{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T07:16:25Z","timestamp":1782976585357,"version":"3.54.5"},"posted":{"date-parts":[[2025,9,21]]},"group-title":"Bioinformatics","reference-count":49,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,9,21]]},"abstract":"<jats:title>\n                  A\n                  <jats:sc>bstract<\/jats:sc>\n                <\/jats:title>\n                <jats:p>\n                  Accurate identification of protein particles in cryo-electron microscopy (cryo-EM) micrographs is crucial for high-resolution structure determination, but remains challenging due to the heavy reliance on extensive annotated datasets and the difficulty of ensuring robustness under low signal-to-noise ratio (SNR) conditions. Current approaches require large annotations and exhibit poor generalization to new protein targets. We present CryoFSL (\n                  <jats:underline>Cryo<\/jats:underline>\n                  -EM\n                  <jats:underline>F<\/jats:underline>\n                  ew\n                  <jats:underline>S<\/jats:underline>\n                  hot-\n                  <jats:underline>L<\/jats:underline>\n                  earning), a novel few-shot learning framework built upon Segment Anything Model 2 (SAM2) with lightweight adapters, enabling robust particle picking using as few as five labeled micrographs, significantly reducing annotation burden. The framework\u2019s hierarchical adapter design supports dynamic feature modulation for low-SNR and heterogeneous conditions, resolving the trade-off between annotation burden and performance. CryoFSL surpasses both traditional template-based methods and state-of-the-art deep learning models across diverse proteins in the few-short learning setting, achieving superior recall, precision and 3D reconstruction resolution with minimal supervision. It maintains stability across heterogeneous micrographs and consistently detects high-quality particles with fewer false positives. Notably, CryoFSL achieves competitive density map reconstruction resolution with just a fraction of the particles picked by other methods, redefining efficiency and quality in cryo-EM analysis. This work paves the way for scalable, generalizable, and annotation-efficient particle picking pipelines. The code is available at\n                  <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/biplabpoudel25\/CryoFSL\">GitHub<\/jats:ext-link>\n                  .\n                <\/jats:p>","DOI":"10.1101\/2025.09.19.677446","type":"posted-content","created":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T22:15:10Z","timestamp":1758492910000},"source":"Crossref","is-referenced-by-count":2,"title":["CryoFSL: An Annotation-Efficient, Few-Shot Learning Framework for Robust Protein Particle Picking in Cryo-EM Micrographs"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8636-1449","authenticated-orcid":false,"given":"Biplab","family":"Poudel","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajan","family":"Gyawali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashwin","family":"Dhakal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianlin","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4809-0514","authenticated-orcid":false,"given":"Dong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2025092509100560000_2025.09.19.677446v1.1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab476"},{"key":"2025092509100560000_2025.09.19.677446v1.2","doi-asserted-by":"publisher","DOI":"10.3390\/molecules25040873"},{"key":"2025092509100560000_2025.09.19.677446v1.3","doi-asserted-by":"publisher","DOI":"10.1101\/2025.07.03.663071"},{"key":"2025092509100560000_2025.09.19.677446v1.4","doi-asserted-by":"publisher","DOI":"10.1021\/acs.chemrev.1c00850"},{"key":"2025092509100560000_2025.09.19.677446v1.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.tibs.2014.10.005"},{"key":"2025092509100560000_2025.09.19.677446v1.6","doi-asserted-by":"publisher","DOI":"10.1111\/febs.12078"},{"key":"2025092509100560000_2025.09.19.677446v1.7","doi-asserted-by":"publisher","DOI":"10.3390\/life12081267"},{"key":"2025092509100560000_2025.09.19.677446v1.8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2019.2957822"},{"key":"2025092509100560000_2025.09.19.677446v1.9","doi-asserted-by":"publisher","DOI":"10.3791\/55448"},{"key":"2025092509100560000_2025.09.19.677446v1.10","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-800144-8.00002-1"},{"key":"2025092509100560000_2025.09.19.677446v1.11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsb.2009.02.012"},{"key":"2025092509100560000_2025.09.19.677446v1.12","doi-asserted-by":"publisher","DOI":"10.1016\/j.str.2022.01.001"},{"key":"2025092509100560000_2025.09.19.677446v1.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsb.2006.05.009"},{"key":"2025092509100560000_2025.09.19.677446v1.14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsb.2012.09.006"},{"key":"2025092509100560000_2025.09.19.677446v1.15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsb.2016.04.010"},{"key":"2025092509100560000_2025.09.19.677446v1.16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsb.2009.01.004"},{"key":"2025092509100560000_2025.09.19.677446v1.17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsb.2009.01.002"},{"key":"2025092509100560000_2025.09.19.677446v1.18","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-025-11181-2"},{"key":"2025092509100560000_2025.09.19.677446v1.19","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaf011"},{"key":"2025092509100560000_2025.09.19.677446v1.20","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-29994-y"},{"key":"2025092509100560000_2025.09.19.677446v1.21","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbae636"},{"key":"2025092509100560000_2025.09.19.677446v1.22","doi-asserted-by":"publisher","DOI":"10.1016\/j.crmeth.2025.101089"},{"key":"2025092509100560000_2025.09.19.677446v1.23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsb.2018.08.012"},{"key":"2025092509100560000_2025.09.19.677446v1.24","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsb.2016.07.006"},{"key":"2025092509100560000_2025.09.19.677446v1.25","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-019-2926-y"},{"key":"2025092509100560000_2025.09.19.677446v1.26","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0580-y"},{"key":"2025092509100560000_2025.09.19.677446v1.27","doi-asserted-by":"publisher","DOI":"10.1038\/s42003-021-01721-1"},{"key":"2025092509100560000_2025.09.19.677446v1.28","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0575-8"},{"key":"2025092509100560000_2025.09.19.677446v1.29","doi-asserted-by":"publisher","DOI":"10.1038\/s42003-019-0437-z"},{"key":"2025092509100560000_2025.09.19.677446v1.30","doi-asserted-by":"crossref","unstructured":"Xu, C. , Zhan, X. , & Xu, M. (2025, February). CryoMAE: few-shot cryo-EM particle picking with masked Autoencoders. In 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (pp. 3876\u20133885). IEEE.","DOI":"10.1109\/WACV61041.2025.00381"},{"key":"2025092509100560000_2025.09.19.677446v1.31","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbae282"},{"key":"2025092509100560000_2025.09.19.677446v1.32","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae109"},{"key":"2025092509100560000_2025.09.19.677446v1.33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2408.00714"},{"key":"2025092509100560000_2025.09.19.677446v1.34","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.4169"},{"key":"2025092509100560000_2025.09.19.677446v1.35","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02280-2"},{"key":"2025092509100560000_2025.09.19.677446v1.36","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkac1062"},{"key":"2025092509100560000_2025.09.19.677446v1.37","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.03080"},{"key":"2025092509100560000_2025.09.19.677446v1.38","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2016.12.023"},{"key":"2025092509100560000_2025.09.19.677446v1.39","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsb.2014.11.010"},{"key":"2025092509100560000_2025.09.19.677446v1.40","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2019.12.030"},{"key":"2025092509100560000_2025.09.19.677446v1.41","doi-asserted-by":"publisher","DOI":"10.1038\/nature22981"},{"key":"2025092509100560000_2025.09.19.677446v1.42","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-04845-4"},{"key":"2025092509100560000_2025.09.19.677446v1.43","doi-asserted-by":"publisher","DOI":"10.2307\/3001968"},{"key":"2025092509100560000_2025.09.19.677446v1.44","doi-asserted-by":"publisher","DOI":"10.1007\/BF02289138"},{"key":"2025092509100560000_2025.09.19.677446v1.45","doi-asserted-by":"publisher","DOI":"10.2307\/2346101"},{"key":"2025092509100560000_2025.09.19.677446v1.46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2025092509100560000_2025.09.19.677446v1.47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2408.04579"},{"key":"2025092509100560000_2025.09.19.677446v1.48","doi-asserted-by":"publisher","DOI":"10.1109\/medai62885.2024.00009"},{"key":"2025092509100560000_2025.09.19.677446v1.49","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6980"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.09.19.677446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T09:38:34Z","timestamp":1768469914000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.09.19.677446"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,21]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1101\/2025.09.19.677446","relation":{},"subject":[],"published":{"date-parts":[[2025,9,21]]},"subtype":"preprint"}}