PRESa2i

PRESa2i predicts A-to-I RNA editing sites from RNA sequences to identify adenosine-to-inosine editing events and support analysis of their biological implications.

Key Features:

• Prediction target: Identifies Adenosine to Inosine (A-to-I) RNA editing sites in RNA sequences.
• Sequence-based features: Utilizes sequence-derived features extracted from RNA data.
• Feature selection: Applies an advanced feature selection technique to enhance predictive accuracy.
• Classifier: Employs an incremental decision tree algorithm as the classification mechanism.
• Evaluation: Validated on a standard benchmark dataset and an independent set with 86.48% accuracy and 90.67% sensitivity.
• Comparative performance: Demonstrates performance superior to existing state-of-the-art RNA editing prediction methods.

Scientific Applications:

• A-to-I site identification: Detection of adenosine-to-inosine editing sites in RNA sequences for downstream analyses.
• Biological implication analysis: Facilitates study of the roles of A-to-I editing in biological processes and diseases, including cancer.
• Method benchmarking: Provides a computational basis for comparing RNA editing prediction methods.

Methodology:

Uses sequence-based features, an advanced feature selection technique, and an incremental decision tree algorithm as the classifier; evaluated on a standard benchmark dataset and an independent set with reported accuracy of 86.48% and sensitivity of 90.67%.