Deep Learning-Enhanced Potentiometric Aptasensing with Magneto-Controlled Sensors

Area of Science:

• Bioelectronic sensors
• Analytical chemistry
• Nanotechnology

Background:

• Potentiometric sensors face challenges like Debye Length limitations for sensitive analyte detection.
• Directly measuring charge changes upon biomolecule target binding is difficult.

Purpose of the Study:

• To develop a magneto-controlled potentiometric method for sensitive detection of small molecules.
• To overcome limitations in current potentiometric measurement techniques.

Main Methods:

• Utilized magnetic beads with DNA aptamers for a polymeric membrane potentiometric ion sensor.
• Employed a magnetic field to dynamically control and modulate aptamer charge responses.
• Integrated a potentiometric array with deep learning algorithms for analysis.

Main Results:

• Successfully measured target-binding induced charge changes of DNA aptamers.
• Demonstrated rapid and reliable classification and quantification of small molecules (antibiotics).
• Achieved sensitive analyte detection overcoming Debye Length limitations.

Conclusions:

• The magneto-controlled potentiometric strategy offers a new approach for sensitive sensing applications.
• This non-equilibrium measurement technique combined with deep learning enhances analyte detection capabilities.