OriC-ENS: A sequence-based ensemble classifier for predicting origin of replication in S. cerevisiae.

Area of Science:

• Genomics
• Molecular Biology
• Bioinformatics

Background:

• DNA Replication is fundamental for biological inheritance, ensuring genetic information transfer.
• The Origin of Replication (ORI) is critical for initiating DNA replication and understanding genomic mechanisms.
• Accurate ORI identification is essential for detailed biochemical and genomic analysis.

Purpose of the Study:

• To develop and evaluate a novel computational approach for accurate identification of DNA replication origins.
• To improve the understanding of molecular mechanisms governing DNA replication initiation.
• To provide a robust tool for genomic analysis related to DNA replication.

Main Methods:

• Proposed OriC-ENS, a novel approach utilizing sequence-based feature extraction (K-mer, K-gapped Mono-Di, Di-Mono).
• Employed an ensemble classification technique with three SVM classifiers and majority voting for prediction.
• Validated the method on S. Cerevisiae and Schizosaccharomyces pombe datasets.

Main Results:

• Achieved 91.62% accuracy on the S. Cerevisiae dataset, surpassing state-of-the-art methods.
• Obtained high scores for MCC (0.83), AUC (0.98), Sensitivity (0.90), and Specificity (0.92).
• Demonstrated efficient and precise ORI prediction on an independent test set from OriDB.

Conclusions:

• OriC-ENS offers a highly accurate and efficient method for identifying DNA replication origins.
• The sequence-based feature extraction and ensemble classification approach proves effective for genomic analysis.
• The developed tool is valuable for advancing research in DNA replication and inheritance, with source code publicly available.