Detection of SARS-CoV-2 using machine learning-enabled paper-assisted ratiometric fluorescent sensors based on target-induced magnetic DNAzyme

Biosens Bioelectron. 2024 Apr 4;255:116272. doi: 10.1016/j.bios.2024.116272. Online ahead of print.ABSTRACTThe development of an advanced analytical platform with regard to SARS-CoV-2 is crucial for public health. Herein, we present a machine learning platform based on paper-assisted ratiometric fluorescent sensors for highly sensitive detection of the SARS-CoV-2 RdRp gene. The assay involves target-induced rolling circle amplification to generate magnetic DNAzyme, which is then detectable using the paper-assisted ratiometric fluorescent sensor. This sensor detects the SARS-CoV-2 RdRp gene with a visible-fluorescence color response. Moreover, leveraging different fluorescence responses, the ResNet algorithm of machine learning assists in accurately identifying fluorescence images and differentiating the concentration of the SARS-CoV-2 RdRp gene with over 99% recognition accuracy. The machine learning platform exhibits exceptional sensitivity and color responsiveness, achieving a limit of detection of 30 fM for the SARS-CoV-2 RdRp gene. The integration of intelligent artificial vision with the paper-assisted ratiometric fluorescent sensor presents a novel approach for the on-site detection of COVID-19 and holds potential for broader use in disease diagnostics in the future.PMID:38581837 | DOI:10.1016/j.bios.2024.116272
Source: Biosensors and Bioelectronics - Category: Biotechnology Authors: Source Type: research