Cargando…

Combination of Single-Molecule Electrical Measurements and Machine Learning for the Identification of Single Biomolecules

[Image: see text] The development of a next-generation DNA sequencer has provided a method for electrically measuring single molecules. Methods for electrically measuring one molecule are roughly divided into methods for measuring tunneling and ion currents. These methods enable identification of a...

Descripción completa

Detalles Bibliográficos
Autor principal: Taniguchi, Masateru
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Chemical Society 2020
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6977028/
https://www.ncbi.nlm.nih.gov/pubmed/31984250
http://dx.doi.org/10.1021/acsomega.9b03660
_version_ 1783490421908832256
author Taniguchi, Masateru
author_facet Taniguchi, Masateru
author_sort Taniguchi, Masateru
collection PubMed
description [Image: see text] The development of a next-generation DNA sequencer has provided a method for electrically measuring single molecules. Methods for electrically measuring one molecule are roughly divided into methods for measuring tunneling and ion currents. These methods enable identification of a single molecule of DNA, a RNA nucleotide, or a single protein based on current histograms. However, overlapping of current histograms of molecules with similar properties has been a major barrier to identifying single molecules with high accuracy. This barrier was broken by introducing machine learning. Combining single-molecule electrical measurement and machine learning enables high-precision identification of single molecules. Highly accurate discrimination has been demonstrated for DNA nucleotides, RNA nucleotides, amino acids, sugars, viruses, and bacteria. This combination enables quantitative evaluation of molecular recognition ability. Furthermore, a device structure suitable for high-precision identification has been designed. Combining single-molecule electrical measurement with machine learning enables digital analytical chemistry that can count certain types of molecules. Digital analytical chemistry enables comprehensive analysis of chemical reactions. This new analytical method will lead to the discovery of unknown or missed valuable molecules.
format Online
Article
Text
id pubmed-6977028
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher American Chemical Society
record_format MEDLINE/PubMed
spelling pubmed-69770282020-01-24 Combination of Single-Molecule Electrical Measurements and Machine Learning for the Identification of Single Biomolecules Taniguchi, Masateru ACS Omega [Image: see text] The development of a next-generation DNA sequencer has provided a method for electrically measuring single molecules. Methods for electrically measuring one molecule are roughly divided into methods for measuring tunneling and ion currents. These methods enable identification of a single molecule of DNA, a RNA nucleotide, or a single protein based on current histograms. However, overlapping of current histograms of molecules with similar properties has been a major barrier to identifying single molecules with high accuracy. This barrier was broken by introducing machine learning. Combining single-molecule electrical measurement and machine learning enables high-precision identification of single molecules. Highly accurate discrimination has been demonstrated for DNA nucleotides, RNA nucleotides, amino acids, sugars, viruses, and bacteria. This combination enables quantitative evaluation of molecular recognition ability. Furthermore, a device structure suitable for high-precision identification has been designed. Combining single-molecule electrical measurement with machine learning enables digital analytical chemistry that can count certain types of molecules. Digital analytical chemistry enables comprehensive analysis of chemical reactions. This new analytical method will lead to the discovery of unknown or missed valuable molecules. American Chemical Society 2020-01-07 /pmc/articles/PMC6977028/ /pubmed/31984250 http://dx.doi.org/10.1021/acsomega.9b03660 Text en Copyright © 2020 American Chemical Society This is an open access article published under a Creative Commons Attribution (CC-BY) License (http://pubs.acs.org/page/policy/authorchoice_ccby_termsofuse.html) , which permits unrestricted use, distribution and reproduction in any medium, provided the author and source are cited.
spellingShingle Taniguchi, Masateru
Combination of Single-Molecule Electrical Measurements and Machine Learning for the Identification of Single Biomolecules
title Combination of Single-Molecule Electrical Measurements and Machine Learning for the Identification of Single Biomolecules
title_full Combination of Single-Molecule Electrical Measurements and Machine Learning for the Identification of Single Biomolecules
title_fullStr Combination of Single-Molecule Electrical Measurements and Machine Learning for the Identification of Single Biomolecules
title_full_unstemmed Combination of Single-Molecule Electrical Measurements and Machine Learning for the Identification of Single Biomolecules
title_short Combination of Single-Molecule Electrical Measurements and Machine Learning for the Identification of Single Biomolecules
title_sort combination of single-molecule electrical measurements and machine learning for the identification of single biomolecules
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6977028/
https://www.ncbi.nlm.nih.gov/pubmed/31984250
http://dx.doi.org/10.1021/acsomega.9b03660
work_keys_str_mv AT taniguchimasateru combinationofsinglemoleculeelectricalmeasurementsandmachinelearningfortheidentificationofsinglebiomolecules