GAT-LI: a graph attention network based learning and interpreting method for functional brain network classification
Background 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...
Uložené v:
| Vydané v: | BMC bioinformatics Ročník 22; číslo 1; s. 1 - 20 |
|---|---|
| Hlavní autori: | , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
London
BioMed Central
22.07.2021
BioMed Central Ltd Springer Nature B.V BMC |
| Predmet: | |
| ISSN: | 1471-2105, 1471-2105 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Background
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.
Results
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’s 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.
Conclusion
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. |
|---|---|
| AbstractList | Background 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. Results 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’s 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. Conclusion 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. Background 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. Results 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’s 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. Conclusion 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. Background 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. Results 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's 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. Conclusion 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. Keywords: Graph attention networks, Functional brain networks, Resting-state functional connectivity data, Classification, Model interpretation 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.BACKGROUNDAutism 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.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's 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.RESULTSIn 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's 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.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.CONCLUSIONWe 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. Abstract Background 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. Results 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’s 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. Conclusion 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. 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. 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's 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. 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. |
| ArticleNumber | 379 |
| Audience | Academic |
| Author | Li, Tenghui Cao, Lijie Dong, Shoubin Hu, Jinlong Li, Ping |
| Author_xml | – sequence: 1 givenname: Jinlong orcidid: 0000-0003-3602-7603 surname: Hu fullname: Hu, Jinlong email: jlhu@scut.edu.cn organization: Guangdong Key Lab of Communication and Computer Network, School of Computer Science and Engineering, South China University of Technology, Zhongshan Institute of Modern Industrial Technology, South China University of Technology – sequence: 2 givenname: Lijie surname: Cao fullname: Cao, Lijie organization: Guangdong Key Lab of Communication and Computer Network, School of Computer Science and Engineering, South China University of Technology – sequence: 3 givenname: Tenghui surname: Li fullname: Li, Tenghui organization: Guangdong Key Lab of Communication and Computer Network, School of Computer Science and Engineering, South China University of Technology – sequence: 4 givenname: Shoubin surname: Dong fullname: Dong, Shoubin organization: Guangdong Key Lab of Communication and Computer Network, School of Computer Science and Engineering, South China University of Technology, Zhongshan Institute of Modern Industrial Technology, South China University of Technology – sequence: 5 givenname: Ping surname: Li fullname: Li, Ping organization: Department of Chinese and Bilingual Studies, Faculty of Humanities, The Hong Kong Polytechnic University |
| BookMark | eNp9kktv1DAUhSNURB_wB1hFYgOLFNuJY4cF0qiCMtJISFDW1o0fGZeMPdhOgX-PM1M0TIUqL2xdf-dc-fqcFyfOO10ULzG6xJi3byMmnHYVIrhCDelohZ8UZ7hhuCIY0ZN_zqfFeYy3CGHGEX1WnNYZb1DDzop0vbipVst3JZRDgO26hJS0S9a70un004fvZQ9Rq3LUEJx1QwlOldYlHbZBp7mw0WntVWl8KM3k5KyFsewD2IOHHCFGa6yE-fp58dTAGPWL-_2i-Pbxw83Vp2r1-Xp5tVhVssU8VbwHgxQFw8AopFXNkKR9p0iPpWR1oyQG2irGaU96gyUC0lIkGaUNMW3P6otiufdVHm7FNtgNhN_CgxW7gg-DgJCsHLVAXU8bClITMA2m0EnEGiK54rrXmqDs9X7vtZ36jVYyDynAeGR6fOPsWgz-TnDStazh2eD1vUHwPyYdk9jYKPU4gtN-ioJQSjGqKaYZffUAvfVTyFOdqZbkz6tpfaAGyA-wzvjcV86mYtEyUjeU8Jm6_A-Vl9IbK3OgjM31I8GbI0Fmkv6VBphiFMuvX45Zvmdl8DEGbYS0affFuYkdBUZiTqrYJ1XkpIpdUgXOUvJA-neUj4rqvShm2A06HAbziOoPJjz75g |
| CitedBy_id | crossref_primary_10_1016_j_neuroimage_2025_121422 crossref_primary_10_3390_brainsci13111578 crossref_primary_10_1016_j_neubiorev_2022_105021 crossref_primary_10_1016_j_chemolab_2022_104713 crossref_primary_10_1016_j_ejro_2023_100495 crossref_primary_10_1001_jamanetworkopen_2023_1671 crossref_primary_10_1016_j_cmpb_2025_108982 crossref_primary_10_1016_j_media_2025_103509 crossref_primary_10_1007_s12264_025_01385_5 crossref_primary_10_1016_j_compbiomed_2023_107667 crossref_primary_10_1016_j_eswa_2025_128240 crossref_primary_10_1109_ACCESS_2024_3466179 crossref_primary_10_1109_TNSRE_2024_3434343 crossref_primary_10_3390_ijms231810220 crossref_primary_10_1016_j_ibmed_2025_100288 crossref_primary_10_1016_j_jpsychires_2025_01_001 crossref_primary_10_3390_s23249647 crossref_primary_10_1038_s41398_024_03024_5 crossref_primary_10_1109_ACCESS_2025_3558752 crossref_primary_10_1016_j_cmpb_2023_107913 crossref_primary_10_1109_ACCESS_2025_3601649 crossref_primary_10_3390_fi16090318 crossref_primary_10_3390_brainsci12070883 crossref_primary_10_3390_brainsci15010017 crossref_primary_10_1007_s42235_025_00754_0 crossref_primary_10_3389_fnagi_2022_948704 crossref_primary_10_1007_s10462_024_10918_9 crossref_primary_10_1109_TMI_2023_3274351 crossref_primary_10_1016_j_media_2022_102665 crossref_primary_10_31083_j_jin2307135 |
| Cites_doi | 10.1016/j.neuroimage.2017.12.052 10.1093/brain/awu083 10.1109/ICDM.2018.00092 10.1038/tp.2015.107 10.1016/j.nicl.2017.08.017 10.1007/978-3-030-32248-9_89 10.1016/j.neuroimage.2006.01.021 10.1007/978-3-030-00689-1_1 10.1002/hbm.20623 10.3389/fnins.2017.00460 10.1006/nimg.2001.0978 10.1016/j.neuroimage.2013.03.053 10.1002/aur.1403 10.3389/fninf.2019.00070 10.1007/978-3-030-20351-1_56 10.1038/mp.2013.78 10.1109/TNNLS.2020.2978386 10.1109/TPAMI.2020.3028391 10.1007/s10803-011-1221-1 10.1007/978-3-030-00931-1_24 10.1016/j.mri.2019.05.031 10.1155/2020/1394830 |
| ContentType | Journal Article |
| Copyright | The Author(s) 2021 COPYRIGHT 2021 BioMed Central Ltd. 2021. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. 2021. The Author(s). |
| Copyright_xml | – notice: The Author(s) 2021 – notice: COPYRIGHT 2021 BioMed Central Ltd. – notice: 2021. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: 2021. The Author(s). |
| DBID | C6C AAYXX CITATION ISR 3V. 7QO 7SC 7X7 7XB 88E 8AL 8AO 8FD 8FE 8FG 8FH 8FI 8FJ 8FK ABUWG AEUYN AFKRA ARAPS AZQEC BBNVY BENPR BGLVJ BHPHI CCPQU DWQXO FR3 FYUFA GHDGH GNUQQ HCIFZ JQ2 K7- K9. L7M LK8 L~C L~D M0N M0S M1P M7P P5Z P62 P64 PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQGLB PQQKQ PQUKI Q9U 7X8 5PM DOA |
| DOI | 10.1186/s12859-021-04295-1 |
| DatabaseName | Springer Nature OA Free Journals CrossRef Gale In Context: Science ProQuest Central (Corporate) Biotechnology Research Abstracts Computer and Information Systems Abstracts Health & Medical Collection ProQuest Central (purchase pre-March 2016) Medical Database (Alumni Edition) Computing Database (Alumni Edition) ProQuest Pharma Collection Technology Research Database ProQuest SciTech Collection ProQuest Technology Collection ProQuest Natural Science Collection Hospital Premium Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest One Sustainability (subscription) ProQuest Central UK/Ireland Advanced Technologies & Computer Science Collection ProQuest Central Essentials - QC Biological Science Collection ProQuest Central Technology Collection Natural Science Collection ProQuest One Community College ProQuest Central Engineering Research Database Proquest Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Central Student SciTech Premium Collection ProQuest Computer Science Collection Computer Science Database ProQuest Health & Medical Complete (Alumni) Advanced Technologies Database with Aerospace Biological Sciences Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Computing Database Health & Medical Collection (Alumni) Medical Database Biological Science Database Advanced Technologies & Aerospace Database ProQuest Advanced Technologies & Aerospace Collection Biotechnology and BioEngineering Abstracts ProQuest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central Basic MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef Publicly Available Content Database Computer Science Database ProQuest Central Student ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Computer Science Collection Computer and Information Systems Abstracts SciTech Premium Collection ProQuest One Applied & Life Sciences ProQuest One Sustainability Health Research Premium Collection Natural Science Collection Health & Medical Research Collection Biological Science Collection ProQuest Central (New) ProQuest Medical Library (Alumni) Advanced Technologies & Aerospace Collection ProQuest Biological Science Collection ProQuest One Academic Eastern Edition ProQuest Hospital Collection ProQuest Technology Collection Health Research Premium Collection (Alumni) Biological Science Database ProQuest Hospital Collection (Alumni) Biotechnology and BioEngineering Abstracts ProQuest Health & Medical Complete ProQuest One Academic UKI Edition Engineering Research Database ProQuest One Academic ProQuest One Academic (New) Technology Collection Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest One Academic Middle East (New) ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest One Health & Nursing ProQuest Natural Science Collection ProQuest Pharma Collection ProQuest Central ProQuest Health & Medical Research Collection Biotechnology Research Abstracts Health and Medicine Complete (Alumni Edition) ProQuest Central Korea Advanced Technologies Database with Aerospace ProQuest Computing ProQuest Central Basic ProQuest Computing (Alumni Edition) ProQuest SciTech Collection Computer and Information Systems Abstracts Professional Advanced Technologies & Aerospace Database ProQuest Medical Library ProQuest Central (Alumni) MEDLINE - Academic |
| DatabaseTitleList | Publicly Available Content Database MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Biology |
| EISSN | 1471-2105 |
| EndPage | 20 |
| ExternalDocumentID | oai_doaj_org_article_09b545ace2af415a9c0742c8d8ebee20 PMC8296748 A672345283 10_1186_s12859_021_04295_1 |
| GeographicLocations | China |
| GeographicLocations_xml | – name: China |
| GrantInformation_xml | – fundername: the Guangdong Pearl River Talents Plan Innovative and Entrepreneurial Team grantid: 2016ZT06S220 – fundername: the Natural Science Foundation of Guangdong Province of China grantid: 2018A030313309; 2021A1515011942 – fundername: the Fundamental Research Funds for the Central Universities, SCUT grantid: 2019KZ20 – fundername: the Innovation fund of introduced high-end scientific research institutions of Zhongshan grantid: 2019AG031 – fundername: ; grantid: 2018A030313309; 2021A1515011942 – fundername: ; grantid: 2016ZT06S220 – fundername: ; grantid: 2019AG031 – fundername: ; grantid: 2019KZ20 |
| GroupedDBID | --- 0R~ 23N 2WC 53G 5VS 6J9 7X7 88E 8AO 8FE 8FG 8FH 8FI 8FJ AAFWJ AAJSJ AAKPC AASML ABDBF ABUWG ACGFO ACGFS ACIHN ACIWK ACPRK ACUHS ADBBV ADMLS ADUKV AEAQA AENEX AEUYN AFKRA AFPKN AFRAH AHBYD AHMBA AHYZX ALMA_UNASSIGNED_HOLDINGS AMKLP AMTXH AOIJS ARAPS AZQEC BAPOH BAWUL BBNVY BCNDV BENPR BFQNJ BGLVJ BHPHI BMC BPHCQ BVXVI C6C CCPQU CS3 DIK DU5 DWQXO E3Z EAD EAP EAS EBD EBLON EBS EMB EMK EMOBN ESX F5P FYUFA GNUQQ GROUPED_DOAJ GX1 HCIFZ HMCUK HYE IAO ICD IHR INH INR ISR ITC K6V K7- KQ8 LK8 M1P M48 M7P MK~ ML0 M~E O5R O5S OK1 OVT P2P P62 PGMZT PHGZM PHGZT PIMPY PJZUB PPXIY PQGLB PQQKQ PROAC PSQYO PUEGO RBZ RNS ROL RPM RSV SBL SOJ SV3 TR2 TUS UKHRP W2D WOQ WOW XH6 XSB AAYXX AFFHD CITATION 3V. 7QO 7SC 7XB 8AL 8FD 8FK FR3 JQ2 K9. L7M L~C L~D M0N P64 PKEHL PQEST PQUKI Q9U 7X8 5PM |
| ID | FETCH-LOGICAL-c618t-8baf0d5af7afd0ed370c5b9d2b1cc734dc1a56d785b2bf1c0a2650c75542f6b73 |
| IEDL.DBID | RSV |
| ISICitedReferencesCount | 40 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000680421000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1471-2105 |
| IngestDate | Fri Oct 03 12:52:33 EDT 2025 Tue Nov 04 02:01:01 EST 2025 Sun Nov 09 10:38:43 EST 2025 Tue Oct 07 05:11:31 EDT 2025 Tue Nov 11 10:23:43 EST 2025 Tue Nov 04 17:52:27 EST 2025 Thu Nov 13 14:38:03 EST 2025 Sat Nov 29 05:40:10 EST 2025 Tue Nov 18 21:50:33 EST 2025 Sat Sep 06 07:27:36 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Keywords | Graph attention networks Model interpretation Functional brain networks Resting-state functional connectivity data Classification |
| Language | English |
| License | Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated in a credit line to the data. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c618t-8baf0d5af7afd0ed370c5b9d2b1cc734dc1a56d785b2bf1c0a2650c75542f6b73 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0003-3602-7603 |
| OpenAccessLink | https://link.springer.com/10.1186/s12859-021-04295-1 |
| PMID | 34294047 |
| PQID | 2562429353 |
| PQPubID | 44065 |
| PageCount | 20 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_09b545ace2af415a9c0742c8d8ebee20 pubmedcentral_primary_oai_pubmedcentral_nih_gov_8296748 proquest_miscellaneous_2555103515 proquest_journals_2562429353 gale_infotracmisc_A672345283 gale_infotracacademiconefile_A672345283 gale_incontextgauss_ISR_A672345283 crossref_citationtrail_10_1186_s12859_021_04295_1 crossref_primary_10_1186_s12859_021_04295_1 springer_journals_10_1186_s12859_021_04295_1 |
| PublicationCentury | 2000 |
| PublicationDate | 2021-07-22 |
| PublicationDateYYYYMMDD | 2021-07-22 |
| PublicationDate_xml | – month: 07 year: 2021 text: 2021-07-22 day: 22 |
| PublicationDecade | 2020 |
| PublicationPlace | London |
| PublicationPlace_xml | – name: London |
| PublicationTitle | BMC bioinformatics |
| PublicationTitleAbbrev | BMC Bioinformatics |
| PublicationYear | 2021 |
| Publisher | BioMed Central BioMed Central Ltd Springer Nature B.V BMC |
| Publisher_xml | – name: BioMed Central – name: BioMed Central Ltd – name: Springer Nature B.V – name: BMC |
| References | GS Dichter (4295_CR32) 2012; 42 MA de Reus (4295_CR27) 2013; 80 RS Desikan (4295_CR23) 2006; 31 M Khosla (4295_CR1) 2019; 64 4295_CR9 4295_CR7 4295_CR6 C Craddock (4295_CR24) 2013; 42 S Arslan (4295_CR11) 2018 CM Urbain (4295_CR30) 2015; 5 X Guo (4295_CR3) 2017; 11 4295_CR25 4295_CR22 BG Travers (4295_CR29) 2015; 8 A Sólon (4295_CR2) 2018; 17 4295_CR21 Z Wu (4295_CR14) 2020; 32 J Wang (4295_CR28) 2009; 30 J Hu (4295_CR5) 2020; 2020 T Eslami (4295_CR4) 2019; 13 N Tzourio-Mazoyer (4295_CR26) 2002; 15 A Di Martino (4295_CR20) 2014; 19 BA Zielinski (4295_CR31) 2014; 137 J Demšar (4295_CR33) 2006; 7 SI Ktena (4295_CR8) 2018; 169 4295_CR19 4295_CR18 4295_CR17 4295_CR16 4295_CR15 4295_CR13 4295_CR12 4295_CR10 |
| References_xml | – volume: 42 start-page: 10-3389 year: 2013 ident: 4295_CR24 publication-title: Front Neuroinform – ident: 4295_CR21 – volume: 169 start-page: 431 year: 2018 ident: 4295_CR8 publication-title: Neuroimage doi: 10.1016/j.neuroimage.2017.12.052 – volume: 137 start-page: 1799 issue: 6 year: 2014 ident: 4295_CR31 publication-title: Brain doi: 10.1093/brain/awu083 – ident: 4295_CR10 doi: 10.1109/ICDM.2018.00092 – volume: 5 start-page: e617 issue: 8 year: 2015 ident: 4295_CR30 publication-title: Transl Psychiatry doi: 10.1038/tp.2015.107 – volume: 17 start-page: 16 year: 2018 ident: 4295_CR2 publication-title: NeuroImage Clin doi: 10.1016/j.nicl.2017.08.017 – ident: 4295_CR12 doi: 10.1007/978-3-030-32248-9_89 – volume: 31 start-page: 968 issue: 3 year: 2006 ident: 4295_CR23 publication-title: Neuroimage doi: 10.1016/j.neuroimage.2006.01.021 – start-page: 3 volume-title: Graphs in biomedical image analysis and integrating medical imaging and non-imaging modalities year: 2018 ident: 4295_CR11 doi: 10.1007/978-3-030-00689-1_1 – ident: 4295_CR13 – ident: 4295_CR17 – ident: 4295_CR19 – volume: 30 start-page: 1511 issue: 5 year: 2009 ident: 4295_CR28 publication-title: Hum Brain Mapp doi: 10.1002/hbm.20623 – volume: 11 start-page: 460 year: 2017 ident: 4295_CR3 publication-title: Front Neurosci doi: 10.3389/fnins.2017.00460 – volume: 15 start-page: 273 issue: 1 year: 2002 ident: 4295_CR26 publication-title: Neuroimage doi: 10.1006/nimg.2001.0978 – volume: 80 start-page: 397 year: 2013 ident: 4295_CR27 publication-title: Neuroimage doi: 10.1016/j.neuroimage.2013.03.053 – ident: 4295_CR9 – ident: 4295_CR22 – volume: 8 start-page: 38 issue: 1 year: 2015 ident: 4295_CR29 publication-title: Autism Res doi: 10.1002/aur.1403 – volume: 7 start-page: 1 year: 2006 ident: 4295_CR33 publication-title: J Mach Learn Res – volume: 13 start-page: 1 year: 2019 ident: 4295_CR4 publication-title: Front Neuroinform doi: 10.3389/fninf.2019.00070 – ident: 4295_CR7 doi: 10.1007/978-3-030-20351-1_56 – volume: 19 start-page: 659 issue: 6 year: 2014 ident: 4295_CR20 publication-title: Mol Psychiatry doi: 10.1038/mp.2013.78 – ident: 4295_CR16 – volume: 32 start-page: 4 year: 2020 ident: 4295_CR14 publication-title: IEEE Trans Neural Netw Learn Syst doi: 10.1109/TNNLS.2020.2978386 – ident: 4295_CR18 – ident: 4295_CR15 doi: 10.1109/TPAMI.2020.3028391 – volume: 42 start-page: 147 issue: 2 year: 2012 ident: 4295_CR32 publication-title: J Autism Dev Disord doi: 10.1007/s10803-011-1221-1 – ident: 4295_CR6 doi: 10.1007/978-3-030-00931-1_24 – ident: 4295_CR25 – volume: 64 start-page: 101 year: 2019 ident: 4295_CR1 publication-title: Magn Reson Imaging doi: 10.1016/j.mri.2019.05.031 – volume: 2020 start-page: 1394830 year: 2020 ident: 4295_CR5 publication-title: Comput Math Methods Med doi: 10.1155/2020/1394830 |
| SSID | ssj0017805 |
| Score | 2.561153 |
| Snippet | Background
Autism spectrum disorders (ASD) imply a spectrum of symptoms rather than a single phenotype. ASD could affect brain connectivity at different degree... Autism spectrum disorders (ASD) imply a spectrum of symptoms rather than a single phenotype. ASD could affect brain connectivity at different degree based on... Background Autism spectrum disorders (ASD) imply a spectrum of symptoms rather than a single phenotype. ASD could affect brain connectivity at different degree... Abstract Background Autism spectrum disorders (ASD) imply a spectrum of symptoms rather than a single phenotype. ASD could affect brain connectivity at... |
| SourceID | doaj pubmedcentral proquest gale crossref springer |
| SourceType | Open Website Open Access Repository Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 1 |
| SubjectTerms | Algorithms Analysis Autism Bioinformatics Biomedical and Life Sciences Biomedical data Brain Classification Computational Biology/Bioinformatics Computer Appl. in Life Sciences Construction methods Decision analysis Deep learning Disorders Functional brain networks Graph attention networks Graph neural networks Graph representations Graph theory Graphical representations Health aspects Identification methods Learning Life Sciences Machine learning Machine Learning and Artificial Intelligence in Bioinformatics Mental disorders Methodology Methodology Article Methods Microarrays Model interpretation Network analysis Neural networks Phenotypes Resting-state functional connectivity data Signs and symptoms Time series |
| SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3fi9QwEA5yKPgi_sSe5xFF8EHDtUnbpPe2iqcHcoiecG8hP88F6R7XXcH_3pmkXa2H-uJrM223mUnmm-30-wh5FjqvlLclg2wdWW2NZR0204gW0HGncIc0SWxCnpyos7Puwy9SX9gTlumB88QdlJ2FJG9QtypCsjGdw2rOKa_g9oGnah1Qz1RMje8PkKl_-kRGtQdDhTxtDNsRcANuWDVLQ4mt_-qefLVP8reXpSkHHd0mt0bwSBf5R98h10J_l9zIcpLf75H128Upe398SA1NPNQUuTNTNyPtc7c3xaTl6SgVcU5N7-lyajvEA1lQmgKSpZjx8h-F1KKOxPYaDgE3dhglp94nn4_enL5-x0ZVBebaSq2ZsiaWvjFRmujL4IUsXWM7z23lnBS1d5VpWi9VY7mNlSsNBxTnJOAOHlsrxQOy06_68JBQgFrBmmBrG33dOoHFV1CmEbaOcBlRkGqaZO1GynFUvviqU-mhWp0do8ExOjlGVwV5sT3nIhNu_NX6Ffpua4lk2ekAhJAeQ0j_K4QK8hQ9r5EOo8d-m3OzGQZ9_OmjXrSSixoJcAryfDSKK3gGZ8bPF2AmkEFrZrk3s4T16ubDU4Dpcb8YNABPwEqdaGD4yXYYz8QeuD6sNmjTIP0hANCCyFlgzh5_PtIvvyTOcMU7lJUpyMsphH_e_M_Tu_s_pvcRucnTypOM8z2ys77chMfkuvu2Xg6X-2nd_gCIT0eK priority: 102 providerName: Directory of Open Access Journals – databaseName: Computer Science Database dbid: K7- link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Li9UwFA46KrjxPVgdJYrgQsM0SdukbuQqjg7KIDrC7EIezfWCtOPtvYL_3pw07VAHZ-O2OX2k59nk9PsQetbUTkpnchKytSeF0YbU0EzDq1Ad1xIipI5kE-LoSJ6c1J_Tgluf2irHmBgDtessrJHvh9QcsknNS_769CcB1ijYXU0UGpfRFcoYBTv_KMi0iwB4_eOPMrLa7ymgtRFoSoAwXBI6S0YRs_98ZD7fLfnXlmnMRAc3_3cOt9CNVIPixWA0t9Glpr2Drg2slL_vos37xTH5dPgKaxzhrDFAcMamSNwOTeMYcp_DiXFiiXXr8GrsXoQDAy81DgUxhsQ5rDdiA3QU0zUs1O3QqBRt4x76dvDu-O0HksgZiK2o3BBptM9dqb3Q3uWN4yK3pakdM9RawQtnqS4rJ2RpmPHU5pqFYtCKUL4wXxnBd9FO27XNfYRDxdYY3ZjCeFdUlsM3XCN1yU3hw2V4huioJWUTcjkQaPxQ8QtGVmrQrAqaVVGzimboxXTO6YDbcaH0G1D-JAmY2_FAt16q5MIqr00oNzUwqPlQ9ujawrqClU4GR2hYnqGnYDoKUDVaaNtZ6m3fq8OvX9SiEowXgKOToedJyHdhDlanvyDCmwAgrpnk3kwyuL2dD482plLY6dWZgWXoyTQMZ0IrXdt0W5ApAUUx1LEZEjPLnk1_PtKuvkfocclqYKfJ0MvRB85u_u_X--DiZ32IrrPolIIwtod2Nutt8whdtb82q379OLr0H-wwVI0 priority: 102 providerName: ProQuest |
| Title | GAT-LI: a graph attention network based learning and interpreting method for functional brain network classification |
| URI | https://link.springer.com/article/10.1186/s12859-021-04295-1 https://www.proquest.com/docview/2562429353 https://www.proquest.com/docview/2555103515 https://pubmed.ncbi.nlm.nih.gov/PMC8296748 https://doaj.org/article/09b545ace2af415a9c0742c8d8ebee20 |
| Volume | 22 |
| WOSCitedRecordID | wos000680421000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVADU databaseName: BioMed Central Open Access Free customDbUrl: eissn: 1471-2105 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017805 issn: 1471-2105 databaseCode: RBZ dateStart: 20000101 isFulltext: true titleUrlDefault: https://www.biomedcentral.com/search/ providerName: BioMedCentral – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1471-2105 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017805 issn: 1471-2105 databaseCode: DOA dateStart: 20000101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 1471-2105 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017805 issn: 1471-2105 databaseCode: M~E dateStart: 20000101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Advanced Technologies & Aerospace Database customDbUrl: eissn: 1471-2105 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017805 issn: 1471-2105 databaseCode: P5Z dateStart: 20090101 isFulltext: true titleUrlDefault: https://search.proquest.com/hightechjournals providerName: ProQuest – providerCode: PRVPQU databaseName: Biological Science Database customDbUrl: eissn: 1471-2105 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017805 issn: 1471-2105 databaseCode: M7P dateStart: 20090101 isFulltext: true titleUrlDefault: http://search.proquest.com/biologicalscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: Computer Science Database customDbUrl: eissn: 1471-2105 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017805 issn: 1471-2105 databaseCode: K7- dateStart: 20090101 isFulltext: true titleUrlDefault: http://search.proquest.com/compscijour providerName: ProQuest – providerCode: PRVPQU databaseName: Health & Medical Collection customDbUrl: eissn: 1471-2105 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017805 issn: 1471-2105 databaseCode: 7X7 dateStart: 20090101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1471-2105 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017805 issn: 1471-2105 databaseCode: BENPR dateStart: 20090101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 1471-2105 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017805 issn: 1471-2105 databaseCode: PIMPY dateStart: 20090101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVAVX databaseName: Springer LINK customDbUrl: eissn: 1471-2105 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017805 issn: 1471-2105 databaseCode: RSV dateStart: 20001201 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lj9MwELZgFyQuvBGBJTIIiQNY5G2HWxftQgVUUXdBhYvlR1IqrdJV0yLx75lxHigsIMHFh3ichzOe-WyPvyHkaZlbIawOGHjriiVaaZZjME2cATrOBVpI5ZJN8NlMLBZ50R0Ka_po935L0llqN6xF9rIJkWuNYUgBGtGUwZxnH9ydwOE4P_k07B0gS39_POa37UYuyDH1X7THF2Mkf9kodf7n-Mb_vflNcr3Dm3TSKsgtcqmsb5OrbQbK73fI9s3klL2fvqKKOupqinSbLgCS1m2AOEU_Z2mXXWJJVW3pqo9UxAttDmoK4Jeik2zXFqnG1BPDPQxidAxKcnpwl3w8Pjp9_ZZ1iRiYyUKxZUKrKrCpqriqbFDamAcm1bmNdGgMjxNrQpVmlotUR7oKTaAiAH6GA1SJqkzz-B7Zq9d1eZ9QQGelVqVOdGWTzMQ4XyuFSmOdVHCb2CNh_2-k6VjKMVnGmXSzFZHJtjcl9KZ0vSlDjzwf2py3HB1_lT7EXz5IIr-2u7DeLGU3XGWQa4CWCrOlVQBxVG5wDcEIK0DpyyjwyBNUGIkMGjWG6CzVrmnk9GQuJxmP4gQ5czzyrBOq1vANRnUnHqAnkHRrJHkwkoQhbsbVvV7KzsQ0ErAqwKs8TqH68VCNLTFsri7XO5RJkTERMKtH-EifR58_rqlXXx3NuIhyzETjkRe9Vv98-J-798G_iT8k1yI3MDiLogOyt93sykfkivm2XTUbn1zmC-5K4ZP9w6NZMffdqgmU7zjzMVK3gLJIv0B9Mf1QfPadMfgBzc9T1A |
| linkProvider | Springer Nature |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1bb9MwFD4aAwQv3BGBAQaBeIBoiXOxg4RQuYxVKxNiReqb8S2lEkpH04L2p_iN-DhJpzCxtz3wGp-4sXt8zrHz5fsAntjCcG5UFLpsXYapkiosEEyT5K46LjhGSOnFJtj-Pp9Mik8b8Lv7FgZhlV1M9IHazDWekW-71OyySZFkyevDHyGqRuHb1U5Co3GLPXv0y23Z6lfDd-7_fUrpzvvx292wVRUIdR7zZciVLCOTyZLJ0kTWJCzSmSoMVbHWLEmNjmWWG8YzRVUZ60hSV8Vo5vIuLXPFEtfvOTjvnoUhhIxN1hu8GPUBug9zeL5dx8gOFyIIAsN-Fsa95Oc1Ak5mgpPozL9e0frMt3P1f5uza3ClrbHJoFkU12HDVjfgYqO6eXQTlh8G43A0fEkk8XTdBClGPeiTVA0onmBuN6RV1JgSWRky69CZeKHR3Sau4CdYGDTnqUSh3Ma6D437EgRied-_BV_OZMi3YbOaV_YOEFeRWiWtSlVp0lwnuEe1XGaJSkvXTRJA3HmF0C0zOwqEfBd-h8Zz0XiScJ4kvCeJOIDn63sOG16SU63foLOtLZFT3F-YL6aiDVEiKpQrpyUqxJWurJOFxnMTzQ13C93SKIDH6KoCWUMqhCVN5aquxfDgsxjkjCYp8gQF8Kw1KuduDFq2X3m4mUCisZ7lVs_ShTXdb-58WrRhtRbHDh3Ao3Uz3olQwcrOV2iTIUukq9MDYL2V1Bt-v6WaffPU6pwWqL4TwItuzR3_-L-n9-7pz_oQLu2OP47EaLi_dw8uUx8QWEjpFmwuFyt7Hy7on8tZvXjgwwmBr2e9Fv8A8fa0AA |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Zb9QwELZQOdQXbkRKCwYh8QBWE-eww9sWWFhRrSpaUN8sn9uVqmy1ySLx7_E4B4QCEuI1HifyZMbz2R5_g9BzWxrOjYqJj9aOZEoqUkIyTVp4dFxymCFlKDbB5nN-eloe_XSLP2S790eS7Z0GYGmqmv0L41oX58V-nQDvGoH0AphQc-LXP1czKBoE6_XjL8M5AjD291dlfttvFI4Ca__luflyvuQvh6YhFk1v_f8obqObHQ7Fk9Zw7qArtrqLrreVKb_dQ837yQk5nL3GEgdKaww0nCExEldt4jiG-GdwV3VigWVl8LLPYIQHbW1q7EExhuDZ7jliBSUphndowO6QrBTs4z76PH138uYD6Qo0EF0kvCFcSRebXDomnYmtSVmsc1UaqhKtWZoZnci8MIzniiqX6FhSDwg18xCGukKx9AHaqlaVfYiwR21WSasy5UxW6BTWcZbLPFWZ869JI5T0_0nojr0cimici7CK4YVotSm8NkXQpkgi9HLoc9Fyd_xV-gB-_yAJvNvhwWq9EJ0bi7hUHnJKqKLmPPSRpYa9Bc0N985gaRyhZ2A8Apg1KkjdWchNXYvZ8ScxKRhNM-DSidCLTsit_Bi07G5CeE0AGddIcnck6V1fj5t7GxXd1FMLj2E97CrT3Dc_HZqhJ6TTVXa1AZkcmBQ9lo0QG9n2aPjjlmp5FujHOS2hQk2EXvUW_uPjf1bvzr-JP0E3jt5OxeFs_vER2qbBRxihdBdtNeuN3UPX9NdmWa8fB3__DrKRVsc |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=GAT-LI%3A+a+graph+attention+network+based+learning+and+interpreting+method+for+functional+brain+network+classification&rft.jtitle=BMC+bioinformatics&rft.au=Hu%2C+Jinlong&rft.au=Cao%2C+Lijie&rft.au=Li%2C+Tenghui&rft.au=Dong%2C+Shoubin&rft.date=2021-07-22&rft.pub=BioMed+Central&rft.eissn=1471-2105&rft.volume=22&rft.issue=1&rft_id=info:doi/10.1186%2Fs12859-021-04295-1&rft.externalDocID=10_1186_s12859_021_04295_1 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1471-2105&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1471-2105&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1471-2105&client=summon |