{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T02:20:15Z","timestamp":1783131615158,"version":"3.54.6"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,7,22]],"date-time":"2021-07-22T00:00:00Z","timestamp":1626912000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,7,22]],"date-time":"2021-07-22T00:00:00Z","timestamp":1626912000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"the Natural Science Foundation of Guangdong Province of China","award":["2018A030313309"],"award-info":[{"award-number":["2018A030313309"]}]},{"name":"the Natural Science Foundation of Guangdong Province of China","award":["2021A1515011942"],"award-info":[{"award-number":["2021A1515011942"]}]},{"name":"the Innovation fund of introduced high-end scientific research institutions of Zhongshan","award":["2019AG031"],"award-info":[{"award-number":["2019AG031"]}]},{"name":"the Fundamental Research Funds for the Central Universities, SCUT","award":["2019KZ20"],"award-info":[{"award-number":["2019KZ20"]}]},{"name":"the Guangdong Pearl River Talents Plan Innovative and Entrepreneurial Team","award":["2016ZT06S220"],"award-info":[{"award-number":["2016ZT06S220"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Autism spectrum disorders (ASD) imply a spectrum of symptoms rather than a single phenotype. ASD could affect brain connectivity at different degree based on the severity of the symptom. Given their excellent learning capability, graph neural networks (GNN) methods have recently been used to uncover functional connectivity patterns and biological mechanisms in neuropsychiatric disorders, such as ASD. However, there remain challenges to develop an accurate GNN learning model and understand how specific decisions of these graph models are made in brain network analysis.\n<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>In this paper, we propose a graph attention network based learning and interpreting method, namely GAT-LI, which learns to classify functional brain networks of ASD individuals versus healthy controls (HC), and interprets the learned graph model with feature importance. Specifically, GAT-LI includes a graph learning stage and an interpreting stage. First, in the graph learning stage, a new graph attention network model, namely GAT2, uses graph attention layers to learn the node representation, and a novel attention pooling layer to obtain the graph representation for functional brain network classification. We experimentally compared GAT2 model\u2019s performance on the ABIDE I database from 1035 subjects against the classification performances of other well-known models, and the results showed that the GAT2 model achieved the best classification performance. We experimentally compared the influence of different construction methods of brain networks in GAT2 model. We also used a larger synthetic graph dataset with 4000 samples to validate the utility and power of GAT2 model. Second, in the interpreting stage, we used GNNExplainer to interpret learned GAT2 model with feature importance. We experimentally compared GNNExplainer with two well-known interpretation methods including Saliency Map and DeepLIFT to interpret the learned model, and the results showed GNNExplainer achieved the best interpretation performance. We further used the interpretation method to identify the features that contributed most in classifying ASD versus HC.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>We propose a two-stage learning and interpreting method GAT-LI to classify functional brain networks and interpret the feature importance in the graph model. The method should also be useful in the classification and interpretation tasks for graph data from other biomedical scenarios.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12859-021-04295-1","type":"journal-article","created":{"date-parts":[[2021,7,22]],"date-time":"2021-07-22T11:03:04Z","timestamp":1626951784000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":59,"title":["GAT-LI: a graph attention network based learning and interpreting method for functional brain network classification"],"prefix":"10.1186","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3602-7603","authenticated-orcid":false,"given":"Jinlong","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijie","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tenghui","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shoubin","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,7,22]]},"reference":[{"key":"4295_CR1","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1016\/j.mri.2019.05.031","volume":"64","author":"M Khosla","year":"2019","unstructured":"Khosla M, Jamison K, Ngo GH, Kuceyeski A, Sabuncu MR. Machine learning in resting-state fMRI analysis. Magn Reson Imaging. 2019;64:101\u201321.","journal-title":"Magn Reson Imaging"},{"key":"4295_CR2","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.nicl.2017.08.017","volume":"17","author":"A S\u00f3lon","year":"2018","unstructured":"S\u00f3lon A, Rosa A, Craddock RC, Buchweitz A, Meneguzzi F. Identification of autism spectrum disorder using deep learning and the ABIDE dataset. NeuroImage Clin. 2018;17:16\u201323.","journal-title":"NeuroImage Clin"},{"key":"4295_CR3","doi-asserted-by":"publisher","first-page":"460","DOI":"10.3389\/fnins.2017.00460","volume":"11","author":"X Guo","year":"2017","unstructured":"Guo X, Dominick KC, Minai AA, Li H, Erickson CA, Lu LJ. Diagnosing autism spectrum disorder from brain resting-state functional connectivity patterns using a deep neural network with a novel feature selection method. Front Neurosci. 2017;11:460.","journal-title":"Front Neurosci"},{"key":"4295_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3389\/fninf.2019.00070","volume":"13","author":"T Eslami","year":"2019","unstructured":"Eslami T, Mirjalili V, Fong A, Laird A, Saeed F. ASD-DiagNet: a hybrid learning approach for detection of autism spectrum disorder using fMRI data. Front Neuroinform. 2019;13:1\u20138.","journal-title":"Front Neuroinform"},{"key":"4295_CR5","doi-asserted-by":"publisher","first-page":"1394830","DOI":"10.1155\/2020\/1394830","volume":"2020","author":"J Hu","year":"2020","unstructured":"Hu J, Cao L, Li T, Liao B, Dong S, Li P. Interpretable learning approaches in resting-state functional connectivity analysis: the case of autism spectrum disorder. Comput Math Methods Med. 2020;2020:1394830.","journal-title":"Comput Math Methods Med"},{"key":"4295_CR6","doi-asserted-by":"crossref","unstructured":"Li X, Dvornek NC, Zhuang J, Ventola P, Duncan JS. Brain biomarker interpretation in ASD using deep learning and Fmri. In: International conference on medical image computing and computer-assisted intervention. Cham: Springer; 2018. p. 206\u2013214.","DOI":"10.1007\/978-3-030-00931-1_24"},{"key":"4295_CR7","doi-asserted-by":"crossref","unstructured":"Li X, Dvornek NC, Zhou Y, Zhuang J, Ventola P, Duncan JS. Efficient interpretation of deep learning models using graph structure and cooperative game theory: application to asd biomarker discovery. In: International conference on information processing in medical imaging. Cham: Springer; 2019. p. 718\u2013730.","DOI":"10.1007\/978-3-030-20351-1_56"},{"key":"4295_CR8","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1016\/j.neuroimage.2017.12.052","volume":"169","author":"SI Ktena","year":"2018","unstructured":"Ktena SI, Parisot S, Ferrante E, Rajchl M, Lee M, Glocker B, Rueckert D. Metric learning with spectral graph convolutions on brain connectivity networks. Neuroimage. 2018;169:431\u201342.","journal-title":"Neuroimage"},{"key":"4295_CR9","unstructured":"Ma G, Ahmed NK, Willke T, Sengupta D, Cole MW, Turk-Browne NB, Yu PS. Similarity learning with higher-order graph convolutions for brain network analysis. arXiv preprint arXiv:1811.02662 (2018)."},{"key":"4295_CR10","doi-asserted-by":"crossref","unstructured":"Zhang X, Chou J, Wang F. Integrative analysis of patient health records and neuroimages via memory-based graph convolutional network. In: 2018 IEEE International conference on data mining (ICDM). IEEE; 2018. p. 767\u2013776.","DOI":"10.1109\/ICDM.2018.00092"},{"key":"4295_CR11","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-00689-1_1","volume-title":"Graphs in biomedical image analysis and integrating medical imaging and non-imaging modalities","author":"S Arslan","year":"2018","unstructured":"Arslan S, Ktena SI, Glocker B, Rueckert D. Graph saliency maps through spectral convolutional networks: application to sex classification with brain connectivity. In: Stoyanov D, Taylor Z, Ferrante E, Dalca AV, editors. Graphs in biomedical image analysis and integrating medical imaging and non-imaging modalities. Berlin: Springer; 2018. p. 3\u201313."},{"key":"4295_CR12","doi-asserted-by":"crossref","unstructured":"Yang H, Li X, Wu Y, Li S, Lu S, Duncan JS, Gee JC, Gu S. Interpretable multimodality embedding of cerebral cortex using attention graph network for identifying bipolar disorder. In: International conference on medical image computing and computer-assisted intervention. Cham: Springer; 2019. p. 799\u2013807.","DOI":"10.1007\/978-3-030-32248-9_89"},{"key":"4295_CR13","unstructured":"Zhou J, Cui G, Zhang Z, Yang C, Liu Z, Wang L, Li C, Sun M. Graph neural networks: a review of methods and applications. arXiv preprint arXiv:1812.08434 (2018)."},{"key":"4295_CR14","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","volume":"32","author":"Z Wu","year":"2020","unstructured":"Wu Z, Pan S, Chen F, Long G, Zhang C, Philip SY. A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learn Syst. 2020;32:4\u201324.","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"4295_CR15","doi-asserted-by":"crossref","unstructured":"Gopinath K, Desrosiers C, Lombaert H. Learnable pooling in graph convolution networks for brain surface analysis. IEEE Trans Pattern Anal Mach Intell (2020).","DOI":"10.1109\/TPAMI.2020.3028391"},{"key":"4295_CR16","unstructured":"Ying Z, You J, Morris C, Ren X, Hamilton W, Leskovec J. Hierarchical graph representation learning with differentiable pooling. In: Advances in neural information processing systems (NeurIPS 2018); 2018. p. 4800\u20134810."},{"key":"4295_CR17","unstructured":"Veli\u010dkovi\u0107 P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)."},{"key":"4295_CR18","unstructured":"Lee J, Lee I, Kang J. Self-attention graph pooling.\u00a0arXiv preprint arXiv:1904.08082 (2019)."},{"key":"4295_CR19","unstructured":"Ying Z, Bourgeois D, You J, Zitnik M, Leskovec J. Gnnexplainer: generating explanations for graph neural networks. In: Advances in neural information processing systems (NeurIPS 2019); 2019. p. 9240\u20139251."},{"issue":"6","key":"4295_CR20","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1038\/mp.2013.78","volume":"19","author":"A Di Martino","year":"2014","unstructured":"Di Martino A, Yan C-G, Li Q, Denio E, Castellanos FX, Alaerts K, Anderson JS, Assaf M, Bookheimer SY, Dapretto M. The autism brain imaging data exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism. Mol Psychiatry. 2014;19(6):659\u201367.","journal-title":"Mol Psychiatry"},{"key":"4295_CR21","unstructured":"Simonyan K, Vedaldi A, Zisserman A. Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint  arXiv:1312.6034 (2013)."},{"key":"4295_CR22","unstructured":"Shrikumar A, Greenside P, Kundaje A. Learning important features through propagating activation differences. In: International conference on machine learning. PMLR; 2017. p. 3145\u20133153."},{"issue":"3","key":"4295_CR23","doi-asserted-by":"publisher","first-page":"968","DOI":"10.1016\/j.neuroimage.2006.01.021","volume":"31","author":"RS Desikan","year":"2006","unstructured":"Desikan RS, S\u00e9gonne F, Fischl B, Quinn BT, Dickerson BC, Blacker D, Buckner RL, Dale AM, Maguire RP, Hyman BT. An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest. Neuroimage. 2006;31(3):968\u201380.","journal-title":"Neuroimage"},{"key":"4295_CR24","first-page":"10-3389","volume":"42","author":"C Craddock","year":"2013","unstructured":"Craddock C, Sikka S, Cheung B, Khanuja R, Ghosh SS, Yan C, Li Q, Lurie D, Vogelstein J, Burns R. Towards automated analysis of connectomes: the configurable pipeline for the analysis of connectomes (C-PAC). Front Neuroinform. 2013;42:10\u20133389.","journal-title":"Front Neuroinform"},{"key":"4295_CR25","unstructured":"Kipf TN, Welling M. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"issue":"1","key":"4295_CR26","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1006\/nimg.2001.0978","volume":"15","author":"N Tzourio-Mazoyer","year":"2002","unstructured":"Tzourio-Mazoyer N, Landeau B, Papathanassiou D, Crivello F, Etard O, Delcroix N, Mazoyer B, Joliot M. Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain. Neuroimage. 2002;15(1):273\u201389.","journal-title":"Neuroimage"},{"key":"4295_CR27","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1016\/j.neuroimage.2013.03.053","volume":"80","author":"MA de Reus","year":"2013","unstructured":"de Reus MA, Van den Heuvel MP. The parcellation-based connectome: limitations and extensions. Neuroimage. 2013;80:397\u2013404.","journal-title":"Neuroimage"},{"issue":"5","key":"4295_CR28","doi-asserted-by":"publisher","first-page":"1511","DOI":"10.1002\/hbm.20623","volume":"30","author":"J Wang","year":"2009","unstructured":"Wang J, Wang L, Zang Y, Yang H, Tang H, Gong Q, Chen Z, Zhu C, He Y. Parcellation-dependent small-world brain functional networks: a resting-state fMRI study. Hum Brain Mapp. 2009;30(5):1511\u201323.","journal-title":"Hum Brain Mapp"},{"issue":"1","key":"4295_CR29","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1002\/aur.1403","volume":"8","author":"BG Travers","year":"2015","unstructured":"Travers BG, Kana RK, Klinger LG, Klein CL, Klinger MR. Motor learning in individuals with autism spectrum disorder: activation in superior parietal lobule related to learning and repetitive behaviors. Autism Res. 2015;8(1):38\u201351.","journal-title":"Autism Res"},{"issue":"8","key":"4295_CR30","doi-asserted-by":"publisher","first-page":"e617","DOI":"10.1038\/tp.2015.107","volume":"5","author":"CM Urbain","year":"2015","unstructured":"Urbain CM, Pang EW, Taylor MJ. Atypical spatiotemporal signatures of working memory brain processes in autism. Transl Psychiatry. 2015;5(8):e617\u2013e617.","journal-title":"Transl Psychiatry"},{"issue":"6","key":"4295_CR31","doi-asserted-by":"publisher","first-page":"1799","DOI":"10.1093\/brain\/awu083","volume":"137","author":"BA Zielinski","year":"2014","unstructured":"Zielinski BA, Prigge MBD, Nielsen JA, et al. Longitudinal changes in cortical thickness in autism and typical development. Brain. 2014;137(6):1799\u2013812.","journal-title":"Brain"},{"issue":"2","key":"4295_CR32","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/s10803-011-1221-1","volume":"42","author":"GS Dichter","year":"2012","unstructured":"Dichter GS, Richey JA, Rittenberg AM, et al. Reward circuitry function in autism during face anticipation and outcomes. J Autism Dev Disord. 2012;42(2):147\u201360.","journal-title":"J Autism Dev Disord"},{"key":"4295_CR33","first-page":"1","volume":"7","author":"J Dem\u0161ar","year":"2006","unstructured":"Dem\u0161ar J. Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res. 2006;7:1\u201330.","journal-title":"J Mach Learn Res"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-021-04295-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-021-04295-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-021-04295-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,22]],"date-time":"2021-07-22T11:04:16Z","timestamp":1626951856000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-021-04295-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,22]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["4295"],"URL":"https:\/\/doi.org\/10.1186\/s12859-021-04295-1","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,22]]},"assertion":[{"value":"6 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No ethics approval was required for the study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"None of the authors has any competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"379"}}