{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:29:59Z","timestamp":1775190599016,"version":"3.50.1"},"reference-count":29,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T00:00:00Z","timestamp":1748908800000},"content-version":"vor","delay-in-days":2,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Science Foundation of Guangdong Province of China","award":["2022A1515011436"],"award-info":[{"award-number":["2022A1515011436"]}]},{"name":"Science and Technology Program of Guangzhou","award":["202102021087"],"award-info":[{"award-number":["202102021087"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Pinpointing the subcellular location of proteins is essential for studying protein function and related diseases. Advances in spatial proteomics have shown that automatic recognition of protein subcellular localization from images could highly facilitate protein translocation analysis and biomarker discovery, but existing machine-learning works have been mostly limited to processing 2D images. By contrast, 3D images have higher spatial resolution\u00a0and allow researchers to observe cellular structures in their natural context, but currently, there are only a few studies of 3D image processing for protein distribution analysis due to the lack of data and complexity of modeling.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We developed a knowledge-enhanced protein subcellular localization model, KE3DLoc, which could recognize distribution patterns in 3D fluorescence microscope images using deep learning methods. The model designs an image feature extraction module that incorporates information from 3D and 2D projected cells and implements asymmetric loss and confidence weights to address data imbalance and weak cell annotation issues. Besides, considering that the biological knowledge in the Gene Ontology (GO) database can provide valuable support for protein location understanding, the KE3DLoc model incorporates a novel knowledge enhancement module that optimizes the protein representation by related knowledge graphs derived from the GO. Since the image module and the knowledge module calculate features from different levels, KE3DLoc designs protein ID aggregation to enhance the consistency of protein features across different cells. Experimental results on three public datasets have demonstrated that the KE3DLoc significantly outperforms existing methods and provides valuable insights for spatial proteomics research.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>All datasets and codes used in this study are available at GitHub: https:\/\/github.com\/PRBioimages\/KE3DLoc.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf331","type":"journal-article","created":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T15:14:39Z","timestamp":1748963679000},"source":"Crossref","is-referenced-by-count":2,"title":["Knowledge-enhanced protein subcellular localization prediction from 3D fluorescence microscope images"],"prefix":"10.1093","volume":"41","author":[{"given":"Guo-Hua","family":"Zeng","sequence":"first","affiliation":[{"name":"School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University , Guangzhou 510515,","place":["China"]},{"name":"Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University , Guangzhou 510515,","place":["China"]}]},{"given":"Xing-Zheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area, Shenzhen Polytechnic University , Shenzhen 518100,","place":["China"]}]},{"given":"Hong-Rui","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University , Guangzhou 510515,","place":["China"]},{"name":"Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University , Guangzhou 510515,","place":["China"]}]},{"given":"Yong-Jia","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University , Guangzhou 510515,","place":["China"]},{"name":"Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University , Guangzhou 510515,","place":["China"]}]},{"given":"Yu-Jia","family":"Zhai","sequence":"additional","affiliation":[{"name":"Cancer Center, Affiliated Hospital of Guangdong Medical University , Zhanjiang 524000,","place":["China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3185-811X","authenticated-orcid":false,"given":"Ying-Ying","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University , Guangzhou 510515,","place":["China"]},{"name":"Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University , Guangzhou 510515,","place":["China"]}]}],"member":"286","published-online":{"date-parts":[[2025,6,3]]},"reference":[{"key":"2025070408273955900_btaf331-B1","doi-asserted-by":"crossref","first-page":"iyad031","DOI":"10.1093\/genetics\/iyad031","article-title":"The gene ontology knowledgebase in 2023","volume":"224","author":"Aleksander","year":"2023","journal-title":"Genetics"},{"key":"2025070408273955900_btaf331-B2","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1038\/75556","article-title":"Gene ontology: tool for the unification of biology","volume":"25","author":"Ashburner","year":"2000","journal-title":"Nat Genet"},{"key":"2025070408273955900_btaf331-B3","first-page":"2787","article-title":"Translating embeddings for modeling multi-relational data","volume":"26","author":"Bordes","year":"2013","journal-title":"Adv Neural Info Process Syst"},{"key":"2025070408273955900_btaf331-B4","first-page":"4360","author":"Chao","year":"2021"},{"key":"2025070408273955900_btaf331-B5","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1186\/s12864-019-6413-7","article-title":"The advantages of the Matthews correlation coefficient (MCC) over f1 score and accuracy in binary classification evaluation","volume":"21","author":"Chicco","year":"2020","journal-title":"BMC Genom"},{"key":"2025070408273955900_btaf331-B6","doi-asserted-by":"crossref","first-page":"eabi6983","DOI":"10.1126\/science.abi6983","article-title":"Opencell: endogenous tagging for the cartography of human cellular organization","volume":"375","author":"Cho","year":"2022","journal-title":"Science"},{"key":"2025070408273955900_btaf331-B7","doi-asserted-by":"crossref","first-page":"1413","DOI":"10.1016\/j.cell.2015.04.051","article-title":"Yeast proteome dynamics from single cell imaging and automated analysis","volume":"161","author":"Chong","year":"2015","journal-title":"Cell"},{"key":"2025070408273955900_btaf331-B8","doi-asserted-by":"crossref","first-page":"e1009155","DOI":"10.1371\/journal.pcbi.1009155","article-title":"A deep generative model of 3d single-cell organization","volume":"18","author":"Donovan-Maiye","year":"2022","journal-title":"PLoS Comput Biol"},{"key":"2025070408273955900_btaf331-B9","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1038\/s41467-017-00623-3","article-title":"Reconstructing cell cycle and disease progression using deep learning","volume":"8","author":"Eulenberg","year":"2017","journal-title":"Nat Commun"},{"key":"2025070408273955900_btaf331-B10","doi-asserted-by":"crossref","first-page":"670","DOI":"10.1016\/j.cels.2021.05.001","article-title":"Cell states beyond transcriptomics: integrating structural organization and gene expression in hiPSC-derived cardiomyocytes","volume":"12","author":"Gerbin","year":"2021","journal-title":"Cell Systems"},{"key":"2025070408273955900_btaf331-B11","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.devcel.2006.12.007","article-title":"Automated subcellular location determination and high-throughput microscopy","volume":"12","author":"Glory","year":"2007","journal-title":"Dev Cell"},{"key":"2025070408273955900_btaf331-B12","first-page":"1","article-title":"Domain-specific language model pretraining for biomedical natural language processing","volume":"3","author":"Gu","year":"2021","journal-title":"ACM Trans Comput Healthcare (HEALTH)"},{"key":"2025070408273955900_btaf331-B13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3447772","article-title":"Knowledge graphs","volume":"54","author":"Hogan","year":"2022","journal-title":"ACM Comput Surv"},{"key":"2025070408273955900_btaf331-B14","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1038\/s42003-023-04840-z","article-title":"Single-cell subcellular protein localisation using novel ensembles of diverse deep architectures","volume":"6","author":"Husain","year":"2023","journal-title":"Commun Biol"},{"key":"2025070408273955900_btaf331-B15","author":"Kipf"},{"key":"2025070408273955900_btaf331-B16","doi-asserted-by":"crossref","first-page":"995","DOI":"10.1038\/s41592-022-01541-z","article-title":"Self-supervised deep learning encodes high-resolution features of protein subcellular localization","volume":"19","author":"Kobayashi","year":"2022","journal-title":"Nat Methods"},{"key":"2025070408273955900_btaf331-B17","doi-asserted-by":"crossref","first-page":"1221","DOI":"10.1038\/s41592-022-01606-z","article-title":"Analysis of the human protein atlas weakly supervised single-cell classification competition","volume":"19","author":"Le","year":"2022","journal-title":"Nat Methods"},{"key":"2025070408273955900_btaf331-B18","doi-asserted-by":"crossref","first-page":"1679","DOI":"10.1093\/bib\/bbaa012","article-title":"Biological applications of knowledge graph embedding models","volume":"22","author":"Mohamed","year":"2021","journal-title":"Brief Bioinform"},{"key":"2025070408273955900_btaf331-B19","doi-asserted-by":"crossref","first-page":"910531","DOI":"10.3389\/fbinf.2022.910531","article-title":"Recent advances in the prediction of subcellular localization of proteins and related topics","volume":"2","author":"Nakai","year":"2022","journal-title":"Front Bioinfo"},{"key":"2025070408273955900_btaf331-B20","first-page":"4710","author":"Nathani","year":"2019"},{"key":"2025070408273955900_btaf331-B21","first-page":"82","author":"Ridnik","year":"2021"},{"key":"2025070408273955900_btaf331-B22","author":"Sun"},{"key":"2025070408273955900_btaf331-B23","doi-asserted-by":"crossref","first-page":"D330","DOI":"10.1093\/nar\/gky1055","article-title":"The gene ontology resource: 20 years and still going strong","volume":"47","author":"The Gene Ontology Consortium","year":"2019","journal-title":"Nucl Acid Res"},{"key":"2025070408273955900_btaf331-B24","first-page":"2071","volume-title":"International Conference on Machine Learning","author":"Trouillon","year":"2016"},{"key":"2025070408273955900_btaf331-B25","author":"Veli\u010dkovi\u0107"},{"key":"2025070408273955900_btaf331-B26","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1038\/s41586-022-05563-7","article-title":"Integrated intracellular organization and its variations in human IPS cells","volume":"613","author":"Viana","year":"2023","journal-title":"Nature"},{"key":"2025070408273955900_btaf331-B27","author":"Zhang"},{"key":"2025070408273955900_btaf331-B28","author":"Zhou"},{"key":"2025070408273955900_btaf331-B29","doi-asserted-by":"crossref","first-page":"bbac609","DOI":"10.1093\/bib\/bbac609","article-title":"Automatic recognition of protein subcellular location patterns in single cells from immunofluorescence images based on deep learning","volume":"24","author":"Zhu","year":"2023","journal-title":"Brief Bioinfo"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf331\/63427208\/btaf331.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/6\/btaf331\/63427208\/btaf331.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/6\/btaf331\/63427208\/btaf331.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T12:27:44Z","timestamp":1751632064000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf331\/8155842"}},"subtitle":[],"editor":[{"given":"Janet","family":"Kelso","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":29,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf331","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,6]]},"published":{"date-parts":[[2025,6]]},"article-number":"btaf331"}}