","author":"Oktay","year":"2021","journal-title":"Turk. J. Biol."},{"issue":"2","key":"2026091409071943500_cit20","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1007\/s11523-022-00944-4","article-title":"Relugolix:\nA Review in Advanced Prostate Cancer","volume":"18","author":"Shirley","year":"2023","journal-title":"Target.\nOncol."},{"issue":"7","key":"2026091409071943500_cit21","doi-asserted-by":"publisher","first-page":"1739","DOI":"10.1021\/jm0306430","article-title":"Glide:\nA New Approach for Rapid, Accurate Docking and Scoring. 1. Method\nand Assessment of Docking Accuracy","volume":"47","author":"Friesner","year":"2004","journal-title":"J. Med.\nChem."},{"issue":"2","key":"2026091409071943500_cit22","doi-asserted-by":"publisher","first-page":"2000012","DOI":"10.1002\/minf.202000012","article-title":"Drug Re-Positioning\nStudies for Novel HIV-1 Inhibitors\nUsing Binary QSAR Models and Multi-Target-Driven In Silico Studies","volume":"40","author":"Dogan","year":"2021","journal-title":"Mol. Inform."},{"issue":"10\u201311","key":"2026091409071943500_cit23","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1080\/00498250600861660","article-title":"Algorithms\nfor Network Analysis in Systems-ADME\/Tox Using the MetaCore and MetaDrug\nPlatforms","volume":"36","author":"Ekins","year":"2006","journal-title":"Xenobiotica"},{"issue":"10","key":"2026091409071943500_cit24","doi-asserted-by":"publisher","first-page":"2525","DOI":"10.1016\/j.bpj.2011.10.024","article-title":"Improving the Physical\nRealism and Structural Accuracy of Protein\nModels by a Two-Step Atomic-Level Energy Minimization","volume":"101","author":"Xu","year":"2011","journal-title":"Biophys. J."},{"issue":"3","key":"2026091409071943500_cit25","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/s10822-013-9644-8","article-title":"Protein and Ligand Preparation: Parameters, Protocols,\nand Influence on Virtual Screening Enrichments","volume":"27","author":"Madhavi Sastry","year":"2013","journal-title":"J. Comput. Aided. Mol. Des."},{"issue":"3","key":"2026091409071943500_cit26","doi-asserted-by":"publisher","first-page":"1863","DOI":"10.1021\/acs.jctc.8b01026","article-title":"OPLS3e: Extending\nForce Field Coverage for Drug-Like Small Molecules","volume":"15","author":"Roos","year":"2019","journal-title":"J. Chem. Theory Comput."},{"issue":"20","key":"2026091409071943500_cit27","doi-asserted-by":"publisher","first-page":"10096","DOI":"10.1063\/1.1808117","article-title":"A Modified TIP3P Water Potential\nfor Simulation with\nEwald Summation","volume":"121","author":"Price","year":"2004","journal-title":"J. Chem. Phys."},{"key":"2026091409071943500_cit28","doi-asserted-by":"crossref","unstructured":"Bowers, K. J.; Chow, E.; Xu, H.; Dror, R. O.; Eastwood, M. P.; Gregersen, B. A.; Klepeis, J. L.; Kolossvary, I.; Moraes, M. A.; Sacerdoti, F. D.; Salmon, J. K.; Shan, Y.; Shaw, D. E.\n          Scalable Algorithms\nfor Molecular\nDynamics Simulations on Commodity Clusters.  Proceedings of the 2006 ACM\/IEEE Conference on Supercomputing, SC\u201906, 2006. 10.1145\/1188455.1188544.","DOI":"10.1145\/1188455.1188544"},{"issue":"8","key":"2026091409071943500_cit29","doi-asserted-by":"publisher","first-page":"4069","DOI":"10.1063\/1.449071","article-title":"The Nose-Hoover\nThermostat","volume":"83","author":"Evans","year":"1985","journal-title":"J.\nChem. Phys."},{"issue":"4","key":"2026091409071943500_cit30","doi-asserted-by":"publisher","first-page":"2635","DOI":"10.1063\/1.463940","article-title":"Nose\u0301\u2013Hoover Chains:\nThe Canonical Ensemble via Continuous Dynamics","volume":"97","author":"Martyna","year":"1992","journal-title":"J. Chem. Phys."},{"issue":"19","key":"2026091409071943500_cit31","doi-asserted-by":"publisher","first-page":"8577","DOI":"10.1063\/1.470117","article-title":"A Smooth Particle Mesh Ewald Method","volume":"103","author":"Essmann","year":"1995","journal-title":"J. Chem. Phys."},{"issue":"2","key":"2026091409071943500_cit32","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1002\/prot.10613","article-title":"A Hierarchical Approach to All-Atom\nProtein Loop Prediction","volume":"55","author":"Jacobson","year":"2004","journal-title":"Proteins"},{"issue":"10","key":"2026091409071943500_cit33","doi-asserted-by":"publisher","first-page":"2794","DOI":"10.1002\/prot.23106","article-title":"The VSGB 2.0 Model: A next Generation\nEnergy Model\nfor High Resolution Protein Structure Modeling","volume":"79","author":"Li","year":"2011","journal-title":"Proteins"}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c01299","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/11361\/66576178\/acs.jcim.6c01299.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/11361\/66576178\/acs.jcim.6c01299.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T13:09:18Z","timestamp":1789391358000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/17\/11361\/5257373\/Targeting-BCL-2-through-Deep-Learning-Based-Drug"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,14]]},"references-count":33,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,8,14]]},"published-print":{"date-parts":[[2026,9,14]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c01299","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,14]]}}}