Generative AI for High-Dimensional Biological Data Under HDLSS Constraints: A Critical Review and Comparative Study

Generative AI for High-Dimensional Biological Data Under HDLSS Constraints: A Critical Review and Comparative Study | 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 Generative AI for High-Dimensional Biological Data Under HDLSS Constraints: A Critical Review and Comparative Study Tomojit Ghosh, Sai Vijay Kumar Surineela, Caleb Hendren, Prathyusha Kanakamalla, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9131243/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 19 You are reading this latest preprint version Abstract Generative artificial intelligence (GenAI) models have become central to modern Artificial Intelligence (AI) systems and analysis in high-dimensional, low-sample-size (HDLSS) biological domains. This article presents a critical review and comparative analysis of major Gen-AI families—including Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), diffusion-based probabilis-tic models, and energy-based models—with emphasis on their behavior, stability, and generative fidelity under data-scarce conditions. We survey the literature from 2015–2025, organize the field through a taxonomy of current generative paradigms, and analyze how these models are adapted to omics settings such as 1 scRNA-seq, bulk RNA-seq, spatial transcriptomics, metabolomics, and related molecular data. A recurring finding across the literature is that most models rely on aggressive preprocessing, such as highly variable gene selection, principal component analysis, or the latent space structure of an encoder-decoder network , effectively replacing the original HDLSS problem with a lower-dimensional proxy. These models are typically applied to moderate to medium-sized data sets and currently lack validation in biological applications where sample size is significantly small, e.g., fewer than 10 replicates. We further identify the absence of embedded sparsity-aware feature selection as a major methodological gap. To complement the survey, we experimentally compare representative VAE-, GAN-, and diffusion-based models on benchmark biological datasets in the HDLSS regime. The results show that VAEs remain comparatively stable in low-sample settings, whereas GANs and diffusion models improve substantially as sample size increases. Overall, this review provides a structured perspective on genera-tive modeling under HDLSS biological constraints and highlights open directions in data-efficient, interpretable, and reproducible Gen-AI for biological discovery. Generative AI HDLSS Omics data GAN VAE Diffusion models Biological data Single-cell RNA-seq Review article Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 17 May, 2026 Reviews received at journal 07 May, 2026 Reviewers agreed at journal 06 May, 2026 Reviewers agreed at journal 04 May, 2026 Reviewers agreed at journal 04 May, 2026 Reviewers agreed at journal 03 May, 2026 Reviewers agreed at journal 02 May, 2026 Reviewers agreed at journal 02 May, 2026 Reviewers agreed at journal 01 May, 2026 Reviewers agreed at journal 01 May, 2026 Reviewers agreed at journal 01 May, 2026 Reviewers agreed at journal 01 May, 2026 Reviewers agreed at journal 30 Apr, 2026 Reviewers agreed at journal 30 Apr, 2026 Reviewers agreed at journal 30 Apr, 2026 Reviewers invited by journal 30 Apr, 2026 Editor assigned by journal 24 Mar, 2026 Submission checks completed at journal 18 Mar, 2026 First submitted to journal 15 Mar, 2026 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-9131243","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":635977857,"identity":"5674f31b-7332-4ce2-b9f1-8ebd5bc08dfe","order_by":0,"name":"Tomojit Ghosh","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABBElEQVRIiWNgGAWjYLACCQMQwcDAzFDBwMDGwAMSY8apmgeixQCq5QxYC2MDQS0MDFAtjG1gMfxa7Nm7Ex9YFPxhkI9uPvy5cN7hfD7+tccfMFRYJzbgsoXn7GYDkMMM7xxLk5657bBlm8Q7oOoz6bi1SORukwBrmZFjxsy77bYBm8QZwwbGtsNEaTH+zDsHpuUfEVrkJXIMpHkbgFr4e4BaGvBoOQP2izGPgURamjTPsf9AW3gMZyQcSzfGpYW9vXfjY4k/cnLyM5IPf+apSTOQ7z9j8OFDjbUsLi0gwAyMEh6DAzCuRAIDQwIe5SDA+AFIyMMN5T+AU+UoGAWjYBSMTAAAQS9Ryx3hSEUAAAAASUVORK5CYII=","orcid":"","institution":"Wright State University","correspondingAuthor":true,"prefix":"","firstName":"Tomojit","middleName":"","lastName":"Ghosh","suffix":""},{"id":635977858,"identity":"a4687ce2-da4c-46e7-843e-2964efe5db38","order_by":1,"name":"Sai Vijay Kumar Surineela","email":"","orcid":"","institution":"Wright State University","correspondingAuthor":false,"prefix":"","firstName":"Sai","middleName":"Vijay Kumar","lastName":"Surineela","suffix":""},{"id":635977859,"identity":"a9317264-625e-4f54-840d-5b5c062fa8ef","order_by":2,"name":"Caleb Hendren","email":"","orcid":"","institution":"Chattanooga State Community College","correspondingAuthor":false,"prefix":"","firstName":"Caleb","middleName":"","lastName":"Hendren","suffix":""},{"id":635977860,"identity":"c69c37bb-d89a-4dc3-a26a-abeed271346a","order_by":3,"name":"Prathyusha Kanakamalla","email":"","orcid":"","institution":"Wright State University","correspondingAuthor":false,"prefix":"","firstName":"Prathyusha","middleName":"","lastName":"Kanakamalla","suffix":""},{"id":635977861,"identity":"699d19e5-e6fc-436e-848c-ff8f14fd2ba3","order_by":4,"name":"Alireza Ghaffarnia","email":"","orcid":"","institution":"University of Tennessee at Chattanooga","correspondingAuthor":false,"prefix":"","firstName":"Alireza","middleName":"","lastName":"Ghaffarnia","suffix":""},{"id":635977862,"identity":"e219b561-aa77-41a5-bb60-a3325c5448ff","order_by":5,"name":"Harigovind Harikumar","email":"","orcid":"","institution":"Wright State University","correspondingAuthor":false,"prefix":"","firstName":"Harigovind","middleName":"","lastName":"Harikumar","suffix":""},{"id":635977863,"identity":"aceded96-8510-4b65-816c-4267f217b78b","order_by":6,"name":"Michael Markey","email":"","orcid":"","institution":"Wright State University","correspondingAuthor":false,"prefix":"","firstName":"Michael","middleName":"","lastName":"Markey","suffix":""}],"badges":[],"createdAt":"2026-03-15 21:53:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9131243/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9131243/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108806697,"identity":"69a00943-37cc-4175-8f06-cd89370ed6a2","added_by":"auto","created_at":"2026-05-08 15:29:16","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5328938,"visible":true,"origin":"","legend":"","description":"","filename":"GenAIHDLSSAIRTGhosh.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9131243/v1_covered_aa7bfe6b-deb1-45aa-bbb6-2449a6349757.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Generative AI for High-Dimensional Biological Data Under HDLSS Constraints: A Critical Review and Comparative Study","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"artificial-intelligence-review","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"aire","sideBox":"Learn more about [Artificial Intelligence Review](http://link.springer.com/journal/10462)","snPcode":"10462","submissionUrl":"https://submission.nature.com/new-submission/10462/3","title":"Artificial Intelligence Review","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Generative AI, HDLSS, Omics data, GAN, VAE, Diffusion models, Biological data, Single-cell RNA-seq, Review article","lastPublishedDoi":"10.21203/rs.3.rs-9131243/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9131243/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Generative artificial intelligence (GenAI) models have become central to modern Artificial Intelligence (AI) systems and analysis in high-dimensional, low-sample-size (HDLSS) biological domains. This article presents a critical review and comparative analysis of major Gen-AI families—including Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), diffusion-based probabilis-tic models, and energy-based models—with emphasis on their behavior, stability, and generative fidelity under data-scarce conditions. We survey the literature from 2015–2025, organize the field through a taxonomy of current generative paradigms, and analyze how these models are adapted to omics settings such as 1 scRNA-seq, bulk RNA-seq, spatial transcriptomics, metabolomics, and related molecular data. A recurring finding across the literature is that most models rely on aggressive preprocessing, such as highly variable gene selection, principal component analysis, or the latent space structure of an encoder-decoder network , effectively replacing the original HDLSS problem with a lower-dimensional proxy. These models are typically applied to moderate to medium-sized data sets and currently lack validation in biological applications where sample size is significantly small, e.g., fewer than 10 replicates. We further identify the absence of embedded sparsity-aware feature selection as a major methodological gap. To complement the survey, we experimentally compare representative VAE-, GAN-, and diffusion-based models on benchmark biological datasets in the HDLSS regime. The results show that VAEs remain comparatively stable in low-sample settings, whereas GANs and diffusion models improve substantially as sample size increases. Overall, this review provides a structured perspective on genera-tive modeling under HDLSS biological constraints and highlights open directions in data-efficient, interpretable, and reproducible Gen-AI for biological discovery.","manuscriptTitle":"Generative AI for High-Dimensional Biological Data Under HDLSS Constraints: A Critical Review and Comparative Study","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-08 07:02:18","doi":"10.21203/rs.3.rs-9131243/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-17T10:35:53+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-07T07:19:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"122675671771402837039327331007697783484","date":"2026-05-06T04:00:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"167209105468228651414834603451330338026","date":"2026-05-04T04:59:59+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"74849587745423271765125164313464590730","date":"2026-05-04T04:08:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"46461866835553442474799436007352023553","date":"2026-05-03T17:31:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"86714204742330205687084508415652852899","date":"2026-05-03T02:39:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"30509533563998291219390703400878125898","date":"2026-05-02T13:07:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"75835526495845771431068146686808383136","date":"2026-05-01T16:09:22+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"45814970070346314236036616355176774665","date":"2026-05-01T15:49:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"128673897776338312534875344891190458456","date":"2026-05-01T14:19:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"162351696197361425356774542350415355288","date":"2026-05-01T04:03:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"56780498159669000040255833038784830806","date":"2026-05-01T02:30:35+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"87986474672532785166410124542104754879","date":"2026-05-01T02:07:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"20081601841654756249069539966576739122","date":"2026-04-30T19:20:28+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-30T13:03:33+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-24T11:09:07+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-18T04:10:40+00:00","index":"","fulltext":""},{"type":"submitted","content":"Artificial Intelligence Review","date":"2026-03-15T21:46:12+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"artificial-intelligence-review","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"aire","sideBox":"Learn more about [Artificial Intelligence Review](http://link.springer.com/journal/10462)","snPcode":"10462","submissionUrl":"https://submission.nature.com/new-submission/10462/3","title":"Artificial Intelligence Review","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"af64757e-73d7-4700-9647-d3dde39d9186","owner":[],"postedDate":"May 8th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-17T10:35:53+00:00","index":41,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-07T07:19:27+00:00","index":40,"fulltext":""},{"type":"reviewerAgreed","content":"122675671771402837039327331007697783484","date":"2026-05-06T04:00:36+00:00","index":39,"fulltext":""},{"type":"reviewerAgreed","content":"167209105468228651414834603451330338026","date":"2026-05-04T04:59:59+00:00","index":38,"fulltext":""},{"type":"reviewerAgreed","content":"74849587745423271765125164313464590730","date":"2026-05-04T04:08:05+00:00","index":37,"fulltext":""},{"type":"reviewerAgreed","content":"46461866835553442474799436007352023553","date":"2026-05-03T17:31:06+00:00","index":36,"fulltext":""},{"type":"reviewerAgreed","content":"86714204742330205687084508415652852899","date":"2026-05-03T02:39:43+00:00","index":35,"fulltext":""},{"type":"reviewerAgreed","content":"30509533563998291219390703400878125898","date":"2026-05-02T13:07:40+00:00","index":34,"fulltext":""},{"type":"reviewerAgreed","content":"75835526495845771431068146686808383136","date":"2026-05-01T16:09:22+00:00","index":33,"fulltext":""},{"type":"reviewerAgreed","content":"45814970070346314236036616355176774665","date":"2026-05-01T15:49:34+00:00","index":32,"fulltext":""},{"type":"reviewerAgreed","content":"128673897776338312534875344891190458456","date":"2026-05-01T14:19:37+00:00","index":31,"fulltext":""},{"type":"reviewerAgreed","content":"162351696197361425356774542350415355288","date":"2026-05-01T04:03:42+00:00","index":30,"fulltext":""},{"type":"reviewerAgreed","content":"56780498159669000040255833038784830806","date":"2026-05-01T02:30:35+00:00","index":29,"fulltext":""},{"type":"reviewerAgreed","content":"87986474672532785166410124542104754879","date":"2026-05-01T02:07:08+00:00","index":28,"fulltext":""},{"type":"reviewerAgreed","content":"20081601841654756249069539966576739122","date":"2026-04-30T19:20:28+00:00","index":27,"fulltext":""},{"type":"reviewersInvited","content":"21","date":"2026-04-30T13:03:33+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-08T07:02:18+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-08 07:02:18","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9131243","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9131243","identity":"rs-9131243","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}