{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,19]],"date-time":"2026-11-19T18:24:35Z","timestamp":1795112675505,"version":"4.10.3"},"reference-count":100,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T00:00:00Z","timestamp":1781568000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T00:00:00Z","timestamp":1781740800000},"content-version":"vor","delay-in-days":2,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Commun"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Integrating diverse biomedical modalities is essential for robust healthcare insights, and graph-based models are increasingly used to capture complex relational structures. Yet, their clinical translation hinges on interpretability. This review surveys interpretable graph-based models applied to multimodal biomedical data, highlighting dominant trends in disease classification, static graph construction, and post-hoc explainability. We categorize explainable artificial intelligence (XAI) techniques, benchmark SHAP, saliency, sensitivity, and graph masking on Alzheimer\u2019s disease data, and reveal complementary strengths. A development flowchart and future directions, such as dynamic graphs, knowledge integration, and LLM-based explainability, position this work as a key reference for trustworthy biomedical AI.<\/jats:p>","DOI":"10.1038\/s41467-026-74126-5","type":"journal-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T11:46:22Z","timestamp":1781610382000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Interpretable graph-based models on multimodal biomedical data integration: a technical review and benchmarking"],"prefix":"10.1038","volume":"17","author":[{"given":"Alireza","family":"Sadeghi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farshid","family":"Hajati","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8276-9774","authenticated-orcid":false,"given":"Ahmadreza","family":"Argha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1637-1079","authenticated-orcid":false,"given":"Nigel","family":"H. Lovell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3814-2728","authenticated-orcid":false,"given":"Min","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2189-9153","authenticated-orcid":false,"given":"Hamid","family":"Alinejad-Rokny","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,16]]},"reference":[{"key":"74126_CR1","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1007\/s42979-021-00815-1","volume":"2","author":"IH Sarker","year":"2021","unstructured":"Sarker, I. H. Deep learning: a comprehensive overview on techniques, taxonomy, applications and research directions. SN Comput. Sci. 2, 420 (2021).","journal-title":"SN Comput. Sci."},{"key":"74126_CR2","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.inffus.2022.12.010","volume":"93","author":"A Shoeibi","year":"2023","unstructured":"Shoeibi, A. et al. Diagnosis of brain diseases in fusion of neuroimaging modalities using deep learning: a review. Inf. Fusion 93, 85\u2013117 (2023).","journal-title":"Inf. Fusion"},{"key":"74126_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13073-021-00968-x","volume":"13","author":"KA Tran","year":"2021","unstructured":"Tran, K. A. et al. Deep learning in cancer diagnosis, prognosis and treatment selection. Genome Med. 13, 1\u201317 (2021).","journal-title":"Genome Med."},{"key":"74126_CR4","doi-asserted-by":"publisher","first-page":"5975","DOI":"10.1007\/s10462-022-10306-1","volume":"56","author":"H Askr","year":"2023","unstructured":"Askr, H. et al. Deep learning in drug discovery: an integrative review and future challenges. Artif. Intell. Rev. 56, 5975\u20136037 (2023).","journal-title":"Artif. Intell. Rev."},{"key":"74126_CR5","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1016\/j.jad.2020.11.104","volume":"281","author":"L Squarcina","year":"2021","unstructured":"Squarcina, L., Villa, F. M., Nobile, M., Grisan, E. & Brambilla, P. Deep learning for the prediction of treatment response in depression. J. Affect. Disord. 281, 618\u2013622 (2021).","journal-title":"J. Affect. Disord."},{"key":"74126_CR6","doi-asserted-by":"publisher","first-page":"166","DOI":"10.3389\/fgene.2019.00166","volume":"10","author":"Z Huang","year":"2019","unstructured":"Huang, Z. et al. SALMON: survival analysis learning with multi-omics neural networks on breast cancer. Front. Genet. 10, 166 (2019).","journal-title":"Front. Genet."},{"key":"74126_CR7","doi-asserted-by":"publisher","first-page":"3055","DOI":"10.1093\/bioinformatics\/bty1054","volume":"35","author":"A Singh","year":"2019","unstructured":"Singh, A. et al. DIABLO: an integrative approach for identifying key molecular drivers from multi-omics assays,. Bioinformatics 35, 3055\u20133062 (2019).","journal-title":"Bioinformatics"},{"key":"74126_CR8","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1038\/s41568-021-00408-3","volume":"22","author":"KM Boehm","year":"2022","unstructured":"Boehm, K. M., Khosravi, P., Vanguri, R., Gao, J. & Shah, S. P. Harnessing multimodal data integration to advance precision oncology. Nat. Rev. Cancer 22, 114\u2013126 (2022).","journal-title":"Nat. Rev. Cancer"},{"key":"74126_CR9","doi-asserted-by":"publisher","first-page":"112069","DOI":"10.1016\/j.asoc.2024.112069","volume":"165","author":"H Cui","year":"2024","unstructured":"Cui, H. et al. Evolving graph convolutional network with transformer for CT segmentation. Appl. Soft Comput. 165, 112069 (2024).","journal-title":"Appl. Soft Comput."},{"key":"74126_CR10","doi-asserted-by":"crossref","unstructured":"Cui, H. et al. \u201cCo-graph attention reasoning based imaging and clinical features integration for lymph node metastasis prediction.\u201d In Proc. Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, 657\u2013666 (Springer, 2021).","DOI":"10.1007\/978-3-030-87240-3_63"},{"key":"74126_CR11","doi-asserted-by":"crossref","unstructured":"Liu, M. et al. Exploiting geometric features via hierarchical graph pyramid transformer for cancer diagnosis using histopathological images. IEEE Trans. Med. Imaging 43, 2888\u20132900 (2024).","DOI":"10.1109\/TMI.2024.3381994"},{"key":"74126_CR12","doi-asserted-by":"publisher","first-page":"546","DOI":"10.1109\/TMI.2022.3224660","volume":"42","author":"N Gaggion","year":"2022","unstructured":"Gaggion, N., Mansilla, L., Mosquera, C., Milone, D. H. & Ferrante, E. Improving anatomical plausibility in medical image segmentation via hybrid graph neural networks: applications to chest X-ray analysis. IEEE Trans. Med. Imaging 42, 546\u2013556 (2022).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"74126_CR13","doi-asserted-by":"publisher","first-page":"2839","DOI":"10.1109\/JBHI.2021.3130110","volume":"26","author":"P Xuan","year":"2021","unstructured":"Xuan, P. et al. Graph triple-attention network for disease-related lncRNA prediction. IEEE J. Biomed. Health Inform. 26, 2839\u20132849 (2021).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"74126_CR14","doi-asserted-by":"crossref","unstructured":"Xuan, P. et al. Meta-path semantic and global-local representation learning enhanced graph convolutional model for disease-related miRNA prediction. IEEE J. Biomed. Health Inform. 28, 4306 \u20134316 (2024).","DOI":"10.1109\/JBHI.2024.3397003"},{"key":"74126_CR15","doi-asserted-by":"publisher","first-page":"14211","DOI":"10.3390\/ijms232214211","volume":"23","author":"M La Rosa","year":"2022","unstructured":"La Rosa, M., Fiannaca, A., La Paglia, L. & Urso, A. A graph neural network approach for the analysis of siRNA-target biological networks. Int. J. Mol. Sci. 23, 14211 (2022).","journal-title":"Int. J. Mol. Sci."},{"key":"74126_CR16","doi-asserted-by":"crossref","unstructured":"Loh, H. W. et al. Application of explainable artificial intelligence for healthcare: a systematic review of the last decade (2011\u20132022). Comput. Methods Programs Biomed. 226, 107161 (2022).","DOI":"10.1016\/j.cmpb.2022.107161"},{"key":"74126_CR17","doi-asserted-by":"crossref","unstructured":"Zahedi, R. et al. Deep learning in spatially resolved transcriptomics: a comprehensive technical view. Brief. Bioinform. 25, bbae082 (2024).","DOI":"10.1093\/bib\/bbae082"},{"key":"74126_CR18","doi-asserted-by":"publisher","first-page":"e1010241","DOI":"10.1371\/journal.pcbi.1010241","volume":"18","author":"H Alinejad-Rokny","year":"2022","unstructured":"Alinejad-Rokny, H. et al. MaxHiC: a robust background correction model to identify biologically relevant chromatin interactions in Hi-C and capture Hi-C experiments. PLoS Comput. Biol. 18, e1010241 (2022).","journal-title":"PLoS Comput. Biol."},{"key":"74126_CR19","unstructured":"Xu, K., Hu, W., Leskovec, J. & Jegelka, S. How powerful are graph neural networks? In International Conference on Learning Representations. Available at: https:\/\/openreview.net\/forum?id=ryGs6iA5Km (2019)."},{"key":"74126_CR20","unstructured":"Kipf, T. N. & Welling, M. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations Available at: https:\/\/openreview.net\/forum?id=SJU4ayYgl (2017)."},{"key":"74126_CR21","unstructured":"Veli\u010dkovi\u0107, P. et al. Graph attention networks. In International Conference on Learning Representations. Available at: https:\/\/openreview.net\/forum?id=rJXMpikCZ (2018)."},{"key":"74126_CR22","doi-asserted-by":"publisher","unstructured":"Dwivedi, V. P. & Bresson, X. A generalization of transformer networks to graphs. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2012.09699 (2020).","DOI":"10.48550\/arXiv.2012.09699"},{"key":"74126_CR23","doi-asserted-by":"crossref","unstructured":"Yang, H. et al. Interpretable multimodality embedding of cerebral cortex using attention graph network for identifying bipolar disorder. In Proc.Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2019: 22nd International Conference, 799\u2013807(Springer, 2019).","DOI":"10.1007\/978-3-030-32248-9_89"},{"key":"74126_CR24","doi-asserted-by":"publisher","first-page":"3564","DOI":"10.1109\/TBME.2021.3077875","volume":"68","author":"G Qu","year":"2021","unstructured":"Qu, G. et al. Ensemble manifold regularized multi-modal graph convolutional network for cognitive ability prediction. IEEE Trans. Biomed. Eng. 68, 3564\u20133573 (2021).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"74126_CR25","doi-asserted-by":"crossref","unstructured":"Sebenius, I. et al. Multimodal graph coarsening for interpretable, MRI-based brain graph neural network. In Proc. 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) 1\u20136 (IEEE, 2021).","DOI":"10.1109\/MLSP52302.2021.9690626"},{"key":"74126_CR26","doi-asserted-by":"crossref","unstructured":"Chen, Y. et al. Attention-based node-edge graph convolutional networks for identification of autism spectrum disorder using multi-modal MRI data. In Proc. Pattern Recognition and Computer Vision: 4th Chinese Conference, PRCV 2021,374\u2013385 (Springer, 2021).","DOI":"10.1007\/978-3-030-88010-1_31"},{"key":"74126_CR27","doi-asserted-by":"crossref","unstructured":"Zhou, H., Zhang, Y., Chen, B. Y., Shen, L. & He, L. Sparse interpretation of graph convolutional networks for multi-modal diagnosis of Alzheimer\u2019s disease. In Proc. International Conference on Medical Image Computing and Computer-Assisted Intervention, 469\u2013478 (Springer, 2022).","DOI":"10.1007\/978-3-031-16452-1_45"},{"key":"74126_CR28","doi-asserted-by":"publisher","first-page":"741489","DOI":"10.3389\/fnins.2021.741489","volume":"15","author":"A Safai","year":"2022","unstructured":"Safai, A. et al. Multimodal brain connectomics-based prediction of Parkinson\u2019s disease using graph attention networks. Front. Neurosci. 15, 741489 (2022).","journal-title":"Front. Neurosci."},{"key":"74126_CR29","doi-asserted-by":"publisher","first-page":"bbac137","DOI":"10.1093\/bib\/bbac137","volume":"23","author":"X-a Bi","year":"2022","unstructured":"Bi, X. -a et al. Feature aggregation graph convolutional network based on imaging genetic data for diagnosis and pathogeny identification of Alzheimer\u2019s disease. Brief. Bioinform. 23, bbac137 (2022).","journal-title":"Brief. Bioinform."},{"key":"74126_CR30","doi-asserted-by":"crossref","unstructured":"Kan, X., Kong, Y., Yu, T. & Guo, Y. BraceNet: graph-embedded neural network for brain network analysis. In Proc. 2022 IEEE International Conference on Big Data (Big Data), 4979\u20134987 (IEEE, 2022).","DOI":"10.1109\/BigData55660.2022.10021060"},{"key":"74126_CR31","doi-asserted-by":"crossref","unstructured":"Zhou, H., He, L., Chen, B. Y., Shen, L. & Zhang, Y. Multi-modal diagnosis of Alzheimer\u2019s disease using interpretable graph convolutional networks. IEEE Trans. Med. Imaging 44, 142\u2013153 (2024).","DOI":"10.1109\/TMI.2024.3432531"},{"key":"74126_CR32","doi-asserted-by":"publisher","first-page":"4144","DOI":"10.3390\/app14104144","volume":"14","author":"B Patel","year":"2024","unstructured":"Patel, B. et al. Explainable multimodal graph isomorphism network for interpreting sex differences in adolescent neurodevelopment. Appl. Sci. 14, 4144 (2024).","journal-title":"Appl. Sci."},{"key":"74126_CR33","doi-asserted-by":"publisher","first-page":"103570","DOI":"10.1016\/j.media.2025.103570","volume":"103","author":"G Qu","year":"2025","unstructured":"Qu, G., Zhou, Z., Calhoun, V. D., Zhang, A. & Wang, Y.-P. Integrated brain connectivity analysis with fMRI, DTI, and sMRI powered by interpretable graph neural networks. Med. Image Anal. 103, 103570 (2025).","journal-title":"Med. Image Anal."},{"key":"74126_CR34","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1038\/s42256-021-00325-y","volume":"3","author":"R Schulte-Sasse","year":"2021","unstructured":"Schulte-Sasse, R., Budach, S., Hnisz, D. & Marsico, A. Integration of multiomics data with graph convolutional networks to identify new cancer genes and their associated molecular mechanisms. Nat. Mach. Intell. 3, 513\u2013526 (2021).","journal-title":"Nat. Mach. Intell."},{"key":"74126_CR35","first-page":"100019","volume":"1","author":"L Zhang","year":"2021","unstructured":"Zhang, L. et al. AutoGGN: a gene graph network AutoML tool for multi-omics research. Artif. Intell. Life Sci. 1, 100019 (2021).","journal-title":"Artif. Intell. Life Sci."},{"key":"74126_CR36","doi-asserted-by":"publisher","first-page":"ii120","DOI":"10.1093\/bioinformatics\/btac478","volume":"38","author":"B Pfeifer","year":"2022","unstructured":"Pfeifer, B., Saranti, A. & Holzinger, A. GNN-SubNet: disease subnetwork detection with explainable graph neural networks. Bioinformatics 38, ii120\u2013ii126 (2022).","journal-title":"Bioinformatics"},{"key":"74126_CR37","doi-asserted-by":"publisher","unstructured":"Pfeifer, B., Baniecki, H., Saranti, A., Biecek, P. & Holzinger, A. Graph-guided random forest for gene set selection. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2108.11674 (2021).","DOI":"10.48550\/arXiv.2108.11674"},{"key":"74126_CR38","doi-asserted-by":"crossref","unstructured":"Kaczmarek, E. et al. Multi-omic graph transformers for cancer classification and interpretation. In Pacific Symposium on Biocomputing 2022, 373\u2013384 (World Scientific, 2021).","DOI":"10.1142\/9789811250477_0034"},{"key":"74126_CR39","doi-asserted-by":"crossref","unstructured":"Hou, W. et al. Hybrid graph convolutional network with online masked autoencoder for robust multimodal cancer survival prediction. IEEE Trans. Med. Imaging 42, 2462\u20132473 (2023).","DOI":"10.1109\/TMI.2023.3253760"},{"key":"74126_CR40","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-36559-0","volume":"14","author":"A Ma","year":"2023","unstructured":"Ma, A. et al. Single-cell biological network inference using a heterogeneous graph transformer. Nat. Commun. 14, 964 (2023).","journal-title":"Nat. Commun."},{"key":"74126_CR41","doi-asserted-by":"crossref","unstructured":"Keicher, Matthias, et al. Multimodal graph attention network for COVID-19 outcome prediction. Sci. Rep. 13, 19539 (2023).","DOI":"10.1038\/s41598-023-46625-8"},{"key":"74126_CR42","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-23774-w","volume":"12","author":"T Wang","year":"2021","unstructured":"Wang, T. et al. MOGONET integrates multi-omics data using graph convolutional networks allowing patient classification and biomarker identification. Nat. Commun. 12, 3445 (2021).","journal-title":"Nat. Commun."},{"key":"74126_CR43","doi-asserted-by":"publisher","first-page":"866666","DOI":"10.3389\/fnins.2022.866666","volume":"16","author":"YH Chan","year":"2022","unstructured":"Chan, Y. H., Wang, C., Soh, W. K. & Rajapakse, J. C. Combining neuroimaging and omics datasets for disease classification using graph neural networks. Front. Neurosci. 16, 866666 (2022).","journal-title":"Front. Neurosci."},{"key":"74126_CR44","doi-asserted-by":"publisher","first-page":"806842","DOI":"10.3389\/fgene.2022.806842","volume":"13","author":"X Li","year":"2022","unstructured":"Li, X., Ma, J., Leng, L., Han, M. & Li, M. MoGCN: a multi-omics integration method based on graph convolutional network for cancer subtype analysis,. Front. Genet. 13, 806842 (2022).","journal-title":"Front. Genet."},{"key":"74126_CR45","doi-asserted-by":"crossref","unstructured":"Bintsi, K.-M., Baltatzis, V., Potamias, R. A., Hammers, A. & Rueckert, D. Multimodal brain age estimation using interpretable adaptive population-graph learning. In Proc. International Conference on Medical Image Computing and Computer-Assisted Intervention, 195\u2013204 (Springer, 2023).","DOI":"10.1007\/978-3-031-43993-3_19"},{"key":"74126_CR46","doi-asserted-by":"crossref","unstructured":"Kazi, A., Farghadani, S., Aganj, I., & Navab, N. IA-GCN: interpretable attention based graph convolutional network for disease prediction. In Proc.International Workshop on Machine Learning in Medical Imaging, 382\u2013392 (Springer, 2023).","DOI":"10.1007\/978-3-031-45673-2_38"},{"key":"74126_CR47","doi-asserted-by":"publisher","first-page":"101950","DOI":"10.1016\/j.inffus.2023.101950","volume":"100","author":"X-a Bi","year":"2023","unstructured":"Bi, X. -a et al. Explainable and programmable hypergraph convolutional network for imaging genetics data fusion. Inf. Fusion 100, 101950 (2023).","journal-title":"Inf. Fusion"},{"key":"74126_CR48","doi-asserted-by":"crossref","unstructured":"Xiao, C., Pham, N., Imel, E. & Luo, X. Patient-GAT: sarcopenia prediction using multi-modal data fusion and weighted graph attention networks. In Proc. 38th ACM\/SIGAPP Symposium on Applied Computing, 614\u2013617 (ACM, 2023).","DOI":"10.1145\/3555776.3578731"},{"key":"74126_CR49","doi-asserted-by":"publisher","first-page":"107303","DOI":"10.1016\/j.compbiomed.2023.107303","volume":"164","author":"D Ouyang","year":"2023","unstructured":"Ouyang, D. et al. Integration of multi-omics data using adaptive graph learning and attention mechanism for patient classification and biomarker identification. Comput. Biol. Med. 164, 107303 (2023).","journal-title":"Comput. Biol. Med."},{"key":"74126_CR50","doi-asserted-by":"publisher","first-page":"bbab346","DOI":"10.1093\/bib\/bbab346","volume":"23","author":"Y Li","year":"2022","unstructured":"Li, Y., Qiao, G., Wang, K. & Wang, G. Drug\u2013target interaction predication via multi-channel graph neural networks. Brief. Bioinform. 23, bbab346 (2022).","journal-title":"Brief. Bioinform."},{"key":"74126_CR51","doi-asserted-by":"publisher","first-page":"103213","DOI":"10.1016\/j.media.2024.103213","volume":"97","author":"B Lei","year":"2024","unstructured":"Lei, B. et al. Alzheimer\u2019s disease diagnosis from multi-modal data via feature inductive learning and dual multilevel graph neural network. Med. Image Anal. 97, 103213 (2024).","journal-title":"Med. Image Anal."},{"key":"74126_CR52","first-page":"2071","volume":"27","author":"S Tang","year":"2023","unstructured":"Tang, S. et al. Predicting 30-day all-cause hospital readmission using multimodal spatiotemporal graph neural networks. IEEE J. Biomed. Health Inform. 27, 2071\u20132082 (2023).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"74126_CR53","doi-asserted-by":"crossref","unstructured":"Ribeiro, M. T., Singh, S. & Guestrin, C. Why should I trust you?\u201d Explaining the predictions of any classifier. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1135\u20131144 (ACM, 2016).","DOI":"10.1145\/2939672.2939778"},{"key":"74126_CR54","unstructured":"Petsiuk, V., Das, A. & Saenko, K. RISE: randomized input sampling for explanation of black-box models. In British Machine Vision Conference. Available at: http:\/\/bmvc2018.org\/contents\/papers\/1064.pdf (2018)."},{"key":"74126_CR55","unstructured":"Feng, Q. et al. DEGREE: decomposition based explanation for graph neural networks. In International Conference on Learning Representations Available at: https:\/\/openreview.net\/forum?id=Ve0Wth3ptT_ (2022)."},{"key":"74126_CR56","first-page":"19620","volume":"33","author":"D Luo","year":"2020","unstructured":"Luo, D. et al. Parameterized explainer for graph neural network. Adv. Neural Inf. Process. Syst. 33, 19620\u201319631 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"74126_CR57","first-page":"19810","volume":"35","author":"S Zhang","year":"2022","unstructured":"Zhang, S., Liu, Y., Shah, N. & Sun, Y. GStarX: explaining graph neural networks with structure-aware cooperative games. Adv. Neural Inf. Process. Syst. 35, 19810\u201319823 (2022).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"74126_CR58","first-page":"6733","volume":"34","author":"M Ding","year":"2021","unstructured":"Ding, M. et al. VQ-GNN: a universal framework to scale up graph neural networks using vector quantization. Adv. Neural Inf. Process. Syst. 34, 6733\u20136746 (2021).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"74126_CR59","doi-asserted-by":"crossref","unstructured":"Liu, N. et al. Explainable recommender systems via resolving learning representations. In Proc. 29th ACM International Conference on Information and Knowledge Management, 895\u2013904 (ACM, 2020).","DOI":"10.1145\/3340531.3411919"},{"key":"74126_CR60","unstructured":"Ma, J., Cui, P., Kuang, K. Wang, X. & Zhu, W. Disentangled graph convolutional networks. In Proc. International Conference on Machine Learning, 4212\u20134221 (PMLR, 2019)."},{"key":"74126_CR61","unstructured":"Lundberg, S. M. & Lee, S.-I. A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst. 30, 4765\u20134774 (2017)."},{"key":"74126_CR62","doi-asserted-by":"publisher","unstructured":"Simonyan, K., Vedaldi, A. & Zisserman, A. Deep inside convolutional networks: visualising image classification models and saliency maps. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1312.6034 (2013).","DOI":"10.48550\/arXiv.1312.6034"},{"key":"74126_CR63","doi-asserted-by":"crossref","unstructured":"Pope, P. E., Kolouri, S., Rostami, M., Martin, C. E., & Hoffmann, H. \u201cExplainability methods for graph convolutional neural networks.\u201d In Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 10772\u201310781 (IEEE, 2019).","DOI":"10.1109\/CVPR.2019.01103"},{"key":"74126_CR64","unstructured":"Sundararajan, M., Taly, A. & Yan, Q. Axiomatic attribution for deep networks. In Proc.International Conference on Machine Learning, 3319\u20133328 (PMLR, 2017)."},{"key":"74126_CR65","unstructured":"Garson, D. G. Interpreting neural network connection weights. AI Expert 6, 46\u201351 (1991)."},{"key":"74126_CR66","unstructured":"Adebayo, J. et al. Sanity checks for saliency maps. Adv. Neural Inf. Process. Syst. 31, 9525\u20139536 (2018)."},{"key":"74126_CR67","unstructured":"Shrikumar, A., Greenside, P. & Kundaje, A. Learning important features through propagating activation differences. In Proc. International Conference on Machine Learning, 3145\u22123153 (PMLR, 2017)."},{"key":"74126_CR68","unstructured":"Ying, Z., Bourgeois, D., You, J., Zitnik, M. & Leskovec, J. GNNExplainer: generating explanations for graph neural networks. Adv. Neural Inf. Process. Syst. 32, 9240\u20139251 (2019)."},{"key":"74126_CR69","doi-asserted-by":"publisher","unstructured":"Cangea, C., Veli\u010dkovi\u0107, P., Jovanovi\u0107, N., Kipf, T. & Li\u00f2, P. Towards sparse hierarchical graph classifiers. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1811.01287 (2018).","DOI":"10.48550\/arXiv.1811.01287"},{"key":"74126_CR70","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1517\/14728222.2016.1135132","volume":"20","author":"RJ Hodes","year":"2016","unstructured":"Hodes, R. J. & Buckholtz, N. Accelerating medicines partnership: Alzheimer\u2019s disease (AMP-AD) knowledge portal aids Alzheimer\u2019s drug discovery through open data sharing. Expert Opin. Ther. Targets 20, 389\u2013391 (2016).","journal-title":"Expert Opin. Ther. Targets"},{"key":"74126_CR71","doi-asserted-by":"publisher","first-page":"e12","DOI":"10.1017\/dap.2021.3","volume":"3","author":"A Nesvijevskaia","year":"2021","unstructured":"Nesvijevskaia, A., Ouillade, S., Guilmin, P. & Zucker, J.-D. The accuracy versus interpretability trade-off in fraud detection model. Data Policy 3, e12 (2021).","journal-title":"Data Policy"},{"key":"74126_CR72","doi-asserted-by":"publisher","first-page":"1564","DOI":"10.1109\/TIV.2022.3229682","volume":"8","author":"Z Zhang","year":"2022","unstructured":"Zhang, Z., Tian, R., Sherony, R., Domeyer, J. & Ding, Z. Attention-based interrelation modeling for explainable automated driving,. IEEE Trans. Intell. Veh. 8, 1564\u20131573 (2022).","journal-title":"IEEE Trans. Intell. Veh."},{"key":"74126_CR73","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1002\/prot.26052","volume":"89","author":"C Chen","year":"2021","unstructured":"Chen, C., Wu, T., Guo, Z. & Cheng, J. Combination of deep neural network with attention mechanism enhances the explainability of protein contact prediction. Proteins Struct. Funct. Bioinform. 89, 697\u2013707 (2021).","journal-title":"Proteins Struct. Funct. Bioinform."},{"key":"74126_CR74","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S. & Wolf, L. Generic attention-model explainability for interpreting bi-modal and encoder-decoder transformers. In Proc. IEEE\/CVF International Conference on Computer Vision, 397\u2013406 (IEEE, 2021).","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"74126_CR75","doi-asserted-by":"publisher","first-page":"108391","DOI":"10.1016\/j.asoc.2021.108391","volume":"117","author":"H Hakkoum","year":"2022","unstructured":"Hakkoum, H., Abnane, I. & Idri, A. Interpretability in the medical field: a systematic mapping and review study. Appl. Soft Comput. 117, 108391 (2022).","journal-title":"Appl. Soft Comput."},{"key":"74126_CR76","unstructured":"Prince, S. J. Understanding Deep Learning (MIT Press, 2023)."},{"key":"74126_CR77","doi-asserted-by":"publisher","unstructured":"Rusch, T. K., Bronstein, M. M. & Mishra, S. A survey on oversmoothing in graph neural networks. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2303.10993 (2023).","DOI":"10.48550\/arXiv.2303.10993"},{"key":"74126_CR78","unstructured":"Topping, J., Di Giovanni, F., Chamberlain, B. P., Dong, X. & Bronstein, M. M. Understanding over-squashing and bottlenecks on graphs via curvature. In International Conference on Learning Representations Available at: https:\/\/openreview.net\/forum?id=7UmjRGzp-A (2022)."},{"key":"74126_CR79","doi-asserted-by":"crossref","unstructured":"Bonabi Mobaraki, E. & Khan, A. A demonstration of interpretability methods for graph neural networks. In Proc. 6th Joint Workshop on Graph Data Management Experiences and Systems (GRADES) and Network Data Analytics (NDA), 1\u20135 (ACM, 2023).","DOI":"10.1145\/3594778.3594880"},{"key":"74126_CR80","doi-asserted-by":"crossref","unstructured":"Gu, J., Ye, J., Uddin, A. & Wang, G. DySTAGE: dynamic graph representation learning for asset pricing via spatio-temporal attention and graph encodings. In Proc. 5th ACM International Conference on AI in Finance, 388\u2013396 (ACM, 2024).","DOI":"10.1145\/3677052.3698680"},{"key":"74126_CR81","doi-asserted-by":"publisher","unstructured":"Cakmak, E. J\u00e4ckle D., Schreck T. & Keim, D. dg2pix: Pixel-Based Visual Analysis of Dynamic Graphs. 2020 Visualization in Data Science (VDS), Salt Lake City, UT, USA, pp. 32\u201341, https:\/\/doi.org\/10.1109\/VDS51726.2020.00008 2020.","DOI":"10.1109\/VDS51726.2020.00008"},{"key":"74126_CR82","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-01974-x","volume":"10","author":"C Agarwal","year":"2023","unstructured":"Agarwal, C., Queen, O., Lakkaraju, H. & Zitnik, M. Evaluating explainability for graph neural networks. Sci. Data 10, 144 (2023).","journal-title":"Sci. Data"},{"key":"74126_CR83","first-page":"5782","volume":"45","author":"H Yuan","year":"2022","unstructured":"Yuan, H., Yu, H., Gui, S. & Ji, S. Explainability in graph neural networks: a taxonomic survey,. IEEE Trans. Pattern Anal. Mach. Intell. 45, 5782\u20135799 (2022).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"74126_CR84","unstructured":"Defferrard, M., Bresson, X. & Vandergheynst, P. \u201cConvolutional neural networks on graphs with fast localized spectral filtering.\u201d Adv. Neural Inf. Process. Syst. 29, 3837\u20133845 (2016)."},{"key":"74126_CR85","doi-asserted-by":"publisher","unstructured":"Bo, D. et al. \u201cA survey on spectral graph neural networks.\u201d Preprint at https:\/\/doi.org\/10.48550\/arXiv.2302.05631 (2023).","DOI":"10.48550\/arXiv.2302.05631"},{"key":"74126_CR86","doi-asserted-by":"crossref","unstructured":"R. M. Byrne. \u201cCounterfactuals in explainable artificial intelligence (XAI): evidence from human reasoning.\u201d In Proc. International Joint Conference on Artificial Intelligence, 6276\u20136282 (IJCAI, 2019).","DOI":"10.24963\/ijcai.2019\/876"},{"key":"74126_CR87","doi-asserted-by":"publisher","first-page":"114040","DOI":"10.1016\/j.dss.2023.114040","volume":"176","author":"L Malandri","year":"2024","unstructured":"Malandri, L., Mercorio, F., Mezzanzanica, M. & Seveso, A. Model-contrastive explanations through symbolic reasoning. Decis. Support Syst. 176, 114040 (2024).","journal-title":"Decis. Support Syst."},{"key":"74126_CR88","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00742-2","volume":"5","author":"X Yang","year":"2022","unstructured":"Yang, X. et al. A large language model for electronic health records. NPJ Digit. Med. 5, 194 (2022).","journal-title":"NPJ Digit. Med."},{"key":"74126_CR89","doi-asserted-by":"publisher","unstructured":"Taylor, R. et al. \u201cGalactica: a large language model for science.\u201dPreprint at https:\/\/doi.org\/10.48550\/arXiv.2211.09085 (2022).","DOI":"10.48550\/arXiv.2211.09085"},{"key":"74126_CR90","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","volume":"29","author":"AJ Thirunavukarasu","year":"2023","unstructured":"Thirunavukarasu, A. J. et al. Large language models in medicine. Nat. Med. 29, 1930\u20131940 (2023).","journal-title":"Nat. Med."},{"key":"74126_CR91","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1007\/s11280-024-01297-w","volume":"27","author":"Y Zhu","year":"2024","unstructured":"Zhu, Y. et al. LLMs for knowledge graph construction and reasoning: recent capabilities and future opportunities. World Wide Web 27, 58 (2024).","journal-title":"World Wide Web"},{"key":"74126_CR92","doi-asserted-by":"crossref","unstructured":"Yan, Y., Hou, Y., Xiao, Y., Zhang, R. & Wang, Q. \u201cKNOWNET: guided health information seeking from LLMs via knowledge graph integration.\u201d IEEE Trans. Visualization Comput. Graphics 31, 547\u2013557 (2024).","DOI":"10.1109\/TVCG.2024.3456364"},{"key":"74126_CR93","doi-asserted-by":"publisher","first-page":"e58670","DOI":"10.2196\/58670","volume":"4","author":"Y Gao","year":"2025","unstructured":"Gao, Y. et al. Leveraging medical knowledge graphs into large language models for diagnosis prediction: design and application study. JMIR AI 4, e58670 (2025).","journal-title":"JMIR AI"},{"key":"74126_CR94","unstructured":"He, X. et al. \u201cHarnessing explanations: LLM-to-LM interpreter for enhanced text-attributed graph representation learning.\u201d In International Conference on Learning Representations Available at: https:\/\/openreview.net\/forum?id=RXFVcynVe1 (2024)."},{"key":"74126_CR95","doi-asserted-by":"crossref","unstructured":"Zhang, X. et al. \u201cFrom Redundancy to Relevance: Information Flow in {LVLM}s Across Reasoning Tasks.\u201d In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies Available at: https:\/\/aclanthology.org\/2025.naacl-long.115\/ (2025).","DOI":"10.18653\/v1\/2025.naacl-long.115"},{"key":"74126_CR96","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal, K. et al. Large language models encode clinical knowledge. Nature 620, 172\u2013180 (2023).","journal-title":"Nature"},{"key":"74126_CR97","doi-asserted-by":"publisher","unstructured":"Tamkin, A., Brundage, M., Clark, J. & Ganguli, D. \u201cUnderstanding the capabilities, limitations, and societal impact of large language models.\u201d Preprint at https:\/\/doi.org\/10.48550\/arXiv.2102.02503 (2021).","DOI":"10.48550\/arXiv.2102.02503"},{"key":"74126_CR98","doi-asserted-by":"crossref","unstructured":"Huang, L. et al. \u201cA survey on hallucination in large language models: principles, taxonomy, challenges, and open questions.\u201d ACM Trans. Inf. Syst. 43, 1\u201355 (2025).","DOI":"10.1145\/3703155"},{"key":"74126_CR99","doi-asserted-by":"crossref","unstructured":"Gallegos, I. O. et al. \u201cBias and fairness in large language models: a survey.\u201d Comput. Linguistics 50, 1097\u20131179 (2024).","DOI":"10.1162\/coli_a_00524"},{"key":"74126_CR100","doi-asserted-by":"publisher","first-page":"W130","DOI":"10.1093\/nar\/gkx356","volume":"45","author":"J Wang","year":"2017","unstructured":"Wang, J., Vasaikar, S., Shi, Z., Greer, M. & Zhang, B. WebGestalt 2017: a more comprehensive, powerful, flexible and interactive gene set enrichment analysis toolkit. Nucleic Acids Res. 45, W130\u2013W137 (2017).","journal-title":"Nucleic Acids Res."}],"container-title":["Nature Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-74126-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-74126-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-74126-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T17:05:14Z","timestamp":1781802314000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-74126-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,16]]},"references-count":100,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["74126"],"URL":"https:\/\/doi.org\/10.1038\/s41467-026-74126-5","relation":{},"ISSN":["2041-1723"],"issn-type":[{"value":"2041-1723","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,16]]},"assertion":[{"value":"4 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"5405"}}