Boosting Pre-trained Model with Silica Nanoparticles Cellular Toxicity Prediction

Boosting Pre-trained Model with Silica Nanoparticles Cellular Toxicity Prediction | 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 Boosting Pre-trained Model with Silica Nanoparticles Cellular Toxicity Prediction Huixia Zhang, Jiajun Tong, Minmin Chen, Xichuan Cao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7735307/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 29 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted 11 You are reading this latest preprint version Abstract Silica nanoparticles have been widely adopted as carriers for drug delivery and components of multifunctional nanocomposites, but potentially lead to off-target accumulation and subsequent cytotoxic effects. Previous works explored data-driven methods to improve the evaluation efficiency and supporting the rational design of nanomedicines. However, there are still two challenges needs to be considered. The one is data leakage problem, as previous methods incorporate either evaluation stage features (e.g., Viability_indicator, Positive_control) or rely on one-hot encoding that requires prior knowledge of all categorical values, leading to data leakage risk. Another is poor model generalizability, since one-hot encoding fixes feature space dimensions, causing model failure when facing unseen categorical values. In this work, we propose a pre-trained model based framework for silica nanoparticles Cellular Toxicity Prediction. To address the data leakage problem, we first removed features that comes from the drug evaluation stage such as Viability_indicator, Positive_control, SiO 2 NP_label, Interference_testing, and Assay_viability. And then we utilize the embedding layer from the TabPFN to process the original categorical values into dense vectors. To improve the model generalizability, we employ in-context learning on pre-trained TabPFN, which has already learned a large number of patterns from amount of synthetic data. The model only needs to change the output prediction distribution through in-context learning without retraining the model or even adjusting the model parameters. Experimental results on publicly available dataset demonstrates that our framework not only achieves state-of-the-art classification performance but also effectively mitigates data leakage and improves generalizability for novel nanoparticle formulations. The code and data are shared in https://github.com/AppleMax1992/pretrained_nanosilica . Physical sciences/Chemistry Biological sciences/Computational biology and bioinformatics Biological sciences/Drug discovery Physical sciences/Mathematics and computing Physical sciences/Nanoscience and technology Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 29 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 07 Dec, 2025 Reviews received at journal 26 Nov, 2025 Reviewers agreed at journal 06 Nov, 2025 Reviewers agreed at journal 05 Nov, 2025 Reviews received at journal 03 Nov, 2025 Reviewers agreed at journal 23 Oct, 2025 Reviewers invited by journal 21 Oct, 2025 Editor assigned by journal 21 Oct, 2025 Editor invited by journal 09 Oct, 2025 Submission checks completed at journal 30 Sep, 2025 First submitted to journal 30 Sep, 2025 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-7735307","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":535067810,"identity":"07888365-a148-4f2a-a5e1-70bb4066b9c2","order_by":0,"name":"Huixia Zhang","email":"","orcid":"","institution":"China University of Mining and Technology","correspondingAuthor":false,"prefix":"","firstName":"Huixia","middleName":"","lastName":"Zhang","suffix":""},{"id":535067811,"identity":"4dfbd7f6-45f2-411e-9995-c2768781d0ff","order_by":1,"name":"Jiajun Tong","email":"","orcid":"","institution":"China University of Mining and Technology","correspondingAuthor":false,"prefix":"","firstName":"Jiajun","middleName":"","lastName":"Tong","suffix":""},{"id":535067812,"identity":"83ed2bb6-51b3-43df-99e4-83260127803a","order_by":2,"name":"Minmin Chen","email":"","orcid":"","institution":"Xuzhou Medical University","correspondingAuthor":false,"prefix":"","firstName":"Minmin","middleName":"","lastName":"Chen","suffix":""},{"id":535067816,"identity":"ebfbb5d3-6cc1-4bc0-9246-beac11f43348","order_by":3,"name":"Xichuan Cao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4UlEQVRIiWNgGAWjYDACZgY2GOsAlJFAtBY2kFIDIrQwwLXwGBCnxeA487PHPDV35Pnbez5+5s35w8DPnmPA8HMHbi2SzWzmxjzHnhnOOHN2szTvNgMGyZ43Boy9Z3Br4WfmYZPmYTucwHAjdxszSIvBjRwDZsY2PB4Ba/l3OEH+Rs4zsBZ7QlrAtvC2HU4AGs4GsUWCgBagX8wk5/YdNtx45pix5NxtxjwSZ54VHOzFo8Xg/OFnEm++HZaXO9788MPbbXJy/O3JGx/8xKMFA/CAiAMkaBgFo2AUjIJRgAUAABNTRxmuqzPmAAAAAElFTkSuQmCC","orcid":"","institution":"China University of Mining and Technology","correspondingAuthor":true,"prefix":"","firstName":"Xichuan","middleName":"","lastName":"Cao","suffix":""}],"badges":[],"createdAt":"2025-09-28 15:23:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7735307/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7735307/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-33872-0","type":"published","date":"2025-12-29T15:58:17+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":94818661,"identity":"d235df2f-3aa8-4966-9c05-5a64c97ca7f1","added_by":"auto","created_at":"2025-10-31 05:37:41","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1267736,"visible":true,"origin":"","legend":"","description":"","filename":"ScientificReportsBoostingPretrainedModelwithSilicaNanoparticlesCellularToxicityPrediction.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7735307/v1/1f2636cdb26fc90de06f06b0.pdf"},{"id":94818662,"identity":"76442fe8-293d-460c-b986-e995989aedb5","added_by":"auto","created_at":"2025-10-31 05:37:41","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6236,"visible":true,"origin":"","legend":"","description":"","filename":"a3ac0521103f460da77e70fb839a3232.json","url":"https://assets-eu.researchsquare.com/files/rs-7735307/v1/cb4f015dc42ad86831272309.json"},{"id":99545348,"identity":"46cfae6b-f29c-48f9-b07c-5babfdcc96fc","added_by":"auto","created_at":"2026-01-05 16:06:11","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1160135,"visible":true,"origin":"","legend":"","description":"","filename":"ScientificReportsBoostingPretrainedModelwithSilicaNanoparticlesCellularToxicityPrediction.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7735307/v1_covered_5845e13e-bc74-4ca7-92f4-c18e4a560161.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Boosting Pre-trained Model with Silica Nanoparticles Cellular Toxicity Prediction","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7735307/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7735307/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Silica nanoparticles have been widely adopted as carriers for drug delivery and components of multifunctional nanocomposites, but potentially lead to off-target accumulation and subsequent cytotoxic effects. Previous works explored data-driven methods to improve the evaluation efficiency and supporting the rational design of nanomedicines. However, there are still two challenges needs to be considered. The one is data leakage problem, as previous methods incorporate either evaluation stage features (e.g., Viability_indicator, Positive_control) or rely on one-hot encoding that requires prior knowledge of all categorical values, leading to data leakage risk. Another is poor model generalizability, since one-hot encoding fixes feature space dimensions, causing model failure when facing unseen categorical values. In this work, we propose a pre-trained model based framework for silica nanoparticles Cellular Toxicity Prediction. To address the data leakage problem, we first removed features that comes from the drug evaluation stage such as Viability_indicator, Positive_control, SiO 2 NP_label, Interference_testing, and Assay_viability. And then we utilize the embedding layer from the TabPFN to process the original categorical values into dense vectors. To improve the model generalizability, we employ in-context learning on pre-trained TabPFN, which has already learned a large number of patterns from amount of synthetic data. The model only needs to change the output prediction distribution through in-context learning without retraining the model or even adjusting the model parameters. Experimental results on publicly available dataset demonstrates that our framework not only achieves state-of-the-art classification performance but also effectively mitigates data leakage and improves generalizability for novel nanoparticle formulations. The code and data are shared in https://github.com/AppleMax1992/pretrained_nanosilica.","manuscriptTitle":"Boosting Pre-trained Model with Silica Nanoparticles Cellular Toxicity Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-31 05:37:36","doi":"10.21203/rs.3.rs-7735307/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-08T04:29:49+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-27T02:07:52+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"216709814187759183407864253936953906912","date":"2025-11-07T02:05:51+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"301244790493276193492264818179968160384","date":"2025-11-06T04:57:13+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-04T00:10:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"144190165355561913227631434750385043282","date":"2025-10-23T11:31:17+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-21T10:06:50+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-21T10:05:34+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-10-09T08:29:08+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-30T09:10:30+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-09-30T08:30:03+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"7e3bf2e0-d98d-4fe7-9411-051c41ecc7e5","owner":[],"postedDate":"October 31st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":56886403,"name":"Physical sciences/Chemistry"},{"id":56886404,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":56886405,"name":"Biological sciences/Drug discovery"},{"id":56886406,"name":"Physical sciences/Mathematics and computing"},{"id":56886407,"name":"Physical sciences/Nanoscience and technology"}],"tags":[],"updatedAt":"2026-01-05T16:01:38+00:00","versionOfRecord":{"articleIdentity":"rs-7735307","link":"https://doi.org/10.1038/s41598-025-33872-0","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-12-29 15:58:17","publishedOnDateReadable":"December 29th, 2025"},"versionCreatedAt":"2025-10-31 05:37:36","video":"","vorDoi":"10.1038/s41598-025-33872-0","vorDoiUrl":"https://doi.org/10.1038/s41598-025-33872-0","workflowStages":[]},"version":"v1","identity":"rs-7735307","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7735307","identity":"rs-7735307","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}