Deep Learning‐Based Ion Channel Kinetics Analysis for Automated Patch Clamp Recording

Abstract The patch clamp technique is a fundamental tool for investigating ion channel dynamics and electrophysiological properties. This study proposes the first artificial intelligence framework for characterizing multiple ion channel kinetics of whole‐cell recordings. The framework integrates mac...

Full description

Saved in:
Bibliographic Details
Main Authors: Shengjie Yang, Jiaqi Xue, Ziqi Li, Shiqing Zhang, Zhang Zhang, Zhifeng Huang, Ken Kin Lam Yung, King Wai Chiu Lai
Format: Article
Language:English
Published: Wiley 2025-03-01
Series:Advanced Science
Subjects:
Online Access:https://doi.org/10.1002/advs.202404166
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850063073869561856
author Shengjie Yang
Jiaqi Xue
Ziqi Li
Shiqing Zhang
Zhang Zhang
Zhifeng Huang
Ken Kin Lam Yung
King Wai Chiu Lai
author_facet Shengjie Yang
Jiaqi Xue
Ziqi Li
Shiqing Zhang
Zhang Zhang
Zhifeng Huang
Ken Kin Lam Yung
King Wai Chiu Lai
author_sort Shengjie Yang
collection DOAJ
description Abstract The patch clamp technique is a fundamental tool for investigating ion channel dynamics and electrophysiological properties. This study proposes the first artificial intelligence framework for characterizing multiple ion channel kinetics of whole‐cell recordings. The framework integrates machine learning for anomaly detection and deep learning for multi‐class classification. The anomaly detection excludes recordings that are incompatible with ion channel behavior. The multi‐class classification combined a 1D convolutional neural network, bidirectional long short‐term memory, and an attention mechanism to capture the spatiotemporal patterns of the recordings. The framework achieves an accuracy of 97.58% in classifying 124 test datasets into six categories based on ion channel kinetics. The utility of the novel framework is demonstrated in two applications: Alzheimer's disease drug screening and nanomatrix‐induced neuronal differentiation. In drug screening, the framework illustrates the inhibitory effects of memantine on endogenous channels, and antagonistic interactions among potassium, magnesium, and calcium ion channels. For nanomatrix‐induced differentiation, the classifier indicates the effects of differentiation conditions on sodium and potassium channels associated with action potentials, validating the functional properties of differentiated neurons for Parkinson's disease treatment. The proposed framework is promising for enhancing the efficiency and accuracy of ion channel kinetics analysis in electrophysiological research.
format Article
id doaj-art-1a9ae4dc59a744c09957a10e63f6e8e8
institution DOAJ
issn 2198-3844
language English
publishDate 2025-03-01
publisher Wiley
record_format Article
series Advanced Science
spelling doaj-art-1a9ae4dc59a744c09957a10e63f6e8e82025-08-20T02:49:46ZengWileyAdvanced Science2198-38442025-03-011212n/an/a10.1002/advs.202404166Deep Learning‐Based Ion Channel Kinetics Analysis for Automated Patch Clamp RecordingShengjie Yang0Jiaqi Xue1Ziqi Li2Shiqing Zhang3Zhang Zhang4Zhifeng Huang5Ken Kin Lam Yung6King Wai Chiu Lai7Department of Biomedical Engineering City University of Hong Kong Tat Chee Avenue, Kowloon Tong Kowloon Hong Kong SAR ChinaDepartment of Biomedical Engineering City University of Hong Kong Tat Chee Avenue, Kowloon Tong Kowloon Hong Kong SAR ChinaDepartment of Biomedical Engineering City University of Hong Kong Tat Chee Avenue, Kowloon Tong Kowloon Hong Kong SAR ChinaJNU‐HKUST Joint Laboratory for Neuroscience and Innovative Drug Research College of Pharmacy Jinan University 601 West Huangpu Road, Tianhe Guangzhou 510632 ChinaSchool of Public Health Guangzhou Medical University Xinzao, Panyu Guangzhou 511436 ChinaDepartment of Chemistry Chinese University of Hong Kong Shatin New Territories Hong Kong SAR ChinaDepartment of Science and Environmental Studies Education University of Hong Kong 10 Lo Ping Road Tai Po New Territories Hong Kong SAR ChinaDepartment of Biomedical Engineering City University of Hong Kong Tat Chee Avenue, Kowloon Tong Kowloon Hong Kong SAR ChinaAbstract The patch clamp technique is a fundamental tool for investigating ion channel dynamics and electrophysiological properties. This study proposes the first artificial intelligence framework for characterizing multiple ion channel kinetics of whole‐cell recordings. The framework integrates machine learning for anomaly detection and deep learning for multi‐class classification. The anomaly detection excludes recordings that are incompatible with ion channel behavior. The multi‐class classification combined a 1D convolutional neural network, bidirectional long short‐term memory, and an attention mechanism to capture the spatiotemporal patterns of the recordings. The framework achieves an accuracy of 97.58% in classifying 124 test datasets into six categories based on ion channel kinetics. The utility of the novel framework is demonstrated in two applications: Alzheimer's disease drug screening and nanomatrix‐induced neuronal differentiation. In drug screening, the framework illustrates the inhibitory effects of memantine on endogenous channels, and antagonistic interactions among potassium, magnesium, and calcium ion channels. For nanomatrix‐induced differentiation, the classifier indicates the effects of differentiation conditions on sodium and potassium channels associated with action potentials, validating the functional properties of differentiated neurons for Parkinson's disease treatment. The proposed framework is promising for enhancing the efficiency and accuracy of ion channel kinetics analysis in electrophysiological research.https://doi.org/10.1002/advs.202404166deep learningelectrophysiologyion channelspatch clampwhole‐cell recording
spellingShingle Shengjie Yang
Jiaqi Xue
Ziqi Li
Shiqing Zhang
Zhang Zhang
Zhifeng Huang
Ken Kin Lam Yung
King Wai Chiu Lai
Deep Learning‐Based Ion Channel Kinetics Analysis for Automated Patch Clamp Recording
Advanced Science
deep learning
electrophysiology
ion channels
patch clamp
whole‐cell recording
title Deep Learning‐Based Ion Channel Kinetics Analysis for Automated Patch Clamp Recording
title_full Deep Learning‐Based Ion Channel Kinetics Analysis for Automated Patch Clamp Recording
title_fullStr Deep Learning‐Based Ion Channel Kinetics Analysis for Automated Patch Clamp Recording
title_full_unstemmed Deep Learning‐Based Ion Channel Kinetics Analysis for Automated Patch Clamp Recording
title_short Deep Learning‐Based Ion Channel Kinetics Analysis for Automated Patch Clamp Recording
title_sort deep learning based ion channel kinetics analysis for automated patch clamp recording
topic deep learning
electrophysiology
ion channels
patch clamp
whole‐cell recording
url https://doi.org/10.1002/advs.202404166
work_keys_str_mv AT shengjieyang deeplearningbasedionchannelkineticsanalysisforautomatedpatchclamprecording
AT jiaqixue deeplearningbasedionchannelkineticsanalysisforautomatedpatchclamprecording
AT ziqili deeplearningbasedionchannelkineticsanalysisforautomatedpatchclamprecording
AT shiqingzhang deeplearningbasedionchannelkineticsanalysisforautomatedpatchclamprecording
AT zhangzhang deeplearningbasedionchannelkineticsanalysisforautomatedpatchclamprecording
AT zhifenghuang deeplearningbasedionchannelkineticsanalysisforautomatedpatchclamprecording
AT kenkinlamyung deeplearningbasedionchannelkineticsanalysisforautomatedpatchclamprecording
AT kingwaichiulai deeplearningbasedionchannelkineticsanalysisforautomatedpatchclamprecording