{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T21:14:46Z","timestamp":1793049286153,"version":"4.5.0"},"posted":{"date-parts":[[2026,6,19]]},"group-title":"Bioinformatics","reference-count":64,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T00:00:00Z","timestamp":1781827200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,6,19]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                <jats:p>RNAs are important therapeutic targets, however identifying ligandable small-molecule binding pockets remains a major barrier to RNA-targeted drug discovery. Here, SMARTPocket, an atomic-level geometric deep learning framework for predicting RNA-small molecule binding pockets directly from three-dimensional structure is introduced. SMARTPocket represents RNA as full-atom point clouds and uses transfer learning from more than 110,000 protein binding interface structures to overcome the limited number of experimentally elucidated RNA-ligand complexes. Across four established single-chain benchmarks and three broader curated benchmarks, SMARTPocket consistently outperforms existing RNA pocket predictors and general biomolecular modeling approaches. The model generalizes to apo RNA structures when conformational changes are modest, identifies cryptic ligandable pockets, and recapitulates experimentally validated binding sites in the SARS-CoV-2 frameshifting element and an RNA aptamer evolved to bind small molecules. SMARTPocket-guided docking further improves near-native RNA-ligand pose recovery and computational efficiency compared with blind docking. These results establish SMARTPocket as a generalizable framework for structure-based identification of ligandable RNA pockets and for accelerating discovery of RNA-targeted small molecules.<\/jats:p>","DOI":"10.64898\/2026.06.18.732920","type":"posted-content","created":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T04:05:19Z","timestamp":1781928319000},"source":"Crossref","is-referenced-by-count":4,"title":["Geometric Deep Learning Reveals Ligandable and Cryptic RNA Binding Small Molecule Pockets (SMARTPocket)"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7569-7087","authenticated-orcid":false,"given":"Riddhish H.","family":"Thakare","sequence":"first","affiliation":[{"name":"University of Florida, Department of Medicinal Chemistry, Center for Natural Products, Drug Discovery and Development, Gainesville, FL 32610, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9270-9145","authenticated-orcid":false,"given":"Amirhossein","family":"Taghavi","sequence":"additional","affiliation":[{"name":"The Herbert Wertheim UF Scripps Institute for Biomedical Innovation and Technology, Department of Chemistry, 130 Scripps Way, Jupiter, FL 33458, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0072-039X","authenticated-orcid":false,"given":"Jielei","family":"Wang","sequence":"additional","affiliation":[{"name":"The Herbert Wertheim UF Scripps Institute for Biomedical Innovation and Technology, Department of Chemistry, 130 Scripps Way, Jupiter, FL 33458, USA"},{"name":"The Scripps Research Institute, Department of Chemistry, 130 Scripps Way, Jupiter, FL 33458, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7829-3240","authenticated-orcid":false,"given":"Jessica L.","family":"Childs-Disney","sequence":"additional","affiliation":[{"name":"The Herbert Wertheim UF Scripps Institute for Biomedical Innovation and Technology, Department of Chemistry, 130 Scripps Way, Jupiter, FL 33458, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9460-3168","authenticated-orcid":false,"given":"Chenglong","family":"Li","sequence":"additional","affiliation":[{"name":"University of Florida, Department of Medicinal Chemistry, Center for Natural Products, Drug Discovery and Development, Gainesville, FL 32610, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8486-1796","authenticated-orcid":false,"given":"Matthew D.","family":"Disney","sequence":"additional","affiliation":[{"name":"The Herbert Wertheim UF Scripps Institute for Biomedical Innovation and Technology, Department of Chemistry, 130 Scripps Way, Jupiter, FL 33458, USA"},{"name":"The Scripps Research Institute, Department of Chemistry, 130 Scripps Way, Jupiter, FL 33458, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6277-4189","authenticated-orcid":false,"given":"Yanjun","family":"Li","sequence":"additional","affiliation":[{"name":"University of Florida, Department of Medicinal Chemistry, Center for Natural Products, Drug Discovery and Development, Gainesville, FL 32610, USA"},{"name":"University of Florida, Department of Computer & Information Science & Engineering, Gainesville, FL 32611, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026062216101423000_2026.06.18.732920v1.1","doi-asserted-by":"crossref","first-page":"714","DOI":"10.1016\/j.cmet.2018.03.004","article-title":"RNA-targeted therapeutics","volume":"27","year":"2018","journal-title":"Cell metabolism"},{"key":"2026062216101423000_2026.06.18.732920v1.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2009.02.011"},{"key":"2026062216101423000_2026.06.18.732920v1.3","doi-asserted-by":"publisher","DOI":"10.1038\/s41573-022-00521-4"},{"key":"2026062216101423000_2026.06.18.732920v1.4","doi-asserted-by":"publisher","DOI":"10.1021\/cr0681546"},{"key":"2026062216101423000_2026.06.18.732920v1.5","doi-asserted-by":"crossref","first-page":"9179","DOI":"10.1038\/srep09179","article-title":"Rsite: a computational method to identify the functional sites of noncoding RNAs","volume":"5","year":"2015","journal-title":"Scientific Reports"},{"key":"2026062216101423000_2026.06.18.732920v1.6","doi-asserted-by":"crossref","first-page":"19016","DOI":"10.1038\/srep19016","article-title":"Rsite2: an efficient computational method to predict the functional sites of noncoding RNAs","volume":"6","year":"2016","journal-title":"Scientific Reports"},{"key":"2026062216101423000_2026.06.18.732920v1.7","doi-asserted-by":"crossref","first-page":"3131","DOI":"10.1093\/bioinformatics\/bty345","article-title":"RBind: computational network method to predict RNA binding sites","volume":"34","year":"2018","journal-title":"Bioinformatics"},{"key":"2026062216101423000_2026.06.18.732920v1.8","first-page":"bbad482","article-title":"RNet: a network strategy to predict RNA binding preferences","volume":"25","year":"2024","journal-title":"Briefings in Bioinformatics"},{"key":"2026062216101423000_2026.06.18.732920v1.9","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa1092"},{"key":"2026062216101423000_2026.06.18.732920v1.10","doi-asserted-by":"crossref","first-page":"6979","DOI":"10.1021\/acs.jcim.4c01264","article-title":"Predicting small molecule binding nucleotides in RNA structures using RNA surface topography","volume":"64","year":"2024","journal-title":"Journal of Chemical Information and Modeling"},{"key":"2026062216101423000_2026.06.18.732920v1.11","doi-asserted-by":"crossref","first-page":"bbac486","DOI":"10.1093\/bib\/bbac486","article-title":"RLBind: a deep learning method to predict RNA\u2013ligand binding sites","volume":"24","year":"2023","journal-title":"Briefings in Bioinformatics"},{"key":"2026062216101423000_2026.06.18.732920v1.12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmb.2025.169010"},{"key":"2026062216101423000_2026.06.18.732920v1.13","doi-asserted-by":"crossref","first-page":"8448","DOI":"10.1021\/acs.jcim.5c00605","article-title":"GATRsite: RNA\u2013ligand binding site prediction using graph attention networks and pretrained RNA language models","volume":"65","year":"2025","journal-title":"Journal of Chemical Information and Modeling"},{"key":"2026062216101423000_2026.06.18.732920v1.14","unstructured":"Xia, Y. et al. Deciphering RNA\u2013ligand binding specificity with GerNA-Bind. Nature Machine Intelligence, 1\u201313 (2025)."},{"key":"2026062216101423000_2026.06.18.732920v1.15","doi-asserted-by":"crossref","unstructured":"Jiang, S. et al. Small Molecule Approach to RNA Targeting Binder Discovery (SMARTBind) Using Deep Learning Without Structural Input. bioRxiv (2025).","DOI":"10.1101\/2025.09.24.678312"},{"key":"2026062216101423000_2026.06.18.732920v1.16","first-page":"151","article-title":"Fpocketr: a platform for identification and analysis of ligand-binding pockets in RNA","volume":"21","year":"2025","journal-title":"ACS Chemical Biology"},{"key":"2026062216101423000_2026.06.18.732920v1.17","doi-asserted-by":"crossref","first-page":"5725","DOI":"10.1038\/s41467-024-49638-7","article-title":"Identifying small-molecules binding sites in RNA conformational ensembles with SHAMAN","volume":"15","year":"2024","journal-title":"Nature communications"},{"key":"2026062216101423000_2026.06.18.732920v1.18","doi-asserted-by":"crossref","first-page":"2175","DOI":"10.1038\/s41467-023-37701-8","article-title":"PeSTo: parameter-free geometric deep learning for accurate prediction of protein binding interfaces","volume":"14","year":"2023","journal-title":"Nature communications"},{"key":"2026062216101423000_2026.06.18.732920v1.19","unstructured":"Vaswani, A. et al. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"2026062216101423000_2026.06.18.732920v1.20","doi-asserted-by":"publisher","DOI":"10.1038\/S41586-024-07487-W"},{"key":"2026062216101423000_2026.06.18.732920v1.21","doi-asserted-by":"crossref","unstructured":"Olenginski, L.T. , Wierzba, A.J. , Laursen, S.P. & Batey, R.T. Designing small molecules targeting a cryptic RNA binding site through base displacement. Nature chemical biology, 1\u201310 (2025).","DOI":"10.1038\/s41589-025-02018-8"},{"key":"2026062216101423000_2026.06.18.732920v1.22","doi-asserted-by":"publisher","DOI":"10.1016\/j.str.2020.05.011"},{"key":"2026062216101423000_2026.06.18.732920v1.23","doi-asserted-by":"crossref","unstructured":"He, K. , Zhang, X. , Ren, S. & Sun, J. in Proceedings of the IEEE conference on computer vision and pattern recognition 770\u2013778 (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2026062216101423000_2026.06.18.732920v1.24","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac483"},{"key":"2026062216101423000_2026.06.18.732920v1.25","doi-asserted-by":"crossref","first-page":"648","DOI":"10.1038\/s43588-025-00820-x","article-title":"RNA\u2013ligand interaction scoring via data perturbation and augmentation modeling","volume":"5","year":"2025","journal-title":"Nature Computational Science"},{"key":"2026062216101423000_2026.06.18.732920v1.26","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1002\/jmr.1000","article-title":"Molecular recognition of RNA: challenges for modelling interactions and plasticity","volume":"23","year":"2010","journal-title":"Journal of Molecular Recognition: An Interdisciplinary Journal"},{"key":"2026062216101423000_2026.06.18.732920v1.27","doi-asserted-by":"crossref","first-page":"1860","DOI":"10.1016\/j.str.2024.08.015","article-title":"Advances in the field of RNA 3D structure prediction and modeling, with purely theoretical approaches, and with the use of experimental data","volume":"32","year":"2024","journal-title":"Structure"},{"key":"2026062216101423000_2026.06.18.732920v1.28","doi-asserted-by":"crossref","unstructured":"Wei, J. et al. GatorAffinity: Boosting Protein-Ligand Binding Affinity Prediction with Large-Scale Synthetic Structural Data. bioRxiv, 2025.2009.2029.679384 (2025).","DOI":"10.1101\/2025.09.29.679384"},{"key":"2026062216101423000_2026.06.18.732920v1.29","unstructured":"Zhang, Y. et al. Decoydb: A dataset for graph contrastive learning in protein-ligand binding affinity prediction. Advances in Neural Information Processing Systems 38 (2026)."},{"key":"2026062216101423000_2026.06.18.732920v1.30","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-019-6413-7"},{"key":"2026062216101423000_2026.06.18.732920v1.31","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/28.1.235"},{"key":"2026062216101423000_2026.06.18.732920v1.32","doi-asserted-by":"crossref","first-page":"2799","DOI":"10.1038\/s41467-025-57852-0","article-title":"RNAmigos2: accelerated structure-based RNA virtual screening with deep graph learning","volume":"16","year":"2025","journal-title":"Nature Communications"},{"key":"2026062216101423000_2026.06.18.732920v1.33","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-019-5631-3"},{"key":"2026062216101423000_2026.06.18.732920v1.34","doi-asserted-by":"publisher","DOI":"10.1126\/science.1129666"},{"key":"2026062216101423000_2026.06.18.732920v1.35","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1038\/s41589-022-00976-x","article-title":"Structure and mechanism of the methyltransferase ribozyme MTR1","volume":"18","year":"2022","journal-title":"Nature chemical biology"},{"key":"2026062216101423000_2026.06.18.732920v1.36","doi-asserted-by":"crossref","first-page":"5633","DOI":"10.1021\/acs.jctc.3c00507","article-title":"How good are current docking programs at nucleic acid\u2013ligand docking? a comprehensive evaluation","volume":"19","year":"2023","journal-title":"Journal of Chemical Theory and Computation"},{"key":"2026062216101423000_2026.06.18.732920v1.37","doi-asserted-by":"publisher","DOI":"10.1261\/rna.039438.113"},{"key":"2026062216101423000_2026.06.18.732920v1.38","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.ymeth.2015.09.013","article-title":"Conformational flexibility of viral RNA switches studied by FRET","volume":"91","year":"2015","journal-title":"Methods"},{"key":"2026062216101423000_2026.06.18.732920v1.39","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1016\/S0300-9084(02)01460-8","article-title":"Rational ligand design for RNA: the role of static structure and conformational flexibility in target recognition","volume":"84","year":"2002","journal-title":"Biochimie"},{"key":"2026062216101423000_2026.06.18.732920v1.40","doi-asserted-by":"publisher","DOI":"10.1038\/nature11498"},{"key":"2026062216101423000_2026.06.18.732920v1.41","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1038\/nchembio.232","article-title":"The role of dynamic conformational ensembles in biomolecular recognition","volume":"5","year":"2009","journal-title":"Nature chemical biology"},{"key":"2026062216101423000_2026.06.18.732920v1.42","doi-asserted-by":"crossref","first-page":"gkaf239","DOI":"10.1093\/nar\/gkaf239","article-title":"DRLiPS: a novel method for prediction of druggable RNA-small molecule binding pockets using machine learning","volume":"53","year":"2025","journal-title":"Nucleic Acids Research"},{"key":"2026062216101423000_2026.06.18.732920v1.43","doi-asserted-by":"publisher","DOI":"10.1021\/jacs.5c11898"},{"key":"2026062216101423000_2026.06.18.732920v1.44","doi-asserted-by":"publisher","DOI":"10.1038\/nature15542"},{"key":"2026062216101423000_2026.06.18.732920v1.45","doi-asserted-by":"publisher","DOI":"10.1038\/nature11607"},{"key":"2026062216101423000_2026.06.18.732920v1.46","doi-asserted-by":"crossref","first-page":"747","DOI":"10.1038\/s41594-021-00653-y","article-title":"Cryo-EM and antisense targeting of the 28-kDa frameshift stimulation element from the SARS-CoV-2 RNA genome","volume":"28","year":"2021","journal-title":"Nature Structural & Molecular Biology"},{"key":"2026062216101423000_2026.06.18.732920v1.47","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.1016\/j.bmcl.2019.04.001","article-title":"A cross-linking approach to map small molecule-RNA binding sites in cells","volume":"29","year":"2019","journal-title":"Bioorganic & medicinal chemistry letters"},{"key":"2026062216101423000_2026.06.18.732920v1.48","doi-asserted-by":"crossref","first-page":"gkaf231","DOI":"10.1093\/nar\/gkaf231","article-title":"Mapping small molecule\u2013RNA binding sites via Chem-CLIP synergized with capillary electrophoresis and nanopore sequencing","volume":"53","year":"2025","journal-title":"Nucleic Acids Research"},{"key":"2026062216101423000_2026.06.18.732920v1.49","doi-asserted-by":"publisher","DOI":"10.1002\/pro.192"},{"key":"2026062216101423000_2026.06.18.732920v1.50","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1002\/prot.22154","article-title":"Improving accuracy and efficiency of blind protein-ligand docking by focusing on predicted binding sites","volume":"74","year":"2009","journal-title":"Proteins: Structure, Function, and Bioinformatics"},{"key":"2026062216101423000_2026.06.18.732920v1.51","doi-asserted-by":"crossref","first-page":"1060","DOI":"10.1021\/acs.jctc.0c01006","article-title":"Accelerating AutoDock4 with GPUs and gradient-based local search","volume":"17","year":"2021","journal-title":"Journal of chemical theory and computation"},{"key":"2026062216101423000_2026.06.18.732920v1.52","doi-asserted-by":"publisher","DOI":"10.1021\/ja043822v"},{"key":"2026062216101423000_2026.06.18.732920v1.53","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.77.8.4679"},{"key":"2026062216101423000_2026.06.18.732920v1.54","doi-asserted-by":"crossref","first-page":"2374","DOI":"10.1021\/acschembio.0c00357","article-title":"PEARL-seq: a photoaffinity platform for the analysis of small molecule-RNA interactions","volume":"15","year":"2020","journal-title":"ACS Chemical Biology"},{"key":"2026062216101423000_2026.06.18.732920v1.55","doi-asserted-by":"publisher","DOI":"10.1021\/nn2006927"},{"key":"2026062216101423000_2026.06.18.732920v1.56","doi-asserted-by":"crossref","first-page":"1720","DOI":"10.1021\/acschembio.6b00001","article-title":"Inforna 2.0: a platform for the sequence-based design of small molecules targeting structured RNAs","volume":"11","year":"2016","journal-title":"ACS chemical biology"},{"key":"2026062216101423000_2026.06.18.732920v1.57","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1038\/s41597-023-02872-y","article-title":"Plas-20k: Extended dataset of protein-ligand affinities from md simulations for machine learning applications","volume":"11","year":"2024","journal-title":"Scientific Data"},{"key":"2026062216101423000_2026.06.18.732920v1.58","unstructured":"Schrodinger, L. , Vol. 1.8 (Schr\u00f6dinger, LLC, 2015)."},{"key":"2026062216101423000_2026.06.18.732920v1.59","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz282"},{"key":"2026062216101423000_2026.06.18.732920v1.60","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bts565"},{"key":"2026062216101423000_2026.06.18.732920v1.61","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btq461"},{"key":"2026062216101423000_2026.06.18.732920v1.62","doi-asserted-by":"crossref","first-page":"7393","DOI":"10.1021\/acs.jcim.5c00814","article-title":"Enabling In-Silico Hit Discovery Workflows Targeting RNA with Small Molecules","volume":"65","year":"2025","journal-title":"Journal of Chemical Information and Modeling"},{"key":"2026062216101423000_2026.06.18.732920v1.63","unstructured":"Loshchilov, I. & Hutter, F. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"2026062216101423000_2026.06.18.732920v1.64","doi-asserted-by":"crossref","unstructured":"Szegedy, C. , Vanhoucke, V. , Ioffe, S. , Shlens, J. & Wojna, Z. in Proceedings of the IEEE conference on computer vision and pattern recognition 2818\u20132826 (2016).","DOI":"10.1109\/CVPR.2016.308"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.06.18.732920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T23:10:32Z","timestamp":1782169832000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.06.18.732920"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.64898\/2026.06.18.732920","relation":{},"subject":[],"published":{"date-parts":[[2026,6,19]]},"subtype":"preprint"}}