Cargando…

Classification of nucleic acid amplification on ISFET arrays using spectrogram-based neural networks

The COVID-19 pandemic has highlighted a significant research gap in the field of molecular diagnostics. This has brought forth the need for AI-based edge solutions that can provide quick diagnostic results whilst maintaining data privacy, security and high standards of sensitivity and specificity. T...

Descripción completa

Detalles Bibliográficos
Autores principales: Tripathi, Prateek, Gulli, Costanza, Broomfield, Joseph, Alexandrou, George, Kalofonou, Melpomeni, Bevan, Charlotte, Moser, Nicolas, Georgiou, Pantelis
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Author(s). Published by Elsevier Ltd. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10176963/
https://www.ncbi.nlm.nih.gov/pubmed/37211003
http://dx.doi.org/10.1016/j.compbiomed.2023.107027
_version_ 1785040529182949376
author Tripathi, Prateek
Gulli, Costanza
Broomfield, Joseph
Alexandrou, George
Kalofonou, Melpomeni
Bevan, Charlotte
Moser, Nicolas
Georgiou, Pantelis
author_facet Tripathi, Prateek
Gulli, Costanza
Broomfield, Joseph
Alexandrou, George
Kalofonou, Melpomeni
Bevan, Charlotte
Moser, Nicolas
Georgiou, Pantelis
author_sort Tripathi, Prateek
collection PubMed
description The COVID-19 pandemic has highlighted a significant research gap in the field of molecular diagnostics. This has brought forth the need for AI-based edge solutions that can provide quick diagnostic results whilst maintaining data privacy, security and high standards of sensitivity and specificity. This paper presents a novel proof-of-concept method to detect nucleic acid amplification using ISFET sensors and deep learning. This enables the detection of DNA and RNA on a low-cost and portable lab-on-chip platform for identifying infectious diseases and cancer biomarkers. We show that by using spectrograms to transform the signal to the time–frequency domain, image processing techniques can be applied to achieve the reliable classification of the detected chemical signals. Transformation to spectrograms is beneficial as it makes the data compatible with 2D convolutional neural networks and helps gain significant performance improvement over neural networks trained on the time domain data. The trained network achieves an accuracy of 84% with a size of [Formula: see text] making it suitable for deployment on edge devices. This facilitates a new wave of intelligent lab-on-chip platforms that combine microfluidics, CMOS-based chemical sensing arrays and AI-based edge solutions for more intelligent and rapid molecular diagnostics.
format Online
Article
Text
id pubmed-10176963
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher The Author(s). Published by Elsevier Ltd.
record_format MEDLINE/PubMed
spelling pubmed-101769632023-05-12 Classification of nucleic acid amplification on ISFET arrays using spectrogram-based neural networks Tripathi, Prateek Gulli, Costanza Broomfield, Joseph Alexandrou, George Kalofonou, Melpomeni Bevan, Charlotte Moser, Nicolas Georgiou, Pantelis Comput Biol Med Article The COVID-19 pandemic has highlighted a significant research gap in the field of molecular diagnostics. This has brought forth the need for AI-based edge solutions that can provide quick diagnostic results whilst maintaining data privacy, security and high standards of sensitivity and specificity. This paper presents a novel proof-of-concept method to detect nucleic acid amplification using ISFET sensors and deep learning. This enables the detection of DNA and RNA on a low-cost and portable lab-on-chip platform for identifying infectious diseases and cancer biomarkers. We show that by using spectrograms to transform the signal to the time–frequency domain, image processing techniques can be applied to achieve the reliable classification of the detected chemical signals. Transformation to spectrograms is beneficial as it makes the data compatible with 2D convolutional neural networks and helps gain significant performance improvement over neural networks trained on the time domain data. The trained network achieves an accuracy of 84% with a size of [Formula: see text] making it suitable for deployment on edge devices. This facilitates a new wave of intelligent lab-on-chip platforms that combine microfluidics, CMOS-based chemical sensing arrays and AI-based edge solutions for more intelligent and rapid molecular diagnostics. The Author(s). Published by Elsevier Ltd. 2023-07 2023-05-12 /pmc/articles/PMC10176963/ /pubmed/37211003 http://dx.doi.org/10.1016/j.compbiomed.2023.107027 Text en © 2023 The Author(s) Since January 2020 Elsevier has created a COVID-19 resource centre with free information in English and Mandarin on the novel coronavirus COVID-19. The COVID-19 resource centre is hosted on Elsevier Connect, the company's public news and information website. Elsevier hereby grants permission to make all its COVID-19-related research that is available on the COVID-19 resource centre - including this research content - immediately available in PubMed Central and other publicly funded repositories, such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source. These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active.
spellingShingle Article
Tripathi, Prateek
Gulli, Costanza
Broomfield, Joseph
Alexandrou, George
Kalofonou, Melpomeni
Bevan, Charlotte
Moser, Nicolas
Georgiou, Pantelis
Classification of nucleic acid amplification on ISFET arrays using spectrogram-based neural networks
title Classification of nucleic acid amplification on ISFET arrays using spectrogram-based neural networks
title_full Classification of nucleic acid amplification on ISFET arrays using spectrogram-based neural networks
title_fullStr Classification of nucleic acid amplification on ISFET arrays using spectrogram-based neural networks
title_full_unstemmed Classification of nucleic acid amplification on ISFET arrays using spectrogram-based neural networks
title_short Classification of nucleic acid amplification on ISFET arrays using spectrogram-based neural networks
title_sort classification of nucleic acid amplification on isfet arrays using spectrogram-based neural networks
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10176963/
https://www.ncbi.nlm.nih.gov/pubmed/37211003
http://dx.doi.org/10.1016/j.compbiomed.2023.107027
work_keys_str_mv AT tripathiprateek classificationofnucleicacidamplificationonisfetarraysusingspectrogrambasedneuralnetworks
AT gullicostanza classificationofnucleicacidamplificationonisfetarraysusingspectrogrambasedneuralnetworks
AT broomfieldjoseph classificationofnucleicacidamplificationonisfetarraysusingspectrogrambasedneuralnetworks
AT alexandrougeorge classificationofnucleicacidamplificationonisfetarraysusingspectrogrambasedneuralnetworks
AT kalofonoumelpomeni classificationofnucleicacidamplificationonisfetarraysusingspectrogrambasedneuralnetworks
AT bevancharlotte classificationofnucleicacidamplificationonisfetarraysusingspectrogrambasedneuralnetworks
AT mosernicolas classificationofnucleicacidamplificationonisfetarraysusingspectrogrambasedneuralnetworks
AT georgioupantelis classificationofnucleicacidamplificationonisfetarraysusingspectrogrambasedneuralnetworks