Interpretable Machine Learning-Driven QSAR Modeling for Coagulation Factor X Inhibitors: From Molecular Descriptors to Predictive Potency

Interpretable Machine Learning-Driven QSAR Modeling for Coagulation Factor X Inhibitors: From Molecular Descriptors to Predictive Potency | 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 Interpretable Machine Learning-Driven QSAR Modeling for Coagulation Factor X Inhibitors: From Molecular Descriptors to Predictive Potency Ali Onur Kaya This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7472281/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 23 Jan, 2026 Read the published version in Journal of Computer-Aided Molecular Design → Version 1 posted 7 You are reading this latest preprint version Abstract The inhibition of Coagulation Factor X (FXa) is a clinically validated strategy in anticoagulant therapy; however, the development of safer and more selective inhibitors remains a critical challenge. In this study, we present a machine learning–enhanced quantitative structure–activity relationship (QSAR) modeling framework to predict the inhibitory potency (pKi) of small molecules targeting FXa. Bioactivity data were curated from the ChEMBL database and standardized, resulting in a filtered dataset of 6400 structurally validated compounds. The molecular descriptors were calculated using the Mordred platform and filtered for statistical robustness. Two predictive approaches were employed: regression using the ExtraTrees Regressor and binary classification using the XGBoost Classifier. The regression model achieved an R² of 0.760 and an RMSE of 0.831 on the test set. The classification model demonstrated strong performance across all key metrics, achieving an accuracy of 0.91, precision of 0.92 (class 0) and 0.89 (class 1), recall of 0.89 (class 0) and 0.92 (class 1 ) , and an F1-score of 0.91 for both classes. These results indicate a balanced and robust predictive capability across active and inactive compounds. SHAP (SHapley Additive exPlanations) analysis enabled the interpretation of key structural features driving activity, revealing that electrostatic and topological descriptors were the most dominant. The applicability domain analysis was conducted using the leverage approach, and the Williams plots indicated that all compounds in both the training and test sets fell within the reliable prediction space of the regression model. We are confident that the models developed in this study provide not only strong predictive performance but also interpretable insights and can be effectively used to guide the rational design and screening of novel FXa inhibitors in anticoagulant drug discovery. Coagulation Factor X QSAR modeling Machine Learning ExtraTreesRegressor XGBoost SHAP analysis Molecular Descriptors Anticoagulant Drug Discovery Applicability Domain pKi Prediction Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 23 Jan, 2026 Read the published version in Journal of Computer-Aided Molecular Design → Version 1 posted Editorial decision: Revision requested 30 Nov, 2025 Reviews received at journal 03 Nov, 2025 Reviewers agreed at journal 25 Oct, 2025 Reviewers invited by journal 23 Oct, 2025 Editor assigned by journal 14 Sep, 2025 Submission checks completed at journal 05 Sep, 2025 First submitted to journal 27 Aug, 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-7472281","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":538606661,"identity":"0ec31c94-4e49-4bdc-a5db-37a87b64c378","order_by":0,"name":"Ali Onur Kaya","email":"data:image/png;base64,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","orcid":"","institution":"Akdeniz University","correspondingAuthor":true,"prefix":"","firstName":"Ali","middleName":"Onur","lastName":"Kaya","suffix":""}],"badges":[],"createdAt":"2025-08-27 13:53:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7472281/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7472281/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s10822-025-00758-2","type":"published","date":"2026-01-23T15:58:32+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":94975804,"identity":"7ae065aa-d746-409a-9e20-7fd5cf4cfa03","added_by":"auto","created_at":"2025-11-03 03:24:00","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":656506,"visible":true,"origin":"","legend":"","description":"","filename":"InterpretableMachineLearningDrivenQSARModeling.docx","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1/6dc7777523e5d85aa1a9d0cb.docx"},{"id":94989118,"identity":"a443b10b-803e-40b1-8050-3adb03acfd89","added_by":"auto","created_at":"2025-11-03 07:12:11","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4131,"visible":true,"origin":"","legend":"","description":"","filename":"d5ba2d993d8b400085a2d2c376e1eb7e.json","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1/8023176819d146475734c4a1.json"},{"id":94975787,"identity":"9f1f4d26-c619-4b1e-b655-538596adbdf0","added_by":"auto","created_at":"2025-11-03 03:23:58","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":62572,"visible":true,"origin":"","legend":"","description":"","filename":"d5ba2d993d8b400085a2d2c376e1eb7e1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1/50bde4db1ed9792639fee03f.xml"},{"id":94975799,"identity":"2471fe90-54f7-46b4-a8c1-b08ee499af0c","added_by":"auto","created_at":"2025-11-03 03:24:00","extension":"jpeg","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":256160,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1/5199dbedd1e9bc81f2229670.jpeg"},{"id":94975792,"identity":"1b35b576-7291-46d3-9014-ab615cb8f3f1","added_by":"auto","created_at":"2025-11-03 03:23:59","extension":"jpeg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":91862,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1/170d8ca37b02527f3a131ea2.jpeg"},{"id":94975794,"identity":"08b7efc4-5582-439d-ae01-46b4574ccd65","added_by":"auto","created_at":"2025-11-03 03:23:59","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21148,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1/f47bc2b8300b4c42d991ddf3.png"},{"id":94975800,"identity":"7d1ad9c6-eda2-4f18-bfe0-94d9a48fabf3","added_by":"auto","created_at":"2025-11-03 03:24:00","extension":"jpeg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":371213,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1/3ca3798c9f7a7d85bbd2bb85.jpeg"},{"id":94975789,"identity":"9445d807-70d4-49b0-808d-332d16e9714e","added_by":"auto","created_at":"2025-11-03 03:23:58","extension":"jpeg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":193972,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1/ae42998502bbca9702072291.jpeg"},{"id":94989141,"identity":"09f2b3ce-d71a-4426-bb0d-bd6e5ff15f2d","added_by":"auto","created_at":"2025-11-03 07:12:16","extension":"jpeg","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":285622,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1/404866f14723f26c0ee0b608.jpeg"},{"id":94975797,"identity":"5cc5e6dc-c408-44bd-91f5-4855f80e4959","added_by":"auto","created_at":"2025-11-03 03:23:59","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33793,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1/ece132e7270e72489a09cb3b.png"},{"id":94975790,"identity":"6ebab024-c320-47d3-8bae-55875a165075","added_by":"auto","created_at":"2025-11-03 03:23:58","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":89979,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1/6aee951a6d71613a57bc9d5d.png"},{"id":94975786,"identity":"f8817335-ed7f-491c-adef-4e496990485b","added_by":"auto","created_at":"2025-11-03 03:23:58","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":25195,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1/ff0601f5a3e9240ae087dd29.png"},{"id":94975796,"identity":"5902c10b-9ed6-4533-a646-eb25f4bfd93c","added_by":"auto","created_at":"2025-11-03 03:23:59","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6185,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1/24cc2f860e2915197642b073.png"},{"id":94975791,"identity":"bb38ee1f-3c3e-4a42-9178-af9e33ee25bd","added_by":"auto","created_at":"2025-11-03 03:23:58","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":80635,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1/e8532c773d059d40c918b75a.png"},{"id":94989212,"identity":"11c44637-9e8d-44fc-ba47-3a7ebdc55152","added_by":"auto","created_at":"2025-11-03 07:12:23","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39687,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1/19f7417cd937ed768a965331.png"},{"id":94989305,"identity":"7de540f3-37d1-4886-a9f3-4fe0e7a070d5","added_by":"auto","created_at":"2025-11-03 07:12:35","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":66835,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1/ad72d4f0c02f8a77c23a6919.png"},{"id":94975798,"identity":"9697eef4-7988-487b-8809-27175ac2c3a1","added_by":"auto","created_at":"2025-11-03 03:23:59","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9962,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1/c3a4a48b55beb73b06d54ce3.png"},{"id":94975803,"identity":"cc738c9e-d6e9-46e5-80bd-d245b91a64f1","added_by":"auto","created_at":"2025-11-03 03:24:00","extension":"xml","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":61308,"visible":true,"origin":"","legend":"","description":"","filename":"d5ba2d993d8b400085a2d2c376e1eb7e1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1/ab3e607400fafa8bd2d1fa84.xml"},{"id":94988405,"identity":"f9080085-03b0-4cb8-9017-0eddd5791e6d","added_by":"auto","created_at":"2025-11-03 07:08:57","extension":"html","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":67219,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1/00d681519a088edf61831ec6.html"},{"id":101153461,"identity":"ccd3d82e-e114-4a91-b051-0342f840e7e3","added_by":"auto","created_at":"2026-01-26 16:15:30","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":645915,"visible":true,"origin":"","legend":"","description":"","filename":"InterpretableMachineLearningDrivenQSARModeling.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7472281/v1_covered_01354213-4f39-485d-adcc-fdc0e3f27fb3.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Interpretable Machine Learning-Driven QSAR Modeling for Coagulation Factor X Inhibitors: From Molecular Descriptors to Predictive Potency","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":"journal-of-computer-aided-molecular-design","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jcam","sideBox":"Learn more about [Journal of Computer-Aided Molecular Design](http://link.springer.com/journal/10822)","snPcode":"10822","submissionUrl":"https://submission.nature.com/new-submission/10822/3","title":"Journal of Computer-Aided Molecular Design","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Coagulation Factor X, QSAR modeling, Machine Learning, ExtraTreesRegressor, XGBoost, SHAP analysis, Molecular Descriptors, Anticoagulant Drug Discovery, Applicability Domain, pKi Prediction","lastPublishedDoi":"10.21203/rs.3.rs-7472281/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7472281/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe inhibition of Coagulation Factor X (FXa) is a clinically validated strategy in anticoagulant therapy; however, the development of safer and more selective inhibitors remains a critical challenge. In this study, we present a machine learning\u0026ndash;enhanced quantitative structure\u0026ndash;activity relationship (QSAR) modeling framework to predict the inhibitory potency (pKi) of small molecules targeting FXa. Bioactivity data were curated from the ChEMBL database and standardized, resulting in a filtered dataset of 6400 structurally validated compounds. The molecular descriptors were calculated using the Mordred platform and filtered for statistical robustness. Two predictive approaches were employed: regression using the ExtraTrees Regressor and binary classification using the XGBoost Classifier. The regression model achieved an R\u0026sup2; of 0.760 and an RMSE of 0.831 on the test set. The classification model demonstrated strong performance across all key metrics, achieving an accuracy of 0.91, precision of 0.92 (class 0) and 0.89 (class 1), recall of 0.89 (class 0) and 0.92 (class 1\u003cb\u003e)\u003c/b\u003e, and an F1-score of 0.91 for both classes. These results indicate a balanced and robust predictive capability across active and inactive compounds. SHAP (SHapley Additive exPlanations) analysis enabled the interpretation of key structural features driving activity, revealing that electrostatic and topological descriptors were the most dominant. The applicability domain analysis was conducted using the leverage approach, and the Williams plots indicated that all compounds in both the training and test sets fell within the reliable prediction space of the regression model. We are confident that the models developed in this study provide not only strong predictive performance but also interpretable insights and can be effectively used to guide the rational design and screening of novel FXa inhibitors in anticoagulant drug discovery.\u003c/p\u003e","manuscriptTitle":"Interpretable Machine Learning-Driven QSAR Modeling for Coagulation Factor X Inhibitors: From Molecular Descriptors to Predictive Potency","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-03 03:23:31","doi":"10.21203/rs.3.rs-7472281/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-01T00:57:42+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-03T12:14:28+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"313684119394020813140667567515485798419","date":"2025-10-25T06:35:44+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-23T05:37:59+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-15T00:29:50+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-05T12:52:50+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Computer-Aided Molecular Design","date":"2025-08-27T13:39:09+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-computer-aided-molecular-design","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jcam","sideBox":"Learn more about [Journal of Computer-Aided Molecular Design](http://link.springer.com/journal/10822)","snPcode":"10822","submissionUrl":"https://submission.nature.com/new-submission/10822/3","title":"Journal of Computer-Aided Molecular Design","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"a7b97151-1e0b-4603-9be6-5535f8953ff9","owner":[],"postedDate":"November 3rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-01-26T16:14:40+00:00","versionOfRecord":{"articleIdentity":"rs-7472281","link":"https://doi.org/10.1007/s10822-025-00758-2","journal":{"identity":"journal-of-computer-aided-molecular-design","isVorOnly":false,"title":"Journal of Computer-Aided Molecular Design"},"publishedOn":"2026-01-23 15:58:32","publishedOnDateReadable":"January 23rd, 2026"},"versionCreatedAt":"2025-11-03 03:23:31","video":"","vorDoi":"10.1007/s10822-025-00758-2","vorDoiUrl":"https://doi.org/10.1007/s10822-025-00758-2","workflowStages":[]},"version":"v1","identity":"rs-7472281","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7472281","identity":"rs-7472281","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}