Simple and Multiplexed Detection of Nucleic Acid Targets Based on Fluorescent Ring Patterns and Deep Learning...

Area of Science:

• Biotechnology
• Molecular Diagnostics
• Bioanalytical Chemistry

Background:

• Simple nucleic acid diagnostic tests are crucial for rapid pathogen detection.
• Existing methods may lack sensitivity, multiplexing capability, or require complex instrumentation.

Purpose of the Study:

• To develop a novel membrane-based assay for multiplexed nucleic acid detection.
• To integrate isothermal amplification with fluorescent pattern visualization for enhanced diagnostics.
• To apply deep learning for automated analysis and quantification of assay results.

Main Methods:

• Developed the isothermal fluorescent ring-based radial flow assay (iFluor-RFA).
• Utilized cellulose nitrate membranes for radial chromatographic flow and solvent evaporation.
• Employed isothermal amplification and fluorescent oligonucleotide probes for target hybridization in a one-pot reaction.
• Applied deep learning algorithms to analyze fluorescence images for pattern classification and quantification.

Main Results:

• Demonstrated specific and sensitive detection of nucleic acid targets in the subpicomole range.
• Achieved multiplexed detection of SARS-CoV-2 receptor binding domain (RBD) and RNA-dependent RNA polymerase (RdRp) genes.
• Showed high accuracy in classifying positive/negative results using deep learning analysis.
• Successfully predicted quantitative amounts of target nucleic acids from fluorescence patterns.

Conclusions:

• The iFluor-RFA method offers a sensitive, specific, and multiplexed approach for nucleic acid detection.
• Integration with deep learning provides a powerful tool for automated diagnostic data analysis.
• This novel platform has versatile applications in rapid infectious pathogen detection and diagnostic development.