Utilizing biological experimental data and molecular dynamics for the classification of mutational hotspots through...

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.