Related Experiment Video
Updated: Jun 14, 2025
Implementation of In Vitro Drug Resistance Assays: Maximizing the Potential for Uncovering Clinically Relevant Resistance Mechanisms
Published on: December 9, 2015
Utilizing biological experimental data and molecular dynamics for the classification of mutational hotspots through
James G Davies1, Georgina E Menzies1
1Molecular Bioscience Division, School of Biosciences, Cardiff University, Cardiff, CF10 3AX, United Kingdom.
Motivation:
Benzo[a]pyrene, a notorious DNA-damaging carcinogen, belongs to the family of polycyclic aromatic hydrocarbons commonly found in tobacco smoke. Surprisingly, nucleotide excision repair (NER) machinery exhibits inefficiency in recognizing specific bulky DNA adducts including Benzo[a]pyrene Diol-Epoxide (BPDE), a Benzo[a]pyrene metabolite. While sequence context is emerging as the leading factor linking the inadequate NER response to BPDE adducts, the precise structural attributes governing these disparities remain inadequately understood. We therefore combined the domains of molecular dynamics and machine learning to conduct a comprehensive assessment of helical distortion caused by BPDE-Guanine adducts in multiple gene contexts. Specifically, we implemented a dual approach involving a random forest classification-based analysis and subsequent feature selection to identify precise topological features that may distinguish adduct sites of variable repair capacity. Our models were trained using helical data extracted from duplexes representing both BPDE hotspot and nonhotspot sites within the TP53 gene, then applied to sites within TP53, cII, and lacZ genes.
Results:
We show our optimized model consistently achieved exceptional performance, with accuracy, precision, and f1 scores exceeding 91%. Our feature selection approach uncovered that discernible variance in regional base pair rotation played a pivotal role in informing the decisions of our model. Notably, these disparities were highly conserved among TP53 and lacZ duplexes and appeared to be influenced by the regional GC content. As such, our findings suggest that there are indeed conserved topological features distinguishing hotspots and nonhotpot sites, highlighting regional GC content as a potential biomarker for mutation.
Availability And Implementation:
Code for comparing machine learning classifiers and evaluating their performance is available at https://github.com/jdavies24/ML-Classifier-Comparison, and code for analysing DNA structure with Curves+ and Canal using Random Forest is available at https://github.com/jdavies24/ML-classification-of-DNA-trajectories.
Insights
This study reveals that regional base pair rotation and GC content in DNA can predict Benzo[a]pyrene Diol-Epoxide (BPDE) adduct repair efficiency. These topological features may serve as biomarkers for mutation hotspots.
Area of Science:
- Molecular Biology
- Bioinformatics
- Computational Chemistry
Background:
- Benzo[a]pyrene (BP) is a carcinogen forming DNA adducts.
- Nucleotide excision repair (NER) is inefficient at removing bulky BP adducts.
- Sequence context influences NER, but structural drivers are unclear.
Purpose of the Study:
- To assess helical distortions caused by BPDE-Guanine adducts using molecular dynamics and machine learning.
- To identify structural features distinguishing BPDE adduct sites with variable repair capacity.
- To investigate these features across different gene contexts (TP53, cII, lacZ).
Main Methods:
- Employed a random forest classification model to analyze helical data from DNA duplexes.
- Utilized feature selection to pinpoint critical topological determinants of repair.
- Trained models on TP53 gene data and applied them to TP53, cII, and lacZ.
Main Results:
- The optimized model achieved >91% accuracy, precision, and F1 scores.
- Regional base pair rotation emerged as a key predictor of repair capacity.
- These rotational disparities were conserved in TP53 and lacZ, influenced by GC content.
Conclusions:
- Conserved topological features, particularly regional base pair rotation and GC content, distinguish BPDE adduct hotspots.
- GC content may serve as a biomarker for DNA mutation hotspots.
- This work provides insights into the structural basis of differential DNA repair.
