{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T08:44:37Z","timestamp":1775119477796,"version":"3.50.1"},"reference-count":44,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T00:00:00Z","timestamp":1718064000000},"content-version":"vor","delay-in-days":19,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01GM146340"],"award-info":[{"award-number":["R01GM146340"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Picking protein particles in cryo-electron microscopy (cryo-EM) micrographs is a crucial step in the cryo-EM-based structure determination. However, existing methods trained on a limited amount of cryo-EM data still cannot accurately pick protein particles from noisy cryo-EM images. The general foundational artificial intelligence\u2013based image segmentation model such as Meta\u2019s Segment Anything Model (SAM) cannot segment protein particles well because their training data do not include cryo-EM images. Here, we present a novel approach (CryoSegNet) of integrating an attention-gated U-shape network (U-Net) specially designed and trained for cryo-EM particle picking and the SAM. The U-Net is first trained on a large cryo-EM image dataset and then used to generate input from original cryo-EM images for SAM to make particle pickings. CryoSegNet shows both high precision and recall in segmenting protein particles from cryo-EM micrographs, irrespective of protein type, shape and size. On several independent datasets of various protein types, CryoSegNet outperforms two top machine learning particle pickers crYOLO and Topaz as well as SAM itself. The average resolution of density maps reconstructed from the particles picked by CryoSegNet is 3.33\u00a0\u00c5, 7% better than 3.58\u00a0\u00c5 of Topaz and 14% better than 3.87\u00a0\u00c5 of crYOLO. It is publicly available at https:\/\/github.com\/jianlin-cheng\/CryoSegNet<\/jats:p>","DOI":"10.1093\/bib\/bbae282","type":"journal-article","created":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T12:40:06Z","timestamp":1717072806000},"source":"Crossref","is-referenced-by-count":28,"title":["CryoSegNet: accurate cryo-EM protein particle picking by integrating the foundational AI image segmentation model and attention-gated U-Net"],"prefix":"10.1093","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7052-4964","authenticated-orcid":false,"given":"Rajan","family":"Gyawali","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Computer Science , University of Missouri, Columbia, MO 65211 , United States"},{"name":"NextGen Precision Health , University of Missouri, Columbia, MO 65211 , United States"}]},{"given":"Ashwin","family":"Dhakal","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science , University of Missouri, Columbia, MO 65211 , United States"},{"name":"NextGen Precision Health , University of Missouri, Columbia, MO 65211 , United States"}]},{"given":"Liguo","family":"Wang","sequence":"additional","affiliation":[{"name":"Laboratory for BioMolecular Structure (LBMS) , Brookhaven National Laboratory, Upton, NY 11973 , United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0305-2853","authenticated-orcid":false,"given":"Jianlin","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science , University of Missouri, Columbia, MO 65211 , United States"},{"name":"NextGen Precision Health , University of Missouri, Columbia, MO 65211 , United States"}]}],"member":"286","published-online":{"date-parts":[[2024,6,11]]},"reference":[{"key":"2024061111091859800_ref1","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab476","article-title":"Artificial intelligence in the prediction of protein-ligand interactions: recent advances and future directions","volume":"23","author":"Dhakal","year":"2022","journal-title":"Brief Bioinform"},{"key":"2024061111091859800_ref2","doi-asserted-by":"crossref","DOI":"10.3390\/biom13010132","article-title":"Improving protein\u2013ligand interaction Modeling with cryo-EM data, templates, and deep learning in 2021 ligand model challenge","volume":"13","author":"Giri","year":"2023","journal-title":"Biomolecules"},{"key":"2024061111091859800_ref3","article-title":"Predicting protein-ligand binding structure using E(n) Equivariant graph neural networks","author":"Dhakal","year":"2023","journal-title":"bioRxiv"},{"key":"2024061111091859800_ref4","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1038\/s41597-023-02280-2","article-title":"A large expert-curated cryo-EM image dataset for machine learning protein particle picking","volume":"10","author":"Dhakal","year":"2023","journal-title":"Sci Data"},{"key":"2024061111091859800_ref5","article-title":"CryoPPP: a large expert-labelled Cryo-EM image dataset for machine learning protein particle picking","author":"Dhakal","year":"2023","journal-title":"bioRxiv"},{"key":"2024061111091859800_ref6","doi-asserted-by":"crossref","first-page":"3239","DOI":"10.1038\/nprot.2007.452","article-title":"Preparation of macromolecular complexes for cryo-electron microscopy","volume":"2","author":"Grassucci","year":"2007","journal-title":"Nat Protoc"},{"key":"2024061111091859800_ref7","article-title":"CryoVirusDB: a Labeled Cryo-EM image dataset for AI-driven virus particle picking","author":"Gyawali","year":"2023","journal-title":"bioRxiv"},{"key":"2024061111091859800_ref8","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.ultramic.2013.06.004","article-title":"High-resolution noise substitution to measure overfitting and validate resolution in 3D structure determination by single particle electron cryomicroscopy","volume":"135","author":"Chen","year":"2013","journal-title":"Ultramicroscopy"},{"key":"2024061111091859800_ref9","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/S0304-3991(98)00065-5","article-title":"Performance of a 2k CCD camera designed for electron crystallography at 400 kV","volume":"75","author":"Downing","year":"1999","journal-title":"Ultramicroscopy"},{"key":"2024061111091859800_ref10","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.jsb.2006.05.009","article-title":"EMAN2: an extensible image processing suite for electron microscopy","volume":"157","author":"Tang","year":"2007","journal-title":"J Struct Biol"},{"key":"2024061111091859800_ref11","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1016\/j.jsb.2012.09.006","article-title":"RELION: implementation of a Bayesian approach to cryo-EM structure determination","volume":"180","author":"Scheres","year":"2012","journal-title":"J Struct Biol"},{"key":"2024061111091859800_ref12","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1038\/nmeth.4169","article-title":"CryoSPARC: algorithms for rapid unsupervised cryo-EM structure determination","volume":"14","author":"Punjani","year":"2017","journal-title":"Nat Methods"},{"key":"2024061111091859800_ref13","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1016\/j.jsb.2009.01.004","article-title":"DoG picker and TiltPicker: software tools to facilitate particle selection in single particle electron microscopy","volume":"166","author":"Voss","year":"2009","journal-title":"J Struct Biol"},{"key":"2024061111091859800_ref14","doi-asserted-by":"crossref","first-page":"1941","DOI":"10.1038\/nprot.2008.156","article-title":"SPIDER image processing for single-particle reconstruction of biological macromolecules from electron micrographs","volume":"3","author":"Shaikh","year":"2008","journal-title":"Nat Protoc"},{"key":"2024061111091859800_ref15","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1016\/j.jsb.2004.06.006","article-title":"XMIPP: a new generation of an open-source image processing package for electron microscopy","volume":"148","author":"Sorzano","year":"2004","journal-title":"J Struct Biol"},{"key":"2024061111091859800_ref16","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/j.jsb.2018.08.012","article-title":"APPLE picker: automatic particle picking, a low-effort cryo-EM framework","volume":"204","author":"Heimowitz","year":"2018","journal-title":"J Struct Biol"},{"key":"2024061111091859800_ref17","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1038\/s42003-019-0437-z","article-title":"SPHIRE-crYOLO is a fast and accurate fully automated particle picker for cryo-EM","volume":"2","author":"Wagner","year":"2019","journal-title":"Commun Biol"},{"key":"2024061111091859800_ref18","article-title":"PIXER: an automated particle-selection method based on segmentation using a deep neural network","volume":"20","author":"Zhang","year":"2019","journal-title":"BMC Bioinformatics"},{"key":"2024061111091859800_ref19","doi-asserted-by":"crossref","first-page":"1146","DOI":"10.1038\/s41592-019-0580-y","article-title":"Real-time cryo-electron microscopy data preprocessing with Warp","volume":"16","author":"Tegunov","year":"2019","journal-title":"Nat Methods"},{"key":"2024061111091859800_ref20","doi-asserted-by":"crossref","first-page":"1153","DOI":"10.1038\/s41592-019-0575-8","article-title":"Positive-unlabeled convolutional neural networks for particle picking in cryo-electron micrographs","volume":"16","author":"Bepler","year":"2019","journal-title":"Nat Methods"},{"key":"2024061111091859800_ref21","doi-asserted-by":"crossref","DOI":"10.1038\/s42003-021-01721-1","article-title":"CASSPER is a semantic segmentation-based particle picking algorithm for single-particle cryo-electron microscopy","volume":"4","author":"George","year":"2021","journal-title":"Commun Biol"},{"key":"2024061111091859800_ref22","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1016\/j.jsb.2016.07.006","article-title":"DeepPicker: a deep learning approach for fully automated particle picking in cryo-EM","volume":"195","author":"Wang","year":"2016","journal-title":"J Struct Biol"},{"key":"2024061111091859800_ref23","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1186\/s12859-019-2926-y","article-title":"Autocryopicker: an unsupervised learning approach for fully automated single particle picking in cryo-em images","volume":"20","author":"Al-Azzawi","year":"2019","journal-title":"BMC Bioinformatics"},{"key":"2024061111091859800_ref24","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1186\/s12859-020-03809-7","article-title":"DeepCryoPicker: fully automated deep neural network for single protein particle picking in cryo-EM","volume":"21","author":"Al-Azzawi","year":"2020","journal-title":"BMC Bioinformatics"},{"key":"2024061111091859800_ref25","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1186\/s12859-020-03948-x","article-title":"DRPnet: automated particle picking in cryo-electron micrographs using deep regression","volume":"22","author":"Nguyen","year":"2021","journal-title":"BMC Bioinformatics"},{"key":"2024061111091859800_ref26","doi-asserted-by":"crossref","first-page":"btae109","DOI":"10.1093\/bioinformatics\/btae109","article-title":"CryoTransformer: a transformer model for picking protein particles from Cryo-EM micrographs","volume":"40","author":"Dhakal","year":"2024","journal-title":"Bioinformatics"},{"key":"2024061111091859800_ref27","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Redmon","year":"2016"},{"key":"2024061111091859800_ref28","doi-asserted-by":"crossref","first-page":"D1503","DOI":"10.1093\/nar\/gkac1062","article-title":"EMPIAR: the electron microscopy public image archive","volume":"51","author":"Iudin","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2024061111091859800_ref29","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.00371","article-title":"Segment anything","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Kirillov","year":"2023"},{"key":"2024061111091859800_ref30","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","volume":"2015","author":"Ronneberger","year":"2015","journal-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI"},{"key":"2024061111091859800_ref31","first-page":"1","article-title":"A fast NL-means method in image denoising based on the similarity of spatially sampled pixels","volume":"2009","author":"Pang","year":"2009","journal-title":"IEEE International Workshop on Multimedia Signal Processing"},{"key":"2024061111091859800_ref32","first-page":"1","article-title":"Guided image filtering","volume":"2010","author":"He","year":"2010","journal-title":"Computer Vision \u2013 ECCV"},{"key":"2024061111091859800_ref33","first-page":"92","article-title":"Optimizing the dice score and Jaccard index for medical image segmentation: theory and practice","volume":"2019","author":"Bertels","year":"2019","journal-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI"},{"key":"2024061111091859800_ref34","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.03080","article-title":"Cryo-EM structure of the plasmodium falciparum 80S ribosome bound to the anti-protozoan drug emetine","volume":"3","author":"Wong","year":"2014","journal-title":"elife"},{"key":"2024061111091859800_ref35","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.cell.2016.12.023","article-title":"Structures of the human HCN1 hyperpolarization-Activated Channel","volume":"168","author":"Lee","year":"2017","journal-title":"Cell"},{"key":"2024061111091859800_ref36","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1016\/j.cell.2019.12.030","article-title":"Cryo-EM reveals integrin-mediated TGF-\u03b2 activation without release from latent TGF-\u03b2","volume":"180","author":"Campbell","year":"2020","journal-title":"Cell"},{"key":"2024061111091859800_ref37","doi-asserted-by":"crossref","first-page":"1021","DOI":"10.1038\/s41586-022-04845-4","article-title":"Structure of the bile acid transporter and HBV receptor NTCP","volume":"606","author":"Asami","year":"2022","journal-title":"Nature"},{"key":"2024061111091859800_ref38","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1017\/S1431927621002348","article-title":"Through-grid wicking enables high-speed cryoEM specimen preparation","volume":"27","author":"Tan","year":"2021","journal-title":"Microsc Microanal"},{"key":"2024061111091859800_ref39","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1038\/nature22981","article-title":"Electron cryo-microscopy structure of the mechanotransduction channel NOMPC","volume":"547","author":"Jin","year":"2017","journal-title":"Nature"},{"key":"2024061111091859800_ref40","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/j.jsb.2014.11.010","article-title":"Semi-automated selection of cryo-EM particles in RELION-1.3","volume":"189","author":"Scheres","year":"2015","journal-title":"J Struct Biol"},{"key":"2024061111091859800_ref41","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1038\/nbt.3988","article-title":"MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets","volume":"35","author":"Steinegger","year":"2017","journal-title":"Nat Biotechnol"},{"key":"2024061111091859800_ref42","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1038\/s41592-023-02099-0","article-title":"DeepMainmast: integrated protocol of protein structure modeling for cryo-EM with deep learning and structure prediction","volume":"21","author":"Terashi","year":"2024","journal-title":"Nat Methods"},{"key":"2024061111091859800_ref43","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1107\/S2059798319011471","article-title":"Macromolecular structure determination using X-rays, neutrons and electrons: recent developments in Phenix","volume":"75","author":"Liebschner","year":"2019","journal-title":"Acta Crystallogr D Struct Biol"},{"key":"2024061111091859800_ref44","article-title":"De novo atomic protein structure Modeling for Cryo-EM density maps using 3D transformer and hidden Markov model","author":"Giri","year":"2024","journal-title":"BioarXiv"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/4\/bbae282\/58195707\/bbae282.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/4\/bbae282\/58195707\/bbae282.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T17:40:20Z","timestamp":1718127620000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbae282\/7690949"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,23]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,5,23]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbae282","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.10.02.560572","asserted-by":"object"}]},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,7]]},"published":{"date-parts":[[2024,5,23]]},"article-number":"bbae282"}}