{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T11:36:04Z","timestamp":1777894564022,"version":"3.51.4"},"reference-count":158,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T00:00:00Z","timestamp":1772496000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003407","name":"Ministero dell\u2019Istruzione, dell\u2019Universit\u00e0 e della Ricerca","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003407","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Science Review"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.cosrev.2026.100943","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T07:51:27Z","timestamp":1773042687000},"page":"100943","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":3,"special_numbering":"C","title":["Explainable AI methods for drug discovery: A survey of interpretability, metrics and mechanistic insight"],"prefix":"10.1016","volume":"61","author":[{"given":"Amit","family":"Gangwal","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2181-8026","authenticated-orcid":false,"given":"Antonio","family":"Lavecchia","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.cosrev.2026.100943_bib0001","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1001\/jama.2020.8648","article-title":"Research and development costs of new drugs","volume":"324","author":"DiMasi","year":"2020","journal-title":"JAMa"},{"key":"10.1016\/j.cosrev.2026.100943_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.drudis.2024.103992","article-title":"Unleashing the power of generative AI in drug discovery","volume":"29","author":"Gangwal","year":"2024","journal-title":"Drug Discov. Today"},{"key":"10.1016\/j.cosrev.2026.100943_bib0003","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s00894-021-04674-8","article-title":"Generative chemistry: drug discovery with deep learning generative models","volume":"27","author":"Bian","year":"2021","journal-title":"J. Mol. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0004","doi-asserted-by":"crossref","unstructured":"D. Huang, M. Yang, W. Zheng, Integrating AI and Deep learning for efficient drug discovery and target identification, (2024).","DOI":"10.20944\/preprints202410.1089.v1"},{"key":"10.1016\/j.cosrev.2026.100943_bib0005","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cosrev.2026.100943_bib0006","doi-asserted-by":"crossref","first-page":"1038","DOI":"10.1038\/s41587-019-0224-x","article-title":"Deep learning enables rapid identification of potent DDR1 kinase inhibitors","volume":"37","author":"Zhavoronkov","year":"2019","journal-title":"Nat. Biotechnol."},{"key":"10.1016\/j.cosrev.2026.100943_bib0007","doi-asserted-by":"crossref","first-page":"1711","DOI":"10.1002\/prot.26257","article-title":"Applying and improving AlphaFold at CASP14","volume":"89","author":"Jumper","year":"2021","journal-title":"Proteins Struct. Funct. Bioinforma."},{"key":"10.1016\/j.cosrev.2026.100943_bib0008","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","article-title":"Accurate structure prediction of biomolecular interactions with AlphaFold 3","volume":"630","author":"Abramson","year":"2024","journal-title":"Nature"},{"key":"10.1016\/j.cosrev.2026.100943_bib0009","doi-asserted-by":"crossref","unstructured":"D. Baker, D. Hassabis, J. Jumper, Nobel Prize in Chemistry 2024, Nobel Prize Organ. (2024).","DOI":"10.1063\/pt.mcbg.rtkn"},{"key":"10.1016\/j.cosrev.2026.100943_bib0010","doi-asserted-by":"crossref","first-page":"1443","DOI":"10.1039\/D2SC05709C","article-title":"AlphaFold accelerates artificial intelligence powered drug discovery: efficient discovery of a novel CDK20 small molecule inhibitor","volume":"14","author":"Ren","year":"2023","journal-title":"Chem. Sci."},{"key":"10.1016\/j.cosrev.2026.100943_bib0011","first-page":"1","article-title":"Explainable AI reveals clever Hans effects in unsupervised learning models","author":"Kauffmann","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.cosrev.2026.100943_bib0012","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1038\/s42256-020-00236-4","article-title":"Drug discovery with explainable artificial intelligence","volume":"2","author":"Jim\u00e9nez-Luna","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.cosrev.2026.100943_bib0013","doi-asserted-by":"crossref","first-page":"e1681","DOI":"10.1002\/wcms.1681","article-title":"Explainable artificial intelligence: a taxonomy and guidelines for its application to drug discovery","volume":"13","author":"Ponzoni","year":"2023","journal-title":"Wiley. Interdiscip. Rev. Comput. Mol. Sci."},{"key":"10.1016\/j.cosrev.2026.100943_bib0014","doi-asserted-by":"crossref","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":"10.1016\/j.cosrev.2026.100943_bib0015","doi-asserted-by":"crossref","first-page":"4501","DOI":"10.2147\/DDDT.S525171","article-title":"Explainable artificial intelligence in the field of drug research","author":"Ding","year":"2025","journal-title":"Drug Des. Devel. Ther."},{"key":"10.1016\/j.cosrev.2026.100943_bib0016","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2024.3373195","article-title":"Explainable artificial intelligence for drug discovery and development-a comprehensive survey","author":"Alizadehsani","year":"2024","journal-title":"IEEe Access."},{"key":"10.1016\/j.cosrev.2026.100943_bib0017","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3583558","article-title":"From anecdotal evidence to quantitative evaluation methods: a systematic review on evaluating explainable ai","volume":"55","author":"Nauta","year":"2023","journal-title":"ACM. Comput. Surv."},{"key":"10.1016\/j.cosrev.2026.100943_bib0018","first-page":"593","article-title":"Evaluating the quality of machine learning explanations: a survey on methods and metrics","volume":"10","author":"Zhou","year":"2021","journal-title":"Electronics. (Basel)"},{"key":"10.1016\/j.cosrev.2026.100943_bib0019","doi-asserted-by":"crossref","first-page":"1096","DOI":"10.1038\/s41467-019-08987-4","article-title":"Unmasking clever Hans predictors and assessing what machines really learn","volume":"10","author":"Lapuschkin","year":"2019","journal-title":"Nat. Commun."},{"key":"10.1016\/j.cosrev.2026.100943_bib0020","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1038\/s42256-021-00338-7","article-title":"AI for radiographic COVID-19 detection selects shortcuts over signal","volume":"3","author":"DeGrave","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.cosrev.2026.100943_bib0021","series-title":"Explainable Fuzzy Systems","author":"Moral","year":"2021"},{"key":"10.1016\/j.cosrev.2026.100943_bib0022","author":"Jain"},{"key":"10.1016\/j.cosrev.2026.100943_bib0023","series-title":"Explain. AI Health Inform","first-page":"113","article-title":"Explainable artificial intelligence in drug discovery","author":"Geevarghese","year":"2024"},{"key":"10.1016\/j.cosrev.2026.100943_bib0024","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1007\/s41666-022-00114-1","article-title":"Explainable artificial intelligence for predictive modeling in healthcare","volume":"6","author":"Yang","year":"2022","journal-title":"J. Healthc. Inform. Res."},{"key":"10.1016\/j.cosrev.2026.100943_bib0025","first-page":"360","article-title":"Inverse molecular design using machine learning: generative models for matter engineering","volume":"361","author":"Sanchez-Lengeling","year":"2018","journal-title":"Science (1979)"},{"key":"10.1016\/j.cosrev.2026.100943_bib0026","doi-asserted-by":"crossref","first-page":"3697","DOI":"10.1039\/D1SC05259D","article-title":"Model agnostic generation of counterfactual explanations for molecules","volume":"13","author":"Wellawatte","year":"2022","journal-title":"Chem. Sci."},{"key":"10.1016\/j.cosrev.2026.100943_bib0027","first-page":"1","article-title":"A survey of methods for explaining black box models","volume":"51","author":"Guidotti","year":"2018","journal-title":"ACM Comput. Surv. CSUR"},{"key":"10.1016\/j.cosrev.2026.100943_bib0028","article-title":"Gnnexplainer: generating explanations for graph neural networks","volume":"32","author":"Ying","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cosrev.2026.100943_bib0029","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1186\/s13321-022-00667-8","article-title":"Human-in-the-loop assisted de novo molecular design","volume":"14","author":"Sundin","year":"2022","journal-title":"J. Cheminformatics"},{"key":"10.1016\/j.cosrev.2026.100943_bib0030","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1007\/s40708-016-0042-6","article-title":"Interactive machine learning for health informatics: when do we need the human-in-the-loop?","volume":"3","author":"Holzinger","year":"2016","journal-title":"Brain Inform."},{"key":"10.1016\/j.cosrev.2026.100943_bib0031","doi-asserted-by":"crossref","unstructured":"D. Slack, S. Hilgard, E. Jia, S. Singh, H. Lakkaraju, Fooling LIME and SHAP: adversarial attacks on post hoc explanation methods, (2020). https:\/\/doi.org\/10.48550\/arXiv.1911.02508.","DOI":"10.1145\/3375627.3375830"},{"key":"10.1016\/j.cosrev.2026.100943_bib0032","author":"Krishna"},{"key":"10.1016\/j.cosrev.2026.100943_bib0033","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/j.inffus.2021.05.008","article-title":"A review of uncertainty quantification in deep learning: techniques, applications and challenges","volume":"76","author":"Abdar","year":"2021","journal-title":"Inf. Fusion."},{"key":"10.1016\/j.cosrev.2026.100943_bib0034","series-title":"International Conference on Machine","first-page":"1050","article-title":"Dropout as a bayesian approximation: representing model uncertainty in deep learning","author":"Gal","year":"2016"},{"key":"10.1016\/j.cosrev.2026.100943_bib0035","doi-asserted-by":"crossref","first-page":"1001","DOI":"10.1007\/s11063-021-10424-x","article-title":"Illustrative discussion of mc-dropout in general dataset: uncertainty estimation in bitcoin","volume":"53","author":"Alarab","year":"2021","journal-title":"Neural Process. Lett."},{"key":"10.1016\/j.cosrev.2026.100943_bib0036","author":"Verdoja"},{"key":"10.1016\/j.cosrev.2026.100943_bib0037","series-title":"2023 IEEE Int. Conf. Syst. Man Cybern. SMC","first-page":"973","article-title":"Controlled dropout for uncertainty estimation","author":"Hasan","year":"2023"},{"key":"10.1016\/j.cosrev.2026.100943_bib0038","unstructured":"U.F. and D. Administration, U.F. and D. Administration, CFR Part 11: Electronic Records; Electronic Signatures, Title, 21."},{"key":"10.1016\/j.cosrev.2026.100943_bib0039","series-title":"Reflection Paper on the Use of Artificial Intelligence (AI) in the Medicinal Product Lifecycle","year":"2023"},{"key":"10.1016\/j.cosrev.2026.100943_bib0040","series-title":"Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min","first-page":"1135","article-title":"\u201c Why should i trust you?\u201d explaining the predictions of any classifier","author":"Ribeiro","year":"2016"},{"key":"10.1016\/j.cosrev.2026.100943_bib0041","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cosrev.2026.100943_bib0042","series-title":"Int. Conf. Mach. Learn.","first-page":"3319","article-title":"Axiomatic attribution for deep networks","author":"Sundararajan","year":"2017"},{"key":"10.1016\/j.cosrev.2026.100943_bib0043","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.103900","article-title":"A comprehensive study on fidelity metrics for XAI","volume":"62","author":"Mir\u00f3-Nicolau","year":"2025","journal-title":"Inf. Process. Manage"},{"key":"10.1016\/j.cosrev.2026.100943_bib0044","doi-asserted-by":"crossref","first-page":"42200","DOI":"10.1109\/ACCESS.2020.2976199","article-title":"Explainable machine learning for scientific insights and discoveries","volume":"8","author":"Roscher","year":"2020","journal-title":"IEEe Access."},{"key":"10.1016\/j.cosrev.2026.100943_bib0045","doi-asserted-by":"crossref","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","article-title":"Peeking inside the black-box: a survey on explainable artificial intelligence (XAI)","volume":"6","author":"Adadi","year":"2018","journal-title":"IEEe Access."},{"key":"10.1016\/j.cosrev.2026.100943_bib0046","first-page":"9391","article-title":"Reliable post hoc explanations: modeling uncertainty in explainability","volume":"34","author":"Slack","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cosrev.2026.100943_bib0047","series-title":"Contributions to the Theory of Games","author":"Kuhn","year":"1953"},{"key":"10.1016\/j.cosrev.2026.100943_bib0048","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1186\/s13321-024-00940-y","article-title":"AttenhERG: a reliable and interpretable graph neural network framework for predicting hERG channel blockers","volume":"16","author":"Yang","year":"2024","journal-title":"J. Cheminformatics"},{"key":"10.1016\/j.cosrev.2026.100943_bib0049","doi-asserted-by":"crossref","DOI":"10.1016\/j.drudis.2024.104067","article-title":"Advancing drug discovery with deep attention neural networks","author":"Lavecchia","year":"2024","journal-title":"Drug Discov. Today"},{"key":"10.1016\/j.cosrev.2026.100943_bib0050","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable Artificial Intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI","volume":"58","author":"Arrieta","year":"2020","journal-title":"Inf. Fusion."},{"key":"10.1016\/j.cosrev.2026.100943_bib0051","doi-asserted-by":"crossref","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":"10.1016\/j.cosrev.2026.100943_bib0052","doi-asserted-by":"crossref","DOI":"10.1016\/j.patter.2022.100628","article-title":"Quantitative evaluation of explainable graph neural networks for molecular property prediction","volume":"3","author":"Rao","year":"2022","journal-title":"Patterns"},{"key":"10.1016\/j.cosrev.2026.100943_bib0053","doi-asserted-by":"crossref","first-page":"6649","DOI":"10.3390\/s25216649","article-title":"eXplainable artificial intelligence (XAI): a systematic review for unveiling the black box models and their relevance to biomedical imaging and sensing","volume":"25","author":"Hettikankanamage","year":"2025","journal-title":"Sensors"},{"key":"10.1016\/j.cosrev.2026.100943_bib0054","doi-asserted-by":"crossref","first-page":"18","DOI":"10.3390\/e23010018","article-title":"A review of machine learning interpretability methods","volume":"23","author":"Linardatos","year":"2021","journal-title":"Entropy"},{"key":"10.1016\/j.cosrev.2026.100943_bib0055","first-page":"50","article-title":"Applications of attention mechanisms in explainable machine learning","volume":"8","author":"Zhu","year":"2025","journal-title":"Acad. J. Comput. Inf. Sci."},{"key":"10.1016\/j.cosrev.2026.100943_bib0056","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.inffus.2021.11.003","article-title":"Counterfactuals and causability in explainable artificial intelligence: theory, algorithms, and applications","volume":"81","author":"Chou","year":"2022","journal-title":"Inf. Fusion."},{"key":"10.1016\/j.cosrev.2026.100943_bib0057","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1021\/acs.jcim.0c00866","article-title":"Explainable deep relational networks for predicting compound\u2013Protein affinities and contacts","volume":"61","author":"Karimi","year":"2021","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0058","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1038\/s41592-019-0666-6","article-title":"Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning","volume":"17","author":"Gainza","year":"2020","journal-title":"Nat. Methods"},{"key":"10.1016\/j.cosrev.2026.100943_bib0059","author":"Xu"},{"key":"10.1016\/j.cosrev.2026.100943_bib0060","unstructured":"E. Hoogeboom, V.G. Satorras, C. Vignac, M. Welling, Equivariant diffusion for molecule generation in 3D, (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.17003."},{"key":"10.1016\/j.cosrev.2026.100943_bib0061","series-title":"Int. Conf. Mach. Learn.","first-page":"2668","article-title":"Interpretability beyond feature attribution: quantitative testing with concept activation vectors (tcav)","author":"Kim","year":"2018"},{"key":"10.1016\/j.cosrev.2026.100943_bib0062","series-title":"Proc. IEEE","first-page":"612","article-title":"Toward causal representation learning","volume":"109","author":"Sch\u00f6lkopf","year":"2021"},{"key":"10.1016\/j.cosrev.2026.100943_bib0063","doi-asserted-by":"crossref","DOI":"10.1016\/j.drudis.2023.103737","article-title":"Causal inference in drug discovery and development","volume":"28","author":"Michoel","year":"2023","journal-title":"Drug Discov. Today"},{"key":"10.1016\/j.cosrev.2026.100943_bib0064","series-title":"Int. Conf. Learn. Represent","article-title":"Analyzing the expressive power of graph neural networks in a spectral perspective","author":"Balcilar","year":"2021"},{"key":"10.1016\/j.cosrev.2026.100943_bib0065","article-title":"Understanding attention and generalization in graph neural networks","volume":"32","author":"Knyazev","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cosrev.2026.100943_bib0066","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00024.001","article-title":"Zoom in: an introduction to circuits","volume":"5","author":"Olah","year":"2020","journal-title":"Distill"},{"key":"10.1016\/j.cosrev.2026.100943_bib0067","doi-asserted-by":"crossref","first-page":"916","DOI":"10.1021\/acs.jcim.7b00403","article-title":"Most ligand-based classification benchmarks reward memorization rather than generalization","volume":"58","author":"Wallach","year":"2018","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0068","series-title":"Int. Conf. Artif. Neural Netw.","first-page":"58","article-title":"Scaffold splits overestimate virtual screening performance","author":"Guo","year":"2024"},{"key":"10.1016\/j.cosrev.2026.100943_bib0069","doi-asserted-by":"crossref","first-page":"7946","DOI":"10.1021\/acs.jmedchem.2c00487","article-title":"On the frustration to predict binding affinities from protein\u2013ligand structures with deep neural networks","volume":"65","author":"Volkov","year":"2022","journal-title":"J. Med. Chem."},{"key":"10.1016\/j.cosrev.2026.100943_bib0070","doi-asserted-by":"crossref","first-page":"11624","DOI":"10.1073\/pnas.1820657116","article-title":"Using attribution to decode binding mechanism in neural network models for chemistry","volume":"116","author":"McCloskey","year":"2019","journal-title":"Proc. Natl. Acad. Sci."},{"key":"10.1016\/j.cosrev.2026.100943_bib0071","doi-asserted-by":"crossref","unstructured":"Y. Liu, Causal descriptors in QSAR: deconfounding high-dimensional molecular features via double machine learning and hypothesis testing, (2025).","DOI":"10.26434\/chemrxiv-2025-nc74b"},{"key":"10.1016\/j.cosrev.2026.100943_bib0072","doi-asserted-by":"crossref","first-page":"1695","DOI":"10.1038\/s41467-021-21895-w","article-title":"Quantitative interpretation explains machine learning models for chemical reaction prediction and uncovers bias","volume":"12","author":"Kov\u00e1cs","year":"2021","journal-title":"Nat. Commun."},{"key":"10.1016\/j.cosrev.2026.100943_bib0073","first-page":"832","article-title":"Machine learning interpretability: a survey on methods and metrics","volume":"8","author":"Carvalho","year":"2019","journal-title":"Electronics. (Basel)"},{"key":"10.1016\/j.cosrev.2026.100943_bib0074","author":"Doshi-Velez"},{"key":"10.1016\/j.cosrev.2026.100943_bib0075","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2023.102560","article-title":"Leveraging artificial intelligence and decision support systems in hospital-acquired pressure injuries prediction: a comprehensive review","volume":"141","author":"Toffaha","year":"2023","journal-title":"Artif. Intell. Med."},{"key":"10.1016\/j.cosrev.2026.100943_bib0076","doi-asserted-by":"crossref","first-page":"17744","DOI":"10.1021\/acs.jmedchem.1c01789","article-title":"Explainable machine learning for property predictions in compound optimization: miniperspective","volume":"64","author":"Rodriguez-Perez","year":"2021","journal-title":"J. Med. Chem."},{"key":"10.1016\/j.cosrev.2026.100943_bib0077","doi-asserted-by":"crossref","first-page":"1324","DOI":"10.1021\/acs.jcim.8b00825","article-title":"Interpretation of QSAR models by coloring atoms according to changes in predicted activity: how robust is it?","volume":"59","author":"Sheridan","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0078","doi-asserted-by":"crossref","first-page":"949","DOI":"10.1080\/17460441.2021.1909567","article-title":"Artificial intelligence in drug discovery: recent advances and future perspectives","volume":"16","author":"Jim\u00e9nez-Luna","year":"2021","journal-title":"Expert. Opin. Drug Discov."},{"key":"10.1016\/j.cosrev.2026.100943_bib0079","unstructured":"J. Adebayo, J. Gilmer, M. Muelly, I. Goodfellow, M. Hardt, B. Kim, Sanity checks for saliency maps, (2020). https:\/\/doi.org\/10.48550\/arXiv.1810.03292."},{"key":"10.1016\/j.cosrev.2026.100943_bib0080","author":"Smilkov"},{"key":"10.1016\/j.cosrev.2026.100943_bib0081","doi-asserted-by":"crossref","first-page":"1083","DOI":"10.1021\/acs.jcim.0c01344","article-title":"Coloring molecules with explainable artificial intelligence for preclinical relevance assessment","volume":"61","author":"Jim\u00e9nez-Luna","year":"2021","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0082","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1186\/s13040-024-00378-w","article-title":"Understanding predictions of drug profiles using explainable machine learning models","volume":"17","author":"K\u00f6nig","year":"2024","journal-title":"BioData Min."},{"key":"10.1016\/j.cosrev.2026.100943_bib0083","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1021\/acs.jcim.1c01163","article-title":"Benchmarking molecular feature attribution methods with activity cliffs","volume":"62","author":"Jim\u00e9nez-Luna","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0084","doi-asserted-by":"crossref","DOI":"10.1111\/cts.70124","article-title":"Integrating model-informed drug development with AI: a synergistic approach to accelerating pharmaceutical innovation","volume":"18","author":"Raman","year":"2025","journal-title":"Clin. Transl. Sci."},{"key":"10.1016\/j.cosrev.2026.100943_bib0085","doi-asserted-by":"crossref","first-page":"5682","DOI":"10.1021\/acs.jcim.0c00599","article-title":"Generative network complex for the automated generation of drug-like molecules","volume":"60","author":"Gao","year":"2020","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0086","author":"Abeer"},{"key":"10.1016\/j.cosrev.2026.100943_bib0087","doi-asserted-by":"crossref","first-page":"2149","DOI":"10.1021\/acs.jctc.2c01235","article-title":"A perspective on explanations of molecular prediction models","volume":"19","author":"Wellawatte","year":"2023","journal-title":"J. Chem. Theory. Comput."},{"key":"10.1016\/j.cosrev.2026.100943_bib0088","series-title":"Int. Conf. Artif. Intell. Stat.","first-page":"8906","article-title":"Structured multi-task learning for molecular property prediction","author":"Liu","year":"2022"},{"key":"10.1016\/j.cosrev.2026.100943_bib0089","first-page":"1","article-title":"An explainable deep learning platform for molecular discovery","author":"Wong","year":"2024","journal-title":"Nat. Protoc."},{"key":"10.1016\/j.cosrev.2026.100943_bib0090","author":"Born"},{"key":"10.1016\/j.cosrev.2026.100943_bib0091","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1186\/s40364-025-00758-2","article-title":"Integrating artificial intelligence in drug discovery and early drug development: a transformative approach","volume":"13","author":"Ocana","year":"2025","journal-title":"Biomark. Res."},{"key":"10.1016\/j.cosrev.2026.100943_bib0092","series-title":"Int. Conf. Comput. Vis. Image Process","first-page":"278","article-title":"Drug recommendation system for cancer patients using XAI: a traceability perspective","author":"Sahoo","year":"2023"},{"key":"10.1016\/j.cosrev.2026.100943_bib0093","series-title":"Proc. 2018 ACM Int. Conf. Bioinforma. Comput. Biol. Health Inform.","first-page":"559","article-title":"Interpretable machine learning in healthcare","author":"Ahmad","year":"2018"},{"key":"10.1016\/j.cosrev.2026.100943_bib0094","doi-asserted-by":"crossref","first-page":"6799","DOI":"10.1021\/acs.jcim.4c00720","article-title":"SmartCADD: AI-QM empowered drug discovery platform with explainability","volume":"64","author":"Madushanka","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0095","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0305949","article-title":"A comprehensive overview of barriers and strategies for AI implementation in healthcare: mixed-method design","volume":"19","author":"Nair","year":"2024","journal-title":"PLoS. One"},{"key":"10.1016\/j.cosrev.2026.100943_bib0096","doi-asserted-by":"crossref","first-page":"1119","DOI":"10.3390\/pharmaceutics17091119","article-title":"Explainable artificial intelligence: a perspective on drug discovery","volume":"17","author":"Qadri","year":"2025","journal-title":"Pharmaceutics."},{"key":"10.1016\/j.cosrev.2026.100943_bib0097","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1186\/s13321-021-00542-y","article-title":"How can SHAP values help to shape metabolic stability of chemical compounds?","volume":"13","author":"Wojtuch","year":"2021","journal-title":"J. Cheminformatics"},{"key":"10.1016\/j.cosrev.2026.100943_bib0098","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1273\/cbij.25.28","article-title":"Visualization of substructure contributing to metabolic stability using Morgan Fingerprint","volume":"25","author":"Esaki","year":"2025","journal-title":"Chem-Bio Inform. J."},{"key":"10.1016\/j.cosrev.2026.100943_bib0099","doi-asserted-by":"crossref","first-page":"2013","DOI":"10.1007\/s10994-023-06369-y","article-title":"Explainable AI in drug discovery: self-interpretable graph neural network for molecular property prediction using concept whitening","volume":"113","author":"Proietti","year":"2024","journal-title":"Mach. Learn."},{"key":"10.1016\/j.cosrev.2026.100943_bib0100","first-page":"1","article-title":"Simplified, interpretable graph convolutional neural networks for small molecule activity prediction","author":"Weber","year":"2022","journal-title":"J. Comput. Aided. Mol. Des."},{"key":"10.1016\/j.cosrev.2026.100943_bib0101","author":"Shi"},{"key":"10.1016\/j.cosrev.2026.100943_bib0102","author":"Ghaffarzadeh-Esfahani"},{"key":"10.1016\/j.cosrev.2026.100943_bib0103","unstructured":"H. Sturm, J. Teufel, K.A. Isfeld, P. Friederich, R.L. Davis, Mitigating molecular aggregation in drug discovery with predictive insights from explainable AI, (2023). https:\/\/doi.org\/10.48550\/arXiv.2306.02206."},{"key":"10.1016\/j.cosrev.2026.100943_bib0104","doi-asserted-by":"crossref","unstructured":"X. Jiang, A. Margeloiu, N. Simidjievski, M. Jamnik, ProtoGate: prototype-based neural networks with global-to-local feature selection for tabular biomedical data, (2023). https:\/\/doi.org\/10.48550\/ARXIV.2306.12330.","DOI":"10.1609\/aaai.v37i8.26090"},{"key":"10.1016\/j.cosrev.2026.100943_bib0105","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1186\/s12859-022-04760-5","article-title":"Exploring kinase family inhibitors and their moiety preferences using deep SHapley additive exPlanations","volume":"23","author":"Fan","year":"2022","journal-title":"BMC. Bioinformatics."},{"key":"10.1016\/j.cosrev.2026.100943_bib0106","doi-asserted-by":"crossref","unstructured":"K. Pikalyova, T. Akhmetshin, A. Orlov, E.F. Haney, N. Akhoundsadegh, J. You, R.E.W. Hancock, D. Horvath, G. Marcou, A. Cherkasov, A. Varnek, Design of highly potent anti-biofilm, antimicrobial peptides using explainable artificial intelligence, (2024). https:\/\/doi.org\/10.1101\/2024.11.17.622654.","DOI":"10.1101\/2024.11.17.622654"},{"key":"10.1016\/j.cosrev.2026.100943_bib0107","doi-asserted-by":"crossref","unstructured":"H.A. Gandhi, A.D. White, Explaining molecular properties with natural language, (2022). https:\/\/doi.org\/10.26434\/chemrxiv-2022-v5p6m-v3.","DOI":"10.26434\/chemrxiv-2022-v5p6m-v3"},{"key":"10.1016\/j.cosrev.2026.100943_bib0108","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1007\/s10822-020-00310-4","article-title":"Revealing cytotoxic substructures in molecules using deep learning","volume":"34","author":"Webel","year":"2020","journal-title":"J. Comput. Aided. Mol. Des."},{"key":"10.1016\/j.cosrev.2026.100943_bib0109","doi-asserted-by":"crossref","unstructured":"M. Bertolini, L. Zhao, F. Montanari, D.A. Clevert, Enhancing interpretability in molecular property prediction with contextual explanations of molecular graphical depictions, in: D.A. Clevert, M. Wand, K. Malinovsk\u00e1, J. Schmidhuber, I.V. Tetko (Eds.), AI Drug Discov., Springer Nature Switzerland, Cham, 2025: pp. 1\u201312. https:\/\/doi.org\/10.1007\/978-3-031-72381-0_1.","DOI":"10.1007\/978-3-031-72381-0_1"},{"key":"10.1016\/j.cosrev.2026.100943_bib0110","doi-asserted-by":"crossref","DOI":"10.1016\/j.chemolab.2024.105197","article-title":"GA-XGBoost, an explainable AI technique, for analysis of thrombin inhibitory activity of diverse pool of molecules and supported by X-ray","volume":"253","author":"Masand","year":"2024","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"10.1016\/j.cosrev.2026.100943_bib0111","doi-asserted-by":"crossref","first-page":"816","DOI":"10.1039\/D1SC05180F","article-title":"MGraphDTA: deep multiscale graph neural network for explainable drug\u2013target binding affinity prediction","volume":"13","author":"Yang","year":"2022","journal-title":"Chem. Sci."},{"key":"10.1016\/j.cosrev.2026.100943_bib0112","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1038\/s41598-024-83090-3","article-title":"Drug discovery and mechanism prediction with explainable graph neural networks","volume":"15","author":"Wang","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.cosrev.2026.100943_bib0113","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1038\/s41564-024-01907-3","article-title":"Explainable deep learning and virtual evolution identifies antimicrobial peptides with activity against multidrug-resistant human pathogens","volume":"10","author":"Wang","year":"2025","journal-title":"Nat. Microbiol."},{"key":"10.1016\/j.cosrev.2026.100943_bib0114","unstructured":"Y. Inoue, T. Song, X. Wang, A. Luna, T. Fu, DrugAgent: multi-agent large language model-based reasoning for drug-target interaction prediction, (2025). https:\/\/doi.org\/10.48550\/arXiv.2408.13378."},{"key":"10.1016\/j.cosrev.2026.100943_bib0115","doi-asserted-by":"crossref","first-page":"3670","DOI":"10.1021\/acs.jcim.4c00127","article-title":"Interpreting neural network models for toxicity prediction by extracting learned chemical features","volume":"64","author":"Walter","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0116","doi-asserted-by":"crossref","first-page":"3329","DOI":"10.1093\/bioinformatics\/btz111","article-title":"DeepAffinity: interpretable deep learning of compound\u2013protein affinity through unified recurrent and convolutional neural networks","volume":"35","author":"Karimi","year":"2019","journal-title":"Bioinformatics."},{"key":"10.1016\/j.cosrev.2026.100943_bib0117","doi-asserted-by":"crossref","first-page":"2585","DOI":"10.1038\/s41467-023-38192-3","article-title":"Chemistry-intuitive explanation of graph neural networks for molecular property prediction with substructure masking","volume":"14","author":"Wu","year":"2023","journal-title":"Nat. Commun."},{"key":"10.1016\/j.cosrev.2026.100943_bib0118","doi-asserted-by":"crossref","first-page":"8693","DOI":"10.1039\/D2SC02023H","article-title":"Learning size-adaptive molecular substructures for explainable drug\u2013drug interaction prediction by substructure-aware graph neural network","volume":"13","author":"Yang","year":"2022","journal-title":"Chem. Sci."},{"key":"10.1016\/j.cosrev.2026.100943_bib0119","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1021\/acs.jcim.1c01263","article-title":"Interpretation of structure\u2013Activity relationships in real-world drug design data sets using explainable artificial intelligence","volume":"62","author":"Harren","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0120","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1021\/acs.jcim.2c01126","article-title":"TIRESIA: an eXplainable artificial intelligence platform for predicting developmental toxicity","volume":"63","author":"Togo","year":"2023","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0121","doi-asserted-by":"crossref","first-page":"i448","DOI":"10.1093\/bioinformatics\/btad207","article-title":"ArkDTA: attention regularization guided by non-covalent interactions for explainable drug\u2013target binding affinity prediction","volume":"39","author":"Gim","year":"2023","journal-title":"Bioinformatics."},{"key":"10.1016\/j.cosrev.2026.100943_bib0122","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1038\/s41586-023-06887-8","article-title":"Discovery of a structural class of antibiotics with explainable deep learning","volume":"626","author":"Wong","year":"2024","journal-title":"Nature"},{"key":"10.1016\/j.cosrev.2026.100943_bib0123","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1038\/s42004-024-01155-w","article-title":"Enhancing property and activity prediction and interpretation using multiple molecular graph representations with MMGX","volume":"7","author":"Kengkanna","year":"2024","journal-title":"Commun. Chem."},{"key":"10.1016\/j.cosrev.2026.100943_bib0124","doi-asserted-by":"crossref","first-page":"4633","DOI":"10.1021\/acs.jcim.3c00396","article-title":"Interpretable molecular property predictions using marginalized graph kernels","volume":"63","author":"Xiang","year":"2023","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0125","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1021\/acs.jcim.2c01091","article-title":"Combining group-contribution concept and graph neural networks toward interpretable molecular property models","volume":"63","author":"Aouichaoui","year":"2023","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0126","doi-asserted-by":"crossref","first-page":"9551","DOI":"10.1021\/acs.jcim.4c00177","article-title":"SDDSynergy: learning important molecular substructures for explainable anticancer drug synergy prediction","volume":"64","author":"Liu","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0127","doi-asserted-by":"crossref","first-page":"5066","DOI":"10.1021\/acs.jcim.3c00689","article-title":"pBRICS: a novel fragmentation method for explainable property prediction of drug-like small molecules","volume":"63","author":"Vangala","year":"2023","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0128","article-title":"A novel framework based on explainable AI and genetic algorithms for designing neurological medicines","volume":"14","author":"Singh","year":"2024","journal-title":"Sci. Rep."},{"key":"10.1016\/j.cosrev.2026.100943_bib0129","doi-asserted-by":"crossref","first-page":"2854","DOI":"10.1021\/acs.jcim.3c00709","article-title":"AttenSyn: an attention-based deep graph neural network for anticancer synergistic drug combination prediction","volume":"64","author":"Wang","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0130","doi-asserted-by":"crossref","first-page":"2788","DOI":"10.1021\/acs.jcim.2c00297","article-title":"IDL-PPBopt: a strategy for prediction and optimization of Human plasma protein binding of compounds via an interpretable deep learning method","volume":"62","author":"Lou","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0131","doi-asserted-by":"crossref","first-page":"1376","DOI":"10.1021\/acs.jcim.1c01467","article-title":"Unified deep learning model for multitask reaction predictions with explanation","volume":"62","author":"Lu","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0132","doi-asserted-by":"crossref","unstructured":"J. Xie, Y. Ji, L. Zeng, X. Xiao, G. Chen, L. Zhu, J.J. Mondal, J. Chen, E2CB2former: effecitve and explainable transformer for CB2 receptor ligand activity prediction, (2025). https:\/\/doi.org\/10.48550\/arXiv.2502.12186.","DOI":"10.1109\/IJCNN64981.2025.11227988"},{"key":"10.1016\/j.cosrev.2026.100943_bib0133","doi-asserted-by":"crossref","first-page":"4877","DOI":"10.1021\/acs.jcim.1c00519","article-title":"Explainable molecular sets: using information theory to generate meaningful descriptions of groups of molecules","volume":"61","author":"Mater","year":"2021","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0134","doi-asserted-by":"crossref","DOI":"10.1016\/j.ebiom.2023.104767","article-title":"Discovering the mechanism of action of drugs with a sparse explainable network","volume":"95","author":"Sada Del Real","year":"2023","journal-title":"EBioMedicine"},{"key":"10.1016\/j.cosrev.2026.100943_bib0135","doi-asserted-by":"crossref","first-page":"2685","DOI":"10.1021\/acs.jcim.2c00462","article-title":"An In Silico explainable multiparameter optimization approach for De Novo drug design against proteins from the Central nervous system","volume":"62","author":"Bung","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.cosrev.2026.100943_bib0136","unstructured":"Z. Wang, Z. Lin, W. Lin, M. Yang, M. Zeng, K.C. Tan, Explainable molecular property prediction: aligning chemical concepts with predictions via language models, (2024). https:\/\/doi.org\/10.48550\/arXiv.2405.16041."},{"key":"10.1016\/j.cosrev.2026.100943_bib0137","unstructured":"A. Kokate, X. Fern, MOSE-GNN: a motif-based self-explaining graph neural network for molecular property prediction, in: Third Learn. Graphs Conf., n.d."},{"key":"10.1016\/j.cosrev.2026.100943_bib0138","series-title":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","first-page":"5164","article-title":"XplainScreen: unveiling the black box of graph neural network drug screening models with a unified XAI framework","author":"Ahn","year":"2024"},{"key":"10.1016\/j.cosrev.2026.100943_bib0139","series-title":"International Conference Machine Learning","first-page":"1263","article-title":"Neural message passing for quantum chemistry","author":"Gilmer","year":"2017"},{"key":"10.1016\/j.cosrev.2026.100943_bib0140","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13321-020-00479-8","article-title":"Could graph neural networks learn better molecular representation for drug discovery? a comparison study of descriptor-based and graph-based models","volume":"13","author":"Jiang","year":"2021","journal-title":"J. Cheminformatics"},{"key":"10.1016\/j.cosrev.2026.100943_bib0141","author":"Rong"},{"key":"10.1016\/j.cosrev.2026.100943_bib0142","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1038\/s42256-022-00447-x","article-title":"Molecular contrastive learning of representations via graph neural networks","volume":"4","author":"Wang","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.cosrev.2026.100943_bib0143","author":"Fang"},{"key":"10.1016\/j.cosrev.2026.100943_bib0144","series-title":"Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","first-page":"694","article-title":"Transforming classifier scores into accurate multiclass probability estimates","author":"Zadrozny","year":"2002"},{"key":"10.1016\/j.cosrev.2026.100943_bib0145","series-title":"International Conference Machine Learning","first-page":"1321","article-title":"On calibration of modern neural networks","author":"Guo","year":"2017"},{"key":"10.1016\/j.cosrev.2026.100943_bib0146","article-title":"Comparative analysis of batch correction methods for FDG PET\/CT using metabolic radiogenomic data of lung cancer patients","volume":"13","author":"Lee","year":"2023","journal-title":"Sci. Rep."},{"key":"10.1016\/j.cosrev.2026.100943_bib0147","doi-asserted-by":"crossref","first-page":"1251","DOI":"10.1038\/nbt1346","article-title":"The OBO foundry: coordinated evolution of ontologies to support biomedical data integration","volume":"25","author":"Smith","year":"2007","journal-title":"Nat. Biotechnol."},{"key":"10.1016\/j.cosrev.2026.100943_bib0148","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1038\/ng.2764","article-title":"The cancer genome atlas pan-cancer analysis project","volume":"45","author":"Weinstein","year":"2013","journal-title":"Nat. Genet."},{"key":"10.1016\/j.cosrev.2026.100943_bib0149","doi-asserted-by":"crossref","first-page":"648","DOI":"10.3390\/genes16060648","article-title":"A comprehensive review of deep learning applications with multi-omics data in cancer research","volume":"16","author":"Sartori","year":"2025","journal-title":"Genes. (Basel)"},{"key":"10.1016\/j.cosrev.2026.100943_bib0150","series-title":"Proceeding IEEECVF Conference Computer Vision and Pattern Recognition","first-page":"782","article-title":"Transformer interpretability beyond attention visualization","author":"Chefer","year":"2021"},{"key":"10.1016\/j.cosrev.2026.100943_bib0151","article-title":"Knowledge-augmented graph machine learning for drug discovery: a survey","author":"Zhong","year":"2023","journal-title":"ACM. Comput. Surv."},{"key":"10.1016\/j.cosrev.2026.100943_bib0152","doi-asserted-by":"crossref","first-page":"1033","DOI":"10.1038\/s41589-022-01131-2","article-title":"Artificial intelligence foundation for therapeutic science","volume":"18","author":"Huang","year":"2022","journal-title":"Nat. Chem. Biol."},{"key":"10.1016\/j.cosrev.2026.100943_bib0153","author":"Huang"},{"key":"10.1016\/j.cosrev.2026.100943_bib0154","doi-asserted-by":"crossref","first-page":"364","DOI":"10.1038\/s41746-025-01764-2","article-title":"Clinician-informed XAI evaluation checklist with metrics (CLIX-M) for AI-powered clinical decision support systems","volume":"8","author":"Brankovic","year":"2025","journal-title":"NPJ. Digit. Med."},{"key":"10.1016\/j.cosrev.2026.100943_bib0155","series-title":"Causality: Models, Reasoning, and Inference","author":"Pearl","year":"2000"},{"key":"10.1016\/j.cosrev.2026.100943_bib0156","doi-asserted-by":"crossref","first-page":"7345","DOI":"10.1073\/pnas.1510507113","article-title":"Causal inference and the data-fusion problem","volume":"113","author":"Bareinboim","year":"2016","journal-title":"Proc. Natl. Acad. Sci."},{"key":"10.1016\/j.cosrev.2026.100943_bib0157","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.cosrev.2026.100943_bib0158","article-title":"Counterfactual fairness","volume":"30","author":"Kusner","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Computer Science Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1574013726000511?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1574013726000511?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T07:25:06Z","timestamp":1777620306000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1574013726000511"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":158,"alternative-id":["S1574013726000511"],"URL":"https:\/\/doi.org\/10.1016\/j.cosrev.2026.100943","relation":{},"ISSN":["1574-0137"],"issn-type":[{"value":"1574-0137","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Explainable AI methods for drug discovery: A survey of interpretability, metrics and mechanistic insight","name":"articletitle","label":"Article Title"},{"value":"Computer Science Review","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cosrev.2026.100943","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"100943"}}