{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T16:58:30Z","timestamp":1761238710377,"version":"3.37.3"},"reference-count":50,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2020,2,13]],"date-time":"2020-02-13T00:00:00Z","timestamp":1581552000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000057","name":"National Institute of General Medical Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R35GM119524"],"award-info":[{"award-number":["R35GM119524"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"US National Science Foundation","doi-asserted-by":"crossref","award":["CCF-1619303"],"award-info":[{"award-number":["CCF-1619303"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100006952","name":"Louisiana Board of Regents","doi-asserted-by":"publisher","award":["LEQSF(2016-19)-RD-B-03"],"award-info":[{"award-number":["LEQSF(2016-19)-RD-B-03"]}],"id":[{"id":"10.13039\/100006952","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Center for Computation and Technology"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>Fast and accurate classification of ligand-binding sites in proteins with respect to the class of binding molecules is invaluable not only to the automatic functional annotation of large datasets of protein structures but also to projects in protein evolution, protein engineering and drug development. Deep learning techniques, which have already been successfully applied to address challenging problems across various fields, are inherently suitable to classify ligand-binding pockets. Our goal is to demonstrate that off-the-shelf deep learning models can be employed with minimum development effort to recognize nucleotide- and heme-binding sites with a comparable accuracy to highly specialized, voxel-based methods.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We developed BionoiNet, a new deep learning-based framework implementing a popular ResNet model for image classification. BionoiNet first transforms the molecular structures of ligand-binding sites to 2D Voronoi diagrams, which are then used as the input to a pretrained convolutional neural network classifier. The ResNet model generalizes well to unseen data achieving the accuracy of 85.6% for nucleotide- and 91.3% for heme-binding pockets. BionoiNet also computes significance scores of pocket atoms, called BionoiScores, to provide meaningful insights into their interactions with ligand molecules. BionoiNet is a lightweight alternative to computationally expensive 3D architectures.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability and implementation<\/jats:title><jats:p>BionoiNet is implemented in Python with the source code freely available at: https:\/\/github.com\/CSBG-LSU\/BionoiNet.<\/jats:p><\/jats:sec><jats:sec><jats:title>Supplementary information<\/jats:title><jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p><\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaa094","type":"journal-article","created":{"date-parts":[[2020,2,5]],"date-time":"2020-02-05T20:10:52Z","timestamp":1580933452000},"page":"3077-3083","source":"Crossref","is-referenced-by-count":15,"title":["BionoiNet: ligand-binding site classification with off-the-shelf deep neural network"],"prefix":"10.1093","volume":"36","author":[{"given":"Wentao","family":"Shi","sequence":"first","affiliation":[{"name":"Division of Electrical and Computer Engineering, Louisiana State University , Baton Rouge, LA 70803, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeffrey M","family":"Lemoine","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, Louisiana State University , Baton Rouge, LA 70803, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abd-El-Monsif A","family":"Shawky","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, Louisiana State University , Baton Rouge, LA 70803, USA"},{"name":"Department of Cell Biology, National Research Centre , 12622 Giza, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manali","family":"Singha","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, Louisiana State University , Baton Rouge, LA 70803, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Limeng","family":"Pu","sequence":"additional","affiliation":[{"name":"Center for Computation & Technology, Louisiana State University , Baton Rouge, LA 70803, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuangyan","family":"Yang","sequence":"additional","affiliation":[{"name":"Division of Electrical and Computer Engineering, Louisiana State University , Baton Rouge, LA 70803, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J","family":"Ramanujam","sequence":"additional","affiliation":[{"name":"Division of Electrical and Computer Engineering, Louisiana State University , Baton Rouge, LA 70803, USA"},{"name":"Center for Computation & Technology, Louisiana State University , Baton Rouge, LA 70803, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6204-2869","authenticated-orcid":false,"given":"Michal","family":"Brylinski","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, Louisiana State University , Baton Rouge, LA 70803, USA"},{"name":"Center for Computation & Technology, Louisiana State University , Baton Rouge, LA 70803, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2020,2,13]]},"reference":[{"key":"2023013111540630200_btaa094-B1","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1016\/S0022-2836(05)80360-2","article-title":"Basic local alignment search tool","volume":"215","author":"Altschul","year":"1990","journal-title":"J. Mol. Biol"},{"key":"2023013111540630200_btaa094-B2","doi-asserted-by":"crossref","first-page":"2679","DOI":"10.1002\/jcc.25715","article-title":"Improving the accuracy of protein-ligand binding mode prediction using a molecular dynamics-based pocket generation approach","volume":"39","author":"Araki","year":"2018","journal-title":"J. Comput. Chem"},{"key":"2023013111540630200_btaa094-B3","doi-asserted-by":"crossref","first-page":"e0141287","DOI":"10.1371\/journal.pone.0141287","article-title":"Continuous distributed representation of biological sequences for deep proteomics and genomics","volume":"10","author":"Asgari","year":"2015","journal-title":"PLoS One"},{"key":"2023013111540630200_btaa094-B4","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1145\/116873.116880","article-title":"Voronoi diagrams\u2014a survey of a fundamental geometric data structure","volume":"23","author":"Aurenhammer","year":"1991","journal-title":"ACM Comput. Surv"},{"key":"2023013111540630200_btaa094-B5","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1093\/bioinformatics\/btp036","article-title":"Fragment-based identification of druggable \u2018hot spots\u2019 of proteins using Fourier domain correlation techniques","volume":"25","author":"Brenke","year":"2009","journal-title":"Bioinformatics"},{"key":"2023013111540630200_btaa094-B6","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1007\/s10822-013-9663-5","article-title":"eFindSite: improved prediction of ligand binding sites in protein models using meta-threading, machine learning and auxiliary ligands","volume":"27","author":"Brylinski","year":"2013","journal-title":"J. Comput. Aided Mol. Des"},{"key":"2023013111540630200_btaa094-B7","doi-asserted-by":"crossref","first-page":"W362","DOI":"10.1093\/nar\/gkl124","article-title":"ScanProsite: detection of PROSITE signature matches and ProRule-associated functional and structural residues in proteins","volume":"34","author":"de Castro","year":"2006","journal-title":"Nucleic Acids Res"},{"key":"2023013111540630200_btaa094-B8","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1186\/s12859-018-2109-2","article-title":"Comparative assessment of strategies to identify similar ligand-binding pockets in proteins","volume":"19","author":"Govindaraj","year":"2018","journal-title":"BMC Bioinformatics"},{"first-page":"770","year":"2016","author":"He","key":"2023013111540630200_btaa094-B9"},{"key":"2023013111540630200_btaa094-B10","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1021\/acs.jcim.7b00616","article-title":"Mol2vec: unsupervised machine learning approach with chemical intuition","volume":"58","author":"Jaeger","year":"2018","journal-title":"J. Chem. Inf. Model"},{"first-page":"2146","year":"2009","author":"Jarrett","key":"2023013111540630200_btaa094-B11"},{"key":"2023013111540630200_btaa094-B12","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.media.2016.10.004","article-title":"Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation","volume":"36","author":"Kamnitsas","year":"2017","journal-title":"Med. Image Anal"},{"key":"2023013111540630200_btaa094-B13","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1007\/s10822-019-00197-w","article-title":"Elucidating the druggability of the human proteome with eFindSite","volume":"33","author":"Kana","year":"2019","journal-title":"J. Comput. Aided Mol. Des"},{"key":"2023013111540630200_btaa094-B14","doi-asserted-by":"crossref","first-page":"1775","DOI":"10.1021\/ci2001023","article-title":"Build-up algorithm for atomic correspondence between chemical structures","volume":"51","author":"Kawabata","year":"2011","journal-title":"J. Chem. Inf. Model"},{"key":"2023013111540630200_btaa094-B15","doi-asserted-by":"crossref","first-page":"e1003321","DOI":"10.1371\/journal.pcbi.1003321","article-title":"Exploring the composition of protein-ligand binding sites on a large scale","volume":"9","author":"Khazanov","year":"2013","journal-title":"PLoS Comput. Biol"},{"volume-title":"Proceedings of 3rd International Conference on Learning Representations.","year":"2015","author":"Kingma","key":"2023013111540630200_btaa094-B16"},{"first-page":"1097","year":"2012","author":"Krizhevsky","key":"2023013111540630200_btaa094-B17"},{"key":"2023013111540630200_btaa094-B18","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/0022-2836(82)90515-0","article-title":"A simple method for displaying the hydropathic character of a protein","volume":"157","author":"Kyte","year":"1982","journal-title":"J. Mol. Biol"},{"key":"2023013111540630200_btaa094-B19","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1186\/1471-2105-10-168","article-title":"Fpocket: an open source platform for ligand pocket detection","volume":"10","author":"Le Guilloux","year":"2009","journal-title":"BMC Bioinformatics"},{"key":"2023013111540630200_btaa094-B20","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"2023013111540630200_btaa094-B21","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"2023013111540630200_btaa094-B22","doi-asserted-by":"crossref","first-page":"865","DOI":"10.1002\/pro.2890","article-title":"G-LoSA: an efficient computational tool for local structure-centric biological studies and drug design","volume":"25","author":"Lee","year":"2016","journal-title":"Prot. Sci"},{"first-page":"197","year":"2014","author":"Li","key":"2023013111540630200_btaa094-B23"},{"key":"2023013111540630200_btaa094-B24","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1186\/1472-6807-11-13","article-title":"Structural analysis of heme proteins: implications for design and prediction","volume":"11","author":"Li","year":"2011","journal-title":"BMC Struct. Biol"},{"year":"2015","author":"Lipton","key":"2023013111540630200_btaa094-B25"},{"key":"2023013111540630200_btaa094-B26","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1016\/j.jmb.2003.12.056","article-title":"Molecular determinants for ATP-binding in proteins: a data mining and quantum chemical analysis","volume":"336","author":"Mao","year":"2004","journal-title":"J. Mol. Biol"},{"first-page":"52","year":"2011","author":"Masci","key":"2023013111540630200_btaa094-B27"},{"key":"2023013111540630200_btaa094-B28","doi-asserted-by":"crossref","first-page":"424","DOI":"10.2307\/210384","article-title":"Notes on a cylindrical world map projection","volume":"32","author":"Miller","year":"1942","journal-title":"Geograph. Rev"},{"key":"2023013111540630200_btaa094-B29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-014-0007-7","article-title":"Deep learning applications and challenges in big data analytics","volume":"2","author":"Najafabadi","year":"2015","journal-title":"J. Big Data"},{"first-page":"5947","year":"2017","author":"Neyshabur","key":"2023013111540630200_btaa094-B30"},{"key":"2023013111540630200_btaa094-B31","doi-asserted-by":"crossref","first-page":"W271","DOI":"10.1093\/nar\/gks441","article-title":"FTMAP: extended protein mapping with user-selected probe molecules","volume":"40","author":"Ngan","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2023013111540630200_btaa094-B32","doi-asserted-by":"crossref","first-page":"e1006718","DOI":"10.1371\/journal.pcbi.1006718","article-title":"DeepDrug3D: classification of ligand-binding pockets in proteins with a convolutional neural network","volume":"15","author":"Pu","year":"2019","journal-title":"PLoS Comput. Biol"},{"key":"2023013111540630200_btaa094-B33","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.artmed.2019.06.003","article-title":"3D-CNN based discrimination of schizophrenia using resting-state fMRI","volume":"98","author":"Qureshi","year":"2019","journal-title":"Artif. Intell. Med"},{"key":"2023013111540630200_btaa094-B34","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comp. Vision"},{"key":"2023013111540630200_btaa094-B35","doi-asserted-by":"crossref","first-page":"5858","DOI":"10.1021\/jm100574m","article-title":"Understanding and predicting druggability. A high-throughput method for detection of drug binding sites","volume":"53","author":"Schmidtke","year":"2010","journal-title":"J. Med. Chem"},{"key":"2023013111540630200_btaa094-B36","article-title":"Deep inside convolutional networks: visualising image classification models and saliency maps","volume-title":"Proceedings of 2nd International Conference on Learning Representations.","author":"Simonyan","year":"2014"},{"volume-title":"Proceedings of 3rd International Conference on Learning Representations.","year":"2015","author":"Simonyan","key":"2023013111540630200_btaa094-B37"},{"key":"2023013111540630200_btaa094-B38","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1093\/bioinformatics\/bty583","article-title":"LigVoxel: inpainting binding pockets using 3D-convolutional neural networks","volume":"35","author":"Skalic","year":"2019","journal-title":"Bioinformatics"},{"key":"2023013111540630200_btaa094-B39","doi-asserted-by":"crossref","first-page":"1163","DOI":"10.1016\/j.bmcl.2015.01.059","article-title":"Implications of the small number of distinct ligand binding pockets in proteins for drug discovery, evolution and biochemical function","volume":"25","author":"Skolnick","year":"2015","journal-title":"Bioorg. Med. Chem. Lett"},{"key":"2023013111540630200_btaa094-B40","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1093\/bioinformatics\/15.4.327","article-title":"Automated analysis of interatomic contacts in proteins","volume":"15","author":"Sobolev","year":"1999","journal-title":"Bioinformatics"},{"key":"2023013111540630200_btaa094-B41","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res"},{"key":"2023013111540630200_btaa094-B42","doi-asserted-by":"crossref","first-page":"809","DOI":"10.1021\/acs.accounts.5b00516","article-title":"Protein binding pocket dynamics","volume":"49","author":"Stank","year":"2016","journal-title":"Acc. Chem. Res"},{"first-page":"1","year":"2015","author":"Szegedy","key":"2023013111540630200_btaa094-B43"},{"first-page":"2818","year":"2016","author":"Szegedy","key":"2023013111540630200_btaa094-B44"},{"key":"2023013111540630200_btaa094-B45","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1002\/jcc.21334","article-title":"AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading","volume":"31","author":"Trott","year":"2010","journal-title":"J. Comput. Chem"},{"key":"2023013111540630200_btaa094-B46","doi-asserted-by":"crossref","first-page":"W469","DOI":"10.1093\/nar\/gkq406","article-title":"3DLigandSite: predicting ligand-binding sites using similar structures","volume":"38","author":"Wass","year":"2010","journal-title":"Nucleic Acids Res"},{"volume-title":"International Conference on Machine learning, Deep Learning Workshop.","year":"2015","author":"Xu","key":"2023013111540630200_btaa094-B47"},{"key":"2023013111540630200_btaa094-B48","doi-asserted-by":"crossref","first-page":"2588","DOI":"10.1093\/bioinformatics\/btt447","article-title":"Protein-ligand binding site recognition using complementary binding-specific substructure comparison and sequence profile alignment","volume":"29","author":"Yang","year":"2013","journal-title":"Bioinformatics"},{"first-page":"818","year":"2014","author":"Zeiler","key":"2023013111540630200_btaa094-B49"},{"key":"2023013111540630200_btaa094-B50","doi-asserted-by":"crossref","first-page":"702","DOI":"10.1002\/prot.20264","article-title":"Scoring function for automated assessment of protein structure template quality","volume":"57","author":"Zhang","year":"2004","journal-title":"Proteins"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa094\/32791218\/btaa094.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/10\/3077\/48990800\/bioinformatics_36_10_3077.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/10\/3077\/48990800\/bioinformatics_36_10_3077.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T03:11:08Z","timestamp":1722395468000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/36\/10\/3077\/5735410"}},"subtitle":[],"editor":[{"given":"Arne","family":"Elofsson","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2020,2,13]]},"references-count":50,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2020,5,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa094","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"type":"print","value":"1367-4803"},{"type":"electronic","value":"1367-4811"}],"subject":[],"published-other":{"date-parts":[[2020,5,15]]},"published":{"date-parts":[[2020,2,13]]}}}