Lukasiewicz Research Network - Krakow Institute of Technology, The Centre for Biomedical Engineering, Kraków, Poland.
Department of Physical Chemistry and Technology of Polymers, Silesian University of Technology, Gliwice, Poland.
Methods Mol Biol. 2024;2796:249-270. doi: 10.1007/978-1-0716-3818-7_15.
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.
膜片钳技术为记录离子通道的活动提供了独特的可能性。该方法能够在受控条件下实时跟踪其功能状态的变化。从通道功能的电生理特性的角度来看，对膜片钳信号进行评估的动力学参数构成了基础。然而，流经通道蛋白的离子电流的嘈杂序列似乎包含着大量的信息，而标准的数据处理技术可能只揭示了其中的一部分。人工智能 (AI) 技术，特别是机器学习 (ML) 的快速发展，为整个通道学带来了新的前景。在这里，我们考虑了 AI 在膜片钳信号分析中的应用问题。事实证明，AI 方法不仅可以实现信号分析的自动化，还可以用于发现通道门控的固有模式，并允许研究人员揭示以前从未考虑过的门控机制的细节。在这项工作中，我们概述了目前已知的 AI 方法，这些方法在膜片钳信号分析中被证明是可用且有用的。本章可以被认为是 AI 方法在通道电流时间序列分析中的应用的入门指南（包括其优点、缺点和局限性），但我们也提出了该领域的新的可能方向。
