i4mC-ROSE

i4mC-ROSE identifies N4-methylcytosine (N4mC) sites in the genomes of Fragaria vesca and Rosa chinensis (Rosaceae) to support analysis of epigenetic modifications involved in DNA replication and chromosome stability.

Key Features:

• Species specificity: Targeted to predict N4mC sites in Fragaria vesca and Rosa chinensis genomes.
• Classifier: Employs a random forest classifier for site prediction.
• Sequence encoding integration: Integrates six distinct encoding methods to capture multiple aspects of DNA sequence information.
• Cross-validation performance: Achieved AUC scores of 0.883 (Fragaria vesca) and 0.889 (Rosa chinensis) under cross-validation.
• Independent evaluation: Outperformed other tested classifiers on independent datasets.

Scientific Applications:

• Epigenetic site mapping in Rosaceae: Enables identification of N4mC sites for genomic and epigenomic studies in Fragaria vesca and Rosa chinensis.
• Functional studies of DNA processes: Supports investigation of N4mC roles in DNA replication and chromosome stability.

Methodology:

Uses a random forest classifier built from features derived via six distinct sequence-encoding methods; performance was assessed by cross-validation and independent-dataset evaluation.