BKDRP: A Biological Knowledge-Driven Approach for Drug Response Prediction Using Multi-Omics Data in Cancer Cell Lines

BKDRP: A Biological Knowledge-Driven Approach for Drug Response Prediction Using Multi-Omics Data in Cancer Cell Lines | 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 BKDRP: A Biological Knowledge-Driven Approach for Drug Response Prediction Using Multi-Omics Data in Cancer Cell Lines Koyel Mandal, Sanghamitra Bandyopadhyay This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7614158/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 17 Mar, 2026 Read the published version in BMC Bioinformatics → Version 1 posted 11 You are reading this latest preprint version Abstract Background: Cancer heterogeneity results in patients with the same diagnosis responding differently to drugs, making treatments extremely challenging. Advances in computational power enable personalized treatments that suppress tumors and extend patient survival. Therefore, accurate prediction of cancer cell response to a particular medication is of utmost importance. Current deep learning-based models have achieved impressive accuracy, but they often function as a "black box'' and cannot explain the reason for the prediction. To address this limitation, we develop a deep learning-based model, BKDRP, which incorporates prior biological information into the architecture, along with molecular fingerprints of drugs, while embedding biological priors into its architecture. Specifically, it incorporates the fact that genes encode proteins that combine to form protein complexes, which in turn regulate biological pathways, ultimately targeted by drugs. Results: We evaluate BKDRP on the GDSC (Genomics of Drug Sensitivity and Cancer) cell line dataset using multi-omics gene expression, protein expression, mutation, and copy number variation. Four rigorous experiments have been conducted to test the model's generalizability: prediction of unknown drug–cell line responses, responses to unseen drugs (LODO: Leave-One-Drug-Out), responses to unseen cell lines (LOCLO: Leave-On-Cell-Line-Out), and responses across unseen cancer types (LOCO: Leave-One-Cancer-Type-Out). The performance of the proposed method and baseline algorithms is assessed using two metrics: Area Under the ROC Curve (AUC) and Area Under the Precision-Recall Curve (AUPR). The experimental results demonstrate that BKDRP performs well in different evaluation techniques. Notably, BKDRP has achieved an AUC of 0.8776, surpassing traditional machine learning and deep learning approaches and demonstrating robustness in handling biological variability across cancer types. A case study of lung adenocarcinoma (LUAD) highlights known biomarkers (KRAS, EGFR, STK11), key proteins (SOCS1, HSPA8, SMC3), and drugs (Erlotinib, Palbociclib) consistent with the literature. Conclusions: In conclusion, BKDRP presents a novel biological knowledge-driven deep neural network model for cancer drug response prediction that shows strong predictive accuracy and interpretability. By integrating multi-omics data and incorporating domain knowledge, BKDRP has the strong potential for applications in biomarker discovery and the advancement of personalized oncology. Drug response prediction multi-omics data cancer cell line deep neural network morgan fingerprint biological knowledge Full Text Additional Declarations No competing interests reported. Supplementary Files supplementary.pdf Cite Share Download PDF Status: Published Journal Publication published 17 Mar, 2026 Read the published version in BMC Bioinformatics → Version 1 posted Editorial decision: Revision requested 22 Oct, 2025 Reviews received at journal 19 Oct, 2025 Reviews received at journal 19 Oct, 2025 Reviewers agreed at journal 25 Sep, 2025 Reviewers agreed at journal 20 Sep, 2025 Reviewers agreed at journal 20 Sep, 2025 Reviewers invited by journal 20 Sep, 2025 Editor invited by journal 18 Sep, 2025 Editor assigned by journal 15 Sep, 2025 Submission checks completed at journal 15 Sep, 2025 First submitted to journal 14 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-7614158","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":520833456,"identity":"a5459067-b120-4821-9028-369b8a1f6886","order_by":0,"name":"Koyel Mandal","email":"","orcid":"","institution":"Indian Statistical Institute","correspondingAuthor":false,"prefix":"","firstName":"Koyel","middleName":"","lastName":"Mandal","suffix":""},{"id":520833457,"identity":"eebfa3a3-4a23-4749-bb04-2f542079add6","order_by":1,"name":"Sanghamitra Bandyopadhyay","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7klEQVRIiWNgGAWjYJACZiDm4QeSBxgYLMAiB4jSItkMVilBvBYGA4gyCcKOkm8/e/h1Qc02GePj7A8P/KiRYOBvP8B4uACPFoMzeWnWM47d5jE7zGNwsOeYBIPEmQSGwzPwaWHIMTPmYQNrYTjMwAZ02A0GBiAbj8P63wC1/LvNY9zM/uAwwz8JBnlCWhhu5Bg/5m27zWPAzGBwmLFNgsGAkBaDG2/MmHn7bvNIgPzS2yfBY3gmsYGAw3KMP/N8u23P33/88Ycf32zk5I4fPvwZr8MYwF5GAKBixgb8GoAx+YGQilEwCkbBKBjhAABa5kmQbeXEyQAAAABJRU5ErkJggg==","orcid":"","institution":"Indian Statistical Institute","correspondingAuthor":true,"prefix":"","firstName":"Sanghamitra","middleName":"","lastName":"Bandyopadhyay","suffix":""}],"badges":[],"createdAt":"2025-09-14 18:08:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7614158/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7614158/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12859-026-06406-2","type":"published","date":"2026-03-17T15:58:10+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":92552916,"identity":"bf488cc2-55f2-4890-8c91-97fa4d39a988","added_by":"auto","created_at":"2025-10-01 01:55:42","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5853,"visible":true,"origin":"","legend":"","description":"","filename":"d6ffbc4eb1ce46058b631ba089941441.json","url":"https://assets-eu.researchsquare.com/files/rs-7614158/v1/960bc68148a59d590eb32a22.json"},{"id":105223525,"identity":"9c78d607-1d14-44bf-8ced-6fb8d6915956","added_by":"auto","created_at":"2026-03-23 16:08:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":463252,"visible":true,"origin":"","legend":"","description":"","filename":"BMCBioinformaticsBKDRP.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7614158/v1_covered_ee6be1f5-7b90-4923-bbdc-5f6771e493e6.pdf"},{"id":92552917,"identity":"def351ee-225b-4b85-9332-46c3c47633fd","added_by":"auto","created_at":"2025-10-01 01:55:42","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":151072,"visible":true,"origin":"","legend":"","description":"","filename":"supplementary.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7614158/v1/0626e17059438a1fccfa2632.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"BKDRP: A Biological Knowledge-Driven Approach for Drug Response Prediction Using Multi-Omics Data in Cancer Cell Lines","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":"bmc-bioinformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"binf","sideBox":"Learn more about [BMC Bioinformatics](http://bmcbioinformatics.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/binf","title":"BMC Bioinformatics","twitterHandle":"@BMC_Bioinformatics","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Drug response prediction, multi-omics data, cancer cell line, deep neural network, morgan fingerprint, biological knowledge","lastPublishedDoi":"10.21203/rs.3.rs-7614158/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7614158/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBackground: Cancer heterogeneity results in patients with the same diagnosis responding differently to drugs, making treatments extremely challenging. Advances in computational power enable personalized treatments that suppress tumors and extend patient survival. Therefore, accurate prediction of cancer cell response to a particular medication is of utmost importance. Current deep learning-based models have achieved impressive accuracy, but they often function as a \"black box'' and cannot explain the reason for the prediction. To address this limitation, we develop a deep learning-based model, BKDRP, which incorporates prior biological information into the architecture, along with molecular fingerprints of drugs, while embedding biological priors into its architecture. Specifically, it incorporates the fact that genes encode proteins that combine to form protein complexes, which in turn regulate biological pathways, ultimately targeted by drugs.\u0026nbsp;\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eResults: We evaluate BKDRP on the GDSC (Genomics of Drug Sensitivity and Cancer) cell line dataset using multi-omics gene expression, protein expression, mutation, and copy number variation. Four rigorous experiments have been conducted to test the model's generalizability: prediction of unknown drug–cell line responses, responses to unseen drugs (LODO: Leave-One-Drug-Out), responses to unseen cell lines (LOCLO: Leave-On-Cell-Line-Out), and responses across unseen cancer types (LOCO: Leave-One-Cancer-Type-Out). The performance of the proposed method and baseline algorithms is assessed using two metrics: Area Under the ROC Curve (AUC) and Area Under the Precision-Recall Curve (AUPR). The experimental results demonstrate that BKDRP performs well in different evaluation techniques. Notably, BKDRP has achieved an AUC of 0.8776, surpassing traditional machine learning and deep learning approaches and demonstrating robustness in handling biological variability across cancer types. A case study of lung adenocarcinoma (LUAD) highlights known biomarkers (KRAS, EGFR,\u0026nbsp; STK11), key proteins (SOCS1, HSPA8, SMC3), and drugs (Erlotinib, Palbociclib) consistent with the literature.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eConclusions:\u0026nbsp;In conclusion, BKDRP presents a novel biological knowledge-driven deep neural network model for cancer drug response prediction that shows strong predictive accuracy and interpretability. By integrating multi-omics data and incorporating domain knowledge, BKDRP has the strong potential for applications in biomarker discovery and the advancement of personalized oncology.\u003c/p\u003e","manuscriptTitle":"BKDRP: A Biological Knowledge-Driven Approach for Drug Response Prediction Using Multi-Omics Data in Cancer Cell Lines","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-01 01:55:37","doi":"10.21203/rs.3.rs-7614158/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-10-22T10:31:49+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-20T00:22:34+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-19T14:21:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"329516554663715019428693714284387399059","date":"2025-09-26T02:21:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"247598535017580976699274319144270999492","date":"2025-09-21T03:12:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"292420625324289641807303966188815848157","date":"2025-09-21T02:02:36+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-21T01:42:02+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-09-18T15:58:09+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-15T08:58:07+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-15T08:57:17+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Bioinformatics","date":"2025-09-14T17:52:00+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-bioinformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"binf","sideBox":"Learn more about [BMC Bioinformatics](http://bmcbioinformatics.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/binf","title":"BMC Bioinformatics","twitterHandle":"@BMC_Bioinformatics","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"0f18248a-a220-4408-9b43-4e888dde1d6b","owner":[],"postedDate":"October 1st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-03-23T16:04:43+00:00","versionOfRecord":{"articleIdentity":"rs-7614158","link":"https://doi.org/10.1186/s12859-026-06406-2","journal":{"identity":"bmc-bioinformatics","isVorOnly":false,"title":"BMC Bioinformatics"},"publishedOn":"2026-03-17 15:58:10","publishedOnDateReadable":"March 17th, 2026"},"versionCreatedAt":"2025-10-01 01:55:37","video":"","vorDoi":"10.1186/s12859-026-06406-2","vorDoiUrl":"https://doi.org/10.1186/s12859-026-06406-2","workflowStages":[]},"version":"v1","identity":"rs-7614158","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7614158","identity":"rs-7614158","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}