{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:44:54Z","timestamp":1792784694532,"version":"4.5.0"},"reference-count":43,"publisher":"American Chemical Society (ACS)","issue":"18","license":[{"start":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:00:00Z","timestamp":1789430400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:00:00Z","timestamp":1789430400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:00:00Z","timestamp":1789430400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2022QF111"],"award-info":[{"award-number":["ZR2022QF111"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation of China (NSFC)","award":["62541607"],"award-info":[{"award-number":["62541607"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>While accurate drug-target affinity prediction accelerates drug discovery, prevailing deep learning approaches are often bottlenecked by poor generalization and an inability to quantify prediction confidence. Here, we introduce CogNet-DTA, a novel memory-augmented framework that synergizes historical binding priors with biophysical constraints. Our approach introduces a Chemical Graph Memory Network that facilitates reasoning by analogy through retrieving canonical binding motifs from historical data. To capture precise structural contexts, we leverage ESM-based evolutionary embeddings combined with Contact-Weighted Attention, which injects ESM-derived residue\u2013residue contact probabilities as spatial biases to refine protein-intrinsic structural context. Distinctively, CogNet-DTA utilizes a Chemo-Geometric Routing Module to organize multimodal inputs into positive and negative predictive pathways under a shared memory prior, providing a conceptual, data-driven decomposition of molecular binding affinity. By integrating Monte Carlo Dropout, our model systematically quantifies uncertainty, providing a critical mechanism to filter out low-confidence, high-risk predictions during virtual screening. Extensive evaluations across diverse benchmark datasets demonstrate that CogNet-DTA achieves highly competitive performance in DTA prediction. Notably, it exhibits robust generalization to novel drugs and targets under strict cold-start and homology-based split settings, successfully mitigating sequence similarity bias.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c01177","type":"journal-article","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T16:01:55Z","timestamp":1789488115000},"page":"12163-12178","source":"Crossref","is-referenced-by-count":0,"title":["Decoding Molecular\nBinding Equilibria through Uncertainty-Aware\nMemory Retrieval"],"prefix":"10.1021","volume":"66","author":[{"given":"Huaibin","family":"Hang","sequence":"first","affiliation":[{"name":"Qingdao University of Technology , , , ,","place":["Qingdao, Shandong, China, 266520"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shunpeng","family":"Pang","sequence":"additional","affiliation":[{"name":"Weifang University , , , ,","place":["Weifang, Shandong, China, 261061"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4861-0697","authenticated-orcid":true,"given":"Wensheng","family":"An","sequence":"additional","affiliation":[{"name":"Qingdao University of Technology , , , ,","place":["Qingdao, Shandong, China, 266520"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjian","family":"Ma","sequence":"additional","affiliation":[{"name":"Qingdao University of Technology , , , ,","place":["Qingdao, Shandong, China, 266520"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junxiao","family":"Feng","sequence":"additional","affiliation":[{"name":"Qingdao University of Technology , , , ,","place":["Qingdao, Shandong, China, 266520"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weina","family":"Pang","sequence":"additional","affiliation":[{"name":"Weifang Xinsheng Biotechnology Development Co., Ltd. , , ,","place":["Weifang, Shandong, China, 261205"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0716-5292","authenticated-orcid":true,"given":"Mingjian","family":"Jiang","sequence":"additional","affiliation":[{"name":"Qingdao University of Technology , , , ,","place":["Qingdao, Shandong, China, 266520"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanpeng","family":"Wu","sequence":"additional","affiliation":[{"name":"Shandong University , , , ,","place":["Jinan, Shandong, China, 250031"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Qingdao University of Technology , , , ,","place":["Qingdao, Shandong, China, 266520"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Qingdao University of Technology , , , ,","place":["Qingdao, Shandong, China, 266520"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"2026092810073969700_cit1","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.jhealeco.2016.01.012","article-title":"Innovation in the pharmaceutical\nindustry: New estimates of R&D costs","volume":"47","author":"DiMasi","year":"2016","journal-title":"J.\nHealth Econ."},{"key":"2026092810073969700_cit2","doi-asserted-by":"publisher","first-page":"110438","DOI":"10.1016\/j.compbiomed.2025.110438","article-title":"Drug-Target Interaction\/Affinity\nPrediction: Deep Learning Models and Advances Review","volume":"196","author":"Vefghi","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"2026092810073969700_cit3","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1186\/s12859-016-0890-3","article-title":"A multiple kernel\nlearning algorithm for drug-target interaction prediction","volume":"17","author":"Nascimento","year":"2016","journal-title":"BMC Bioinf."},{"key":"2026092810073969700_cit4","doi-asserted-by":"publisher","first-page":"i821","DOI":"10.1093\/bioinformatics\/bty593","article-title":"DeepDTA: deep drug-target binding\naffinity prediction","volume":"34","author":"O\u0308ztu\u0308rk","year":"2018","journal-title":"Bioinformatics"},{"key":"2026092810073969700_cit5","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1109\/TCBB.2022.3170365","article-title":"AttentionDTA: Drug-Target\nBinding Affinity Prediction by Sequence-Based\nDeep Learning With Attention Mechanism","volume":"20","author":"Zhao","year":"2023","journal-title":"IEEE\/ACM\nTrans. Comput. Biol. Bioinf."},{"key":"2026092810073969700_cit6","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1093\/bioinformatics\/btaa921","article-title":"GraphDTA:\npredicting drug-target binding affinity with graph neural networks","volume":"37","author":"Nguyen","year":"2021","journal-title":"Bioinformatics"},{"key":"2026092810073969700_cit7","volume-title":"How Powerful\nare Graph Neural Networks?","author":"Xu","year":"2019"},{"key":"2026092810073969700_cit8","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1186\/s13321-024-00938-6","article-title":"DeepTGIN: a novel hybrid\nmultimodal approach using transformers and\ngraph isomorphism networks for protein-ligand binding affinity prediction","volume":"16","author":"Wang","year":"2024","journal-title":"J. Cheminf."},{"key":"2026092810073969700_cit9","doi-asserted-by":"publisher","first-page":"2006","DOI":"10.1021\/acs.jcim.5c02334","article-title":"More Accurate\nBinding Affinity Prediction Using Protein Homology and Ligand-Based\nTransfer Learning","volume":"66","author":"Purnomo","year":"2026","journal-title":"J. Chem. Inf. Model."},{"key":"2026092810073969700_cit10","doi-asserted-by":"publisher","first-page":"101508","DOI":"10.1016\/j.jpha.2025.101508","article-title":"Intelligence on the\ngraph: Graph neural networks for mechanistic drug target discovery","volume":"16","author":"Chen","year":"2026","journal-title":"J. Pharm. Anal."},{"key":"2026092810073969700_cit11","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1039\/D1SC05180F","article-title":"MGraphDTA:\ndeep multiscale graph neural network for explainable drug-target binding\naffinity prediction","volume":"13","author":"Yang","year":"2022","journal-title":"Chem. Sci."},{"key":"2026092810073969700_cit12","doi-asserted-by":"publisher","first-page":"106110","DOI":"10.1016\/j.bspc.2024.106110","article-title":"GDilatedDTA:\nGraph dilation convolution strategy for drug target binding affinity\nprediction","volume":"92","author":"Zhang","year":"2024","journal-title":"Biomed. Signal Process. Control."},{"key":"2026092810073969700_cit13","first-page":"17176","article-title":"Drug Discovery under\nCovariate Shift with Domain-Informed Prior Distributions over Functions","volume-title":"Proceedings of Machine Learning Research","author":"Klarner","year":"2023"},{"key":"2026092810073969700_cit14","doi-asserted-by":"publisher","first-page":"808","DOI":"10.1073\/pnas.0610202104","article-title":"Motifs\nfor molecular recognition exploiting hydrophobic enclosure in protein-ligand\nbinding","volume":"104","author":"Young","year":"2007","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"key":"2026092810073969700_cit15","doi-asserted-by":"publisher","first-page":"bbac269","DOI":"10.1093\/bib\/bbac269","article-title":"Mitigating\ncold-start problems in\ndrug-target affinity prediction with interaction knowledge transferring","volume":"23","author":"Nguyen","year":"2022","journal-title":"Briefings Bioinf."},{"key":"2026092810073969700_cit16","doi-asserted-by":"publisher","first-page":"bbab506","DOI":"10.1093\/bib\/bbab506","article-title":"FusionDTA: attention-based feature\npolymerizer and knowledge distillation for drug-target binding affinity\nprediction","volume":"23","author":"Yuan","year":"2022","journal-title":"Briefings Bioinf."},{"key":"2026092810073969700_cit17","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1186\/s12864-025-11234-4","article-title":"GS-DTA: integrating\ngraph and sequence models for predicting drug-target binding affinity","volume":"26","author":"Luo","year":"2025","journal-title":"BMC Genomics"},{"key":"2026092810073969700_cit18","doi-asserted-by":"publisher","first-page":"1989","DOI":"10.1038\/s41467-023-37572-z","article-title":"Improving\nthe generalizability of\nprotein-ligand binding predictions with AI-Bind","volume":"14","author":"Chatterjee","year":"2023","journal-title":"Nat. Commun."},{"key":"2026092810073969700_cit19","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1146\/annurev-biophys-070816-033654","article-title":"Predicting Binding\nFree Energies: Frontiers and Benchmarks","volume":"46","author":"Mobley","year":"2017","journal-title":"Annu.\nRev. Biophys."},{"issue":"3","key":"2026092810073969700_cit20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1011036","article-title":"BiComp-DTA: Drug-target binding affinity\nprediction through complementary biological-related and compression-based\nfeaturization approach","volume":"19","author":"Kalemati","year":"2023","journal-title":"PLoS Comput. Biol."},{"key":"2026092810073969700_cit21","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale\nprediction of atomic-level protein structure with\na language model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"key":"2026092810073969700_cit22","doi-asserted-by":"publisher","first-page":"107512","DOI":"10.1016\/j.compbiomed.2023.107512","article-title":"GPCNDTA: Prediction\nof drug-target binding affinity through cross-attention networks augmented\nwith graph features and pharmacophores","volume":"166","author":"Zhang","year":"2023","journal-title":"Comput.\nBiol. Med."},{"key":"2026092810073969700_cit23","article-title":"Learning protein\nsequence embeddings using information from structure","author":"Bepler","year":"2019","journal-title":"Int. Conf. Learn. Representations."},{"key":"2026092810073969700_cit24","first-page":"6533","volume-title":"Protein Interface\nPrediction using\nGraph Convolutional Networks","author":"Fout","year":"2017"},{"key":"2026092810073969700_cit25","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.inffus.2021.05.008","article-title":"A review of\nuncertainty quantification in deep learning: Techniques, applications\nand challenges","volume":"76","author":"Abdar","year":"2021","journal-title":"Inf. Fusion"},{"key":"2026092810073969700_cit26","doi-asserted-by":"publisher","first-page":"btaf512","DOI":"10.1093\/bioinformatics\/btaf512","article-title":"UAMRL: multi-granularity\nuncertainty-aware multimodal representation learning for drug-target\naffinity prediction","volume":"41","author":"Xu","year":"2025","journal-title":"Bioinformatics"},{"key":"2026092810073969700_cit27","doi-asserted-by":"publisher","first-page":"1658","DOI":"10.1093\/bioinformatics\/btl158","article-title":"Cd-hit: a fast program\nfor clustering and comparing\nlarge sets of protein or nucleotide sequences","volume":"22","author":"Li","year":"2006","journal-title":"Bioinformatics"},{"key":"2026092810073969700_cit28","first-page":"1","volume-title":"Gated End-to-End Memory Networks","author":"Liu","year":"2017"},{"key":"2026092810073969700_cit29","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"SMILES, a\nchemical language and information system. 1. Introduction to methodology\nand encoding rules","volume":"28","author":"Weininger","year":"1988","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"2026092810073969700_cit30","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-Connectivity\nFingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J. Chem.\nInf. Model."},{"key":"2026092810073969700_cit31","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1005324","article-title":"Accurate De Novo Prediction\nof Protein Contact Map by Ultra-Deep Learning Model","volume":"13","author":"Wang","year":"2017","journal-title":"PLoS Comput. Biol."},{"key":"2026092810073969700_cit32","volume-title":"How Attentive are Graph Attention Networks?","author":"Brody","year":"2022"},{"key":"2026092810073969700_cit33","doi-asserted-by":"publisher","first-page":"6999","DOI":"10.1109\/TNNLS.2021.3084827","article-title":"A Survey of Convolutional\nNeural Networks: Analysis, Applications, and Prospects","volume":"33","author":"Li","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"2026092810073969700_cit34","doi-asserted-by":"publisher","first-page":"60","DOI":"10.12338\/j.issn.2096-9015.2025.0204","article-title":"Exploration of Deep\nLearning Uncertainty Based on Monte Carlo Dropout","volume":"70","author":"Wang","year":"2026","journal-title":"Metrol. Sci. Technol."},{"key":"2026092810073969700_cit35","doi-asserted-by":"publisher","first-page":"1046","DOI":"10.1038\/nbt.1990","article-title":"Comprehensive\nanalysis of kinase inhibitor selectivity","volume":"29","author":"Davis","year":"2011","journal-title":"Nat.\nBiotechnol."},{"key":"2026092810073969700_cit36","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1021\/ci400709d","article-title":"Making sense\nof large-scale kinase\ninhibitor bioactivity data sets: a comparative and integrative analysis","volume":"54","author":"Tang","year":"2014","journal-title":"J. Chem. Inf. Model."},{"key":"2026092810073969700_cit37","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1038\/nchembio.530","article-title":"Navigating the kinome","volume":"7","author":"Metz","year":"2011","journal-title":"Nat. Chem.\nBiol."},{"key":"2026092810073969700_cit38","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1093\/bioinformatics\/btw680","article-title":"tcpl: the\nToxCast pipeline for high-throughput screening data","volume":"33","author":"Filer","year":"2017","journal-title":"Bioinformatics"},{"key":"2026092810073969700_cit39","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1093\/bioinformatics\/btu626","article-title":"PDB-wide collection\nof binding data:\ncurrent status of the PDBbind database","volume":"31","author":"Liu","year":"2015","journal-title":"Bioinformatics"},{"key":"2026092810073969700_cit40","doi-asserted-by":"publisher","first-page":"730","DOI":"10.1021\/acs.jpcb.5c08598","article-title":"Leak Proof\nPDBBind: A Reorganized\nData Set of Protein-Ligand Complexes for More Generalizable Binding\nAffinity Prediction","volume":"130","author":"Li","year":"2026","journal-title":"J. Phys. Chem. B"},{"key":"2026092810073969700_cit41","doi-asserted-by":"publisher","first-page":"1713","DOI":"10.1038\/s42256-025-01124-5","article-title":"Resolving\ndata bias improves generalization in binding\naffinity prediction","volume":"7","author":"Graber","year":"2025","journal-title":"Nat. Mach. Intell"},{"key":"2026092810073969700_cit42","doi-asserted-by":"publisher","first-page":"8326","DOI":"10.3390\/ijms24098326","article-title":"MSGNN-DTA:\nMulti-Scale Topological Feature Fusion Based\non Graph Neural Networks for Drug-Target Binding Affinity Prediction","volume":"24","author":"Wang","year":"2023","journal-title":"Int. J. Mol. Sci."},{"key":"2026092810073969700_cit43","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1038\/s41746-025-01464-x","article-title":"Dual modality\nfeature fused neural network integrating binding site information\nfor drug target affinity prediction","volume":"8","author":"He","year":"2025","journal-title":"NPJ. Digital\nMed."}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c01177","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/18\/12163\/68518148\/acs.jcim.6c01177.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/18\/12163\/68518148\/acs.jcim.6c01177.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T14:29:39Z","timestamp":1790605779000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/18\/12163\/5430414\/Decoding-Molecular-Binding-Equilibria-through"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,15]]},"references-count":43,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9,15]]},"published-print":{"date-parts":[[2026,9,28]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c01177","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,15]]}}}