Machine Learning Methods for the Analysis of the Patch-Clamp Signals

Patch-clamp technique provides a unique possibility to record the ion channels' activity. This method enables tracking the changes in their functional states at controlled conditions on a real-time scale. Kinetic parameters evaluated for the patch-clamp signals form the fundamentals of electrophysiological characteristics of the channel functioning. Nevertheless, the noisy series of ionic currents flowing through the channel protein(s) seem to be bountiful of information, and the standard data processing techniques likely unravel only its part. Rapid development of artificial intelligence (AI) techniques, especially machine learning (ML), gives new prospects for whole channelology. Here we consider the question of the AI applications in the patch-clamp signal analysis. It turns out that the AI methods may not only enable for automatizing of signal analysis, but also they can be used in finding inherent patterns of channel gating and allow the researchers to uncover the details of gating machinery, which had been never considered before. In this work, we outline the currently known AI methods that turned out to be utilizable and useful in the analysis of patch-clamp signals. This chapter can be considered an introductory guide to the application of AI methods in the analysis of the time series of channel currents (together with its advantages, disadvantages, and limitations), but we also propose new possible directions in this field.