Celik, Numan ORCID: 0000-0003-1813-1036, O’Brien, Fiona, Brennan, Sean
ORCID: 0000-0002-7604-9842, Rainbow, Richard D
ORCID: 0000-0002-0532-1992, Dart, Caroline
ORCID: 0000-0002-3509-8349, Zheng, Yalin
ORCID: 0000-0002-7873-0922, Coenen, Frans
ORCID: 0000-0003-1026-6649 and Barrett-Jolley, Richard
ORCID: 0000-0003-0449-9972
(2020)
Deep-Channel uses deep neural networks to detect single-molecule events from patch-clamp data.
Communications Biology, 3 (1).
pp. 1-10.
Text
s42003-019-0729-3.pdf - Published version Download (1MB) | Preview |
Abstract
Single-molecule research techniques such as patch-clamp electrophysiology deliver unique biological insight by capturing the movement of individual proteins in real time, unobscured by whole-cell ensemble averaging. The critical first step in analysis is event detection, so called “idealisation”, where noisy raw data are turned into discrete records of protein movement. To date there have been practical limitations in patch-clamp data idealisation; high quality idealisation is typically laborious and becomes infeasible and subjective with complex biological data containing many distinct native single-ion channel proteins gating simultaneously. Here, we show a deep learning model based on convolutional neural networks and long short-term memory architecture can automatically idealise complex single molecule activity more accurately and faster than traditional methods. There are no parameters to set; baseline, channel amplitude or numbers of channels for example. We believe this approach could revolutionise the unsupervised automatic detection of single-molecule transition events in the future.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | Humans, Ion Channels, Patch-Clamp Techniques, ROC Curve, Ion Channel Gating, Models, Biological, Artificial Intelligence, Electrophysiological Phenomena, Workflow, Supervised Machine Learning, Single Molecule Imaging, Neural Networks, Computer |
Depositing User: | Symplectic Admin |
Date Deposited: | 15 Jan 2020 08:23 |
Last Modified: | 19 Jan 2023 00:09 |
DOI: | 10.1038/s42003-019-0729-3 |
Related URLs: | |
URI: | https://livrepository.liverpool.ac.uk/id/eprint/3070646 |