Machine Learning-Driven Sensor Array Based on a DNA-Programmed Pt Nanozyme with Enhanced Dual-Enzyme-like Activities...

Area of Science:

• Nanotechnology
• Environmental Science
• Analytical Chemistry

Background:

• Nanozyme sensor arrays face limitations in practical applications due to complexity and interference.
• Simultaneous detection of multiple sulfur-containing species is crucial for environmental monitoring.

Purpose of the Study:

• To develop a machine-learning-empowered sensor array using a single nanozyme with dual-enzyme activity.
• To enable simultaneous discrimination of five sulfur-containing species (sulfide, thiosulfate, persulfate, sulfite, sulfate).

Main Methods:

• Fabrication of platinum nanozymes (Pt nanozymes) with enhanced peroxidase-like and laccase-like activities using a DNA-modulating strategy.
• Development of a sensor array utilizing a single A10@Pt nanozyme as the sensing element.
• Application of a machine-learning algorithm to build a stepwise prediction model for species identification.

Main Results:

• The A10@Pt nanozyme exhibited significantly enhanced peroxidase-like (5.5-fold) and laccase-like (3.5-fold) activities compared to pure Pt nanozymes.
• The developed sensor array successfully discriminated and predicted five sulfur-containing species with high accuracy.
• The platform's efficacy was validated in real-world water samples (canal and Yangtze River water).

Conclusions:

• A robust, rapid, and intelligent detection platform for sulfur-containing species was established.
• This nanozyme sensor array offers a promising solution for environmental monitoring and sulfur pollution assessment.
• The integration of machine learning with nanozyme technology advances sensing capabilities for complex environmental matrices.