{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T01:41:08Z","timestamp":1768527668259,"version":"3.49.0"},"posted":{"date-parts":[[2025,10,6]]},"group-title":"Biophysics","reference-count":58,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T00:00:00Z","timestamp":1759708800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"NIH","award":["R35-GM138206"],"award-info":[{"award-number":["R35-GM138206"]}]},{"name":"NIH","award":["T32-GM008326"],"award-info":[{"award-number":["T32-GM008326"]}]},{"name":"NIH","award":["S10-OD032471"],"award-info":[{"award-number":["S10-OD032471"]}]},{"DOI":"10.13039\/100014185","name":"Searle Scholars Program","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100014185","id-type":"DOI","asserted-by":"crossref"}]},{"name":"George W. and Carol A. Lattimer UCSD Faculty Research Fellowship"},{"name":"Goeddel Family Technology Sandbox Fellowship"},{"name":"Cottrell Scholars Award"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,10,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Despite the maturation of cryogenic electron microscopy (cryoEM) methodologies, generating high-resolution three-dimensional (3-D) reconstructions from micrographs is a time-intensive process involving iterative rounds of subjective data curation and hyperparameter optimization. Current approaches to particle classification are often unable to remove all low-quality particles from particle stacks, largely due to the low signal-to-noise ratio, the high dimensionality of particle images, and the multiple degrees of freedom associated with each particle\u2019s unknown rotation, orientation, and class assignment. The retention of low-quality particles negatively affects the overall quality of the final EM density and continued efforts to eliminate their deleterious contributions are warranted. Here, we present ANTIDOTE (A Neural network Trained In Deleterious Object deTection and Elimination), a neural network framework that discriminates between constructive and deleterious particles using per-particle metadata generated during 3-D classification in RELION. Using benchmark and real-world cryoEM datasets, we demonstrate that ANTIDOTE paired with RELION 3-D classification achieves higher particle classification accuracy than conventional data processing approaches alone, yielding improvements in reconstruction quality, global and local resolution, and map interpretability while reducing time-consuming hyperparameter optimization. We additionally detail practical use-case scenarios for ANTIDOTE and demonstrate its versatility in increasing particle curation accuracy for high-quality cryoEM reconstruction.<\/jats:p>","DOI":"10.1101\/2025.10.06.680814","type":"posted-content","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T04:45:11Z","timestamp":1759812311000},"source":"Crossref","is-referenced-by-count":0,"title":["ANTIDOTE: A Metadata-Driven Neural Network for Improving CryoEM 3-D Particle Sorting"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3567-1547","authenticated-orcid":false,"given":"Raymond F.","family":"Berkeley","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5777-3464","authenticated-orcid":false,"given":"Brian D.","family":"Cook","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2008-9583","authenticated-orcid":false,"given":"Daniel","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Armin","family":"Foroughi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7647-9635","authenticated-orcid":false,"given":"Yifei","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0989-1538","authenticated-orcid":false,"given":"Maxwell J.","family":"Bachochin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6653-6682","authenticated-orcid":false,"suffix":"Jr.","given":"Mark A.","family":"Herzik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2025101101250664000_2025.10.06.680814v2.1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2829-0"},{"key":"2025101101250664000_2025.10.06.680814v2.2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2833-4"},{"key":"2025101101250664000_2025.10.06.680814v2.3","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1038\/nmeth.3700","volume":"13","year":"2016","journal-title":"Nature methods"},{"key":"2025101101250664000_2025.10.06.680814v2.4","doi-asserted-by":"publisher","DOI":"10.1016\/j.molcel.2015.02.019"},{"key":"2025101101250664000_2025.10.06.680814v2.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.mib.2017.10.005"},{"key":"2025101101250664000_2025.10.06.680814v2.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2015.03.050"},{"key":"2025101101250664000_2025.10.06.680814v2.7","doi-asserted-by":"publisher","DOI":"10.1074\/jbc.REV118.005602"},{"key":"2025101101250664000_2025.10.06.680814v2.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsb.2012.09.006"},{"key":"2025101101250664000_2025.10.06.680814v2.9","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1038\/nmeth.4169","volume":"14","year":"2017","journal-title":"Nature Methods"},{"key":"2025101101250664000_2025.10.06.680814v2.10","doi-asserted-by":"publisher","DOI":"10.1016\/j.str.2011.12.014"},{"key":"2025101101250664000_2025.10.06.680814v2.11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmb.2003.07.013"},{"key":"2025101101250664000_2025.10.06.680814v2.12","doi-asserted-by":"crossref","first-page":"1404885","DOI":"10.3389\/fmolb.2024.1404885","volume":"11","year":"2024","journal-title":"Frontiers in Molecular Biosciences"},{"key":"2025101101250664000_2025.10.06.680814v2.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmb.2011.11.010"},{"key":"2025101101250664000_2025.10.06.680814v2.14","unstructured":"Lauzirika, O. ; Pernica, M. ; Herreros, D. ; Ram\u00edrez-Aportela, E. ; Krieger, J. ; Gragera, M. ; Iceta, M. ; Conesa, P. ; Fonseca, Y. ; Jim\u00e9nez, J. , et al. Biological Crystallography 2025, 81."},{"key":"2025101101250664000_2025.10.06.680814v2.15","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.9b01178"},{"key":"2025101101250664000_2025.10.06.680814v2.16","doi-asserted-by":"crossref","first-page":"1523","DOI":"10.1016\/j.str.2023.11.005","volume":"31","year":"2023","journal-title":"Structure"},{"key":"2025101101250664000_2025.10.06.680814v2.17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsb.2013.07.005"},{"key":"2025101101250664000_2025.10.06.680814v2.18","doi-asserted-by":"publisher","DOI":"10.1016\/bs.mie.2016.04.012"},{"key":"2025101101250664000_2025.10.06.680814v2.19","first-page":"57","volume":"65","year":"2015","journal-title":"Journal of Electron Microscopy"},{"key":"2025101101250664000_2025.10.06.680814v2.20","first-page":"100020","volume":"4","year":"2020","journal-title":"Journal of Structural Biology: X"},{"key":"2025101101250664000_2025.10.06.680814v2.21","doi-asserted-by":"publisher","DOI":"10.1126\/science.abq7641"},{"key":"2025101101250664000_2025.10.06.680814v2.22","doi-asserted-by":"crossref","first-page":"10815","DOI":"10.1038\/s41467-024-54499-1","volume":"15","year":"2024","journal-title":"Nature Communications"},{"key":"2025101101250664000_2025.10.06.680814v2.23","doi-asserted-by":"crossref","first-page":"3528","DOI":"10.1038\/s41467-025-58243-1","volume":"16","year":"2025","journal-title":"Nature Communications"},{"key":"2025101101250664000_2025.10.06.680814v2.24","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.06380"},{"key":"2025101101250664000_2025.10.06.680814v2.25","doi-asserted-by":"crossref","first-page":"1302680","DOI":"10.3389\/fmolb.2023.1302680","volume":"10","year":"2023","journal-title":"Frontiers in Molecular Biosciences"},{"key":"2025101101250664000_2025.10.06.680814v2.26","doi-asserted-by":"crossref","first-page":"6086","DOI":"10.1038\/s41598-024-56706-x","volume":"14","year":"2024","journal-title":"Scientific Reports"},{"key":"2025101101250664000_2025.10.06.680814v2.27","doi-asserted-by":"crossref","first-page":"124","DOI":"10.2307\/2223319","volume":"31","year":"1921","journal-title":"The economic journal"},{"key":"2025101101250664000_2025.10.06.680814v2.28","year":"2014","journal-title":"arXiv preprint"},{"key":"2025101101250664000_2025.10.06.680814v2.29","year":"2015","journal-title":"arXiv preprint"},{"key":"2025101101250664000_2025.10.06.680814v2.30","year":"2023","journal-title":"Attention Is All You Need"},{"key":"2025101101250664000_2025.10.06.680814v2.31","first-page":"1","volume":"18","year":"2018","journal-title":"Journal of Machine Learning Research"},{"key":"2025101101250664000_2025.10.06.680814v2.32","doi-asserted-by":"publisher","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3"},{"key":"2025101101250664000_2025.10.06.680814v2.33","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1038\/s41592-020-01049-4","volume":"18","year":"2021","journal-title":"Nature Methods"},{"key":"2025101101250664000_2025.10.06.680814v2.34","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1038\/nmeth.2115","volume":"9","year":"2012","journal-title":"Nature methods"},{"key":"2025101101250664000_2025.10.06.680814v2.35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsb.2013.12.010"},{"key":"2025101101250664000_2025.10.06.680814v2.36","doi-asserted-by":"crossref","first-page":"2279","DOI":"10.1038\/s41598-023-29396-0","volume":"13","year":"2023","journal-title":"Scientific Reports"},{"key":"2025101101250664000_2025.10.06.680814v2.37","doi-asserted-by":"crossref","first-page":"3821","DOI":"10.1038\/s41467-023-39388-3","volume":"14","year":"2023","journal-title":"Nature Communications"},{"key":"2025101101250664000_2025.10.06.680814v2.38","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"2025101101250664000_2025.10.06.680814v2.39","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsb.2021.107702"},{"key":"2025101101250664000_2025.10.06.680814v2.40","unstructured":"Asarnow, D. ; Palovcak, E. ; Cheng, Y. asarnow\/pyem: UCSF pyem v0.5, 2019."},{"key":"2025101101250664000_2025.10.06.680814v2.41","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.42166"},{"key":"2025101101250664000_2025.10.06.680814v2.42","doi-asserted-by":"crossref","first-page":"1214","DOI":"10.1038\/s41592-020-00990-8","volume":"17","year":"2020","journal-title":"Nature Methods"},{"key":"2025101101250664000_2025.10.06.680814v2.43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsb.2015.08.007"},{"key":"2025101101250664000_2025.10.06.680814v2.44","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsb.2005.03.010"},{"key":"2025101101250664000_2025.10.06.680814v2.45","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1038\/nmeth.4193","volume":"14","year":"2017","journal-title":"Nature Methods"},{"key":"2025101101250664000_2025.10.06.680814v2.46","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsb.2015.11.003"},{"key":"2025101101250664000_2025.10.06.680814v2.47","unstructured":"Nguyen, H. P. M. ; McGuire, K. L. ; Cook, B. D. ; Herzik Jr., M. A. Journal of Visualized Experiments 2022, 62765."},{"key":"2025101101250664000_2025.10.06.680814v2.48","doi-asserted-by":"publisher","DOI":"10.1002\/2211-5463.13873"},{"key":"2025101101250664000_2025.10.06.680814v2.49","first-page":"249","volume-title":"In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics","volume":"9","year":"2010"},{"key":"2025101101250664000_2025.10.06.680814v2.50","year":"2017","journal-title":"Adam: A Method for Stochastic Optimization"},{"key":"2025101101250664000_2025.10.06.680814v2.51","year":"2016","journal-title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems"},{"key":"2025101101250664000_2025.10.06.680814v2.52","year":"2019","journal-title":"TensorFlow Eager: A Multi-Stage, Python-Embedded DSL for Machine Learning"},{"key":"2025101101250664000_2025.10.06.680814v2.53","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2649-2"},{"key":"2025101101250664000_2025.10.06.680814v2.54","unstructured":"McKinney, W. In Austin, Texas, 2010, pp 56\u201361."},{"key":"2025101101250664000_2025.10.06.680814v2.55","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","volume":"17","year":"2020","journal-title":"Nature Methods"},{"key":"2025101101250664000_2025.10.06.680814v2.56","year":"2018","journal-title":"Scikit-learn: Machine Learning in Python"},{"key":"2025101101250664000_2025.10.06.680814v2.57","doi-asserted-by":"publisher","DOI":"10.1109\/mcse.2007.55"},{"key":"2025101101250664000_2025.10.06.680814v2.58","unstructured":"Odland, T. tommyod\/KDEpy: Kernel Density Estimation in Python, Language: en, 2018."}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.10.06.680814","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T09:43:31Z","timestamp":1768470211000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.10.06.680814"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,6]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1101\/2025.10.06.680814","relation":{},"subject":[],"published":{"date-parts":[[2025,10,6]]},"subtype":"preprint"}}