{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T08:14:23Z","timestamp":1770279263100,"version":"3.49.0"},"reference-count":35,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010909","name":"Young Scientists Fund","doi-asserted-by":"publisher","award":["62006210"],"award-info":[{"award-number":["62006210"]}],"id":[{"id":"10.13039\/501100010909","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Biomedical Informatics"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1016\/j.jbi.2025.104813","type":"journal-article","created":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T11:51:23Z","timestamp":1742644283000},"page":"104813","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["A graph neural network explainability strategy driven by key subgraph connectivity"],"prefix":"10.1016","volume":"165","author":[{"given":"L.N.","family":"Dai","sequence":"first","affiliation":[]},{"given":"D.H.","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Y.F.","family":"Gao","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.jbi.2025.104813_b0005","first-page":"34","article-title":"A review of graph neural networks [J]","volume":"59","author":"Ma","year":"2022","journal-title":"J. Comput. Res. Dev."},{"issue":"06","key":"10.1016\/j.jbi.2025.104813_b0010","first-page":"282","article-title":"A survey of graph neural networks [J]","volume":"51","author":"Hou","year":"2024","journal-title":"Comput. Sci."},{"key":"10.1016\/j.jbi.2025.104813_b0015","unstructured":"N. Tishby, N.C.F. Pereira, W. Bialek, The Information Bottleneck Method [J], CoRR, 2000, Physics\/0004057."},{"key":"10.1016\/j.jbi.2025.104813_b0020","doi-asserted-by":"crossref","unstructured":"N. Tishby, N. Zaslavsky. Deep Learning and the Information Bottleneck Principle [J]. CoRR, 2015, abs\/1503.02406.","DOI":"10.1109\/ITW.2015.7133169"},{"issue":"11","key":"10.1016\/j.jbi.2025.104813_b0025","doi-asserted-by":"crossref","first-page":"216","DOI":"10.21037\/atm.2018.05.32","article-title":"Opening the black box of neural networks: methods for interpreting neural network models in clinical applications [J]","volume":"6","author":"Zhang","year":"2018","journal-title":"Ann. Translat. Med."},{"issue":"09","key":"10.1016\/j.jbi.2025.104813_b0030","first-page":"1","article-title":"A review of deep neural network interpretation methods [J]","volume":"46","author":"Su","year":"2020","journal-title":"Comput. Eng."},{"issue":"11","key":"10.1016\/j.jbi.2025.104813_b0035","first-page":"3588","article-title":"A survey on the explainability of deep learning [J]","volume":"42","author":"Lei","year":"2022","journal-title":"J. Comput. Appl."},{"key":"10.1016\/j.jbi.2025.104813_b0040","unstructured":"F. Baldassarre, H. Azizpour, Explainability techniques for graph convolutional networks [J], CoRR, 2019, abs\/1905.13686."},{"issue":"07","key":"10.1016\/j.jbi.2025.104813_b0045","first-page":"195","article-title":"Grad-CAM-based mask-FGSM adversarial sample attack [J]","volume":"39","author":"Yu","year":"2022","journal-title":"Comput. Appl. Software"},{"key":"10.1016\/j.jbi.2025.104813_b0050","first-page":"9240","article-title":"GNNExplainer: generating explanations for graph neural networks [J]","volume":"32","author":"Ying","year":"2019","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"10.1016\/j.jbi.2025.104813_b0055","first-page":"PP","article-title":"Reinforced causal explainer for graph neural networks [J]","author":"Wang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"10.1016\/j.jbi.2025.104813_b0060","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1017\/S135132491900024X","article-title":"Analyzing and interpreting neural networks for NLP: a report on the first BlackboxNLP workshop [J]","volume":"25","author":"Alishahi","year":"2019","journal-title":"Nat. Lang. Eng."},{"key":"10.1016\/j.jbi.2025.104813_b0065","unstructured":"A. H, S. G, S. Z, et al. A New Concept for Explaining Graph Neural Networks [J]. CEUR Workshop Proceedings, 2021, 2986:1-5."},{"issue":"4","key":"10.1016\/j.jbi.2025.104813_b0070","first-page":"1","article-title":"A review of anomaly detection models based on deep learning","volume":"41","author":"Zhou","year":"2023","journal-title":"J. Civil Aviation Univ. China"},{"issue":"6","key":"10.1016\/j.jbi.2025.104813_b0075","doi-asserted-by":"crossref","first-page":"1889","DOI":"10.1002\/ima.22762","article-title":"Interpretable ensemble deep learning model for early detection of Alzheimer's disease using local interpretable model\u2010agnostic explanations[J]","volume":"32","author":"Atefe","year":"2022","journal-title":"Int. J. Imaging Syst. Technol."},{"issue":"4","key":"10.1016\/j.jbi.2025.104813_b0080","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1007\/s13534-023-00291-x","article-title":"Feasibility of local interpretable model-agnostic explanations (LIME) algorithm as an effective and interpretable feature selection method: comparative fNIRS study [J]","volume":"13","author":"Jaeyoung","year":"2023","journal-title":"Biomed. Eng. Lett."},{"issue":"1","key":"10.1016\/j.jbi.2025.104813_b0085","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1162\/NECO_a_00537","article-title":"High-dimensional feature selection by feature-wise kernelized lasso [J]","volume":"26","author":"Makoto","year":"2014","journal-title":"Neural Comput."},{"key":"10.1016\/j.jbi.2025.104813_b0090","doi-asserted-by":"crossref","DOI":"10.5772\/intechopen.111293","article-title":"Functional relation field: a model-agnostic framework for multivariate time series forecasting [J]","author":"Li","year":"2024","journal-title":"Artif. Intell."},{"key":"10.1016\/j.jbi.2025.104813_b0095","unstructured":"P. Schwab, W. Karlen. CXPlain: Causal Explanations for Model Interpretation under Uncertainty [J], 2019."},{"key":"10.1016\/j.jbi.2025.104813_b0100","unstructured":"M.N. Vu, M.T. Thai, PGM-explainer: probabilistic graphical model explanations for graph neural networks [J], 2020."},{"key":"10.1016\/j.jbi.2025.104813_b0105","unstructured":"Z. Wu, S. Pan, F. Chen, et al., A comprehensive survey on graph neural networks [J], CoRR, 2019, abs\/1901.00596."},{"key":"10.1016\/j.jbi.2025.104813_b0110","unstructured":"N.T. Kipf, M. Welling, Variational graph auto-encoders [J], CoRR, 2016, abs\/1611.07308."},{"key":"10.1016\/j.jbi.2025.104813_b0115","unstructured":"Y. Zhang, P. Tino, A. Leonardis, et al., A survey on neural network interpretability [J], IEEE Trans. Emerg. Top. Computat. Intel 99 (2021) 1-17."},{"key":"10.1016\/j.jbi.2025.104813_b0120","unstructured":"Z. Yu, H. Gao. MotifExplainer: A motif-based graph neural network explainer [J], 2022."},{"issue":"1","key":"10.1016\/j.jbi.2025.104813_b0125","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1021\/jm040835a","article-title":"Derivation and validation of toxicophores for mutagenicity prediction [J]","volume":"48","author":"Kazius","year":"2005","journal-title":"J. Med. Chem."},{"issue":"1","key":"10.1016\/j.jbi.2025.104813_b0130","doi-asserted-by":"crossref","DOI":"10.1038\/s41597-023-01974-x","article-title":"Evaluating explainability for graph neural networks [J]","volume":"10","author":"Agarwal","year":"2023","journal-title":"Sci. Data"},{"issue":"04","key":"10.1016\/j.jbi.2025.104813_b0135","first-page":"5470","article-title":"ASAP: adaptive structure aware pooling for learning hierarchical graph representations [J]","volume":"34","author":"Ranjan","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.jbi.2025.104813_b0140","unstructured":"P.D. Kingma, J. Ba, Adam: A Method for Stochastic Optimization [J], CoRR, 2014, abs\/1412.6980."},{"issue":"09","key":"10.1016\/j.jbi.2025.104813_b0145","first-page":"2444","article-title":"Research progress on learning rate strategies in deep neural networks [J]","volume":"38","author":"Liu","year":"2023","journal-title":"Control and Decision"},{"issue":"13","key":"10.1016\/j.jbi.2025.104813_b0150","first-page":"i457","article-title":"Modeling polypharmacy side effects with graph convolutional networks [J]","volume":"34","author":"Marinka","year":"2018","journal-title":"Bioinformat. (Oxford, England)"},{"issue":"06","key":"10.1016\/j.jbi.2025.104813_b0155","first-page":"122","article-title":"Analysis and Evaluation of smart grid operational state based on graph neural networks [J]","volume":"45","author":"Liu","year":"2024","journal-title":"J. Zhengzhou Univ. (Eng. Edition)"},{"issue":"01","key":"10.1016\/j.jbi.2025.104813_b0160","first-page":"64","article-title":"A survey on classifier evaluation and design based on AUC [J]","volume":"24","author":"Wang","year":"2011","journal-title":"Pattern Recognit. Artif. Intell."},{"key":"10.1016\/j.jbi.2025.104813_b0165","doi-asserted-by":"crossref","unstructured":"P. Li, X. He, D. Song, et al. Improved Categorical Cross-Entropy Loss for Training Deep Neural Networks with Noisy Labels [C], Chinese Conference on Pattern Recognition and Computer Vision (PRCV). Springer, Cham, 2021.","DOI":"10.1007\/978-3-030-88013-2_7"},{"key":"10.1016\/j.jbi.2025.104813_b0170","article-title":"Loss-based estimation with cross-validation","author":"Dudoit","year":"2004","journal-title":"Appl. Microarray Data Analysis and Motif Finding [j]."},{"key":"10.1016\/j.jbi.2025.104813_b0175","unstructured":"Greg Landrum and other RDKit contributors. The RDKit Documentation [EB\/OL]. (2011-08-07). https:\/\/www.rdkit.org\/docs\/."}],"container-title":["Journal of Biomedical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046425000425?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046425000425?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T23:01:13Z","timestamp":1745535673000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1532046425000425"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":35,"alternative-id":["S1532046425000425"],"URL":"https:\/\/doi.org\/10.1016\/j.jbi.2025.104813","relation":{},"ISSN":["1532-0464"],"issn-type":[{"value":"1532-0464","type":"print"}],"subject":[],"published":{"date-parts":[[2025,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A graph neural network explainability strategy driven by key subgraph connectivity","name":"articletitle","label":"Article Title"},{"value":"Journal of Biomedical Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jbi.2025.104813","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104813"}}