Kim Taehoon, Chen Dexiong, Hornauer Philipp, Emmenegger Vishalini, Bartram Julian, Ronchi Silvia, Hierlemann Andreas, Schröter Manuel, Roqueiro Damian
Bioengineering Laboratory, Department of Biosystems Science and Engineering, ETH Zurich, Basel, Switzerland.
Machine Learning and Computational Biology Laboratory, Department of Biosystems Science and Engineering, ETH Zurich, Basel, Switzerland.
Front Neuroinform. 2023 Jan 11;16:1032538. doi: 10.3389/fninf.2022.1032538. eCollection 2022.
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 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-a second dataset with cultures perturbed with Bicuculline and a dataset perturbed with the GABA 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.
现代图神经网络（GNN）为研究生物神经元网络复杂活动模式背后的决定因素提供了机会。在本研究中，我们将GNN应用于通过高密度微电极阵列（HD-MEA）获得的啮齿动物初级神经元网络的大规模电生理数据集。HD-MEA允许对单个神经元和网络的细胞外尖峰活动进行长期记录，并能够在单神经元和群体水平上提取生理相关特征。我们采用已建立的GNN来生成从HD-MEA数据中获得的单神经元和连接特征的组合表示，最终目标是预测药理学扰动引起的单神经元放电率变化。主要预测任务的目的是评估在基线条件下推断出的单神经元和功能连接特征是否有助于预测用GABA受体拮抗剂荷包牡丹碱进行扰动后神经元活动的变化。我们的结果表明，从基线记录中提取的节点特征和功能连接的联合表示有助于预测扰动后单个神经元的放电率变化。具体而言，我们具有归纳学习能力的GNN模型（GraphSAGE）的实现优于其他仅依赖单神经元特征的预测模型。我们在另外两个HD-MEA记录数据集上测试了结果的可推广性——一个是用荷包牡丹碱扰动的培养物的第二个数据集，另一个是用GABA受体拮抗剂加巴喷丁扰动的数据集。GraphSAGE模型显示出比其他预测模型更高的预测准确率。我们的结果证明了考虑神经元之间功能连接的附加价值以及GNN研究神经元之间复杂相互作用的潜力。
