{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T19:21:46Z","timestamp":1773948106061,"version":"3.50.1"},"reference-count":94,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,1,11]],"date-time":"2023-01-11T00:00:00Z","timestamp":1673395200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neuroinform."],"abstract":"<jats:p>Modern Graph Neural Networks (GNNs) provide opportunities to study the determinants underlying the complex activity patterns of biological neuronal networks. In this study, we applied GNNs to a large-scale electrophysiological dataset of rodent primary neuronal networks obtained by means of high-density microelectrode arrays (HD-MEAs). HD-MEAs allow for long-term recording of extracellular spiking activity of individual neurons and networks and enable the extraction of physiologically relevant features at the single-neuron and population level. We employed established GNNs to generate a combined representation of single-neuron and connectivity features obtained from HD-MEA data, with the ultimate goal of predicting changes in single-neuron firing rate induced by a pharmacological perturbation. The aim of the main prediction task was to assess whether single-neuron and functional connectivity features, inferred under baseline conditions, were informative for predicting changes in neuronal activity in response to a perturbation with Bicuculline, a GABA<jats:sub><jats:italic>A<\/jats:italic><\/jats:sub> receptor antagonist. Our results suggest that the joint representation of node features and functional connectivity, extracted from a baseline recording, was informative for predicting firing rate changes of individual neurons after the perturbation. Specifically, our implementation of a GNN model with inductive learning capability (GraphSAGE) outperformed other prediction models that relied only on single-neuron features. We tested the generalizability of the results on two additional datasets of HD-MEA recordings\u2013a second dataset with cultures perturbed with Bicuculline and a dataset perturbed with the GABA<jats:sub><jats:italic>A<\/jats:italic><\/jats:sub> receptor antagonist Gabazine. GraphSAGE models showed improved prediction accuracy over other prediction models. Our results demonstrate the added value of taking into account the functional connectivity between neurons and the potential of GNNs to study complex interactions between neurons.<\/jats:p>","DOI":"10.3389\/fninf.2022.1032538","type":"journal-article","created":{"date-parts":[[2023,1,11]],"date-time":"2023-01-11T06:49:24Z","timestamp":1673419764000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Predicting in vitro single-neuron firing rates upon pharmacological perturbation using Graph Neural Networks"],"prefix":"10.3389","volume":"16","author":[{"given":"Taehoon","family":"Kim","sequence":"first","affiliation":[]},{"given":"Dexiong","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Philipp","family":"Hornauer","sequence":"additional","affiliation":[]},{"given":"Vishalini","family":"Emmenegger","sequence":"additional","affiliation":[]},{"given":"Julian","family":"Bartram","sequence":"additional","affiliation":[]},{"given":"Silvia","family":"Ronchi","sequence":"additional","affiliation":[]},{"given":"Andreas","family":"Hierlemann","sequence":"additional","affiliation":[]},{"given":"Manuel","family":"Schr\u00f6ter","sequence":"additional","affiliation":[]},{"given":"Damian","family":"Roqueiro","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2023,1,11]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"e1800308","DOI":"10.1002\/adbi.201800308","article-title":"The axon initial segment is the dominant contributor to the neuron's extracellular electrical potential landscape","volume":"3","author":"Bakkum","year":"2019","journal-title":"Adv. Biosyst."},{"key":"B2","doi-asserted-by":"publisher","first-page":"11553","DOI":"10.48550\/arXiv.2009.11553","article-title":"Multi-View brain HyperConnectome AutoEncoder for brain state classification","volume":"2020","author":"Banka","year":"2020","journal-title":"arXiv"},{"key":"B3","doi-asserted-by":"publisher","first-page":"4509","DOI":"10.48550\/arXiv.1612.00222","article-title":"Interaction networks for learning about objects, relations and physics","volume":"2016","author":"Battaglia","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B4","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-32281-6_11","article-title":"Hierarchical adversarial connectomic domain alignment for target brain graph prediction and classification from a source graph","volume-title":"Predictive Intelligence in Medicine. PRIME 2019. Lecture Notes in Computer Science, Vol 11843","author":"Bessadok","year":"2019"},{"key":"B5","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1016\/j.neuron.2010.09.023","article-title":"Neural syntax: Cell assemblies, synapsembles, and readers","volume":"68","author":"Buzs\u00e1ki","year":"2010","journal-title":"Neuron"},{"key":"B6","doi-asserted-by":"publisher","first-page":"866666","DOI":"10.3389\/fnins.2022.866666","article-title":"Combining neuroimaging and omics datasets for disease classification using graph neural networks","volume":"16","author":"Chan","year":"2022","journal-title":"Front. Neurosci."},{"key":"B7","doi-asserted-by":"publisher","first-page":"828512","DOI":"10.3389\/fnins.2021.828512","article-title":"An invertible dynamic graph convolutional network for multi-Center ASD classification","volume":"15","author":"Chen","year":"2021","journal-title":"Front. Neurosci."},{"key":"B8","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1162\/neco_a_01277","article-title":"Comparison of different spike train synchrony measures regarding their robustness to erroneous data from bicuculline-induced epileptiform activity","volume":"32","author":"Ciba","year":"2020","journal-title":"Neural Comput."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1594","DOI":"10.1038\/nn.2439","article-title":"Attention improves performance primarily by reducing interneuronal correlations","volume":"12","author":"Cohen","year":"2009","journal-title":"Nat. Neurosci."},{"key":"B10","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1126\/science.abg0501","article-title":"Voltage compartmentalization in dendritic spines in vivo","volume":"375","author":"Cornejo","year":"2022","journal-title":"Science"},{"key":"B11","volume-title":"Convolutional Networks on Graphs for Learning Molecular Fingerprints","author":"Cortes","year":"2015"},{"key":"B12","doi-asserted-by":"publisher","first-page":"17429","DOI":"10.48550\/arXiv.2006.11287","article-title":"Discovering symbolic models from deep learning with inductive biases","volume":"33","author":"Cranmer","year":"2020","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"B13","doi-asserted-by":"publisher","first-page":"e2026053118","DOI":"10.1073\/pnas.2026053118","article-title":"A bayesian neural network predicts the dissolution of compact planetary systems","volume":"118","author":"Cranmer","year":"2021","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"key":"B14","doi-asserted-by":"publisher","first-page":"5097","DOI":"10.48550\/arXiv.2107.05097","article-title":"BrainNNExplainer: An interpretable graph neural network framework for brain network based disease analysis","volume":"2021","author":"Cui","year":"2021","journal-title":"arXiv"},{"key":"B15","doi-asserted-by":"publisher","first-page":"4883","DOI":"10.1109\/TITS.2019.2950416","article-title":"Traffic graph convolutional recurrent neural network: A deep learning framework for Network-Scale traffic learning and forecasting","volume":"21","author":"Cui","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"B16","doi-asserted-by":"publisher","first-page":"14288","DOI":"10.1523\/JNEUROSCI.2767-14.2014","article-title":"Detecting pairwise correlations in spike trains: An objective comparison of methods and application to the study of retinal waves","volume":"34","author":"Cutts","year":"2014","journal-title":"J. Neurosci."},{"key":"B17","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1177\/003591573502800330","article-title":"Pharmacology and nerve-endings (walter ernest dixon memorial lecture): Section of therapeutics and pharmacology","volume":"28","author":"Dale","year":"1935","journal-title":"Proc. R. Soc. Med."},{"key":"B18","doi-asserted-by":"publisher","first-page":"13848","DOI":"10.1073\/pnas.0601417103","article-title":"Consistent resting-state networks across healthy subjects","volume":"103","author":"Damoiseaux","year":"2006","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"key":"B19","doi-asserted-by":"publisher","first-page":"P19","DOI":"10.5281\/zenodo.7307401","article-title":"Collaborative HPC-enabled workflows on the HBP collaboratory using the elephant framework","author":"Denker","year":"2018","journal-title":"Neuroinformatics"},{"key":"B20","doi-asserted-by":"crossref","first-page":"750","DOI":"10.1145\/3292500.3330958","article-title":"Graph transformation policy network for chemical reaction prediction","volume-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '19","author":"Do","year":"2019"},{"key":"B21","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1007\/978-1-4419-5675-0_5","article-title":"Pair-Correlation in the time and frequency domain","volume-title":"Analysis of Parallel Spike Trains","author":"Eggermont","year":"2010"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1059","DOI":"10.1152\/jn.00079.2015","article-title":"Quantification of bursting and synchrony in cultured hippocampal neurons","volume":"114","author":"Eisenman","year":"2015","journal-title":"J. Neurophysiol."},{"key":"B23","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1016\/j.neuron.2017.09.033","article-title":"Pyramidal cell-interneuron circuit architecture and dynamics in hippocampal networks","volume":"96","author":"English","year":"2017","journal-title":"Neuron"},{"key":"B24","doi-asserted-by":"publisher","first-page":"797500","DOI":"10.3389\/fnins.2021.797500","article-title":"Learning cortical parcellations using graph neural networks","volume":"15","author":"Eschenburg","year":"2021","journal-title":"Front. Neurosci."},{"key":"B25","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1145\/3308558.3313488","article-title":"Graph neural networks for social recommendation","volume-title":"The World Wide Web Conference, WWW '19","author":"Fan","year":"2019"},{"key":"B26","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1016\/j.tins.2011.02.007","article-title":"Dissecting functional connectivity of neuronal microcircuits: Experimental and theoretical insights","volume":"34","author":"Feldt","year":"2011","journal-title":"Trends Neurosci."},{"key":"B27","article-title":"Fast graph representation learning with PyTorch geometric","volume-title":"ICLR Workshop on Representation Learning on Graphs and Manifolds","author":"Fey","year":"2019"},{"key":"B28","first-page":"6533","article-title":"Protein interface prediction using graph convolutional networks","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS'17","author":"Fout","year":"2017"},{"key":"B29","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1002\/hbm.460020107","article-title":"Functional and effective connectivity in neuroimaging: A synthesis","volume":"2","author":"Friston","year":"1994","journal-title":"Hum. Brain Mapp."},{"key":"B30","doi-asserted-by":"publisher","first-page":"214262","DOI":"10.1101\/214262","article-title":"A theory of multineuronal dimensionality, dynamics and measurement","volume":"2017","author":"Gao","year":"2017","journal-title":"bioRxiv"},{"key":"B31","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1073\/pnas.0135058100","article-title":"Functional connectivity in the resting brain: A network analysis of the default mode hypothesis","volume":"100","author":"Greicius","year":"2003","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"key":"B32","doi-asserted-by":"publisher","first-page":"922","DOI":"10.1609\/aaai.v33i01.3301922","article-title":"Attention based spatial-temporal graph convolutional networks for traffic flow forecasting","volume":"33","author":"Guo","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"B33","doi-asserted-by":"publisher","first-page":"2216","DOI":"10.48550\/arXiv.1706.02216","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"B34","doi-asserted-by":"publisher","first-page":"8699","DOI":"10.1523\/JNEUROSCI.0971-11.2011","article-title":"Quality metrics to accompany spike sorting of extracellular signals","volume":"31","author":"Hill","year":"2011","journal-title":"J. Neurosci."},{"key":"B35","doi-asserted-by":"publisher","first-page":"2698","DOI":"10.48550\/arXiv.1706.06122","article-title":"VAIn: Attentional multi-agent predictive modeling","volume":"30","author":"Hoshen","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B36","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1162\/089976606775093882","article-title":"Polychronization: Computation with spikes","volume":"18","author":"Izhikevich","year":"2006","journal-title":"Neural Comput."},{"key":"B37","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1111\/j.1469-7793.2001.0625e.x","article-title":"The functional role of a bicuculline-sensitive ca2+-activated k+ current in rat medial preoptic neurons","volume":"532","author":"Johansson","year":"2001","journal-title":"J. Physiol."},{"key":"B38","doi-asserted-by":"publisher","first-page":"595","DOI":"10.48550\/arXiv.1603.00856","article-title":"Molecular graph convolutions: Moving beyond fingerprints","volume":"30","author":"Kearnes","year":"2016","journal-title":"J. Comput. Aided Mol. Des."},{"key":"B39","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.cell.2021.12.007","article-title":"Fluorescence imaging of large-scale neural ensemble dynamics","volume":"185","author":"Kim","year":"2022","journal-title":"Cell"},{"key":"B40","doi-asserted-by":"publisher","first-page":"4209","DOI":"10.48550\/arXiv.1802.04687","article-title":"Neural relational inference for interacting systems","volume":"6","author":"Kipf","year":"2018","journal-title":"35th Int. Conf. Machine Learn."},{"key":"B41","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"5th International Conference on Learning Representations (ICLR-17)","author":"Kipf","year":"2016"},{"key":"B42","doi-asserted-by":"publisher","first-page":"48","DOI":"10.2307\/2033241","article-title":"On the shortest spanning subtree of a graph and the traveling salesman problem","volume":"7","author":"Kruskal","year":"1956","journal-title":"Proc. Am. Math. Soc."},{"key":"B43","doi-asserted-by":"publisher","first-page":"1106","DOI":"10.1016\/j.neuron.2016.10.027","article-title":"The impact of structural heterogeneity on excitation-inhibition balance in cortical networks","volume":"92","author":"Landau","year":"2016","journal-title":"Neuron"},{"key":"B44","doi-asserted-by":"publisher","first-page":"e67490","DOI":"10.7554\/eLife.67490","article-title":"Non-linear dimensionality reduction on extracellular waveforms reveals cell type diversity in premotor cortex","volume":"10","author":"Lee","year":"2021","journal-title":"Elife"},{"key":"B45","doi-asserted-by":"publisher","first-page":"102233","DOI":"10.1016\/j.media.2021.102233","article-title":"BrainGNN: Interpretable brain graph neural network for fMRI analysis","volume":"74","author":"Li","year":"2021","journal-title":"Med. Image Anal."},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2008.13118","article-title":"Deep hypergraph U-Net for brain graph embedding and classification","author":"Lostar","year":"2020","journal-title":"arXiv"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.10660","article-title":"Exploring graph neural networks for stock market predictions with rolling window analysis","author":"Matsunaga","year":"2019","journal-title":"arXiv"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.03426","article-title":"UMAP: Uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018","journal-title":"ArXiv"},{"key":"B49","doi-asserted-by":"publisher","first-page":"1010","DOI":"10.1016\/j.celrep.2013.07.039","article-title":"Preconfigured, skewed distribution of firing rates in the hippocampus and entorhinal cortex","volume":"4","author":"Mizuseki","year":"2013","journal-title":"Cell Rep."},{"key":"B50","doi-asserted-by":"publisher","first-page":"3536","DOI":"10.1016\/j.celrep.2020.02.027","article-title":"Cellular classes in the human brain revealed in vivo by heartbeat-related modulation of the extracellular action potential waveform","volume":"30","author":"Mosher","year":"2020","journal-title":"Cell Rep."},{"key":"B51","doi-asserted-by":"publisher","first-page":"2767","DOI":"10.1039\/C5LC00133A","article-title":"High-resolution CMOS MEA platform to study neurons at subcellular, cellular, and network levels","volume":"15","author":"M\u00fcller","year":"2015","journal-title":"Lab Chip"},{"key":"B52","doi-asserted-by":"publisher","first-page":"e061481","DOI":"10.1101\/061481","article-title":"Kilosort: Realtime spike-sorting for extracellular electrophysiology with hundreds of channels","volume":"2016","author":"Pachitariu","year":"2016","journal-title":"bioRxiv"},{"key":"B53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pcbi.1006381","article-title":"Identification of excitatory-inhibitory links and network topology in large-scale neuronal assemblies from multi-electrode recordings","volume":"14","author":"Pastore","year":"2018","journal-title":"PLoS Comput. Biol."},{"key":"B54","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1016\/s0304-3940(03)00747-x","article-title":"Modulation of calcium-activated potassium small conductance (SK) current in rat dopamine neurons of the ventral tegmental area","volume":"348","author":"Paul","year":"2003","journal-title":"Neurosci. Lett."},{"key":"B55","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res"},{"key":"B56","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1016\/j.neuron.2020.05.023","article-title":"Cooling of medial septum reveals theta phase lag coordination of hippocampal cell assemblies","volume":"107","author":"Petersen","year":"2020","journal-title":"Neuron"},{"key":"B57","doi-asserted-by":"publisher","first-page":"3594","DOI":"10.1016\/j.neuron.2021.09.002","article-title":"CellExplorer: A framework for visualizing and characterizing single neurons","volume":"109","author":"Petersen","year":"2021","journal-title":"Neuron"},{"key":"B58","doi-asserted-by":"publisher","first-page":"1731","DOI":"10.1073\/pnas.1109895109","article-title":"Spatiotemporal dynamics of neocortical excitation and inhibition during human sleep","volume":"109","author":"Peyrache","year":"2012","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"key":"B59","doi-asserted-by":"publisher","first-page":"104500","DOI":"10.1016\/j.nbd.2019.104500","article-title":"Electrophysiological monitoring of inhibition in mammalian species, from rodents to humans","volume":"130","author":"Peyrache","year":"2019","journal-title":"Neurobiol. Dis."},{"key":"B60","doi-asserted-by":"crossref","first-page":"10764","DOI":"10.1109\/CVPR.2019.01103","article-title":"Explainability methods for graph convolutional neural networks","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Pope","year":"2019"},{"key":"B61","doi-asserted-by":"publisher","first-page":"838347","DOI":"10.3389\/fnins.2022.838347","article-title":"Unrevealing reliable cortical parcellation of individual brains using resting-state functional magnetic resonance imaging and masked graph convolutions","volume":"16","author":"Qiu","year":"2022","journal-title":"Front. Neurosci."},{"key":"B62","doi-asserted-by":"publisher","first-page":"100555","DOI":"10.1016\/j.patter.2022.100555","article-title":"A scale-dependent measure of system dimensionality","volume":"3","author":"Recanatesi","year":"2020","journal-title":"bioRxiv"},{"key":"B63","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2007.03092","article-title":"Neural subgraph matching","author":"Rex","year":"2020","journal-title":"arXiv"},{"key":"B64","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2018\/490","article-title":"Hybrid approach of relation network and localized graph convolutional filtering for breast cancer subtype classification","volume-title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","author":"Rhee","year":"2018"},{"key":"B65","doi-asserted-by":"publisher","first-page":"208","DOI":"10.3389\/fnins.2019.00208","article-title":"Single-cell electrical stimulation using CMOS-based high-density microelectrode arrays","volume":"13","author":"Ronchi","year":"2019","journal-title":"Front. Neurosci."},{"key":"B66","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","article-title":"Silhouettes: A graphical aid to the interpretation and validation of cluster analysis","volume":"20","author":"Rousseeuw","year":"1987","journal-title":"J. Comput. Appl. Math."},{"key":"B67","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1038\/nn.3077","article-title":"Control of timing, rate and bursts of hippocampal place cells by dendritic and somatic inhibition","volume":"15","author":"Royer","year":"2012","journal-title":"Nat. Neurosci."},{"key":"B68","doi-asserted-by":"publisher","first-page":"4470","DOI":"10.48550\/arXiv.1806.01242","article-title":"Graph networks as learnable physics engines for inference and control","volume":"80","author":"Sanchez-Gonzalez","year":"2018","journal-title":"PMLR"},{"key":"B69","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2009","journal-title":"IEEE Trans. Neural Netw."},{"key":"B70","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1007\/978-3-319-93417-4_38","article-title":"Modeling relational data with graph convolutional networks","volume-title":"The Semantic Web","author":"Schlichtkrull","year":"2018"},{"key":"B71","doi-asserted-by":"publisher","first-page":"3589","DOI":"10.48550\/arXiv.2006.03589","article-title":"Higher-order explanations of graph neural networks via relevant walks","volume":"2021","author":"Schnake","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B72","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1016\/j.neuron.2018.12.009","article-title":"Layer-specific physiological features and interlaminar interactions in the primary visual cortex of the mouse","volume":"101","author":"Senzai","year":"2019","journal-title":"Neuron"},{"key":"B73","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1093\/cercor\/bhr099","article-title":"Decoding subject-driven cognitive states with whole-brain connectivity patterns","volume":"22","author":"Shirer","year":"2012","journal-title":"Cereb. Cortex"},{"key":"B74","doi-asserted-by":"publisher","first-page":"220601","DOI":"10.48550\/arXiv.2007.09240","article-title":"New method for parameter estimation in probabilistic models: Minimum probability flow","volume":"107","author":"Sohl-Dickstein","year":"2011","journal-title":"Phys. Rev. Lett."},{"key":"B75","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1016\/B978-008045046-9.00308-9","article-title":"Functional connectivity","volume-title":"Encyclopedia of Neuroscience","author":"Stephan","year":"2009"},{"key":"B76","volume-title":"Business Concentration and Price Policy. Technical Report univ55-1","author":"Stigler","year":"1955"},{"key":"B77","first-page":"2252","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems, NIPS'16","author":"Sukhbaatar","year":"2016"},{"key":"B78","doi-asserted-by":"publisher","first-page":"3073","DOI":"10.1152\/jn.00995.2015","article-title":"Network burst activity in hippocampal neuronal cultures: The role of synaptic and intrinsic currents","volume":"115","author":"Suresh","year":"2016","journal-title":"J. Neurophysiol."},{"key":"B79","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1523\/JNEUROSCI.17-02-00625.1997","article-title":"Bicuculline and gabazine are allosteric inhibitors of channel opening of the GABAA receptor","volume":"17","author":"Ueno","year":"1997","journal-title":"J. Neurosci."},{"key":"B80","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.02263","article-title":"Graph convolutional matrix completion","author":"van den Berg","year":"2017","journal-title":"arXiv"},{"key":"B81","doi-asserted-by":"publisher","first-page":"963125","DOI":"10.3389\/fnimg.2022.963125","article-title":"Extracting default mode network based on graph neural network for resting state fMRI study","volume":"1","author":"Wang","year":"2022","journal-title":"Front. Neuroimag."},{"key":"B82","doi-asserted-by":"publisher","first-page":"618372","DOI":"10.3389\/frai.2021.618372","article-title":"Generalizable machine learning in neuroscience using graph neural networks","volume":"4","author":"Wang","year":"2021","journal-title":"Front. Artif. Intell. Appl."},{"key":"B83","doi-asserted-by":"publisher","first-page":"4539","DOI":"10.48550\/arXiv.1706.01433","article-title":"Visual interaction networks","volume":"2017","author":"Watters","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B84","doi-asserted-by":"publisher","first-page":"8061","DOI":"10.1038\/s41598-021-87411-8","article-title":"A graph neural network framework for causal inference in brain networks","volume":"11","author":"Wein","year":"2021","journal-title":"Sci. Rep."},{"key":"B85","doi-asserted-by":"publisher","first-page":"460","DOI":"10.3389\/fncel.2014.00460","article-title":"Comparison of spike parameters from optically identified GABAergic and glutamatergic neurons in sparse cortical cultures","volume":"8","author":"Weir","year":"2014","journal-title":"Front. Cell. Neurosci."},{"key":"B86","doi-asserted-by":"crossref","first-page":"2091","DOI":"10.1145\/3308558.3313442","article-title":"Dual graph attention networks for deep latent representation of multifaceted social effects in recommender systems","volume-title":"The World Wide Web Conference, WWW '19","author":"Wu","year":"2019"},{"key":"B87","doi-asserted-by":"publisher","first-page":"1259","DOI":"10.1093\/cercor\/bhaa292","article-title":"DS-GCNs: Connectome classification using dynamic spectral graph convolution networks with assistant task training","volume":"31","author":"Xing","year":"2021","journal-title":"Cereb. Cortex"},{"key":"B88","first-page":"2161","article-title":"Using external knowledge for financial event prediction based on graph neural networks","volume-title":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management, CIKM '19","author":"Yang","year":"2019"},{"key":"B89","doi-asserted-by":"publisher","first-page":"9240","DOI":"10.48550\/arXiv.1903.03894","article-title":"GNNExplainer: Generating explanations for graph neural networks","volume":"32","author":"Ying","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B90","doi-asserted-by":"crossref","first-page":"974","DOI":"10.1145\/3219819.3219890","article-title":"Graph convolutional neural networks for Web-Scale recommender systems","volume-title":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '18","author":"Ying","year":"2018"},{"key":"B91","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2018\/505","article-title":"Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting","volume-title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","author":"Yu","year":"2018"},{"key":"B92","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.48550\/arXiv.1911.08415","article-title":"GMAN: A graph multi-attention network for traffic prediction","volume":"34","author":"Zheng","year":"2020","journal-title":"AAAI"},{"key":"B93","doi-asserted-by":"publisher","first-page":"57","DOI":"10.48550\/arXiv.1812.08434","article-title":"Graph neural networks: A review of methods and applications","volume":"1","author":"Zhou","year":"2020","journal-title":"AI Open"},{"key":"B94","doi-asserted-by":"publisher","first-page":"i457","DOI":"10.1093\/bioinformatics\/bty294","article-title":"Modeling polypharmacy side effects with graph convolutional networks","volume":"34","author":"Zitnik","year":"2018","journal-title":"Bioinformatics"}],"container-title":["Frontiers in Neuroinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2022.1032538\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,11]],"date-time":"2023-01-11T06:49:51Z","timestamp":1673419791000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2022.1032538\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,11]]},"references-count":94,"alternative-id":["10.3389\/fninf.2022.1032538"],"URL":"https:\/\/doi.org\/10.3389\/fninf.2022.1032538","relation":{},"ISSN":["1662-5196"],"issn-type":[{"value":"1662-5196","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,11]]},"article-number":"1032538"}}