Deep-Channel uses deep neural networks to detect single-molecule events from patch-clamp data

Celik, Numan, O’Brien, Fiona, Brennan, Sean, Rainbow, Richard 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 (2019) Deep-Channel uses deep neural networks to detect single-molecule events from patch-clamp data. Communications Biology.

There is a more recent version of this item available.

Text
MS_AIP2_19-1074_1575579916_1_R4FOB.pdf - Author Accepted Manuscript
Download (1MB) | Preview

Abstract

Abstract Single-molecule research such as patch-clamp recording delivers 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
Depositing User:	Symplectic Admin
Date Deposited:	10 Dec 2019 09:16
Last Modified:	19 Jan 2023 00:13
DOI:	10.1101/767418
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3065604