MicroSEC: Sequence error filtering pipeline for formalin-fixed and paraffin-embedded samples

MicroSEC: Sequence error filtering pipeline for formalin-fixed and paraffin-embedded samples | 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 MicroSEC: Sequence error filtering pipeline for formalin-fixed and paraffin-embedded samples Masachika Ikegami, Shinji Kohsaka, Takeshi Hirose, Toshihide Ueno, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-153650/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 15 Dec, 2021 Read the published version in Communications Biology → Version 1 posted You are reading this latest preprint version Abstract The clinical sequencing of tumors is usually performed on formalin-fixed, paraffin-embedded (FFPE) samples and results in many sequencing errors. Most of these errors are detected in chimeric reads caused by single-strand DNA molecules with microhomology. Our filtering pipeline, MicroSEC, focuses on the uneven distribution of mutations in each read and removes the sequencing errors in FFPE samples without eliminating the true mutations that are also detected in fresh frozen samples. Computational Biology Bioinformatics Software Engineering Medical Genetics formalin-fixed paraffin-embedded samples MicroSEC sequencing errors Figures Figure 1 Full Text Additional Declarations There is NO Competing Interest. Supplementary Files supplementarydataIkegami.xlsx Supplementary Data Cite Share Download PDF Status: Published Journal Publication published 15 Dec, 2021 Read the published version in Communications Biology → 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-153650","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Brief Communication","associatedPublications":[],"authors":[{"id":9010061,"identity":"c9f251e9-ff81-4dc6-8588-4b8b633dae78","order_by":0,"name":"Masachika Ikegami","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8ElEQVRIiWNgGAWjYBACNh4wJcHAwMPA+ADMgPIJa+HhYWA2IEoLAw+M5mFgw6sQDvh4Dh9+8TPHgsGe54xZNW+ORR4D++EHDJY78DiMty3Nsncb0GG8PWa3ebdJFDPwpBkwSJ7Bo4Wfx8wAqLK+B8gAaUlsYMhhYJBsw6eF/5vhX5AtQC3FYC38bwho4e1hfswLdRgzWIsEIVt4jpkxy4K0nDlWLDkXqKVN4pnBAXx+ke9Jfvzx7bY6Bvae5I0fgIzEfv7kh48l8YQYyCJodHAYQLhAfFiyAa8W5g8Qmv0BXIjxI34to2AUjIJRMLIAAJYaQq4rgnSlAAAAAElFTkSuQmCC","orcid":"","institution":"National Cancer Center Research Institute","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Masachika","middleName":"","lastName":"Ikegami","suffix":""},{"id":9010062,"identity":"0c4b330f-6977-4bd1-9375-3a388c267572","order_by":1,"name":"Shinji Kohsaka","email":"","orcid":"","institution":"Division of Cellular Signaling, National Cancer Center Research Institute","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Shinji","middleName":"","lastName":"Kohsaka","suffix":""},{"id":9010063,"identity":"0340aff2-6859-4168-aab2-ad9f659e0896","order_by":2,"name":"Takeshi Hirose","email":"","orcid":"","institution":"Division of Cellular Signaling, National Cancer Center Research Institute","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Takeshi","middleName":"","lastName":"Hirose","suffix":""},{"id":9010064,"identity":"2d3356b8-daad-4b37-823a-4ce78725990b","order_by":3,"name":"Toshihide Ueno","email":"","orcid":"","institution":"Division of Cellular Signaling, National Cancer Center Research Institute","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Toshihide","middleName":"","lastName":"Ueno","suffix":""},{"id":9010065,"identity":"54cab968-2d1e-4c8f-9b31-187cca84f482","order_by":4,"name":"Naoki Kanomata","email":"","orcid":"","institution":"Department of Pathology, St Luke’s International Hospital","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Naoki","middleName":"","lastName":"Kanomata","suffix":""},{"id":9010066,"identity":"191e544c-56cd-49b6-839c-0d0488f4f338","order_by":5,"name":"Hideko Yamauchi","email":"","orcid":"","institution":"Department of Breast Surgical Oncology, St Luke’s International Hospital","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Hideko","middleName":"","lastName":"Yamauchi","suffix":""},{"id":9010067,"identity":"6467fea9-b7de-43f3-aef9-7ab2e0808478","order_by":6,"name":"Hiroshi Kobayashi","email":"","orcid":"","institution":"Department of Orthopaedic Surgery, Faculty of Medicine, The University of Tokyo","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Hiroshi","middleName":"","lastName":"Kobayashi","suffix":""},{"id":9010068,"identity":"5d824d21-4365-4315-a98c-bdad05159ba1","order_by":7,"name":"Sakae Tanaka","email":"","orcid":"","institution":"The University of Tokyo","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Sakae","middleName":"","lastName":"Tanaka","suffix":""},{"id":9010069,"identity":"7552c413-8e41-4696-8f6a-a0ca74e23f6c","order_by":8,"name":"Hiroyuki Mano","email":"","orcid":"https://orcid.org/0000-0003-4645-0181","institution":"National Cancer Center Research Institute","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Hiroyuki","middleName":"","lastName":"Mano","suffix":""}],"badges":[],"createdAt":"2021-01-23 05:15:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-153650/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-153650/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s42003-021-02930-4","type":"published","date":"2021-12-15T05:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":5345946,"identity":"325e3ef9-dedb-46af-9c6a-1db5ab37f5fc","added_by":"auto","created_at":"2021-01-28 17:56:47","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":66731,"visible":true,"origin":"","legend":"An example of microhomology-induced chimeric 383 read (MICR)-originated\n sequencing error.\n a. The genomic sequence visualized by Integrative Genomics Viewer exhibits a T-to-C\nartifact in the FGFR4 gene. In all mutation-supporting reads, only six bases downstream of\n the mutation were mapped, and the rest is soft-clipped.\n b. A representative read supporting the mutation. The upstream sequence was mapped to the\n forward strand (blue arrow), and the downstream sequence was mapped to the reverse strand\n(green arrow). The red box represented the T-to-C artifact. Most of the downstream bases\n were soft-clipped.\n c. Two palindromic sequences in a single-stranded DNA (ssDNA) formed a hairpin structure.\n After nicking and partial denaturation, the double-stranded DNA was regenerated during the\n end-repair step of library preparation. The mismatched base between two palindromic\n sequences was defined as a mutation.\nd. The MicroSEC algorithm is based on three criteria. Filter 1, 3: the distance from the\nmutation position to the most distant mapped base is distributed over a limited range for any\n reads. Filter 2: MICR-originated sequencing errors are generated when two palindromic\n sequences are in the same DNA fragment. Filter 4: The mis-annealing of ssDNA derived\n from two distant homologous regions also creates an artifact.\n e. Mutations identified by capture-based sequencing were validated by amplicon-based sequencing. The mutations that passed through the MicroSEC filter were detected with a\n similar level of variant allele frequency (VAF) by both methods (blue). A potential CG-to-TG artifact with a VAF of 5.5% was not amplified by amplicon-based sequencing (red). Filtered out mutations were not detected by amplicon-based sequencing (green).","description":"","filename":"Fig1.png","url":"https://assets-eu.researchsquare.com/files/rs-153650/v1/85c977b6879a262eaa8cb6c6.png"},{"id":19032556,"identity":"6f4f7b03-51cd-48c8-8d01-97e91ec23eb7","added_by":"auto","created_at":"2022-03-09 17:35:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":977490,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptIkegami.pdf","url":"https://assets-eu.researchsquare.com/files/rs-153650/v1_covered.pdf"},{"id":13579506,"identity":"ff3d297e-474d-46fa-8acd-7d0e9430f99c","added_by":"auto","created_at":"2021-09-17 04:20:04","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":972399,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptIkegami.pdf","url":"https://assets-eu.researchsquare.com/files/rs-153650/v1_covered.pdf"},{"id":5346076,"identity":"0a6dea70-134a-4844-ad6c-bb4c5e6a3960","added_by":"auto","created_at":"2021-01-28 18:00:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":962879,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptIkegami.pdf","url":"https://assets-eu.researchsquare.com/files/rs-153650/v1_stamped.pdf"},{"id":5345683,"identity":"52b2209b-41aa-4e45-a072-6800d8230217","added_by":"auto","created_at":"2021-01-28 17:53:47","extension":"xlsx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":1263629,"visible":true,"origin":"","legend":"Supplementary Data","description":"","filename":"supplementarydataIkegami.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-153650/v1/eecafcbfecdb783806101b51.xlsx"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"MicroSEC: Sequence error filtering pipeline for formalin-fixed and paraffin-embedded samples","fulltext":[{"header":"Full Text","content":"\u003cp\u003eThis preprint is available for \u003ca href='/article/rs-153650/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e.\u003c/p\u003e"}],"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":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"formalin-fixed, paraffin-embedded samples, MicroSEC, sequencing errors","lastPublishedDoi":"10.21203/rs.3.rs-153650/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-153650/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The clinical sequencing of tumors is usually performed on formalin-fixed, paraffin-embedded (FFPE) samples and results in many sequencing errors. Most of these errors are detected in chimeric reads caused by single-strand DNA molecules with microhomology. Our filtering pipeline, MicroSEC, focuses on the uneven distribution of mutations in each read and removes the sequencing errors in FFPE samples without eliminating the true mutations that are also detected in fresh frozen samples.","manuscriptTitle":"MicroSEC: Sequence error filtering pipeline for formalin-fixed and paraffin-embedded samples","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2021-01-28 17:53:45","doi":"10.21203/rs.3.rs-153650/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"1d24f0f5-4edf-4b71-ac8d-df7d1caf6213","owner":[],"postedDate":"January 28th, 2021","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":2127741,"name":"Computational Biology"},{"id":2127742,"name":"Bioinformatics"},{"id":2127743,"name":"Software Engineering"},{"id":2127744,"name":"Medical Genetics"}],"tags":[],"updatedAt":"2022-03-09T17:35:22+00:00","versionOfRecord":{"articleIdentity":"rs-153650","link":"https://doi.org/10.1038/s42003-021-02930-4","journal":{"identity":"communications-biology","isVorOnly":false,"title":"Communications Biology"},"publishedOn":"2021-12-15 05:00:00","publishedOnDateReadable":"December 15th, 2021"},"versionCreatedAt":"2021-01-28 17:53:45","video":"","vorDoi":"10.1038/s42003-021-02930-4","vorDoiUrl":"https://doi.org/10.1038/s42003-021-02930-4","workflowStages":[]},"version":"v1","identity":"rs-153650","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-153650","identity":"rs-153650","version":["v1"]},"buildId":"ehx78VzkSd0WSzXnipQa-","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}