Machine Learning-Enhanced Bacteria Detection Using a Fluorescent Sensor Array with Functionalized Graphene Quantum...

Area of Science:

• Biotechnology
• Materials Science
• Analytical Chemistry

Background:

• Pathogenic bacteria cause significant health issues, including foodborne illnesses and hospital-acquired infections.
• Accurate and rapid detection of these pathogens is crucial for public health security and disease control.
• Traditional detection methods often rely on large, costly equipment and can be time-consuming.

Purpose of the Study:

• To develop a rapid, cost-effective, and environmentally friendly fluorescent sensor array for pathogenic bacteria detection.
• To utilize nitrogen- and sulfur-doped graphene quantum dots (NS-GQDs) for broad-spectrum bacterial sensing.
• To enable quick and accurate identification and quantification of various bacterial species.

Main Methods:

• Synthesized nitrogen- and sulfur-doped graphene quantum dots (NS-GQDs) via a hydrothermal process.
• Functionalized NS-GQDs with antibiotics (spectinomycin, kanamycin, polymyxin B) to create S-NS-GQDs, K-NS-GQDs, and B-NS-GQDs.
• Employed a fluorescence quenching mechanism upon bacterial binding and utilized machine learning algorithms for data analysis.

Main Results:

• The sensor array achieved detection of bacteria within five minutes.
• The functionalized NS-GQDs exhibited variable affinities for different bacteria, enabling broad-spectrum detection.
• The platform demonstrated high accuracy, sensitivity, and stability in identifying and quantifying five bacterial species.

Conclusions:

• The developed fluorescent sensor array offers a rapid and efficient method for pathogenic bacterial detection.
• The use of NS-GQDs presents an environmentally friendly alternative to traditional detection methods.
• This technology holds significant promise for practical applications in public health and diagnostics.