Physical formula enhanced multi-task learning for pharmacokinetics prediction

Physical formula enhanced multi-task learning for pharmacokinetics 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 Physical formula enhanced multi-task learning for pharmacokinetics prediction Yuqiang Li, Ruifeng Li, Dongzhan Zhou, Ancheng Shen, Ao Zhang, and 7 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3863697/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 Artificial intelligence (AI) technology has demonstrated remarkable potential in drug discovery, where pharmacokinetics plays a crucial role in determining the dosage, safety, and efficacy of new drugs. A major challenge for AI-driven drug discovery (AIDD) is the scarcity of high-quality data, which often requires extensive wet-lab work. A typical example of this is pharmacokinetic experiments. In this work, we develop a physical formula enhanced multi-task learning (PEMAL) method that predicts four key parameters of pharmacokinetics simultaneously. By incorporating physical formulas into the multi-task framework, PEMAL facilitates effective knowledge sharing and target alignment among the pharmacokinetic parameters, thereby enhancing the accuracy of prediction. Our experiments reveal that PEMAL significantly lowers the data demand, compared to typical Graph Neural Networks. Moreover, we demonstrate that PEMAL enhances the robustness to noise, an advantage that conventional Neural Networks do not possess. Another advantage of PEMAL is its high flexibility, which can be potentially applied to other multi-task machine learning scenarios. Overall, our work illustrates the benefits and potential of using PEMAL in AIDD and other scenarios with data scarcity and noise. Biological sciences/Biological techniques/Bioinformatics Biological sciences/Computational biology and bioinformatics/Virtual drug screening Physical sciences/Chemistry/Cheminformatics Biological sciences/Drug discovery/Drug screening Full Text Additional Declarations There is NO Competing Interest. Supplementary Files SupplementInformation.pdf supplementary information 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-3863697","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":284529278,"identity":"b2365021-619d-4de5-ad84-a2fb942b6c35","order_by":0,"name":"Yuqiang Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9UlEQVRIie3SIQvCQBTA8SeDzfBwdUPQr/AsgsXvYbvDKjIwKmjSonZR8Cu4ZjwZaJlgFDTMYlIwCYKIp2GYbouG+3O3HYMf3LED0On+sJzxeZKcVg8oApFMzJigAGKpSLxyGEA6YmHZuXjVZrF2FR7rHMHOb3bwWKo2hmV3RvVW6dBkxNZncMcNLzMK1SSPZHB/2iBiZgAUIjMy/UTS5f4klOSVngR87iAR73+IJRKI2arMaMMXKM/Cx2d0hwirkYLYduDvL882nw+2a7rdjwUbrVP0UBCALAHKFwk0v39UDhIqIC9K9CXFHhpR/EWn0+l0P70BEJtL5evjP/UAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0001-6756-6154","institution":"Shanghai Artificial Intelligence Laboratory","correspondingAuthor":true,"prefix":"","firstName":"Yuqiang","middleName":"","lastName":"Li","suffix":""},{"id":284529279,"identity":"fbb86188-a138-4246-839a-7dc741fda0d1","order_by":1,"name":"Ruifeng Li","email":"","orcid":"https://orcid.org/0000-0002-4373-5811","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Ruifeng","middleName":"","lastName":"Li","suffix":""},{"id":284529280,"identity":"cd5d4c5c-89ab-4216-aa28-9176543eaa99","order_by":2,"name":"Dongzhan Zhou","email":"","orcid":"","institution":"Shanghai AI Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Dongzhan","middleName":"","lastName":"Zhou","suffix":""},{"id":284529281,"identity":"0f7d6b95-0ef5-4c84-89f1-4ecb61cb3099","order_by":3,"name":"Ancheng Shen","email":"","orcid":"","institution":"Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Ancheng","middleName":"","lastName":"Shen","suffix":""},{"id":284529282,"identity":"c0e18ab7-26a5-42e7-b204-4f5fb594c1ee","order_by":4,"name":"Ao Zhang","email":"","orcid":"https://orcid.org/0000-0001-7205-9202","institution":"Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Ao","middleName":"","lastName":"Zhang","suffix":""},{"id":284529283,"identity":"e83b83a7-2a03-4c3e-a527-1ee7776591ff","order_by":5,"name":"Mao Su","email":"","orcid":"https://orcid.org/0000-0003-2066-881X","institution":"Shanghai Artificial Intelligence Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Mao","middleName":"","lastName":"Su","suffix":""},{"id":284529284,"identity":"0c4e2a26-a732-47a6-b3fa-7969e1be4098","order_by":6,"name":"Mingqian Li","email":"","orcid":"","institution":"Zhejiang Lab","correspondingAuthor":false,"prefix":"","firstName":"Mingqian","middleName":"","lastName":"Li","suffix":""},{"id":284529285,"identity":"c4b6a750-6f70-4eca-9b6d-922a02930fc2","order_by":7,"name":"Hongyang Chen","email":"","orcid":"https://orcid.org/0000-0002-7626-0162","institution":"Zhejiang Lab","correspondingAuthor":false,"prefix":"","firstName":"Hongyang","middleName":"","lastName":"Chen","suffix":""},{"id":284529286,"identity":"e22e64fc-da69-4fc8-b363-5b52251a46e3","order_by":8,"name":"Gang Chen","email":"","orcid":"","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Gang","middleName":"","lastName":"Chen","suffix":""},{"id":284529287,"identity":"1948a4f9-2552-4f01-a37f-3f9c38200f5e","order_by":9,"name":"Yin Zhang","email":"","orcid":"","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Yin","middleName":"","lastName":"Zhang","suffix":""},{"id":284529288,"identity":"b409cc1d-13a7-4c0e-8a54-2739453e4db3","order_by":10,"name":"Shufei Zhang","email":"","orcid":"","institution":"Shanghai AI Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Shufei","middleName":"","lastName":"Zhang","suffix":""},{"id":284529289,"identity":"47eeb609-d9b7-432e-813f-a55fe5d27cdd","order_by":11,"name":"Wanli Ouyang","email":"","orcid":"","institution":"Shanghai Artificial Intelligence Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Wanli","middleName":"","lastName":"Ouyang","suffix":""}],"badges":[],"createdAt":"2024-01-14 15:45:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3863697/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3863697/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":54785883,"identity":"23e12a77-139b-4f5d-95f9-eae7e7e086f9","added_by":"auto","created_at":"2024-04-16 18:28:46","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1160963,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3863697/v1_covered_8bf729f6-7f5f-4ddd-98d1-af2c79125bae.pdf"},{"id":54785674,"identity":"a444dc38-3439-4edf-93f2-de34c21c676d","added_by":"auto","created_at":"2024-04-16 18:20:43","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":778172,"visible":true,"origin":"","legend":"\u003cp\u003esupplementary information\u003c/p\u003e","description":"","filename":"SupplementInformation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3863697/v1/99fd6fe1563575ddbecd280e.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Physical formula enhanced multi-task learning for pharmacokinetics prediction","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-3863697/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3863697/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Artificial intelligence (AI) technology has demonstrated remarkable potential in drug discovery, where pharmacokinetics plays a crucial role in determining the dosage, safety, and efficacy of new drugs. A major challenge for AI-driven drug discovery (AIDD) is the scarcity of high-quality data, which often requires extensive wet-lab work. A typical example of this is pharmacokinetic experiments. In this work, we develop a physical formula enhanced multi-task learning (PEMAL) method that predicts four key parameters of pharmacokinetics simultaneously. By incorporating physical formulas into the multi-task framework, PEMAL facilitates effective knowledge sharing and target alignment among the pharmacokinetic parameters, thereby enhancing the accuracy of prediction. Our experiments reveal that PEMAL significantly lowers the data demand, compared to typical Graph Neural Networks. Moreover, we demonstrate that PEMAL enhances the robustness to noise, an advantage that conventional Neural Networks do not possess. Another advantage of PEMAL is its high flexibility, which can be potentially applied to other multi-task machine learning scenarios. Overall, our work illustrates the benefits and potential of using PEMAL in AIDD and other scenarios with data scarcity and noise.","manuscriptTitle":"Physical formula enhanced multi-task learning for pharmacokinetics prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-16 18:20:38","doi":"10.21203/rs.3.rs-3863697/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":"0e5dc186-8bb9-450f-91db-4d8db1619e5a","owner":[],"postedDate":"April 16th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":29953626,"name":"Biological sciences/Biological techniques/Bioinformatics"},{"id":29953627,"name":"Biological sciences/Computational biology and bioinformatics/Virtual drug screening"},{"id":29953628,"name":"Physical sciences/Chemistry/Cheminformatics"},{"id":29953629,"name":"Biological sciences/Drug discovery/Drug screening"}],"tags":[],"updatedAt":"2024-04-16T18:20:38+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-16 18:20:38","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3863697","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3863697","identity":"rs-3863697","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}