{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T05:02:20Z","timestamp":1789448540401,"version":"build-2803163510"},"reference-count":58,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T00:00:00Z","timestamp":1788912000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Pharmaceuticals"],"abstract":"<jats:p>Background\/Objective: Activated coagulation factor XII (FXIIa) is a component of the contact activation pathway and a pharmacologically relevant target in contact-system-associated processes. In this study, scaffold-aware and interpretable machine-learning QSAR models were developed for human FXIIa activity. Methods: Bioactivity records for the human single protein target CHEMBL2821 were retrieved from ChEMBL release 37. Modeling was restricted to exact IC50 measurements from assays explicitly referring to FXIIa, Factor XIIa, or activated Factor XII. Median-consolidated pIC50 values and two-dimensional Mordred descriptors were evaluated using leakage-safe preprocessing, scaffold-disjoint validation, Y-randomization, applicability domain analysis, structural similarity auditing, and SHAP interpretation. Results: The regression dataset comprised 424 compounds and 166 Bemis\u2013Murcko scaffolds in this study. The Gradient Boosting regressor achieved R2 = 0.7560, RMSE = 0.6924, and MAE = 0.4965 on the locked scaffold-disjoint test set (n = 85); across 50 repeated scaffold partitions, the mean R2 was 0.6892 \u00b1 0.1515. The classification model achieved ROC-AUC = 0.9453, PR-AUC = 0.9807, balanced accuracy = 0.7561, and MCC = 0.5972 (n = 73). Y-randomization supported nonrandom predictive signals (empirical p = 0.0099). Conclusions: The models support computational prioritization within the represented FXIIa chemical domain, while prospective evaluation of independently generated compounds remains necessary.<\/jats:p>","DOI":"10.3390\/ph19091426","type":"journal-article","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T16:43:16Z","timestamp":1788972196000},"page":"1426","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Development of an Interpretable QSAR Model for Predicting Coagulation Factor XIIa Inhibitors Using Ensemble Machine Learning"],"prefix":"10.3390","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4220-1866","authenticated-orcid":false,"given":"Ali Onur","family":"Kaya","sequence":"first","affiliation":[{"name":"Radiotherapy Department, Health Services Vocational School, Akdeniz University, 07070 Antalya, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1445-0358","authenticated-orcid":false,"given":"Mert Can","family":"Emre","sequence":"additional","affiliation":[{"name":"Motor Vehicles Department, Sorgun Vocational School, Yozgat Bozok University, 66000 Yozgat, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"St\u0119pnicki, J., Imiela, A.M., Szyma\u0144ska, M., Miko\u0142ajczuk, J., and Pruszczyk, P. (2026). Factor XII in Thrombosis and Thromboinflammation: From Molecular Biology to Clinical Translation. Int. J. Mol. Sci., 27.","DOI":"10.3390\/ijms27073336"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"814","DOI":"10.1055\/s-0036-1598003","article-title":"Factor XII Contact Activation","volume":"43","author":"Naudin","year":"2017","journal-title":"Semin. Thromb. Hemost."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1903","DOI":"10.1182\/blood-2017-04-569111","article-title":"Coagulation Factor XII in Thrombosis and Inflammation","volume":"131","author":"Maas","year":"2018","journal-title":"Blood"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1161\/ATVBAHA.116.308595","article-title":"Factor XII as a Therapeutic Target in Thromboembolic and Inflammatory Diseases","volume":"37","author":"Nickel","year":"2017","journal-title":"Arterioscler. Thromb. Vasc. Biol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1182\/blood-2016-10-744110","article-title":"Proteolytic Properties of Single-Chain Factor XII: A Mechanism for Triggering Contact Activation","volume":"129","author":"Ivanov","year":"2017","journal-title":"Blood"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1160\/TH13-03-0258","article-title":"Plasma Kallikrein: The Bradykinin-Producing Enzyme","volume":"110","year":"2013","journal-title":"Thromb. Haemost."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1111\/jth.13235","article-title":"Contact System Revisited: An Interface between Inflammation, Coagulation, and Innate Immunity","volume":"14","author":"Long","year":"2016","journal-title":"J. Thromb. Haemost."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1016\/j.cellsig.2018.08.006","article-title":"Factor XII in Coagulation, Inflammation and Beyond","volume":"51","author":"Didiasova","year":"2018","journal-title":"Cell. Signal."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1498","DOI":"10.1111\/jth.13383","article-title":"Factor XII: Form Determines Function","volume":"14","author":"Maas","year":"2016","journal-title":"J. Thromb. Haemost."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Weitz, J.I., and Fredenburgh, J.C. (2017). Factors XI and XII as Targets for New Anticoagulants. Front. Med., 4.","DOI":"10.3389\/fmed.2017.00019"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Badimon, J.J., Escolar, G., and Zafar, M.U. (2022). Factor XI\/XIa Inhibition: The Arsenal in Development for a New Therapeutic Target in Cardio- and Cerebrovascular Disease. J. Cardiovasc. Dev. Dis., 9.","DOI":"10.3390\/jcdd9120437"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1084\/jem.20050664","article-title":"Defective Thrombus Formation in Mice Lacking Coagulation Factor XII","volume":"202","author":"Schuh","year":"2005","journal-title":"J. Exp. Med."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1084\/jem.20052458","article-title":"Targeting Coagulation Factor XII Provides Protection from Pathological Thrombosis in Cerebral Ischemia without Interfering with Hemostasis","volume":"203","author":"Kleinschnitz","year":"2006","journal-title":"J. Exp. Med."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"4296","DOI":"10.1182\/blood-2012-07-292094","article-title":"In Vivo Roles of Factor XII","volume":"120","author":"Schmaier","year":"2012","journal-title":"Blood"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"4068","DOI":"10.1073\/pnas.1423764112","article-title":"Activation of the Factor XII-Driven Contact System in Alzheimer\u2019s Disease Patient and Mouse Model Plasma","volume":"112","author":"Zamolodchikov","year":"2015","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"S78","DOI":"10.1016\/j.thromres.2012.08.284","article-title":"Crosstalk of the Plasma Contact System with Bacteria","volume":"130","author":"Nickel","year":"2012","journal-title":"Thromb. Res."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1186\/s12959-015-0048-y","article-title":"Contact Pathway of Coagulation and Inflammation","volume":"13","author":"Wu","year":"2015","journal-title":"Thromb. J."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1079","DOI":"10.1016\/S0140-6736(23)00350-1","article-title":"Efficacy and Safety of Garadacimab, a Factor XIIa Inhibitor for Hereditary Angioedema Prevention (VANGUARD): A Global, Multicentre, Randomised, Double-Blind, Placebo-Controlled, Phase 3 Trial","volume":"401","author":"Craig","year":"2023","journal-title":"Lancet"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1002\/rth2.12235","article-title":"Factor XII\u2014What\u2019s Important but Not Commonly Thought About","volume":"3","author":"Schmaier","year":"2019","journal-title":"Res. Pract. Thromb. Haemost."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"222ra17","DOI":"10.1126\/scitranslmed.3006804","article-title":"Cardiovascular Disease: A Factor XIIa Inhibitory Antibody Provides Thromboprotection in Extracorporeal Circulation without Increasing Bleeding Risk","volume":"6","author":"Larsson","year":"2014","journal-title":"Sci. Transl. Med."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1739","DOI":"10.1182\/blood-2013-04-499111","article-title":"Factor XII Inhibition Reduces Thrombus Formation in a Primate Thrombosis Model","volume":"123","author":"Matafonov","year":"2014","journal-title":"Blood"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"10694","DOI":"10.1021\/acsomega.3c09335","article-title":"New Triazole-Based Potent Inhibitors of Human Factor as Anticoagulants","volume":"9","author":"Woodland","year":"2024","journal-title":"ACS Omega"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1016\/j.ejmech.2017.08.056","article-title":"Identifying Novel Factor XIIa Inhibitors with PCA-GA-SVM Developed VHTS Models","volume":"140","author":"Chen","year":"2017","journal-title":"Eur. J. Med. Chem."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"3672","DOI":"10.1002\/cmdc.202100431","article-title":"Microscale Parallel Synthesis of Acylated Aminotriazoles Enabling the Development of Factor XIIa and Thrombin Inhibitors","volume":"16","author":"Platte","year":"2021","journal-title":"ChemMedChem"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"10946","DOI":"10.1021\/acs.jmedchem.4c00475","article-title":"Discovery of Highly Selective, Potent, Covalent, and Orally Bioavailable Factor XIIa Inhibitors for the Treatment of Thrombo-Inflammation","volume":"67","author":"Meng","year":"2024","journal-title":"J. Med. Chem."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"11720","DOI":"10.1021\/acs.jmedchem.6c01243","article-title":"Discovery of the First Highly Potent, Selective, Irreversible-Molecule Factor XIIa Inhibitor for Treating Sepsis","volume":"69","author":"Geng","year":"2026","journal-title":"J. Med. Chem."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1155","DOI":"10.1080\/13543776.2021.1945580","article-title":"Factor XII(a) Inhibitors: A Review of the Patent Literature","volume":"31","author":"Kalinin","year":"2021","journal-title":"Expert Opin. Ther. Pat."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"112753","DOI":"10.1016\/j.ejmech.2020.112753","article-title":"Factor XII\/XIIa Inhibitors: Their Discovery, Development, and Potential Indications","volume":"208","author":"Davoine","year":"2020","journal-title":"Eur. J. Med. Chem."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1042\/bj3570263","article-title":"Relationships between Inhibition Constants, Inhibitor Concentrations for 50% Inhibition and Types of Inhibition: New Ways of Analysing Data","volume":"357","author":"Cascante","year":"2001","journal-title":"Biochem. J."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Kalliokoski, T., Kramer, C., Vulpetti, A., and Gedeck, P. (2013). Comparability of Mixed IC50 Data\u2014A Statistical Analysis. PLoS ONE, 8.","DOI":"10.1371\/journal.pone.0061007"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1560","DOI":"10.1021\/acs.jcim.4c00049","article-title":"Combining IC50 or Ki Values from Different Sources Is a Source of Significant Noise","volume":"64","author":"Landrum","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"D1180","DOI":"10.1093\/nar\/gkad1004","article-title":"The ChEMBL Database in 2023: A Drug Discovery Platform Spanning Multiple Bioactivity Data Types and Time Periods","volume":"52","author":"Zdrazil","year":"2024","journal-title":"Nucleic Acids Res."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1021\/ci400084k","article-title":"Time-Split-Validation as a Method for Estimating the Goodness of Prospective Prediction","volume":"53","author":"Sheridan","year":"2013","journal-title":"J. Chem. Inf. Model."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"2887","DOI":"10.1021\/jm9602928","article-title":"The Properties of Known Drugs. 1. Molecular Frameworks","volume":"39","author":"Bemis","year":"1996","journal-title":"J. Med. Chem."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"2951","DOI":"10.1021\/acs.jcim.6c00514","article-title":"Defining the Data Set Defines the QSAR Claim","volume":"66","author":"Nael","year":"2026","journal-title":"J. Chem. Inf. Model."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"2570","DOI":"10.1021\/ci300338w","article-title":"Does Rational Selection of Training and Test Sets the Outcome of QSAR Modeling?","volume":"52","author":"Martin","year":"2012","journal-title":"J. Chem. Inf. Model."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1021\/ci100176x","article-title":"Trust, but Verify: On the Importance of Chemical Structure Curation in Cheminformatics and QSAR Modeling Research","volume":"50","author":"Fourches","year":"2010","journal-title":"J. Chem. Inf. Model."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"4977","DOI":"10.1021\/jm4004285","article-title":"QSAR Modeling: Where Have You Been? Where Are You Going To?","volume":"57","author":"Cherkasov","year":"2014","journal-title":"J. Med. Chem."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1002\/minf.201000061","article-title":"Best Practices for QSAR Model Development, Validation, and Exploitation","volume":"29","author":"Tropsha","year":"2010","journal-title":"Mol. Inform."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1016\/S1093-3263(01)00123-1","article-title":"Beware of Q2!","volume":"20","author":"Golbraikh","year":"2002","journal-title":"J. Mol. Graph. Model."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1002\/qsar.200610151","article-title":"Principles of QSAR Models Validation: Internal and External","volume":"26","author":"Gramatica","year":"2007","journal-title":"QSAR Comb. Sci."},{"key":"ref_42","unstructured":"Lundberg, S.M., Allen, P.G., and Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. Adv. Neural Inf. Process. Syst., 30."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1007\/s10822-025-00758-2","article-title":"Interpretable Machine Learning-Driven QSAR Modeling for Coagulation Factor X Inhibitors: From Molecular Descriptors to Predictive Potency","volume":"40","author":"Kaya","year":"2026","journal-title":"J. Comput.-Aided Mol. Des."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Kaya, A.O., Emre, M.C., and Emre, N. (2026). Machine Learning-Driven QSAR Modeling of FXIa Inhibitors for Virtual Screening and Rational Drug Design. Pharmaceuticals, 19.","DOI":"10.3390\/ph19060912"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1177\/026119290503300209","article-title":"Current Status of Methods for Defining the Applicability Domain of (Quantitative) Structure-Activity Relationships","volume":"33","author":"Netzeva","year":"2005","journal-title":"ATLA Altern. Lab. Anim."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"4791","DOI":"10.3390\/molecules17054791","article-title":"Comparison of Different Approaches to Define the Applicability Domain of QSAR Models","volume":"17","author":"Sahigara","year":"2012","journal-title":"Molecules"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1186\/s13321-018-0258-y","article-title":"Mordred: A Molecular Descriptor Calculator","volume":"10","author":"Moriwaki","year":"2018","journal-title":"J. Cheminform."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Chicco, D., and Jurman, G. (2020). The Advantages of the Matthews Correlation Coefficient (MCC) over F1 Score and Accuracy in Binary Classification Evaluation. BMC Genom., 21.","DOI":"10.1186\/s12864-019-6413-7"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From Local Explanations to Global Understanding with Explainable AI for Trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","article-title":"Extremely Randomized Trees","volume":"63","author":"Geurts","year":"2006","journal-title":"Mach. Learn."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Natekin, A., and Knoll, A. (2013). Gradient Boosting Machines, a Tutorial. Front. Neurorobot., 7.","DOI":"10.3389\/fnbot.2013.00021"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1021\/ci034160g","article-title":"Random Forest: A Classification and Regression Tool for Compound Classification and QSAR Modeling","volume":"43","author":"Svetnik","year":"2003","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1007\/978-3-031-72359-9_5","article-title":"Scaffold Splits Overestimate Virtual Screening Performance","volume":"Volume 15025","author":"Guo","year":"2024","journal-title":"Artificial Neural Networks and Machine Learning\u2014ICANN 2024"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1160\/TH13-08-0668","article-title":"Factor XIIa Inhibition by Infestin-4: In Vitro Mode of Action and in Vivo Antithrombotic Benefit","volume":"111","author":"Xu","year":"2013","journal-title":"Thromb. Haemost."},{"key":"ref_56","unstructured":"Landrum, G., Tosco, P., Kelly, B., Rodriguez, R., Cosgrove, D., Vianello, R., Gedeck, P., Jones, G., Kawashima, E., and Schneider, N. (2015). RDKit, Zenodo. 2026.03.5."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"2837","DOI":"10.1021\/ci400482e","article-title":"Using Random To Model the Domain Applicability of Another Random Forest Model","volume":"53","author":"Sheridan","year":"2013","journal-title":"J. Chem. Inf. Model."},{"key":"ref_58","first-page":"2825","article-title":"Scikit-Learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."}],"container-title":["Pharmaceuticals"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8247\/19\/9\/1426\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T04:11:41Z","timestamp":1789445501000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8247\/19\/9\/1426"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,9]]},"references-count":58,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["ph19091426"],"URL":"https:\/\/doi.org\/10.3390\/ph19091426","relation":{},"ISSN":["1424-8247"],"issn-type":[{"value":"1424-8247","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,9]]}}}