Rapid and Sensitive Protein Complex Alignment with Foldseek-Multimer

Rapid and Sensitive Protein Complex Alignment with Foldseek-Multimer | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Brief Communication Rapid and Sensitive Protein Complex Alignment with Foldseek-Multimer Martin Steinegger, Emmanuel Levy, Woosub Kim, Milot Mirdita, Eli Karin, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4413778/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 05 Feb, 2025 Read the published version in Nature Methods → Version 1 posted You are reading this latest preprint version Abstract Advances in computational structure prediction will vastly augment the hundreds of thousands of currently-available protein complex structures. Translating these into discoveries requires aligning them, which is computationally prohibitive. Foldseek-Multimer computes complex alignments from compatible chain-to-chain alignments, identified by efficiently clustering their superposition vectors. Foldseek-Multimer is 3-4 orders of magnitudes faster than the gold standard, while producing comparable alignments; allowing it to compare dozens of billions of complex-pairs in 14 hours. Foldseek-Multimer is open-source software: github.com/steineggerlab/foldseek and webserver: search.foldseek.com. Biological sciences/Computational biology and bioinformatics/Protein analysis Biological sciences/Computational biology and bioinformatics/Software Full Text Additional Declarations Yes there is potential Competing Interest. M.S. acknowledges outside interest in Stylus Medicine Cite Share Download PDF Status: Published Journal Publication published 05 Feb, 2025 Read the published version in Nature Methods → Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4413778","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Brief Communication","associatedPublications":[],"authors":[{"id":305592174,"identity":"61855848-5b97-409f-ad63-6af595ccf894","order_by":0,"name":"Martin Steinegger","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0001-8781-9753","institution":"Seoul National University","correspondingAuthor":true,"prefix":"","firstName":"Martin","middleName":"","lastName":"Steinegger","suffix":""},{"id":305592175,"identity":"516febfc-2765-4628-bd98-e591b4f1d4ee","order_by":1,"name":"Emmanuel Levy","email":"","orcid":"","institution":"Weizmann Institute of Science","correspondingAuthor":false,"prefix":"","firstName":"Emmanuel","middleName":"","lastName":"Levy","suffix":""},{"id":305592176,"identity":"8d11d476-65e3-4833-bcd2-44465d7010dd","order_by":2,"name":"Woosub Kim","email":"","orcid":"","institution":"Seoul National University","correspondingAuthor":false,"prefix":"","firstName":"Woosub","middleName":"","lastName":"Kim","suffix":""},{"id":305592177,"identity":"2483f971-6433-48a4-a470-c370d098e621","order_by":3,"name":"Milot Mirdita","email":"","orcid":"https://orcid.org/0000-0001-8637-6719","institution":"Seoul National University","correspondingAuthor":false,"prefix":"","firstName":"Milot","middleName":"","lastName":"Mirdita","suffix":""},{"id":305592178,"identity":"266e30b9-cfe6-43c6-b8f7-9592dae00612","order_by":4,"name":"Eli Karin","email":"","orcid":"","institution":"ELKMO","correspondingAuthor":false,"prefix":"","firstName":"Eli","middleName":"","lastName":"Karin","suffix":""},{"id":305592179,"identity":"44446008-a709-41f8-9f59-c4bfe7da6dd7","order_by":5,"name":"Cameron Gilchrist","email":"","orcid":"","institution":"Seoul National University","correspondingAuthor":false,"prefix":"","firstName":"Cameron","middleName":"","lastName":"Gilchrist","suffix":""},{"id":305592180,"identity":"4ebd5782-5290-4e2d-8752-bd7e65451805","order_by":6,"name":"Hugo Schweke","email":"","orcid":"","institution":"Weizmann Institute of Science","correspondingAuthor":false,"prefix":"","firstName":"Hugo","middleName":"","lastName":"Schweke","suffix":""},{"id":305592181,"identity":"0446308c-4222-459b-8efd-631123c4bcce","order_by":7,"name":"Johannes Söding","email":"","orcid":"","institution":"Max Planck Institute for Multidisciplinary Sciences","correspondingAuthor":false,"prefix":"","firstName":"Johannes","middleName":"","lastName":"Söding","suffix":""}],"badges":[],"createdAt":"2024-05-13 14:11:47","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4413778/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4413778/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41592-025-02593-7","type":"published","date":"2025-02-05T05:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":75596653,"identity":"cfcf1490-66d3-474e-995e-b133eb223e5b","added_by":"auto","created_at":"2025-02-06 08:06:54","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2168817,"visible":true,"origin":"","legend":"","description":"","filename":"KimetalFoldseekMM.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4413778/v1_covered_cfe2aba4-9c75-44c2-87d6-e677b8d8e185.pdf"}],"financialInterests":"\u003cb\u003eYes\u003c/b\u003e there is potential Competing Interest.\nM.S. acknowledges outside interest in Stylus Medicine","formattedTitle":"Rapid and Sensitive Protein Complex Alignment with Foldseek-Multimer","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-4413778/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4413778/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Advances in computational structure prediction will vastly augment the hundreds of thousands of currently-available protein complex structures. Translating these into discoveries requires aligning them, which is computationally prohibitive. Foldseek-Multimer computes complex alignments from compatible chain-to-chain alignments, identified by efficiently clustering their superposition vectors. Foldseek-Multimer is 3-4 orders of magnitudes faster than the gold standard, while producing comparable alignments; allowing it to compare dozens of billions of complex-pairs in 14 hours. Foldseek-Multimer is open-source software: github.com/steineggerlab/foldseek and webserver: search.foldseek.com.","manuscriptTitle":"Rapid and Sensitive Protein Complex Alignment with Foldseek-Multimer","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-05-23 03:00:12","doi":"10.21203/rs.3.rs-4413778/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-methods","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"nmeth","sideBox":"Learn more about [Nature Methods](http://www.nature.com/nmeth)","snPcode":"","submissionUrl":"","title":"Nature Methods","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Research","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"2d40ee05-3885-4c5e-ac1b-bd7c5f2d51b1","owner":[],"postedDate":"May 23rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":32270523,"name":"Biological sciences/Computational biology and bioinformatics/Protein analysis"},{"id":32270524,"name":"Biological sciences/Computational biology and bioinformatics/Software"}],"tags":[],"updatedAt":"2025-02-06T08:06:47+00:00","versionOfRecord":{"articleIdentity":"rs-4413778","link":"https://doi.org/10.1038/s41592-025-02593-7","journal":{"identity":"nature-methods","isVorOnly":false,"title":"Nature Methods"},"publishedOn":"2025-02-05 05:00:00","publishedOnDateReadable":"February 5th, 2025"},"versionCreatedAt":"2024-05-23 03:00:12","video":"","vorDoi":"10.1038/s41592-025-02593-7","vorDoiUrl":"https://doi.org/10.1038/s41592-025-02593-7","workflowStages":[]},"version":"v1","identity":"rs-4413778","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4413778","identity":"rs-4413778","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}