Ultrasensitive MicroRNA Detection Combining Reduced Graphene Oxide Electrolyte-Gated Transistors and Machine Learning

Area of Science:

• Biomolecular Engineering
• Nanotechnology
• Machine Learning

Background:

• MicroRNAs (miRNAs) are vital biomarkers for disease diagnosis.
• Conventional detection methods like RT-PCR are complex and not suitable for portable diagnostics.
• The miR-34 family is linked to cancer and neurological disorders.

Purpose of the Study:

• To develop an ultrasensitive and selective biosensor for miRNA detection.
• To enable portable molecular diagnostics.
• To target the miR-34 family for disease association studies.

Main Methods:

• Integration of DNA-functionalized reduced graphene oxide (rGO) and electrolyte-gated transistors (EGTs).
• Utilized machine learning (ML) for data analysis of EGT transfer curves.
• Developed a biosensor for discriminating perfectly matched from mismatched miRNA sequences.

Main Results:

• Achieved an ultralow limit of detection of 0.098 amol L ^-1.
• Demonstrated high selectivity and a wide dynamic range (0.1-1000 amol L ^-1).
• ML enabled effective feature extraction from high-dimensional data.

Conclusions:

• The developed biosensor advances point-of-care technologies for miRNA detection.
• This platform shows strong potential for highly sensitive and selective portable molecular diagnostics.
• The integration of rGO, EGTs, and ML offers a promising approach for future diagnostic tools.