{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T12:49:43Z","timestamp":1791809383791,"version":"4.3.4"},"reference-count":92,"publisher":"American Chemical Society (ACS)","issue":"19","license":[{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"name":"Department of Biotechnology , Ministry of Science and Technology","award":["BT\/PR40144\/BTIS\/137\/46\/2022"],"award-info":[{"award-number":["BT\/PR40144\/BTIS\/137\/46\/2022"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Predictive computational models of potency and pharmacokinetic properties of antiviral drug candidates can dramatically accelerate the path from molecular design to clinical evaluation. The ASAP-Polaris-OpenADMET consortium hosted the open-science Antiviral Drug Discovery Challenge 2025, providing a rigorous setting for this problem and requiring prediction of potency against the SARS-CoV-2 and MERS-CoV Mpro alongside five ADME end points (LogD, KSOL, HLM, MLM, and MDR1-MDCKII). In response, we pursued a domain-aware modeling strategy, reasoning that the distinctive chemical properties of antiviral compounds could be explicitly engineered in the feature space. We tested this premise by isolating the key molecular descriptors capable of identifying antivirals, augmenting challenge data sets with curated public data, and building both classical machine learning and graph neural network (GNN) variants. For ADME modeling, ensemble gradient boosting models trained on our bespoke feature space consistently outperformed both broader tree-based approaches and GNN variants across the five ADME end points in blind evaluation. By a factorial design of experiments and statistical benchmarking, we evaluated the performance of the optimal XGBoost model for each end point. For modeling potency, we explored varied pretraining paradigms and ensemble fusion strategies, and found that a stacking ensemble combining docking-enhanced XGBoost with a stereochemistry-aware AttentiveFP Graph-Transformer model yielded the strongest significant generalization on the Challenge test set, suggesting that orthogonal model families reduced epistemic uncertainty attributable to model selection in data-limited, multitarget settings. Beyond benchmarking, our experiments provided a testbed for evaluating critical assumptions in the field, encompassing data augmentation strategies, splitting protocols, and ensemble integration approaches. Our analysis revealed that a consistently optimal model is elusive, and that several standard industry practices fail to withstand close inspection. Overall, our work provides both practical benchmarked modeling strategies for ADME and potency prediction and a reproducible computational foundation for AI-driven antiviral drug discovery efforts.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c00304","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T19:02:02Z","timestamp":1790708522000},"page":"12549-12567","source":"Crossref","is-referenced-by-count":0,"title":["Benchmarking Experiments\nwith External Data, Domain-Specific\nFeatures, and Learning Strategies for Modeling ADME and Potency of\nCoronavirus Main Protease Inhibitors"],"prefix":"10.1021","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9667-2618","authenticated-orcid":true,"given":"Ida","family":"Titus","sequence":"first","affiliation":[{"name":"SASTRA Deemed University , , , ,","place":["Thanjavur, Tamil Nadu, India, 613401"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2841-9527","authenticated-orcid":true,"given":"Ashok","family":"Palaniappan","sequence":"additional","affiliation":[{"name":"SASTRA Deemed University , , , ,","place":["Thanjavur, Tamil Nadu, India, 613401"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,9,29]]},"reference":[{"issue":"7","key":"2026101208073910000_cit1","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1080\/14787210.2019.1635009","article-title":"Broad-Spectrum Antiviral Agents: A Crucial Pandemic\nTool","volume":"17","author":"Adalja","year":"2019","journal-title":"Expert Rev. Anti Infect Ther"},{"issue":"1","key":"2026101208073910000_cit2","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1038\/s41591-024-03434-4","article-title":"Artificial intelligence\nin drug development","volume":"31","author":"Zhang","year":"2025","journal-title":"Nat. Med."},{"issue":"1","key":"2026101208073910000_cit3","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1021\/acsptsci.0c00174","article-title":"Antibacterial\nand Antiviral Functional\nMaterials: Chemistry and Biological Activity toward Tackling COVID-19-like\nPandemics","volume":"4","author":"Balasubramaniam","year":"2021","journal-title":"ACS Pharmacol. Transl. Sci."},{"issue":"7811","key":"2026101208073910000_cit4","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1038\/s41586-020-2223-y","article-title":"Structure of Mpro from\nSARS-CoV-2 and Discovery of Its Inhibitors","volume":"582","author":"Jin","year":"2020","journal-title":"Nature"},{"issue":"2","key":"2026101208073910000_cit5","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1016\/j.antiviral.2011.08.001","article-title":"Peptide aldehyde\ninhibitors challenge\nthe substrate specificity of the SARS-coronavirus main protease","volume":"92","author":"Zhu","year":"2011","journal-title":"Antiviral Res."},{"key":"2026101208073910000_cit6","doi-asserted-by":"publisher","DOI":"10.1002\/mco2.151","article-title":"The SARS-CoV-2\nmain protease (Mpro):\nStructure, Function, and Emerging Therapies for COVID-19","volume":"3","author":"Hu","year":"2020","journal-title":"MedComm."},{"key":"2026101208073910000_cit7","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1038\/d41573-024-00036-0","article-title":"When Can AI\nDeliver the Drug Discovery Hits?","volume":"23","author":"Mullard","year":"2024","journal-title":"Nat. Rev.\nDrug Discovery"},{"issue":"2","key":"2026101208073910000_cit8","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1021\/acs.jcim.8b00545","article-title":"Comparative\nAssessment of Scoring Functions: The CASF-2016\nUpdate","volume":"59","author":"Su","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"2026101208073910000_cit9","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1038\/s41570-022-00363-z","article-title":"CACHE (Critical Assessment of Computational Hit-Finding Experiments):\nA Public\u2013Private Partnership Benchmarking Initiative to Enable\nthe Development of Computational Methods for Hit-Finding","volume":"6","author":"Ackloo","year":"2022","journal-title":"Nat. Rev. Chem."},{"issue":"2","key":"2026101208073910000_cit10","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/s10822-020-00289-y","article-title":"D3R\nGrand Challenge 4: Blind Prediction of Protein-Ligand Poses, Affinity\nRankings, and Relative Binding Free Energies","volume":"34","author":"Parks","year":"2020","journal-title":"J. Comput. Aided Mol. Des."},{"key":"2026101208073910000_cit11","unstructured":"Dream challenges. https:\/\/dreamchallenges.org\/ (accessed Aug 25, 2025)."},{"key":"2026101208073910000_cit12","doi-asserted-by":"publisher","first-page":"374","DOI":"10.12688\/wellcomeopenres.22645.1","article-title":"Enabling\nequitable and affordable\naccess to novel therapeutics for pandemic preparedness and response\nvia creative intellectual property agreements","volume":"9","author":"Griffen","year":"2024","journal-title":"Wellcome Open Res."},{"issue":"6671","key":"2026101208073910000_cit13","doi-asserted-by":"publisher","DOI":"10.1126\/science.abo7201","article-title":"Open science discovery\nof potent noncovalent SARS-CoV-2 main protease inhibitors","volume":"382","author":"Boby","year":"2023","journal-title":"Science"},{"issue":"6","key":"2026101208073910000_cit14","doi-asserted-by":"publisher","first-page":"3129","DOI":"10.1021\/acs.jcim.5c02106","article-title":"A Computational Community\nBlind Challenge on Pan-Coronavirus Drug Discovery Data","volume":"66","author":"MacDermott-Opeskin","year":"2026","journal-title":"J. Chem. Inf. Model."},{"key":"2026101208073910000_cit15","doi-asserted-by":"publisher","first-page":"6395","DOI":"10.1038\/s41467-023-41948-6","article-title":"A Systematic\nStudy of Key Elements Underlying Molecular Property Prediction","volume":"14","author":"Deng","year":"2023","journal-title":"Nat. Commun."},{"issue":"1","key":"2026101208073910000_cit16","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s13321-020-00479-8","article-title":"Could Graph\nNeural Networks Learn Better Molecular Representation for Drug Discovery?\nA Comparison Study of Descriptor-Based and Graph-Based Models","volume":"13","author":"Jiang","year":"2021","journal-title":"J. Chemin."},{"issue":"1","key":"2026101208073910000_cit17","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1186\/s13321-023-00743-7","article-title":"Practical Guidelines for the Use\nof Gradient Boosting\nfor Molecular Property Prediction","volume":"15","author":"Boldini","year":"2023","journal-title":"J. Chemin."},{"key":"2026101208073910000_cit18","doi-asserted-by":"publisher","first-page":"102616","DOI":"10.1016\/j.sbi.2023.102616","article-title":"Application\nof message passing neural networks for\nmolecular property prediction","volume":"81","author":"Tang","year":"2023","journal-title":"Curr. Opin. Struct.\nBiol."},{"key":"2026101208073910000_cit19","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","article-title":"Graph neural networks: A review of methods\nand applications","volume":"1","author":"Zhou","year":"2020","journal-title":"AI Open"},{"key":"2026101208073910000_cit20","doi-asserted-by":"publisher","first-page":"106177","DOI":"10.1016\/j.compbiomed.2022.106177","article-title":"A unified GCNN model\nfor predicting CYP450 inhibitors by using graph convolutional neural\nnetworks with attention mechanism","volume":"150","author":"Qiu","year":"2022","journal-title":"Comput. Biol.\nMed."},{"issue":"3","key":"2026101208073910000_cit21","doi-asserted-by":"publisher","first-page":"3236","DOI":"10.1021\/acsomega.2c06702","article-title":"Attention-Based\nGraph Neural Network\nfor Molecular Solubility Prediction","volume":"8","author":"Ahmad","year":"2023","journal-title":"ACS Omega"},{"issue":"17","key":"2026101208073910000_cit22","doi-asserted-by":"publisher","first-page":"1645","DOI":"10.1021\/acs.biochem.0c00278","article-title":"Parsing Molecules for Drug Discovery","volume":"59","author":"Walker","year":"2020","journal-title":"Biochemistry"},{"issue":"8","key":"2026101208073910000_cit23","doi-asserted-by":"publisher","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","article-title":"Analyzing\nLearned Molecular\nRepresentations for Property Prediction","volume":"59","author":"Yang","year":"2019","journal-title":"J.\nChem. Inf. Model."},{"key":"2026101208073910000_cit24","doi-asserted-by":"publisher","first-page":"arXiv:2205.03834","DOI":"10.48550\/arXiv.2205.03834","article-title":"FP-GNN: a\nversatile deep learning architecture for enhanced molecular property\nprediction","author":"Cai","year":"2022","journal-title":"arXiv"},{"issue":"8","key":"2026101208073910000_cit25","doi-asserted-by":"publisher","first-page":"3849","DOI":"10.1021\/acs.molpharmaceut.4c00307","article-title":"Platelet Membrane-Camouflaged\nSilver Metal-Organic Framework Biomimetic Nanoparticles for the Treatment\nof Triple-Negative Breast Cancer","volume":"21","author":"Liu","year":"2024","journal-title":"Mol. Pharmaceutics"},{"key":"2026101208073910000_cit26","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1021\/acs.jcim.3c01250","article-title":"Chemprop:\nA Machine Learning Package for Chemical Property Prediction","volume":"64","author":"Heid","year":"2024","journal-title":"J. Chem. Inf. Model."},{"issue":"17","key":"2026101208073910000_cit27","doi-asserted-by":"publisher","first-page":"i821","DOI":"10.1093\/bioinformatics\/bty593","article-title":"DeepDTA: Deep Drug\u2013Target\nBinding Affinity Prediction","volume":"34","author":"O\u0308ztu\u0308rk","year":"2018","journal-title":"Bioinformatics"},{"issue":"22","key":"2026101208073910000_cit28","doi-asserted-by":"publisher","first-page":"12279","DOI":"10.1021\/acs.jcim.5c02063","article-title":"Learning Binding Affinities via Fine-Tuning of Protein\nand Ligand Language Models","volume":"65","author":"Gorantla","year":"2025","journal-title":"J. Chem. Inf. Model."},{"issue":"16","key":"2026101208073910000_cit29","doi-asserted-by":"publisher","first-page":"8749","DOI":"10.1021\/acs.jmedchem.9b00959","article-title":"Pushing the Boundaries\nof Molecular Representation for Drug Discovery\nwith the Graph Attention Mechanism","volume":"63","author":"Xiong","year":"2020","journal-title":"J. Med.\nChem."},{"issue":"1","key":"2026101208073910000_cit30","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1038\/s42004-025-01583-2","article-title":"Leveraging\nviral genome sequences and machine learning models for identification\nof potentially selective antiviral agents","volume":"8","author":"Xu","year":"2025","journal-title":"Commun.\nChem."},{"issue":"6","key":"2026101208073910000_cit31","doi-asserted-by":"publisher","first-page":"3647","DOI":"10.1039\/D0CS01118E","article-title":"Antiviral\ndrug discovery: preparing for the next pandemic","volume":"50","author":"Adamson","year":"2021","journal-title":"Chem. Soc. Rev."},{"key":"2026101208073910000_cit32","doi-asserted-by":"publisher","first-page":"1013285","DOI":"10.3389\/fddsv.2022.1013285","article-title":"Artificial\nintelligence for antiviral drug discovery in low resourced settings:\nA perspective","volume":"2","author":"Namba-Nzanguim","year":"2022","journal-title":"Front Drug Discov"},{"issue":"3","key":"2026101208073910000_cit33","doi-asserted-by":"publisher","first-page":"030001","DOI":"10.1103\/y3fg-s9vg","article-title":"Essay: Using Machine Learning for\nAntibiotic Discovery","volume":"135","author":"De La Fuente-Nunez","year":"2025","journal-title":"Phys. Rev. Lett."},{"issue":"D1","key":"2026101208073910000_cit34","doi-asserted-by":"publisher","first-page":"D1074","DOI":"10.1093\/nar\/gkx1037","article-title":"DrugBank 5.0: a major\nupdate to the DrugBank database for 2018","volume":"46","author":"Wishart","year":"2018","journal-title":"Nucleic\nAcids Res."},{"issue":"10","key":"2026101208073910000_cit35","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.1038\/s41589-022-01131-2","article-title":"Artificial intelligence foundation for therapeutic\nscience","volume":"18","author":"Huang","year":"2022","journal-title":"Nat. Chem. Biol."},{"issue":"11","key":"2026101208073910000_cit36","doi-asserted-by":"publisher","first-page":"3263","DOI":"10.1021\/acs.jcim.3c00160","article-title":"Prospective Validation\nof Machine Learning Algorithms for Absorption, Distribution, Metabolism,\nand Excretion Prediction: An Industrial Perspective","volume":"63","author":"Fang","year":"2023","journal-title":"J. Chem. Inf. Model."},{"issue":"D1","key":"2026101208073910000_cit37","doi-asserted-by":"publisher","first-page":"D1180","DOI":"10.1093\/nar\/gkad1004","article-title":"The ChEMBL\nDatabase\nin 2023: a drug discovery platform spanning multiple bioactivity data\ntypes and time periods","volume":"52","author":"Zdrazil","year":"2024","journal-title":"Nucleic Acids Res."},{"issue":"6","key":"2026101208073910000_cit38","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1007\/s10822-011-9440-2","article-title":"Online chemical modeling\nenvironment (OCHEM): web platform for data storage, model development\nand publishing of chemical information","volume":"25","author":"Sushko","year":"2011","journal-title":"J. Comput.\nAided Mol. Des"},{"issue":"D1","key":"2026101208073910000_cit39","doi-asserted-by":"publisher","first-page":"D1373","DOI":"10.1093\/nar\/gkac956","article-title":"PubChem 2023 update","volume":"51","author":"Kim","year":"2023","journal-title":"Nucleic Acids Res."},{"issue":"D1","key":"2026101208073910000_cit40","doi-asserted-by":"publisher","first-page":"D506","DOI":"10.1093\/nar\/gky1049","article-title":"UniProt:\na worldwide hub of protein knowledge","volume":"47","author":"The UniProt Consortium.","year":"2019","journal-title":"Nucleic\nAcids Res."},{"issue":"1","key":"2026101208073910000_cit41","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s13321-018-0258-y","article-title":"Mordred: a molecular\ndescriptor calculator","volume":"10","author":"Moriwaki","year":"2018","journal-title":"J. Chemin."},{"key":"2026101208073910000_cit42","unstructured":"RDKit: Open-source Cheminformatics. https:\/\/www.rdkit.org\/ (accessed\nAug 29, 2025)."},{"issue":"4","key":"2026101208073910000_cit43","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1016\/j.cell.2020.01.021","article-title":"A Deep Learning Approach\nto Antibiotic Discovery","volume":"180","author":"Stokes","year":"2020","journal-title":"Cell"},{"key":"2026101208073910000_cit44","doi-asserted-by":"crossref","unstructured":"Chen, T.; Guestrin, C.\n          XGBoost:\nA Scalable\nTree Boosting System. In  Proceedings of the\n22nd ACM SIGKDD International Conference on Knowledge Discovery and\nData Mining, 2016; pp 785\u2013794.10.1145\/2939672.2939785.","DOI":"10.1145\/2939672.2939785"},{"key":"2026101208073910000_cit45","unstructured":"Ke, G., Meng, Q., Finley, T.; et al., LightGBM: A\nHighly Efficient Gradient Boosting Decision Tree.\nIn:  Advances in Neural Information Processing Systems; Curran Associates, Inc., 2017."},{"issue":"1","key":"2026101208073910000_cit46","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"2026101208073910000_cit47","doi-asserted-by":"publisher","first-page":"arXiv:1810.11363","DOI":"10.48550\/arXiv.1810.11363","article-title":"CatBoost:\ngradient boosting with\ncategorical features support","author":"Dorogush","year":"2018","journal-title":"arXiv"},{"key":"2026101208073910000_cit48","doi-asserted-by":"crossref","unstructured":"Ansel, J.; Yang, E.; He, H.; Gimelshein, N.; Jain, A.; Voznesensky, M.; Bao, B.; Bell, P.; Berard, D.; Burovski, E.; et al.; PyTorch 2: Faster Machine Learning Through Dynamic Python Bytecode\nTransformation and Graph Compilation. In  ASPLOS\n\u201924: Proceedings of the 29th ACM International Conference on\nArchitectural Support for Programming Languages and Operating Systems, 2024.10.1145\/3620665.3640366.","DOI":"10.1145\/3620665.3640366"},{"key":"2026101208073910000_cit49","doi-asserted-by":"publisher","first-page":"arXiv:2507.16991","DOI":"10.48550\/arXiv.2507.16991","article-title":"PyG 2.0: Scalable Learning\non Real World Graphs","author":"Fey","year":"2025","journal-title":"arXiv"},{"key":"2026101208073910000_cit50","doi-asserted-by":"publisher","first-page":"arXiv:1903.02428","DOI":"10.48550\/arXiv.1903.02428","article-title":"Fast Graph Representation\nLearning with PyTorch Geometric","author":"Fey","year":"2019","journal-title":"arXiv"},{"key":"2026101208073910000_cit51","doi-asserted-by":"publisher","first-page":"3329","DOI":"10.1093\/bioinformatics\/btz111","article-title":"DeepAffinity:\ninterpretable deep\nlearning of compound\u2013protein affinity through unified recurrent\nand convolutional neural networks","volume":"35","author":"Karimi","year":"2019","journal-title":"Bioinformatics"},{"issue":"2","key":"2026101208073910000_cit52","doi-asserted-by":"publisher","first-page":"161","DOI":"10.3390\/ph17020161","article-title":"De Novo\nDrug Design Using Transformer-Based\nMachine Translation and Reinforcement Learning of an Adaptive Monte\nCarlo Tree Search","volume":"17","author":"Ang","year":"2024","journal-title":"Pharmaceuticals"},{"key":"2026101208073910000_cit53","doi-asserted-by":"publisher","first-page":"arXiv.1710.03740","DOI":"10.48550\/arXiv.1710.03740","article-title":"Mixed precision training","author":"Micikevicius","year":"2017","journal-title":"arXiv"},{"key":"2026101208073910000_cit54","doi-asserted-by":"publisher","first-page":"arXiv:2411.09539","DOI":"10.48550\/arXiv.2411.09539","article-title":"A Practical\nGuide to Fine-tuning Language Models with Limited Data","author":"Szep","year":"2024","journal-title":"arXiv"},{"issue":"6","key":"2026101208073910000_cit55","doi-asserted-by":"publisher","first-page":"bbab211","DOI":"10.1093\/bib\/bbab211","article-title":"A transferable deep\nlearning approach to fast screen potential antiviral drugs against\nSARS-CoV-2","volume":"22","author":"Wang","year":"2021","journal-title":"Brief Bioinform"},{"key":"2026101208073910000_cit56","doi-asserted-by":"publisher","first-page":"arXiv:2202.10054","DOI":"10.48550\/arXiv.2202.10054","article-title":"Fine-Tuning\ncan Distort Pretrained Features and Underperform Out-of-Distribution","author":"Kumar","year":"2022","journal-title":"arXiv"},{"key":"2026101208073910000_cit57","doi-asserted-by":"publisher","first-page":"arXiv:2312.15681","DOI":"10.48550\/arXiv.2312.15681","article-title":"Partial Fine-Tuning:\nA Successor to Full Fine-Tuning for Vision Transformers","author":"Ye","year":"2023","journal-title":"arXiv"},{"key":"2026101208073910000_cit58","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.03983","article-title":"Partial Is Better\nThan All: Revisiting Fine-tuning Strategy for Few-shot Learning","author":"Shen","year":"2021","journal-title":"arXiv. Preprint posted online"},{"issue":"W1","key":"2026101208073910000_cit59","doi-asserted-by":"publisher","first-page":"W363","DOI":"10.1093\/nar\/gky473","article-title":"CASTp 3.0:\ncomputed atlas of surface topography of proteins","volume":"46","author":"Tian","year":"2018","journal-title":"Nucleic Acids Res."},{"issue":"3","key":"2026101208073910000_cit60","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1006\/jmbi.1996.0477","article-title":"A Fast Flexible Docking\nMethod Using an Incremental Construction Algorithm","volume":"261","author":"Rarey","year":"1996","journal-title":"J. Mol. Biol."},{"issue":"12","key":"2026101208073910000_cit61","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1007\/s10822-006-9091-x","article-title":"Ultrafast de Novo Docking\nCombining Pharmacophores and Combinatorics","volume":"20","author":"Gastreich","year":"2007","journal-title":"J. Comput. Aided. Mol. Des."},{"issue":"18","key":"2026101208073910000_cit62","doi-asserted-by":"publisher","first-page":"9398","DOI":"10.1021\/acs.jcim.5c01609","article-title":"Practically Significant Method Comparison Protocols\nfor Machine Learning in Small Molecule Drug Discovery","volume":"65","author":"Ash","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"2026101208073910000_cit63","doi-asserted-by":"publisher","first-page":"arXiv:1411.1792","DOI":"10.48550\/arXiv.1411.1792","article-title":"How transferable\nare\nfeatures in deep neural networks?","author":"Yosinski","year":"2014","journal-title":"arXiv"},{"issue":"5","key":"2026101208073910000_cit64","doi-asserted-by":"publisher","first-page":"1560","DOI":"10.1021\/acs.jcim.4c00049","article-title":"Combining IC50 or Ki Values from\nDifferent Sources\nIs a Source of Significant Noise","volume":"64","author":"Landrum","year":"2024","journal-title":"J. Chem. Inf.\nModel."},{"issue":"4","key":"2026101208073910000_cit65","doi-asserted-by":"publisher","first-page":"2200186","DOI":"10.1002\/minf.202200186","article-title":"A. Comparison between 2D and 3D Descriptors in QSAR Modeling Based\non Bio-Active Conformations","volume":"42","author":"Bahia","year":"2023","journal-title":"Mol. Inform."},{"issue":"1","key":"2026101208073910000_cit66","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1021\/acsptsci.0c00174","article-title":"Antibacterial\nand Antiviral Functional\nMaterials: Chemistry and Biological Activity toward Tackling COVID-19-like\nPandemics","volume":"4","author":"Balasubramaniam","year":"2021","journal-title":"ACS Pharmacol. Transl. Sci."},{"issue":"12","key":"2026101208073910000_cit67","doi-asserted-by":"publisher","first-page":"2353","DOI":"10.1021\/acs.jcim.6b00591","article-title":"Extreme\nGradient Boosting as a Method for Quantitative Structure-Activity\nRelationships","volume":"56","author":"Sheridan","year":"2016","journal-title":"J. Chem. Inf. Model."},{"issue":"3","key":"2026101208073910000_cit68","doi-asserted-by":"publisher","first-page":"498","DOI":"10.3390\/biom13030498","article-title":"On the Best Way to Cluster NCI-60 Molecules","volume":"13","author":"Herna\u0301ndez-Herna\u0301ndez","year":"2023","journal-title":"Biomolecules"},{"key":"2026101208073910000_cit69","unstructured":"Walters, P.\n          \n          Some Thoughts\non Splitting Chemical Datasets. 2024. https:\/\/practicalcheminformatics.blogspot.com\/2024\/11\/some-thoughts-on-splitting-chemical.html."},{"key":"2026101208073910000_cit70","unstructured":"Klarner, L.; Rudner, T. G. J.; Reutlinger, M.; Schindler, T.; Morris, G. M.; Deane, C.; Teh, Y. W.\n          Drug Discovery\nunder Covariate Shift with Domain-Informed Prior Distributions over\nFunctions. In  Proceedings of the 40th International\nConference on Machine Learning, in Proceedings of Machine Learning\nResearch, 2023."},{"key":"2026101208073910000_cit71","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1385\/1-59259-802-1:261","article-title":"Derivation\nand Applications of Molecular Descriptors Based on Approximate Surface\nArea","volume":"275","author":"Labute","year":"2004","journal-title":"Methods Mol. Biol."},{"issue":"1\u20134","key":"2026101208073910000_cit72","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1080\/10629369708039123","article-title":"Novel Indices\nfor the Topological Complexity of Molecules","volume":"7","author":"Bonchev","year":"1997","journal-title":"SAR QSAR Environ. Res."},{"issue":"20","key":"2026101208073910000_cit73","doi-asserted-by":"publisher","first-page":"3714","DOI":"10.1021\/jm000942e","article-title":"Fast Calculation of\nMolecular Polar\nSurface Area as a Sum of Fragment-Based Contributions and Its Application\nto the Prediction of Drug Transport Properties","volume":"43","author":"Ertl","year":"2000","journal-title":"J. Med. Chem."},{"issue":"6","key":"2026101208073910000_cit74","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1021\/ci00028a014","article-title":"Electrotopological State Indices for Atom Types: A\nNovel Combination of Electronic, Topological, and Valence State Information","volume":"35","author":"Hall","year":"1995","journal-title":"J. Chem. Inf. Comput. Sci."},{"issue":"5","key":"2026101208073910000_cit75","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1016\/s0092-8240(83)80030-5","article-title":"On the\nComplexity of Graphs and Molecules","volume":"45","author":"Bertz","year":"1983","journal-title":"Bull. Math.\nBiol."},{"issue":"24","key":"2026101208073910000_cit76","doi-asserted-by":"publisher","first-page":"13115","DOI":"10.1021\/acs.jcim.5c01982","article-title":"Deep Learning vs Classical\nMethods in Potency and ADME Prediction: Insights from a Computational\nBlind Challenge","volume":"65","author":"Fischer","year":"2025","journal-title":"J. Chem. Inf. Model."},{"issue":"24","key":"2026101208073910000_cit77","doi-asserted-by":"publisher","first-page":"13255","DOI":"10.1021\/acs.jcim.5c02014","article-title":"Fingerprint-Based Machine\nLearning for SARS-CoV-2 and MERS-CoV M pro Inhibition: Highlighting\nthe Potential of Bayesian Neural Networks","volume":"65","author":"Doering","year":"2025","journal-title":"J.\nChem. Inf. Model."},{"issue":"7","key":"2026101208073910000_cit78","doi-asserted-by":"publisher","first-page":"btae416","DOI":"10.1093\/bioinformatics\/btae416","article-title":"ADMET-AI:\na machine\nlearning ADMET platform for evaluation of large-scale chemical libraries","volume":"40","author":"Swanson","year":"2024","journal-title":"Bioinformatics"},{"issue":"1","key":"2026101208073910000_cit79","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1186\/s13321-024-00830-3","article-title":"Effectiveness of molecular fingerprints\nfor exploring the chemical space of natural products","volume":"16","author":"Boldini","year":"2024","journal-title":"J. Chemin."},{"issue":"5","key":"2026101208073910000_cit80","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-Connectivity\nFingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J. Chem.\nInf. Model."},{"issue":"2","key":"2026101208073910000_cit81","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1021\/ci00046a002","article-title":"Atom pairs\nas molecular features\nin structure-activity studies: definition and applications","volume":"25","author":"Carhart","year":"1985","journal-title":"J. Chem. Inf. Comput. Sci."},{"issue":"7","key":"2026101208073910000_cit82","doi-asserted-by":"publisher","first-page":"1892","DOI":"10.1021\/ci500232g","article-title":"Atom Pair 2D-Fingerprints Perceive 3D-Molecular Shape\nand Pharmacophores for Very Fast Virtual Screening of ZINC and GDB-17","volume":"54","author":"Awale","year":"2014","journal-title":"J. Chem. Inf. Model."},{"issue":"2","key":"2026101208073910000_cit83","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1021\/ci00054a008","article-title":"Topological\ntorsion: a new molecular descriptor for SAR applications. Comparison\nwith other descriptors","volume":"27","author":"Nilakantan","year":"1987","journal-title":"J. Chem. Inf. Comput.\nSci."},{"issue":"1","key":"2026101208073910000_cit84","doi-asserted-by":"publisher","first-page":"bbac560","DOI":"10.1093\/bib\/bbac560","article-title":"Fusing 2D\nand 3D Molecular Graphs as Unambiguous Molecular Descriptors for Conformational\nand Chiral Stereoisomers","volume":"24","author":"Du","year":"2023","journal-title":"Briefings Bioinf."},{"issue":"35","key":"2026101208073910000_cit85","doi-asserted-by":"publisher","first-page":"8100","DOI":"10.1039\/C9SC02097G","article-title":"A generalized deep learning approach\nfor local structure\nidentification in molecular simulations","volume":"10","author":"Geiger","year":"2019","journal-title":"Chem.\nSci."},{"issue":"21","key":"2026101208073910000_cit86","doi-asserted-by":"publisher","first-page":"3666","DOI":"10.1093\/bioinformatics\/bty374","article-title":"Development and evaluation of a deep\nlearning model for protein-ligand binding affinity prediction","volume":"34","author":"Stepniewska-Dziubinska","year":"2018","journal-title":"Bioinformatics"},{"issue":"2","key":"2026101208073910000_cit87","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1038\/s41592-019-0666-6","article-title":"Deciphering\ninteraction\nfingerprints from protein molecular surfaces using geometric deep\nlearning","volume":"17","author":"Gainza","year":"2020","journal-title":"Nat. Methods"},{"key":"2026101208073910000_cit88","doi-asserted-by":"publisher","first-page":"arXiv:1802.08219","DOI":"10.48550\/arXiv.1802.08219","article-title":"Tensor Field\nNetworks: Rotation-\nand translation-equivariant Neural Networks for 3D Point Clouds","author":"Thomas","year":"2018","journal-title":"arXiv"},{"issue":"7873","key":"2026101208073910000_cit89","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly Accurate Protein Structure Prediction\nwith AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"issue":"6","key":"2026101208073910000_cit90","doi-asserted-by":"publisher","first-page":"bbae480","DOI":"10.1093\/bib\/bbae480","article-title":"Protein language\nmodels are performant in structure-free virtual screening","volume":"25","author":"Lam","year":"2024","journal-title":"Brief Bioinform"},{"issue":"6736","key":"2026101208073910000_cit91","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1126\/science.ads0018","article-title":"Simulating 500 Million Years of Evolution with a Language Model","volume":"387","author":"Hayes","year":"2025","journal-title":"Science"},{"issue":"10","key":"2026101208073910000_cit92","doi-asserted-by":"publisher","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"ProtTrans: Toward Understanding the Language\nof Life Through Self-Supervised Learning","volume":"44","author":"Elnaggar","year":"2022","journal-title":"IEEE\nTrans. Pattern Anal. Mach. Intell."}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c00304","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/19\/12549\/68702224\/acs.jcim.6c00304.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/19\/12549\/68702224\/acs.jcim.6c00304.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T12:30:13Z","timestamp":1791808213000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/19\/12549\/5441801\/Benchmarking-Experiments-with-External-Data-Domain"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,29]]},"references-count":92,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,9,29]]},"published-print":{"date-parts":[[2026,10,12]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c00304","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,29]]}}}