{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T09:27:31Z","timestamp":1791538051960,"version":"4.3.4"},"reference-count":42,"publisher":"American Chemical Society (ACS)","issue":"17","license":[{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/na","name":"No Funding","doi-asserted-by":"publisher","award":["NA"],"award-info":[{"award-number":["NA"]}],"id":[{"id":"10.13039\/na","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>PROTACs recruit an E3 ligase to a protein of interest via a bifunctional linker, and their activity is critically dependent on the geometry and chemical integrity of that linker. Diffusion-based generative models, which operate in continuous coordinate space, lack explicit mechanisms for enforcing discrete bond connectivity under fixed anchor constraints; as a result, they routinely produce linker structures that are geometrically plausible yet chemically disconnected or valence invalid. Because these generation artifacts arise from a systematic gap between the continuous output space and the discrete requirements of chemical bonding, they recur across samples and are not remedied by naive resampling. Pro-GAT is a graph attention-based framework for geometry-preserving molecular graph repair that operates on chemically disconnected diffusion-generated PROTAC candidates by predicting bounded coordinate corrections and constrained atom-type modifications through geometry-aware graph attention layers. The model is trained on PROTAC data sets with introduced disconnections to address systematic connectivity challenges inherent to diffusion-based PROTAC generation under fixed anchor constraints and recovers 31.58% of disconnected structures in the DiffPROTAC test set. When combined with DiffPROTAC and DiffLinker fine-tuned on PROTAC-specific data, Pro-GAT improves the proportion of chemically valid candidates in the aggregated output from 76.70% to 83.92% and from 63.16% to 68.73%, while maintaining uniqueness levels of 80.18% and 63.80% among valid candidates, respectively, thereby converting otherwise unusable disconnected diffusion outputs into viable PROTAC candidates. Structural validation was performed across three experimentally characterized ternary complexes: 7Z76 (SMARCA2\u2013VHL), 7JTO (WDR5\u2013VHL), and 6W8I (BTK\u2013cIAP1), where repaired candidates yielded docking scores comparable to reference crystal poses across all three systems; in the BTK\u2013cIAP1 case (6W8I), repair produced an improvement from \u22129.9 to \u221211.3 kcal\/mol, with anchor coordinates fixed throughout repair by construction.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c01049","type":"journal-article","created":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T07:11:56Z","timestamp":1788419516000},"page":"11433-11444","source":"Crossref","is-referenced-by-count":1,"title":["Pro-GAT: Reconnecting Fragmented PROTACs Using Graph\nAttention Transformer"],"prefix":"10.1021","volume":"66","author":[{"given":"Saahithi","family":"Vemuri","sequence":"first","affiliation":[{"name":"Keshav Memorial College of Engineering , , Ibrahimpatnam , , ,","place":["Hyderabad, Telangana, India, 501510"]},{"name":"Drugparadigm Research Lab , Uppal , , ,","place":["Hyderabad, Telangana, India, 500039"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laxmi Priya","family":"Bijigiri","sequence":"additional","affiliation":[{"name":"Keshav Memorial College of Engineering , , Ibrahimpatnam , , ,","place":["Hyderabad, Telangana, India, 501510"]},{"name":"Drugparadigm Research Lab , Uppal , , ,","place":["Hyderabad, Telangana, India, 500039"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanjana","family":"Gogte","sequence":"additional","affiliation":[{"name":"Drugparadigm Research Lab , Uppal , , ,","place":["Hyderabad, Telangana, India, 500039"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0991-5003","authenticated-orcid":true,"given":"Vani","family":"Kondaparthi","sequence":"additional","affiliation":[{"name":"Drugparadigm Research Lab , Uppal , , ,","place":["Hyderabad, Telangana, India, 500039"]},{"name":"Keshav Memorial Engineering College , , Uppal , , ,","place":["Hyderabad, Telangana, India, 500088"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,8,31]]},"reference":[{"key":"2026091409064228700_cit1","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2022.103395","article-title":"PROTAC\ntechnology: A new drug design for chemical biology with many challenges\nin drug discovery","volume":"28","author":"Guedeney","year":"2023","journal-title":"Drug Discovery Today"},{"key":"2026091409064228700_cit2","doi-asserted-by":"publisher","DOI":"10.2533\/chimia.2020.274","article-title":"Exploring the Ubiquitin-Proteasome\nSystem (UPS) through\nPROTAC Technology","volume":"74","author":"Cecchini","year":"2020","journal-title":"Chimia"},{"key":"2026091409064228700_cit3","doi-asserted-by":"publisher","DOI":"10.1002\/advs.202508138","article-title":"Interpretable\nPROTAC Degradation Prediction With Structure-Informed\nDeep Ternary Attention Framework","volume":"12","author":"Chen","year":"2025","journal-title":"Adv. Sci."},{"key":"2026091409064228700_cit4","doi-asserted-by":"publisher","DOI":"10.1016\/j.seminoncol.2025.152339","article-title":"S. Exploring the clinical trials,\nregulatory insights,\nand challenges of PROTACs in oncology","volume":"52","author":"Joga","year":"2025","journal-title":"Semin.\nOncol."},{"key":"2026091409064228700_cit5","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1021\/acs.biochem.4c00577","article-title":"Journey of PROTAC:\nFrom Bench to Clinical Trial and Beyond","volume":"64","author":"Berkley","year":"2025","journal-title":"Biochemistry"},{"key":"2026091409064228700_cit6","doi-asserted-by":"publisher","DOI":"10.1002\/fsn3.70011","article-title":"Navigating\nPROTACs in Cancer Therapy: Advancements,\nChallenges, and Future Horizons","volume":"13","author":"Ibrahim","year":"2025","journal-title":"Food Sci. Nutr."},{"key":"2026091409064228700_cit7","doi-asserted-by":"publisher","DOI":"10.1186\/s13045-020-00885-3","article-title":"Proteolysis-targeting\nchimera (PROTAC) for targeted protein degradation\nand cancer therapy","volume":"13","author":"Li","year":"2020","journal-title":"J. Hematol. Oncol."},{"key":"2026091409064228700_cit8","doi-asserted-by":"publisher","first-page":"4266","DOI":"10.1016\/j.apsb.2024.04.007","article-title":"Characteristic\nroadmap of linker governs the rational design of PROTACs","volume":"14","author":"Dong","year":"2024","journal-title":"Acta Pharm. Sin. B"},{"key":"2026091409064228700_cit9","doi-asserted-by":"publisher","first-page":"5408","DOI":"10.1021\/acs.jcim.3c00603","article-title":"Targeted\nProtein Degradation: Advances,\nChallenges, and Prospects for Computational Methods","volume":"63","author":"Mostofian","year":"2023","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409064228700_cit10","doi-asserted-by":"publisher","DOI":"10.1186\/s43556-021-00043-2","article-title":"E3 ubiquitin\nligases:\nstyles, structures and functions","volume":"2","author":"Yang","year":"2021","journal-title":"Mol. Biomed."},{"key":"2026091409064228700_cit11","doi-asserted-by":"publisher","first-page":"934","DOI":"10.1016\/j.chembiol.2021.04.011","article-title":"Targeted protein\ndegradation: A promise for undruggable\nproteins","volume":"28","author":"Samarasinghe","year":"2021","journal-title":"Cell Chem. Biol."},{"key":"2026091409064228700_cit12","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbae358","article-title":"DiffPROTACs is a deep\nlearning-based generator for proteolysis targeting chimeras","volume":"25","author":"Li","year":"2024","journal-title":"Briefings Bioinf."},{"key":"2026091409064228700_cit13","unstructured":"Ho, J.; Jain, A.; Abbeel, P.\n          Denoising Diffusion Probabilistic\nModels, 2020. arXiv:2006.11239. arXiv.org\ne-Print archive. https:\/\/arxiv.org\/abs\/2006.11239."},{"key":"2026091409064228700_cit14","doi-asserted-by":"crossref","unstructured":"Lim, S.; Yoon, E.; Byun, T.; Kang, T.; Kim, S.; Lee, K.; et al. In  Score-Based Generative Modeling Through\nStochastic\nEvolution Equations in Hilbert Spaces; Proceedings of the\n37th International Conference on Neural Information Processing Systems Curran Associates Inc.: New Orleans,\nLA, USA, 2023.","DOI":"10.52202\/075280-1645"},{"key":"2026091409064228700_cit15","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1021\/acs.jcim.8b00839","article-title":"GuacaMol: Benchmarking\nModels for de Novo Molecular Design","volume":"59","author":"Brown","year":"2019","journal-title":"J. Chem.\nInf. Model."},{"key":"2026091409064228700_cit16","doi-asserted-by":"publisher","first-page":"1983","DOI":"10.1021\/acs.jcim.9b01120","article-title":"Deep Generative\nModels for 3D Linker Design","volume":"60","author":"Imrie","year":"2020","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409064228700_cit17","unstructured":"Huang, Y.; Peng, X.; Ma, J.; Zhang, M.\n          3DLinker: An E(3) Equivariant Variational Autoencoder\nfor Molecular Linker Design, 2022. arXiv:2205.07309.\narXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2205.07309."},{"key":"2026091409064228700_cit18","doi-asserted-by":"crossref","unstructured":"Guo, J.; Knuth, F.; Margreitter, C.; Janet, J. P.; Papadopoulos, K.; Engkvist, O.; Patronov, A.\n          Link-INVENT: Generative Linker\nDesign with Reinforcement Learning\n          ChemRxiv\n          2022\n          10.26434\/chemrxiv-2022-qkx9f.","DOI":"10.26434\/chemrxiv-2022-qkx9f"},{"key":"2026091409064228700_cit19","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/abcf91","article-title":"Graph\nnetworks for molecular\ndesign","volume":"2","author":"Mercado","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"2026091409064228700_cit20","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad323","article-title":"3D based generative\nPROTAC linker design with reinforcement\nlearning","volume":"24","author":"Li","year":"2023","journal-title":"Briefings Bioinform."},{"key":"2026091409064228700_cit21","doi-asserted-by":"publisher","first-page":"D1510","DOI":"10.1093\/nar\/gkae768","article-title":"PROTAC-DB 3.0: an updated database of PROTACs with extended pharmacokinetic\nparameters","volume":"53","author":"Ge","year":"2025","journal-title":"Nucleic Acids Res."},{"key":"2026091409064228700_cit22","doi-asserted-by":"publisher","first-page":"273","DOI":"10.37349\/etat.2020.00018","article-title":"Current strategies for the design\nof PROTAC linkers: a critical review","volume":"1","author":"Troup","year":"2020","journal-title":"Explor.\nTargeted Anti-Tumor Ther."},{"key":"2026091409064228700_cit23","unstructured":"Velickovic, P.; Cucurull, G.; Casanova, A.; Romero, A.; Lio\u0300, P.; Bengio, Y.\n          Graph\nAttention Networks. 2017. arXiv:1710.10903.\narXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1710.10903."},{"key":"2026091409064228700_cit24","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating\nerrors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"2026091409064228700_cit25","first-page":"9","volume-title":"Efficient BackProp","author":"LeCun","year":"2012"},{"key":"2026091409064228700_cit26","doi-asserted-by":"publisher","DOI":"10.3390\/biom13030503","article-title":"Molecular Property Prediction by\nCombining LSTM and GAT","volume":"13","author":"Xu","year":"2023","journal-title":"Biomolecules"},{"key":"2026091409064228700_cit27","unstructured":"Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A. N. In  Attention\nis All you Need, Advances in Neural Information Processing\nSystems; NeurIPS, 2017."},{"key":"2026091409064228700_cit28","unstructured":"Gilmer, J.; Schoenholz, S. S.; Riley, P. F.; Vinyals, O.; Dahl, G. E. In  Neural Message Passing\nfor Quantum Chemistry, International Conference on Machine\nLearning; PLMR, 2017."},{"key":"2026091409064228700_cit29","unstructured":"Battaglia, P. W.; Hamrick, J. B.; Bapst, V.; Sanchez-Gonzalez, A.; Zambaldi, V. F.; Malinowski, M.; et al.\n          Relational\ninductive biases, deep learning, and graph networks, 2018. arXiv:1806.01261. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1806.01261."},{"key":"2026091409064228700_cit30","doi-asserted-by":"publisher","first-page":"3052","DOI":"10.1109\/TNNLS.2025.3646122","article-title":"Graph\nTransformers: A Survey","volume":"37","author":"Shehzad","year":"2024","journal-title":"IEEE Trans. Neural\nNetworks Learn. Syst."},{"key":"2026091409064228700_cit31","unstructured":"Satorras, V. G.; Hoogeboom, E.; Welling, M. In  E(n) Equivariant Graph\nNeural Networks,; Proceedings of the 38th International Conference on Machine Learning; PMLR, 2021."},{"key":"2026091409064228700_cit32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100520","article-title":"Are we ready for\na new paradigm shift? A survey on visual deep MLP","volume":"3","author":"Liu","year":"2022","journal-title":"Patterns"},{"key":"2026091409064228700_cit33","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1016\/j.neunet.2021.08.015","article-title":"On the approximation of functions\nby tanh neural networks","volume":"143","author":"De Ryck","year":"2021","journal-title":"Neural Networks"},{"key":"2026091409064228700_cit34","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1002\/(SICI)1096-987X(199604)17:5\/6&lt;616:AID-JCC5&gt;3.0.CO;2-X","article-title":"Merck molecular\nforce field. V. Extension of MMFF94 using experimental data, additional\ncomputational data, and empirical rules","volume":"17","author":"Halgren","year":"1996","journal-title":"J.\nComput. Chem."},{"key":"2026091409064228700_cit35","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1096987X(199604)17:5\/6&lt;520:AID-JCC2&gt;3.0.CO;2-W","article-title":"Merck molecular\nforce field. II. MMFF94 van der Waals and electrostatic parameters\nfor intermolecular interactions","volume":"17","author":"Halgren","year":"1996","journal-title":"J. Comput.\nChem."},{"key":"2026091409064228700_cit36","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1002\/(SICI)1096-987X(199604)17:5\/6&lt;553:AID-JCC3&gt;3.0.CO;2-T","article-title":"Merck molecular\nforce field. III. Molecular geometries and vibrational frequencies\nfor MMFF94","volume":"17","author":"Halgren","year":"1996","journal-title":"J. Comput. Chem."},{"key":"2026091409064228700_cit37","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1002\/(SICI)1096-987X(199604)17:5\/6&lt;587:AID-JCC4&gt;3.0.CO;2-Q","article-title":"Merck molecular\nforce field. IV. Conformational energies\nand geometries for MMFF94","volume":"17","author":"Halgren","year":"1996","journal-title":"J. Comput. Chem."},{"key":"2026091409064228700_cit38","doi-asserted-by":"publisher","first-page":"490","DOI":"10.1002\/(SICI)1096-987X(199604)17:5\/6&lt;490:AID-JCC1&gt;3.0.CO;2-P","article-title":"Merck molecular\nforce field. I. Basis, form, scope, parameterization, and performance\nof MMFF94","volume":"17","author":"Halgren","year":"1996","journal-title":"J. Comput. Chem."},{"key":"2026091409064228700_cit39","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1038\/nchem.1243","article-title":"Quantifying\nthe chemical beauty of drugs","volume":"4","author":"Bickerton","year":"2012","journal-title":"Nat. Chem."},{"key":"2026091409064228700_cit40","doi-asserted-by":"publisher","DOI":"10.1186\/1758-2946-1-8","article-title":"Estimation of synthetic accessibility score of drug-like\nmolecules based on molecular complexity and fragment contributions","volume":"1","author":"Ertl","year":"2009","journal-title":"J. Cheminform."},{"issue":"8","key":"2026091409064228700_cit41","doi-asserted-by":"publisher","first-page":"3891","DOI":"10.1021\/acs.jcim.1c00203","article-title":"AutoDock Vina 1.2.0:\nNew Docking Methods, Expanded Force Field, and Python Bindings","volume":"61","author":"Eberhardt","year":"2021","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409064228700_cit42","doi-asserted-by":"publisher","first-page":"D1367","DOI":"10.1093\/nar\/gkac946","article-title":"PROTAC-DB 2.0: an updated\ndatabase of PROTACs","volume":"51","author":"Weng","year":"2023","journal-title":"Nucleic Acids Res."}],"container-title":["Journal of Chemical Information and Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c01049","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/11433\/68064461\/acs.jcim.6c01049.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/11433\/68064461\/acs.jcim.6c01049.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T13:18:12Z","timestamp":1789391892000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/17\/11433\/5391811\/Pro-GAT-Reconnecting-Fragmented-PROTACs-Using"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,31]]},"references-count":42,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,8,31]]},"published-print":{"date-parts":[[2026,9,14]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c01049","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,31]]}}}