{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T08:39:43Z","timestamp":1780389583641,"version":"3.54.1"},"reference-count":37,"publisher":"Oxford University Press (OUP)","issue":"12","license":[{"start":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T00:00:00Z","timestamp":1701216000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Technology Innovation Plan Of Shanghai Science and Technology Commission","award":["23S41900400"],"award-info":[{"award-number":["23S41900400"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>The biological functions of proteins are determined by the chemical and geometric properties of their surfaces. Recently, with the booming progress of deep learning, a series of learning-based surface descriptors have been proposed and achieved inspirational performance in many tasks such as protein design, protein\u2013protein interaction prediction, etc. However, they are still limited by the problem of label scarcity, since the labels are typically obtained through wet experiments. Inspired by the great success of self-supervised learning in natural language processing and computer vision, we introduce ProteinMAE, a self-supervised framework specifically designed for protein surface representation to mitigate label scarcity. Specifically, we propose an efficient network and utilize a large number of accessible unlabeled protein data to pretrain it by self-supervised learning. Then we use the pretrained weights as initialization and fine-tune the network on downstream tasks. To demonstrate the effectiveness of our method, we conduct experiments on three different downstream tasks including binding site identification in protein surface, ligand-binding protein pocket classification, and protein\u2013protein interaction prediction. The extensive experiments show that our method not only successfully improves the network\u2019s performance on all downstream tasks, but also achieves competitive performance with state-of-the-art methods. Moreover, our proposed network also exhibits significant advantages in terms of computational cost, which only requires less than a tenth of memory cost of previous methods.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>https:\/\/github.com\/phdymz\/ProteinMAE.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad724","type":"journal-article","created":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T19:11:20Z","timestamp":1701285080000},"source":"Crossref","is-referenced-by-count":18,"title":["ProteinMAE: masked autoencoder for protein surface self-supervised learning"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1322-7530","authenticated-orcid":false,"given":"Mingzhi","family":"Yuan","sequence":"first","affiliation":[{"name":"Digital Medical Research Center, School of Basic Medical Sciences, Fudan University , Shanghai 200032, China"},{"name":"Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Fudan University , Shanghai 200032, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ao","family":"Shen","sequence":"additional","affiliation":[{"name":"Digital Medical Research Center, School of Basic Medical Sciences, Fudan University , Shanghai 200032, China"},{"name":"Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Fudan University , Shanghai 200032, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1204-0942","authenticated-orcid":false,"given":"Kexue","family":"Fu","sequence":"additional","affiliation":[{"name":"Digital Medical Research Center, School of Basic Medical Sciences, Fudan University , Shanghai 200032, China"},{"name":"Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Fudan University , Shanghai 200032, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaming","family":"Guan","sequence":"additional","affiliation":[{"name":"Digital Medical Research Center, School of Basic Medical Sciences, Fudan University , Shanghai 200032, China"},{"name":"Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Fudan University , Shanghai 200032, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5436-7997","authenticated-orcid":false,"given":"Yingfan","family":"Ma","sequence":"additional","affiliation":[{"name":"Digital Medical Research Center, School of Basic Medical Sciences, Fudan University , Shanghai 200032, China"},{"name":"Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Fudan University , Shanghai 200032, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8369-6135","authenticated-orcid":false,"given":"Qin","family":"Qiao","sequence":"additional","affiliation":[{"name":"Digital Medical Research Center, School of Basic Medical Sciences, Fudan University , Shanghai 200032, China"},{"name":"Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Fudan University , Shanghai 200032, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manning","family":"Wang","sequence":"additional","affiliation":[{"name":"Digital Medical Research Center, School of Basic Medical Sciences, Fudan University , Shanghai 200032, China"},{"name":"Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Fudan University , Shanghai 200032, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,11,29]]},"reference":[{"key":"2023121122510072500_btad724-B1","author":"Bao","year":"2021"},{"key":"2023121122510072500_btad724-B2","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The Protein Data Bank","volume":"28","author":"Berman","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2023121122510072500_btad724-B3","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab087","article-title":"Deep learning in bioinformatics and biomedicine","author":"Berrar","year":"2021"},{"key":"2023121122510072500_btad724-B4","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1145\/357306.357310","article-title":"A generalization of algebraic surface drawing","volume":"1","author":"Blinn","year":"1982","journal-title":"ACM Trans Graph"},{"key":"2023121122510072500_btad724-B5","first-page":"26","article-title":"Efficient curvature estimation for oriented point clouds","volume":"1050","author":"Cao","year":"2019","journal-title":"stat"},{"key":"2023121122510072500_btad724-B6","first-page":"1597","author":"Chen","year":"2020"},{"key":"2023121122510072500_btad724-B7","first-page":"15750","author":"Chen","year":"2021"},{"key":"2023121122510072500_btad724-B8","doi-asserted-by":"crossref","first-page":"1870","DOI":"10.1093\/bioinformatics\/bty918","article-title":"Antibody interface prediction with 3D Zernike descriptors and SVM","volume":"35","author":"Daberdaku","year":"2019","journal-title":"Bioinformatics"},{"key":"2023121122510072500_btad724-B9","author":"Devlin","year":"2018"},{"key":"2023121122510072500_btad724-B10","author":"Dosovitskiy","year":"2020"},{"key":"2023121122510072500_btad724-B11","first-page":"605","author":"Fan","year":"2017"},{"key":"2023121122510072500_btad724-B12","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1038\/s41592-019-0666-6","article-title":"Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning","volume":"17","author":"Gainza","year":"2020","journal-title":"Nat Methods"},{"key":"2023121122510072500_btad724-B13","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1038\/s41586-023-05993-x","article-title":"De novo design of protein interactions with learned surface fingerprints","volume":"617","author":"Gainza","year":"2023","journal-title":"Nature"},{"key":"2023121122510072500_btad724-B14","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","article-title":"A survey on vision transformer","volume":"45","author":"Han","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2023121122510072500_btad724-B15","first-page":"16000","author":"He","year":"2022"},{"key":"2023121122510072500_btad724-B16","first-page":"9729","author":"He","year":"2020"},{"key":"2023121122510072500_btad724-B17","first-page":"1","article-title":"Subdivision-based mesh convolution networks","volume":"41","author":"Hu","year":"2022","journal-title":"ACM Trans Graph"},{"key":"2023121122510072500_btad724-B18","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1002\/pro.3280","article-title":"Improvements to the APBS biomolecular solvation software suite","volume":"27","author":"Jurrus","year":"2018","journal-title":"Protein Sci"},{"key":"2023121122510072500_btad724-B19","doi-asserted-by":"crossref","first-page":"520","DOI":"10.2174\/138920311796957612","article-title":"Molecular surface representation using 3D Zernike descriptors for protein shape comparison and docking","volume":"12","author":"Kihara","year":"2011","journal-title":"Curr Protein Pept Sci"},{"key":"2023121122510072500_btad724-B20","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":"2023121122510072500_btad724-B21","first-page":"1","article-title":"Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu","year":"2023","journal-title":"ACM Comput Surv"},{"key":"2023121122510072500_btad724-B22","author":"Loshchilov","year":"2017"},{"key":"2023121122510072500_btad724-B23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2105-6-96","article-title":"PREP-Mt: predictive RNA editor for plant mitochondrial genes","volume":"6","author":"Mower","year":"2005","journal-title":"BMC Bioinformatics"},{"key":"2023121122510072500_btad724-B24","doi-asserted-by":"crossref","first-page":"1841","DOI":"10.1093\/bioinformatics\/btq302","article-title":"Applying the na\u00efve Bayes classifier with kernel density estimation to the prediction of protein\u2013protein interaction sites","volume":"26","author":"Murakami","year":"2010","journal-title":"Bioinformatics"},{"key":"2023121122510072500_btad724-B25","first-page":"604","author":"Pang","year":"2022"},{"key":"2023121122510072500_btad724-B26","author":"Paszke","year":"2017"},{"key":"2023121122510072500_btad724-B27","doi-asserted-by":"crossref","first-page":"1210","DOI":"10.1016\/j.jmb.2013.01.014","article-title":"Understanding protein\u2013protein interactions using local structural features","volume":"425","author":"Planas-Iglesias","year":"2013","journal-title":"J Mol Biol"},{"key":"2023121122510072500_btad724-B28","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1002\/prot.21248","article-title":"Prediction-based fingerprints of protein\u2013protein interactions","volume":"66","author":"Porollo","year":"2007","journal-title":"Proteins"},{"key":"2023121122510072500_btad724-B29","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1002\/(SICI)1097-0282(199603)38:3<305::AID-BIP4>3.0.CO;2-Y","article-title":"Reduced surface: an efficient way to compute molecular surfaces","volume":"38","author":"Sanner","year":"1996","journal-title":"Biopolymers"},{"key":"2023121122510072500_btad724-B30","first-page":"15272","author":"Sverrisson","year":"2021"},{"key":"2023121122510072500_btad724-B31","volume-title":"Pattern Recognition","author":"Theodoridis","year":"2006"},{"key":"2023121122510072500_btad724-B32","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2023121122510072500_btad724-B33","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1186\/1758-2946-1-19","article-title":"Application of 3D Zernike descriptors to shape-based ligand similarity searching","volume":"1","author":"Venkatraman","year":"2009","journal-title":"J Cheminform"},{"key":"2023121122510072500_btad724-B34","doi-asserted-by":"crossref","first-page":"1029","DOI":"10.3390\/ijms18051029","article-title":"PCVMZM: using the probabilistic classification vector machines model combined with a Zernike moments descriptor to predict protein\u2013protein interactions from protein sequences","volume":"18","author":"Wang","year":"2017","journal-title":"Int J Mol Sci"},{"key":"2023121122510072500_btad724-B35","doi-asserted-by":"crossref","first-page":"16622","DOI":"10.1073\/pnas.0906146106","article-title":"Fast screening of protein surfaces using geometric invariant fingerprints","volume":"106","author":"Yin","year":"2009","journal-title":"Proc Natl Acad Sci USA"},{"key":"2023121122510072500_btad724-B36","author":"Zhang","year":"2022"},{"key":"2023121122510072500_btad724-B37","doi-asserted-by":"crossref","first-page":"707","DOI":"10.1093\/bioinformatics\/btu724","article-title":"Large-scale binding ligand prediction by improved patch-based method patch-surfer2.0","volume":"31","author":"Zhu","year":"2015","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad724\/53933331\/btad724.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/12\/btad724\/54256970\/btad724.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/12\/btad724\/54256970\/btad724.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,12]],"date-time":"2023-12-12T01:52:59Z","timestamp":1702345979000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad724\/7455256"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,11,29]]},"references-count":37,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023,12,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad724","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,12,1]]},"published":{"date-parts":[[2023,11,29]]},"article-number":"btad724"}}