Single-Cell Nanomotion and Machine Learning for Parallel Bacterial Identification and Antibiotic Screening

Area of Science:

• Biotechnology
• Nanotechnology
• Machine Learning

Background:

• Accurate bacterial identification and antibiotic susceptibility testing (AST) are crucial for clinical decisions and combating antimicrobial resistance.
• Current methods like MALDI-TOF and standard AST are often segmented, time-consuming, and lack concurrent identification capabilities.
• Existing diagnostic tools present limitations in speed and integrated functionality for comprehensive bacterial profiling.

Purpose of the Study:

• To develop a single, rapid, and accurate method for simultaneous bacterial identification and antibiotic susceptibility profiling.
• To overcome the limitations of segmented diagnostic approaches by integrating nanomotion detection with machine learning.
• To provide a label-free, single-cell level diagnostic tool for bacterial infections.

Main Methods:

• Integration of single-cell nanomotion detection using graphene drums with machine learning (ML) algorithms.
• Real-time recording of nanomotion signals (nanoscale vibrations) from single living bacterial cells.
• Transformation of nanomotion signals into time-frequency spectrograms for ML model input and pattern recognition.

Main Results:

• Successful differentiation of bacterial species including Escherichia coli, Staphylococcus aureus, and Klebsiella pneumoniae.
• Simultaneous distinction between resistant and susceptible bacterial strains with 98% precision.
• Demonstration of label-free bacterial diagnostics with identification and susceptibility profiling within hours at the single-cell level.

Conclusions:

• The developed framework offers a significant advancement in bacterial diagnostics by combining sensitive graphene nanomotion sensors with ML.
• This integrated approach provides rapid, accurate, and simultaneous identification and antibiotic susceptibility profiling.
• The technology holds promise for improving clinical decision-making and addressing the challenge of antimicrobial resistance.