Determination of Neuron Activation States Facilitated by Artificial Intelligence

Abstract

Environmental stimuli evoke gene expression changes in neurons to achieve synaptic reconfiguration and memory formation. During the neuronal activation process, immediate early genes (IEGs) and late response genes (LRGs) have been defined according to their temporal changes in gene expression. Recent single cell studies indicated that different subtypes of neurons may have distinct sets of IEGs and LRGs in response to neuronal activation. Currently, it remains unexplored whether the gene expression patterns provided by single cell studies are sufficient to distinguish neuronal subtypes together with their activation states. In this study, we adopt Artificial Neural Network (ANN) models to predict neuron cell subtypes and activation states simultaneously based on a single cell RNA-Seq dataset generated from mouse visual cortex in response to light stimulus exposure. Four kinds of ANN architectures were designed to compare the prediction efficacies using two kinds of inputs: the full list of genes or the markers selected for neuron cell subtypes, IEGs, and LRGs. We observed that, with single-cell RNA-Seq data, neuron cell subtypes and activation states can be predicted accurately by ANN models. Moreover, compared to feeding the entire list of genes to fully connected ANNs, using selected marker genes and partially connected ANNs achieves comparable prediction accuracy with substantially improved computational efficiency. Altogether, our results demonstrated that ANNs are powerful in predicting neuron activation states and cell subtypes and may serve as a useful data mining approach to explore single cell RNA-Seq profiles.