Related Experiment Video
Updated: May 11, 2026

Efficient Purification and LC-MS/MS-based Assay Development for Ten-Eleven Translocation-2 5-Methylcytosine Dioxygenase
Published on: October 15, 2018
Quantum-Transport Informed Machine Learning for Identifying Tobacco-Induced Regioisomeric DNA Adducts
Dipti Maurya1, Sneha Mittal1, Dyuti Chatterjee1
1Department of Chemistry, Indian Institute of Technology (IIT) Indore, Indore, Madhya Pradesh 453552, India.
Abstract:
Tobacco smoke contains a complex array of genotoxic carcinogens that form structurally diverse DNA adducts, driving mutagenesis and carcinogenesis. Among these, certain adducts exist as regioisomers, differing in the specific site of covalent attachment on the nucleobase, which in turn alters their structural and electronic properties. Detecting these adducts remains challenging due to subtle structural variations. To overcome the limitations of conventional protein-based nanopores, we developed a machine learning-empowered graphene nanogap platform integrating quantum transport analysis with a semisupervised framework. Distinct tunneling signatures extracted from transmission spectra and I-V characteristics serve as electronic fingerprints for precise adduct identification. Employing a self-training random forest classifier, the system achieved high accuracy in automated recognition. Our approach enables the rapid and real-time detection of tobacco carcinogen DNA adducts, advancing biomarker discovery and cancer risk assessment.
Insights
This study introduces a new graphene nanogap platform using machine learning to detect tobacco carcinogen DNA adducts. This technology offers rapid, real-time identification of cancer-causing agents for improved risk assessment.
Area of Science:
- Nanotechnology
- Molecular Biology
- Machine Learning
Background:
- Tobacco smoke contains genotoxic carcinogens forming DNA adducts, crucial in mutagenesis and carcinogenesis.
- Regioisomers of DNA adducts present detection challenges due to subtle structural differences.
- Conventional protein-based nanopores have limitations in precise adduct identification.
Purpose of the Study:
- To develop an advanced platform for detecting and identifying tobacco carcinogen DNA adducts, including regioisomers.
- To overcome the limitations of existing nanopore technologies for adduct analysis.
- To enhance cancer risk assessment through improved biomarker discovery.
Main Methods:
- Development of a machine learning-empowered graphene nanogap platform.
- Integration of quantum transport analysis with a semisupervised learning framework.
- Utilizing transmission spectra and I-V characteristics for electronic fingerprint extraction.
- Employing a self-training random forest classifier for automated recognition.
Main Results:
- The platform successfully extracted distinct tunneling signatures for precise adduct identification.
- High accuracy was achieved in the automated recognition of DNA adducts.
- Demonstrated rapid and real-time detection capabilities for tobacco carcinogen DNA adducts.
Conclusions:
- The developed graphene nanogap platform offers a novel solution for detecting complex DNA adducts.
- This approach advances biomarker discovery for tobacco-related carcinogens.
- The technology holds significant potential for improving cancer risk assessment and early detection strategies.
More Related Videos
12:15Quantification of three DNA Lesions by Mass Spectrometry and Assessment of Their Levels in Tissues of Mice Exposed to Ambient Fine Particulate Matter
Published on: May 29, 2019
10:12Author Spotlight: Quantitative Detection of DNA Protein Crosslinks and Their Post-Translational Modifications
Published on: April 21, 2023
Related Concept Videos
Labeling DNA Probes
Radioisotopes, fluorophores, or small molecule binding partners like biotin or digoxigenin, are the most widely used reporter tags for labeling DNA probes. These labels can be attached to the probe DNA molecule via...
In vitro Mutagenesis
Pharmacogenomics: Identification of New Drug Targets
Applications of Molecular Taxonomy