Sökning: id:"swepub:oai:DiVA.org:uu-457566" >
Deep Learning of Na...
Deep Learning of Nanopore Sensing Signals Using a Bi-Path Network
-
- Dematties, Dario (författare)
- Consejo Nacl Invest Cient & Tecn, Mendoza Technol Sci Ctr, Inst Ciencias Humanas Sociales & Ambientales, M5500, Mendoza, Argentina.
-
- Wen, Chenyu (författare)
- Uppsala universitet,Fasta tillståndets elektronik,Uppsala Univ, Dept Elect Engn, Div Solid State Elect, SE-75103 Uppsala, Sweden.
-
- Perez, Mauricio D. (författare)
- Uppsala universitet,Fasta tillståndets elektronik,Uppsala Univ, Dept Elect Engn, Div Solid State Elect, SE-75103 Uppsala, Sweden.
-
visa fler...
-
- Zhou, Dian (författare)
- Univ Texas Dallas, Dept Elect & Comp Engn, Richardson, TX 75080 USA.
-
- Zhang, Shi-Li (författare)
- Uppsala universitet,Fasta tillståndets elektronik
-
visa färre...
-
Consejo Nacl Invest Cient & Tecn, Mendoza Technol Sci Ctr, Inst Ciencias Humanas Sociales & Ambientales, M5500, Mendoza, Argentina Fasta tillståndets elektronik (creator_code:org_t)
- 2021-08-17
- 2021
- Engelska.
-
Ingår i: ACS Nano. - : American Chemical Society (ACS). - 1936-0851 .- 1936-086X. ; 15:9, s. 14419-14429
- Relaterad länk:
-
https://doi.org/10.1...
-
visa fler...
-
https://uu.diva-port... (primary) (Raw object)
-
https://pubs.acs.org...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- 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 bipath 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.
Ämnesord
- NATURVETENSKAP -- Biologi -- Biofysik (hsv//swe)
- NATURAL SCIENCES -- Biological Sciences -- Biophysics (hsv//eng)
Nyckelord
- neural network
- deep learning
- nanopore sensors
- pulse-like signals
- feature extraction
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
-
ACS Nano
(Sök värdpublikationen i LIBRIS)
Till lärosätets databas