{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T15:25:25Z","timestamp":1787325925269,"version":"build-2736575974"},"reference-count":50,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T00:00:00Z","timestamp":1787270400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100009392","name":"Prince Sattam Bin Abdulaziz University","doi-asserted-by":"publisher","award":["PSAU\/2025\/01\/33835"],"award-info":[{"award-number":["PSAU\/2025\/01\/33835"]}],"id":[{"id":"10.13039\/100009392","id-type":"DOI","asserted-by":"publisher"}]},{"award":["PSAU\/2025\/01\/33835"],"award-info":[{"award-number":["PSAU\/2025\/01\/33835"]}],"id":[{"id":"https:\/\/ror.org\/04jt46d36","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Pharmaceuticals"],"abstract":"<jats:p>Background\/Objectives: Human carbonic anhydrase (CA) isoforms are clinically relevant zinc metalloenzymes, but their highly conserved catalytic Zn2+ site makes isoform-selective inhibitor design challenging. This study developed an explainable multi-isoform QSAR workflow for prioritizing selective inhibitors of human CA I, CA II, CA IX, and CA XII, integrating PubChem experimental concordance and applicability-domain (AD) analysis to distinguish model-supported candidates from exploratory extrapolative hypotheses. Methods: Curated ChEMBL Ki datasets were standardized to pKi and modeled in KNIME using 4185 two-dimensional descriptors, Random Forest-based feature selection, and H2O.ai AutoML stacked ensembles. A matched 3200-compound four-isoform matrix supported direct selectivity profiling. Potent ChEMBL inhibitors (Ki &lt; 10 nM) seeded 90% PubChem similarity expansion; analogues were scored across all four isoform-specific models, while PubChem records were filtered to retain only human isoform-specific Ki evidence. AD was calibrated using Morgan fingerprint similarity, descriptor-space distance, and leverage analysis. Candidates were prioritized by predicted potency, selectivity, SAR plausibility, SwissADME profile, structural alerts, and AD membership. Results: Models achieved held-out R2 values of 0.727, 0.719, 0.652, and 0.607 for CA I, CA II, CA IX, and CA XII, respectively. PubChem concordance identified 1098 prioritized compounds with assay records, including 847 with direct Ki evidence and 428 with complete four-isoform coverage; same-target agreement showed Pearson r &gt; 0.86 and linear-fit R2 &gt; 0.74. Test-set error rose from very-high-AD to low\/out-of-domain classes. Conclusions: The workflow integrates QSAR prediction, PubChem concordance, explainable SAR, ADME triage, and AD-based reliability assessment. CA II and CA XII candidates showed the strongest support, CA IX showed intermediate support, and CA I candidates require cautious interpretation as low-domain exploratory hypotheses.<\/jats:p>","DOI":"10.3390\/ph19081322","type":"journal-article","created":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T14:20:36Z","timestamp":1787322036000},"page":"1322","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable Multi-Isoform QSAR, PubChem Concordance, and Applicability-Domain-Guided Prioritization of Selective Human Carbonic Anhydrase I, II, IX, and XII Inhibitors"],"prefix":"10.3390","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8053-9759","authenticated-orcid":false,"given":"Alaa M.","family":"Elsayad","sequence":"first","affiliation":[{"name":"Biomedical Group, Department of Electrical Engineering, College of Engineering, Prince Sattam Bin Abdulaziz University, Wadi Alddawasir 11991, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khaled A.","family":"Elsayad","sequence":"additional","affiliation":[{"name":"Pharmacy Department, Cairo University Hospitals, Cairo University, Cairo 11662, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Garc\u00eda-Llorca, A., Carta, F., and Supuran, C.T. (2024). Carbonic anhydrase, its inhibitors and vascular function. Front. Mol. Biosci., 11.","DOI":"10.3389\/fmolb.2024.1338528"},{"key":"ref_2","first-page":"116","article-title":"Carbonic anhydrase IX-based tumor imaging and therapy: A review","volume":"39","author":"Lin","year":"2023","journal-title":"Chin. J. Biotechnol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1186\/s13000-023-01325-9","article-title":"The relationship between carbonic anhydrase IX (CAIX) and patient survival in breast cancer: Systematic review and meta-analysis","volume":"18","author":"Shamis","year":"2023","journal-title":"Diagn. Pathol."},{"key":"ref_4","first-page":"221","article-title":"Carbonic anhydrase inhibitors: Designing isozyme-specific inhibitors as therapeutic agents","volume":"Volume 75","author":"Supuran","year":"2021","journal-title":"The Carbonic Anhydrases: Current and Emerging Therapeutic Targets"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"7422","DOI":"10.1021\/acs.jmedchem.0c00733","article-title":"Sulfonamide inhibitors of human carbonic anhydrases designed through a three-tails approach: Improving ligand\/isoform matching and selectivity of action","volume":"63","author":"Bonardi","year":"2020","journal-title":"J. Med. Chem."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"35769","DOI":"10.1039\/D4RA06290F","article-title":"Exploring heterocyclic scaffolds in carbonic anhydrase inhibition: A decade of structural and therapeutic insights","volume":"14","author":"Naeem","year":"2024","journal-title":"RSC Adv."},{"key":"ref_7","first-page":"2227","article-title":"Combination of carbonic anhydrase isoform IX inhibitors and gefitinib suppresses the invasive potential of non-small cell lung cancer cells","volume":"89","author":"Bunev","year":"2024","journal-title":"Biochemistry"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Chen, K.-T., and Seimbille, Y. (2022). New developments in carbonic anhydrase IX-targeted fluorescence and nuclear imaging agents. Int. J. Mol. Sci., 23.","DOI":"10.3390\/ijms23116125"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Eloranta, K., Pihlajoki, M., Liljestr\u00f6m, E., Nousiainen, R., Soini, T., Lohi, J., Cairo, S., Wilson, D.B., Parkkila, S., and Heikinheimo, M. (2023). SLC-0111, an inhibitor of carbonic anhydrase IX, attenuates hepatoblastoma cell viability and migration. Front. Oncol., 13.","DOI":"10.3389\/fonc.2023.1118268"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1031","DOI":"10.1021\/acsmedchemlett.5c00099","article-title":"Unraveling the potential of amino-, acylamino-, and ureido-substituted 3H-1,2-benzoxaphosphepine 2-oxides toward nanomolar inhibitors of tumor-associated carbonic anhydrases IX and XII","volume":"16","author":"Pustenko","year":"2025","journal-title":"ACS Med. Chem. Lett."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"105920","DOI":"10.1016\/j.bioorg.2022.105920","article-title":"A decade of tail-approach based design of selective as well as potent tumor associated carbonic anhydrase inhibitors","volume":"126","author":"Kumar","year":"2022","journal-title":"Bioorg. Chem."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Moi, D., Carradori, S., Gallorini, M., Mencarelli, N., Deplano, A., Angeli, A., Vittorio, S., Supuran, C.T., and Onnis, V. (2025). Investigation on human carbonic anhydrase IX and XII inhibitory activity and A549 antiproliferative activity of a new class of coumarinamides. Pharmaceuticals, 18.","DOI":"10.3390\/ph18030372"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1000","DOI":"10.1021\/acsmedchemlett.0c00062","article-title":"Looking toward the rim of the active site cavity of druggable human carbonic anhydrase isoforms","volume":"11","author":"Mancuso","year":"2020","journal-title":"ACS Med. Chem. Lett."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1186\/s13321-021-00499-y","article-title":"Prediction of activity and selectivity profiles of hCA inhibitors using machine learning","volume":"13","author":"Tinivella","year":"2021","journal-title":"J. Cheminform."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Wang, T., Pulkkinen, O.I., and Aittokallio, T. (2022). Target-specific compound selectivity for multi-target drug discovery and repurposing. Front. Pharmacol., 13.","DOI":"10.3389\/fphar.2022.1003480"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2166503","DOI":"10.1080\/14756366.2023.2166503","article-title":"Click chemistry approaches for developing carbonic anhydrase inhibitors and their applications","volume":"38","author":"Angeli","year":"2023","journal-title":"J. Enzym. Inhib. Med. Chem."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1186\/s13065-025-01634-8","article-title":"Entrance-channel plugging by natural sulfonamide antibiotics yields isoform-selective carbonic anhydrase IX inhibitors: An integrated in silico\/in vitro discovery of the lead SB-203207","volume":"19","author":"Kamel","year":"2025","journal-title":"BMC Chem."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1462","DOI":"10.1080\/14756366.2020.1788009","article-title":"Coumarin carbonic anhydrase inhibitors from natural sources","volume":"35","author":"Supuran","year":"2020","journal-title":"J. Enzym. Inhib. Med. Chem."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Arunachalam, S., Balamurali, M.M., and Gnanasekaran, R. (2025). Computational insights into novel inhibitors: Virtual screening of small molecules against human carbonic anhydrase II. Front. Chem., 13.","DOI":"10.3389\/fchem.2025.1627793"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Shams Ghamsary, M., Rayka, M., and Naghavi, S.S. (2025). Interpretable Machine Learning Unveils Carbonic Anhydrase Inhibition via Conformal and Counterfactual Prediction. ChemRxiv, Available online: https:\/\/chemrxiv.org\/engage\/api-gateway\/chemrxiv\/assets\/orp\/resource\/item\/68a9751da94eede154350c8a\/original\/interpretable-machine-learning-unveils-carbonic-anhydrase-inhibition-via-conformal-and-counterfactual-prediction.pdf.","DOI":"10.26434\/chemrxiv-2025-m69tw"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"3944","DOI":"10.1021\/acs.jcim.4c02372","article-title":"PoseidonQ: A free machine learning platform for the development, analysis, and validation of efficient and portable QSAR models for drug discovery","volume":"65","author":"Kabier","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Koirala, M., Yan, L., Mohamed, Z., and DiPaola, M. (2025). AI-integrated QSAR modeling for enhanced drug discovery: From classical approaches to deep learning and structural insight. Int. J. Mol. Sci., 26.","DOI":"10.3390\/ijms26199384"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1038\/s41573-023-00832-0","article-title":"Integrating QSAR modelling and deep learning in drug discovery: The emergence of deep QSAR","volume":"23","author":"Tropsha","year":"2024","journal-title":"Nat. Rev. Drug Discov."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1530","DOI":"10.1002\/jcc.27335","article-title":"Explainable artificial intelligence in the design of selective carbonic anhydrase I\u2013II inhibitors via molecular fingerprinting","volume":"45","author":"Kirboga","year":"2024","journal-title":"J. Comput. Chem."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1080\/14756366.2022.2036137","article-title":"Synthesis, molecular modelling and QSAR study of new N-phenylacetamide-2-oxoindole benzenesulfonamide conjugates as carbonic anhydrase inhibitors with antiproliferative activity","volume":"37","author":"Said","year":"2022","journal-title":"J. Enzym. Inhib. Med. Chem."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"e2200196","DOI":"10.1002\/minf.202200186","article-title":"A comparison between 2D and 3D descriptors in QSAR modeling based on bio-active conformations","volume":"42","author":"Bahia","year":"2023","journal-title":"Mol. Inform."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"62121","DOI":"10.1007\/s11356-023-28277-3","article-title":"QSAR modeling of pyrazoline derivatives as carbonic anhydrase inhibitors","volume":"31","author":"Hammoudan","year":"2024","journal-title":"Environ. Sci. Pollut. Res."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Roy, K. (2020). alvaDesc: A tool to calculate and analyze molecular descriptors and fingerprints. Ecotoxicological QSARs, Springer.","DOI":"10.1007\/978-1-0716-0150-1"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-connectivity fingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J. Chem. Inf. Model."},{"key":"ref_30","first-page":"LIANBS131.009","article-title":"Quantitative Structure\u2013Activity Relationship for Novel Benzenesulfonamide Derivatives as Prominent Inhibitors of Carbonic Anhydrase Isoforms Based on Cell-Line Cytotoxic Screening Activity","volume":"13","author":"Ghorab","year":"2023","journal-title":"Lett. Appl. NanoBioSci."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1186\/s13040-024-00378-w","article-title":"Understanding predictions of drug profiles using explainable ML models","volume":"17","author":"Vellido","year":"2024","journal-title":"BioData Min."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"e70049","DOI":"10.1002\/wcms.70049","article-title":"Explainable artificial intelligence in drug discovery: Bridging predictive power and mechanistic insight","volume":"15","author":"Lavecchia","year":"2025","journal-title":"WIREs Comput. Mol. Sci."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Qadri, Y.A., Shaikh, S., Ahmad, K., Choi, I., Kim, S.W., and Vasilakos, A.V. (2025). Explainable artificial intelligence: A perspective on drug discovery. Pharmaceutics, 17.","DOI":"10.3390\/pharmaceutics17091119"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"2400304","DOI":"10.1002\/aisy.202400304","article-title":"A perspective on explainable artificial intelligence methods: SHAP and LIME","volume":"7","author":"Salih","year":"2025","journal-title":"Adv. Intell. Syst."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"D1516","DOI":"10.1093\/nar\/gkae1059","article-title":"PubChem 2025 update","volume":"53","author":"Kim","year":"2025","journal-title":"Nucleic Acids Res."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1387","DOI":"10.1080\/17460441.2025.2558161","article-title":"Exploiting PubChem and other public databases for virtual screening in 2025: What are the latest trends?","volume":"20","year":"2025","journal-title":"Expert Opin. Drug Discov."},{"key":"ref_37","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_38","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1145\/1656274.1656280","article-title":"KNIME\u2014The Konstanz information miner: Version 2.0 and beyond","volume":"11","author":"Berthold","year":"2009","journal-title":"ACM SIGKDD Explor. Newsl."},{"key":"ref_39","unstructured":"LeDell, E., and Poirier, S. (2020, January 17\u201318). H2O AutoML: Scalable automatic machine learning. Proceedings of the AutoML Workshop at ICML 2020, Virtual Event."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Biswas, S., Grundlingh, N., Boardman, J., White, J., and Le, L. (2025). A target permutation test for statistical significance of feature importance in differentiable models. Electronics, 14.","DOI":"10.3390\/electronics14030571"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/s41060-024-00509-w","article-title":"A review of random forest-based feature selection methods for data science education and applications","volume":"20","author":"Iranzad","year":"2025","journal-title":"Int. J. Data Sci. Anal."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Almansour, N.M. (2025). Computational discovery of selective carbonic anhydrase IX (CA IX) inhibitors via pharmacophore modeling and molecular simulations for cancer therapy. Int. J. Mol. Sci., 26.","DOI":"10.3390\/ijms26178465"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"e2400439","DOI":"10.1002\/ardp.202400439","article-title":"Tail-approach based design, synthesis, and molecular modeling of benzenesulfonamides carrying thiadiazole and urea moieties as novel carbonic anhydrase inhibitors","volume":"357","author":"Han","year":"2024","journal-title":"Arch. Pharm."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"W324","DOI":"10.1093\/nar\/gkae300","article-title":"SwissDock 2024: Major enhancements for small-molecule docking with Attracting Cavities and AutoDock Vina","volume":"52","author":"Bugnon","year":"2024","journal-title":"Nucleic Acids Res."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"3891","DOI":"10.1021\/acs.jcim.1c00203","article-title":"AutoDock Vina 1.2.0: New docking methods, expanded force field, and Python bindings","volume":"61","author":"Eberhardt","year":"2021","journal-title":"J. Chem. Inf. Model."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1089\/omi.2021.0059","article-title":"Discovery of natural compounds as potential inhibitors of human carbonic anhydrase II: An integrated virtual screening, docking, and molecular dynamics simulation study","volume":"25","author":"Anjum","year":"2021","journal-title":"OMICS J. Integr. Biol."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"42717","DOI":"10.1038\/srep42717","article-title":"SwissADME: A free web tool to evaluate pharmacokinetics, drug-likeness and medicinal chemistry friendliness of small molecules","volume":"7","author":"Daina","year":"2017","journal-title":"Sci. Rep."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1117","DOI":"10.1002\/cmdc.201600182","article-title":"A BOILED-Egg to predict gastrointestinal absorption and brain penetration of small molecules","volume":"11","author":"Daina","year":"2016","journal-title":"ChemMedChem"},{"key":"ref_49","unstructured":"RDKit Developers (2026, July 19). RDKit: Open-Source Cheminformatics Software. Available online: https:\/\/www.rdkit.org."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"OECD (2023). Q(SAR) Assessment Framework: Guidance for the Regulatory Assessment of (Quantitative) Structure Activity Relationship Models and Predictions, OECD Publishing. OECD Series on Testing and Assessment No. 386.","DOI":"10.1787\/d96118f6-en"}],"container-title":["Pharmaceuticals"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8247\/19\/8\/1322\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T14:24:28Z","timestamp":1787322268000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8247\/19\/8\/1322"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,21]]},"references-count":50,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["ph19081322"],"URL":"https:\/\/doi.org\/10.3390\/ph19081322","relation":{},"ISSN":["1424-8247"],"issn-type":[{"value":"1424-8247","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,21]]}}}