Deep Learning of Nanopore Sensing Signals Using a Bi-Path Network.
ACS Nano
; 15(9): 14419-14429, 2021 09 28.
Article
em En
| MEDLINE
| ID: mdl-34583465
ABSTRACT
Temporal changes in electrical resistance of a nanopore sensor caused by translocating target analytes are recorded as a sequence of pulses on current traces. Prevalent algorithms for feature extraction in pulse-like signals lack objectivity because empirical amplitude thresholds are user-defined to single out the pulses from the noisy background. Here, we use deep learning for feature extraction based on a bi-path network (B-Net). After training, the B-Net acquires the prototypical pulses and the ability of both pulse recognition and feature extraction without a priori assigned parameters. The B-Net is evaluated on simulated data sets and further applied to experimental data of DNA and protein translocation. The B-Net results are characterized by small relative errors and stable trends. The B-Net is further shown capable of processing data with a signal-to-noise ratio equal to 1, an impossibility for threshold-based algorithms. The B-Net presents a generic architecture applicable to pulse-like signals beyond nanopore currents.
Palavras-chave
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Nanoporos
/
Aprendizado Profundo
Idioma:
En
Revista:
ACS Nano
Ano de publicação:
2021
Tipo de documento:
Article