Deep Learning Models for Atypical Serotoninergic Cells Recognition

Background The serotonergic system modulates brain processes via functionally distinct subpopulations of neurons with heterogeneous properties, including their electrophysiological activity. In extracellular recordings, serotonergic neurons to be investigated for their functional properties are commonly identified on the basis of “typical” features of their activity, i.e. slow regular firing and relatively long duration of spikes. Thus, due to the lack of equally robust criteria for discriminating serotonergic neurons with “atypical” features from non-serotonergic cells, the physiological relevance of the diversity of serotonergic neuron activities results largely understudied. New Methods We propose deep learning models capable of discriminating typical and atypical serotonergic neurons from non-serotonergic cells with high accuracy. The research utilized electrophysiological in vitro recordings from serotonergic neurons identified by the expression of fluorescent proteins specific to the serotonergic system and non-serotonergic cells. These recordings formed the basis of the training, validation, and testing data for the deep learning models. The study employed convolutional neural networks (CNNs), known for their efficiency in pattern recognition, to classify neurons based on the specific characteristics of their action potentials. Results The models were trained on a dataset comprising 43,327 original spike samples, alongside an extensive set of 6.7 million synthetic spike samples, designed to mitigate the risk of overfitting the background noise in the recordings, a potential source of bias. Results show that the models achieved high accuracy and were further validated on “non-homogeneous” data, i.e., data not used for constructing the model, to confirm their robustness and reliability in real-world experimental conditions. Comparison with existing methods Conventional methods for identifying serotonergic neurons allow recognition of serotonergic neurons defined as typical. Our model based on the analysis of the sole spike reliably recognizes over 92 features of spike and activity. Conclusions The model is ready for use in experiments conducted with the here described recording parameters. We release the codes and procedures allowing to adapt the model to different acquisition parameters or for identification of other classes of spontaneously active neurons. PACS 87.19.L, 87.19.lv, 87.85.dm, 07.05.Mh, 87.85.Tu