scRNA-seq Bias Detector: An Integrated Unsupervised Anomaly Recognition and Multi-Track Quality Control Framework for Single-Cell Transcriptomics

scRNA-seq Bias Detector: An Integrated Unsupervised Anomaly Recognition and Multi-Track Quality Control Framework for Single-Cell Transcriptomics | 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 Research Article scRNA-seq Bias Detector: An Integrated Unsupervised Anomaly Recognition and Multi-Track Quality Control Framework for Single-Cell Transcriptomics Yashwant Nama This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9160410/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Single-cell RNA sequencing (scRNA-seq) has emerged as a transformative technology for profiling cellular heterogeneity and identifying cell-type-specific gene expression signatures at genome-wide resolution. However, the integration of scRNA-seq datasets across experimental batches, sequencing runs, and protocols introduces systematic technical biases and batch effects that can mask true biological signals and confound downstream analyses. We present the scRNA-seq Bias Detector , a comprehensive, open-source Python framework designed to bridge the gap between wet-lab biological intuition and the algorithmic foundations of quality control in single-cell genomics. The platform integrates seven complementary computational modules: (1) differential expression analysis for identifying batch-biased genes, (2) principal component analysis for quantifying batch-induced separation, (3) isolation forest-based unsupervised anomaly detection for contaminating cell identification, (4) comprehensive gene expression quality metrics including zero-inflation and variance distribution profiling, (5) UMAP and t-SNE nonlinear dimensionality reduction for batch mixing assessment, (6) Harmony batch correction with quantitative separation scoring, and (7) graph neural network (GNN)-based cell similarity analysis for neighbourhood-aware anomaly detection. Deployed via a lightweight Streamlit interface, the framework provides researchers with interactive visualizations, statistical reports, and directly actionable outputs compatible with batch correction workflows such as ComBat, Harmony, and Scanorama. We validated our approach using synthetic datasets with known batch effects and a biologically realistic semi-synthetic PBMC dataset modelled after established IFN-β stimulation experimental designs [1], demonstrating robust performance across both controlled and biologically meaningful batch-effect scenarios. The scRNA-seq Bias Detector serves as both a scalable prototyping environment for automated quality control pipelines and a translational tool to render computational batch assessment interpretable and actionable in immunometabolism and host-pathogen interaction studies. Bioinformatics Computational Biology Epigenetics & Genomics Artificial Intelligence and Machine Learning batch effects quality control single-cell RNA-seq scRNA-seq anomaly detection bioinformatics Streamlit computational genomics explainable AI Full Text Additional Declarations The authors declare no competing interests. Supplementary Files scRNAseqBiasDetectorQCSupplementary.pdf scRNAseq_BiasDetector_QC_Supplementary Cite Share Download PDF Status: Posted 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-9160410","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":608324541,"identity":"72508272-7bd5-4ed7-aef2-73d9594665b9","order_by":0,"name":"Yashwant Nama","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA80lEQVRIiWNgGAWjYDADAzBZAcTMzA0kaDlwBqSFkRQtB9tAJAEt5uynEz8wttnZm0skP3v8cV5tNH87UMuPim04tVj25G6WYGxLTtw5I83c4OC247kzDjM2MPacuY3bPQdyNwC1MCcY3E4wkzi47VhuA1ALM2MbHi3n327+wdhWb29wO/2bxME5x3LnE9RyI3cb0JbDjBtu5wBtaajJ3UBYy9ttFgnnjiduuP+mTOLMsQO5G4FaDuL1y/nczTc+lFXbG5w5vk2ioqYud975wwcf/KjArQUMEtngzMNg8gB+9SDwB86qI6x4FIyCUTAKRhwAAHzEYxurZSi+AAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0003-3443-4413","institution":"Independent Computational Researcher, Jaipur, Rajasthan, India","correspondingAuthor":true,"prefix":"","firstName":"Yashwant","middleName":"","lastName":"Nama","suffix":""}],"badges":[],"createdAt":"2026-03-18 14:13:21","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":true,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":true},"doi":"10.21203/rs.3.rs-9160410/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9160410/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105035010,"identity":"75626aec-c030-432d-8f24-7d4c3a49fdb7","added_by":"auto","created_at":"2026-03-20 07:25:15","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1607422,"visible":true,"origin":"","legend":"","description":"","filename":"NamaYscRNAseqBiasDetectorQC2026.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9160410/v1_covered_fb910d69-3b86-4ee9-9d01-7cc2bbd14908.pdf"},{"id":104967769,"identity":"e0f134ff-7429-46bb-b48a-32399099598d","added_by":"auto","created_at":"2026-03-19 10:11:51","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":646100,"visible":true,"origin":"","legend":"\u003cp\u003escRNAseq_BiasDetector_QC_Supplementary\u003c/p\u003e","description":"","filename":"scRNAseqBiasDetectorQCSupplementary.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9160410/v1/16e82f46da079f319e15116b.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003escRNA-seq Bias Detector: An Integrated Unsupervised Anomaly Recognition and Multi-Track Quality Control Framework for Single-Cell Transcriptomics\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":" Independent Computational Researcher, Jaipur, Rajasthan, India","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"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":"batch effects, quality control, single-cell RNA-seq, scRNA-seq, anomaly detection, bioinformatics, Streamlit, computational genomics, explainable AI","lastPublishedDoi":"10.21203/rs.3.rs-9160410/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9160410/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSingle-cell RNA sequencing (scRNA-seq) has emerged as a transformative technology for profiling cellular heterogeneity and identifying cell-type-specific gene expression signatures at genome-wide resolution. However, the integration of scRNA-seq datasets across experimental batches, sequencing runs, and protocols introduces systematic technical biases and batch effects that can mask true biological signals and confound downstream analyses. We present the \u003cstrong\u003escRNA-seq Bias Detector\u003c/strong\u003e, a comprehensive, open-source Python framework designed to bridge the gap between wet-lab biological intuition and the algorithmic foundations of quality control in single-cell genomics. The platform integrates seven complementary computational modules: (1) differential expression analysis for identifying batch-biased genes, (2) principal component analysis for quantifying batch-induced separation, (3) isolation forest-based unsupervised anomaly detection for contaminating cell identification, (4) comprehensive gene expression quality metrics including zero-inflation and variance distribution profiling, (5) UMAP and t-SNE nonlinear dimensionality reduction for batch mixing assessment, (6) Harmony batch correction with quantitative separation scoring, and (7) graph neural network (GNN)-based cell similarity analysis for neighbourhood-aware anomaly detection. Deployed via a lightweight Streamlit interface, the framework provides researchers with interactive visualizations, statistical reports, and directly actionable outputs compatible with batch correction workflows such as ComBat, Harmony, and Scanorama. We validated our approach using synthetic datasets with known batch effects and a biologically realistic semi-synthetic PBMC dataset modelled after established IFN-β stimulation experimental designs [1], demonstrating robust performance across both controlled and biologically meaningful batch-effect scenarios. The \u003cstrong\u003escRNA-seq Bias Detector \u003c/strong\u003eserves as both a scalable prototyping environment for automated quality control pipelines and a translational tool to render computational batch assessment interpretable and actionable in immunometabolism and host-pathogen interaction studies.\u003c/p\u003e","manuscriptTitle":"scRNA-seq Bias Detector: An Integrated Unsupervised Anomaly Recognition and Multi-Track Quality Control Framework for Single-Cell Transcriptomics","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-19 10:11:20","doi":"10.21203/rs.3.rs-9160410/v1","editorialEvents":[{"type":"communityComments","content":0}],"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":"299aff48-257c-4329-b689-7e2e5280d22e","owner":[],"postedDate":"March 19th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":64731758,"name":"Bioinformatics"},{"id":64731759,"name":"Computational Biology"},{"id":64731760,"name":"Epigenetics \u0026 Genomics"},{"id":64731761,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2026-03-19T10:11:20+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-19 10:11:20","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9160410","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9160410","identity":"rs-9160410","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}