Identifying Discriminative Codons in Brain Data using Class-Discernment Maps: Pearls in Hand without Exploring the Sea

Identifying Discriminative Codons in Brain Data using Class-Discernment Maps: Pearls in Hand without Exploring the Sea | 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 Article Identifying Discriminative Codons in Brain Data using Class-Discernment Maps: Pearls in Hand without Exploring the Sea MohammadAli Shaeri, Mahsa Shoaran This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4954085/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 Conventional neural correlates are useful in brain studies but often fall short in capturing discriminative information related to stimuli or action classes, particularly in multi-class scenarios. Here, we introduce truly ‘discriminative codons’ as features that markedly differentiate neural activity classes. This definition allows us to create an efficient framework for visualizing discriminative information through ‘class-discernment maps’. Our framework generates deterministic codons with straightforward interpretations provided by closed-form class saliency expressions, thereby eliminating the need for laborious hyperparameter tuning and iterative model optimization typically required by deep learning models. Class saliency effectively captures both unilateral and bilateral discrimination while being insensitive to distant confounders, outperforming Pearson correlation, mutual information, and Fisher’s discriminant ratio in extracting various discriminative data structures. By effectively analyzing these codons, we quantitatively investigated temporal resolution, sparsity, and similarities in neural encoding. We further employed the proposed model to decode movement intentions from intracortical and electrocortical activities in distinct tasks, achieving state-of-the-art decoding accuracies of 94% and 82% on the handwriting and finger movement tasks, respectively. Our approach offers in-depth data analysis and accurate predictions, bridging the gap between interpretability and decodability in modern neuroscience research. Biological sciences/Neuroscience/Sensorimotor processing Biological sciences/Computational biology and bioinformatics/Data processing Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Neuroscience/Cognitive neuroscience Biological sciences/Neuroscience/Computational neuroscience Full Text Additional Declarations There is NO Competing Interest. 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-4954085","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":361559148,"identity":"d9fefffc-6dd4-42e1-9d4f-d7f95c496ee9","order_by":0,"name":"MohammadAli Shaeri","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwElEQVRIiWNgGAWjYFACHhAhIQciDzwgRYsxWEsCCVoYEhtAJFFaDM6fPfjh4x6L9Plhhx8CbbGT020gpOVGXrLkjGcSuRtvpxkAtSQbmx0gqIXHQJrnAFDL7ASQlgOJ2whqOX/G+PefAxLphrPTPxCp5UCOmTTDAYkEeekcIm2RvJFjZtlzQMJwg3ROwYEEAyL8wgd02I0fB+rk5Wenb/7wocJOjqAWBZgCAzDDgIByEJBvQGeMglEwCkbBKEAHAFDVSGFO9ltWAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0002-6922-0453","institution":"École polytechnique fédérale de Lausanne ‐ EPFL,","correspondingAuthor":true,"prefix":"","firstName":"MohammadAli","middleName":"","lastName":"Shaeri","suffix":""},{"id":361559149,"identity":"ebc0db66-91ce-498d-bf88-bdc6aa704ef3","order_by":1,"name":"Mahsa Shoaran","email":"","orcid":"","institution":"Ecole Polytechnique Fédérale de Lausanne (EPFL)","correspondingAuthor":false,"prefix":"","firstName":"Mahsa","middleName":"","lastName":"Shoaran","suffix":""}],"badges":[],"createdAt":"2024-08-21 23:10:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4954085/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4954085/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94729093,"identity":"feb2bbaf-6ce2-4892-8ad7-43dd9fa410ed","added_by":"auto","created_at":"2025-10-30 07:04:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4045113,"visible":true,"origin":"","legend":"","description":"","filename":"2024NatureBMEShaeriShoaranDNCManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4954085/v1_covered_62196c7d-4f02-4794-80b1-f5154e6a3bcc.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Identifying Discriminative Codons in Brain Data using Class-Discernment Maps: Pearls in Hand without\r\nExploring the Sea","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","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":"","lastPublishedDoi":"10.21203/rs.3.rs-4954085/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4954085/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Conventional neural correlates are useful in brain studies but often fall short in capturing discriminative information related to stimuli or action classes, particularly in multi-class scenarios. Here, we introduce truly ‘discriminative codons’ as features that markedly differentiate neural activity classes. This definition allows us to create an efficient framework for visualizing discriminative information through ‘class-discernment maps’. Our framework generates deterministic codons with straightforward interpretations provided by closed-form class saliency expressions, thereby eliminating the need for laborious hyperparameter tuning and iterative model optimization typically required by deep learning models. Class saliency effectively captures both unilateral and bilateral discrimination while being insensitive to distant confounders, outperforming Pearson correlation, mutual information, and Fisher’s discriminant ratio in extracting various discriminative data structures. By effectively analyzing these codons, we quantitatively investigated temporal resolution, sparsity, and similarities in neural encoding. We further employed the proposed model to decode movement intentions from intracortical and electrocortical activities in distinct tasks, achieving state-of-the-art decoding accuracies of 94% and 82% on the handwriting and finger movement tasks, respectively. Our approach offers in-depth data analysis and accurate predictions, bridging the gap between interpretability and decodability in modern neuroscience research.","manuscriptTitle":"Identifying Discriminative Codons in Brain Data using Class-Discernment Maps: Pearls in Hand without\nExploring the Sea","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-10-03 10:06:27","doi":"10.21203/rs.3.rs-4954085/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":"c6eb9d9f-27a2-44d1-9f9e-37dd2bb59513","owner":[],"postedDate":"October 3rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":38466499,"name":"Biological sciences/Neuroscience/Sensorimotor processing"},{"id":38466500,"name":"Biological sciences/Computational biology and bioinformatics/Data processing"},{"id":38466501,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":38466502,"name":"Biological sciences/Neuroscience/Cognitive neuroscience"},{"id":38466503,"name":"Biological sciences/Neuroscience/Computational neuroscience"}],"tags":[],"updatedAt":"2025-10-29T18:46:13+00:00","versionOfRecord":[],"versionCreatedAt":"2024-10-03 10:06:27","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4954085","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4954085","identity":"rs-4954085","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}