Quantum Transport Informed Machine Learning Mapping of Current-Voltage Characteristics for Precision Deoxyribonucleic...

Area of Science:

• Genomics
• Quantum Physics
• Machine Learning

Background:

• Quantum tunneling DNA sequencing offers potential for high-accuracy, high-throughput genomic analysis.
• Challenges include molecular conductance variations, signal noise, and overlapping patterns, hindering precise nucleotide identification.

Purpose of the Study:

• To develop a quantum transport and machine learning approach for accurate DNA molecule classification.
• To enhance single-molecule DNA sequencing by improving nucleotide identification accuracy.

Main Methods:

• Utilized a quantum transport model combined with a supervised machine learning algorithm.
• Classified DNA molecules based on electrical transmission, conductance, and tunneling current readouts.

Main Results:

• Achieved high classification accuracies: 100% for current, 98% for transmission, and 97% for conductance.
• Identified current-voltage characteristics as the most effective parameters for nucleotide differentiation.
• Demonstrated significant resolution of overlapping signal patterns.

Conclusions:

• The developed quantum transport and ML approach enables rapid and high-precision DNA sequencing.
• Findings provide a framework for mapping quantum readouts for advanced genomic applications.