MCL-DTI: Using Drug Multimodal Informationand Bi-directional Cross-Attention Learningmethod for Predicting Drug-Target Interaction

MCL-DTI: Using Drug Multimodal Informationand Bi-directional Cross-Attention Learningmethod for Predicting Drug-Target Interaction | 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 MCL-DTI: Using Drug Multimodal Informationand Bi-directional Cross-Attention Learningmethod for Predicting Drug-Target Interaction Ying Qian, Jian Wu, Qian Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2435781/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 26 Aug, 2023 Read the published version in BMC Bioinformatics → Version 1 posted 13 You are reading this latest preprint version Abstract Background: Prediction of drug-target interaction (DTI) is an essential step fordrug discovery and drug reposition. Traditional methods are mostlytime-consuming and labor-intensive, and deep learning-based methods addressthese limitations and are applied to engineering. Most of the current deeplearning methods employ representation learning of unimodal information such as SMILES sequences, molecular graphs, or molecular images of drugs. In addition,most methods focus on feature extraction from drug and target alone withoutfusion learning from drug-target interacting parties, which may lead toinsufficient feature representation. Results: To enhance feature learning between drugs and targets, we propose anovel model based on deep learning for DTI task called MCL-DTI which usesmultimodal information of drug and learn the representation of drug-targetinteraction for drug-target prediction. In order to further explore a morecomprehensive representation of drug features, this paper first exploits twomultimodal information of drugs, molecular image and chemical text, to representthe drug. We also introduce to use bi-rectional multi-head corss attention (MCA)method to learn the interrelationships between drugs and targets. Thus, we buildtwo decoders, which include an multi-head self attention (MSA) block and anMCA block, for cross-information learning. We use a decoder for the drug andtarget separately to obtain the interaction feature maps. Finally, we feed thesefeature maps generated by decoders into a fusion block for feature extraction andoutput the prediction results. Conclusions: MCL-DTI achieves the best results in all the three datasets:Human, C.elegans and Davis, including the balanced datasets and an unbalanceddataset. The results on the drug-drug interaction (DDI) task show that MCL-DTIhas a strong generalization capability and can be easily applied to other tasks. drug-target interaction deep learning multimodal information multi-head self-attention mechanism cross-attention mechanism Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 26 Aug, 2023 Read the published version in BMC Bioinformatics → Version 1 posted Editorial decision: Major revision 03 Jul, 2023 Reviews received at journal 17 Jun, 2023 Reviews received at journal 11 Jun, 2023 Reviewers agreed at journal 09 Jun, 2023 Reviewers agreed at journal 09 Jun, 2023 Reviews received at journal 05 Jun, 2023 Reviewers agreed at journal 25 May, 2023 Reviewers agreed at journal 25 May, 2023 Reviewers invited by journal 25 May, 2023 Editor assigned by journal 02 Feb, 2023 Editor invited by journal 05 Jan, 2023 Submission checks completed at journal 05 Jan, 2023 First submitted to journal 02 Jan, 2023 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-2435781","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":165209500,"identity":"e10e5256-f7b7-45a5-8fd1-8bf7731cedc4","order_by":0,"name":"Ying Qian","email":"","orcid":"","institution":"East China Normal University","correspondingAuthor":false,"prefix":"","firstName":"Ying","middleName":"","lastName":"Qian","suffix":""},{"id":165209501,"identity":"3cac4d19-89d7-4306-b657-48492c8d9c6e","order_by":1,"name":"Jian Wu","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Jian","middleName":"","lastName":"Wu","suffix":""},{"id":165209502,"identity":"2c468ec8-9ad1-46f0-92b7-800bc5d69b32","order_by":2,"name":"Qian Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA40lEQVRIie3RsQqCQBjA8YsDp09bk4PuFRTBpehZLoRmW1oTAlukOd/CRzgRajFdBaee4SCiHNJoaLpyC7r/8HHfcb/pEFKpfjLoxvTtgn9HFv1J1oMY5SkV/q2kNMCpWIZobFRsIHwJMXnhkXhX2wnX2kOIHLNimOwlxEoji+hRzSwELtZDNE8qpmGQkQycux4VjAbDS0fWn8kBXAJXzhAHrSPM+kTMHNyJHnh2kmkOgWJkx/l5Q2TEKHOnhmZG6XZzFrCaUuPopUJGnr8wCNuBn+uoWwMZeH1cI3+jUqlUf94DzjJGjFQMSzcAAAAASUVORK5CYII=","orcid":"","institution":"East China Normal University","correspondingAuthor":true,"prefix":"","firstName":"Qian","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2023-01-02 13:29:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-2435781/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-2435781/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12859-023-05447-1","type":"published","date":"2023-08-26T15:02:04+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":42781123,"identity":"ea08d30c-72dc-408e-8999-bcc832199356","added_by":"auto","created_at":"2023-09-07 15:08:23","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3882285,"visible":true,"origin":"","legend":"","description":"","filename":"MCLDTIUsingDrugMultimodalInformationandBidirectionalCrossAttentionLearningmethodforPredictingDrugTargetInteraction.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2435781/v1_covered_34bb6c19-91f0-4062-b7ea-15f1d4d56bdd.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"MCL-DTI: Using Drug Multimodal Informationand Bi-directional Cross-Attention Learningmethod for Predicting Drug-Target Interaction","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-target interaction, deep learning, multimodal information, multi-head self-attention mechanism, cross-attention mechanism","lastPublishedDoi":"10.21203/rs.3.rs-2435781/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2435781/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground: \u003c/strong\u003ePrediction of drug-target interaction (DTI) is an essential step fordrug discovery and drug reposition. Traditional methods are mostlytime-consuming and labor-intensive, and deep learning-based methods addressthese limitations and are applied to engineering. Most of the current deeplearning methods employ representation learning of unimodal information such as SMILES sequences, molecular graphs, or molecular images of drugs. In addition,most methods focus on feature extraction from drug and target alone withoutfusion learning from drug-target interacting parties, which may lead toinsufficient feature representation.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults:\u003c/strong\u003e To enhance feature learning between drugs and targets, we propose anovel model based on deep learning for DTI task called MCL-DTI which usesmultimodal information of drug and learn the representation of drug-targetinteraction for drug-target prediction. In order to further explore a morecomprehensive representation of drug features, this paper first exploits twomultimodal information of drugs, molecular image and chemical text, to representthe drug. We also introduce to use bi-rectional multi-head corss attention (MCA)method to learn the interrelationships between drugs and targets. Thus, we buildtwo decoders, which include an multi-head self attention (MSA) block and anMCA block, for cross-information learning. We use a decoder for the drug andtarget separately to obtain the interaction feature maps. Finally, we feed thesefeature maps generated by decoders into a fusion block for feature extraction andoutput the prediction results.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusions:\u003c/strong\u003e MCL-DTI achieves the best results in all the three datasets:Human, C.elegans and Davis, including the balanced datasets and an unbalanceddataset. The results on the drug-drug interaction (DDI) task show that MCL-DTIhas a strong generalization capability and can be easily applied to other tasks.\u003c/p\u003e","manuscriptTitle":"MCL-DTI: Using Drug Multimodal Informationand Bi-directional Cross-Attention Learningmethod for Predicting Drug-Target Interaction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-01-09 11:13:53","doi":"10.21203/rs.3.rs-2435781/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revision","date":"2023-07-03T10:38:58+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2023-06-17T05:26:38+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2023-06-11T09:07:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"cb0a65d5-5502-410f-87e1-8d88afd095d5_SNPRID","date":"2023-06-09T14:37:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"0e2dfc5e-117b-4299-9396-c1d067ae3c15","date":"2023-06-09T09:19:20+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2023-06-05T07:47:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"8f0e50ee-4541-475d-b3ca-7dfb92a696a1","date":"2023-05-25T19:40:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"c16bc18b-1cf4-4483-b269-898a681209c9_SNPRID","date":"2023-05-25T15:17:55+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2023-05-25T14:06:27+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2023-02-02T21:30:49+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2023-01-05T09:34:02+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2023-01-05T08:34:05+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Bioinformatics","date":"2023-01-02T13:28:15+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":"e8bfad6c-a98c-42d1-9972-7ca29f3f75b8","owner":[],"postedDate":"January 9th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2023-09-07T15:05:00+00:00","versionOfRecord":{"articleIdentity":"rs-2435781","link":"https://doi.org/10.1186/s12859-023-05447-1","journal":{"identity":"bmc-bioinformatics","isVorOnly":false,"title":"BMC Bioinformatics"},"publishedOn":"2023-08-26 15:02:04","publishedOnDateReadable":"August 26th, 2023"},"versionCreatedAt":"2023-01-09 11:13:53","video":"","vorDoi":"10.1186/s12859-023-05447-1","vorDoiUrl":"https://doi.org/10.1186/s12859-023-05447-1","workflowStages":[]},"version":"v1","identity":"rs-2435781","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2435781","identity":"rs-2435781","version":["v1"]},"buildId":"_2-kVJe1T_tPrBINL-cwx","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}