ORFhunteR

ORFhunteR predicts and annotates open reading frames in large sets of RNA molecules using a machine learning model based on nucleotide sequence vectorization and random forest classification.

Key Features:

• ORF Prediction: Automatically determines and annotates open reading frames in nucleotide sequences.
• Machine Learning Classification: Implements random forest classification on vectorized nucleotide sequences.
• Multi-Database Validation: Efficiency confirmed using RNA molecules from NCBI RefSeq and Ensembl databases.
• Integrated Implementation: Combines R language functions with C++ for computational performance.

Scientific Applications:

• Transcriptome Analysis: Supports study of transcriptomes in normal human cells.
• Cancer Research: Supports study of transcriptomes in altered human cells such as cancer cells.
• Biomedical Research: Applicable to basic and applied biomedical research involving RNA sequence analysis.

Methodology:

ORFhunteR uses vectorization of nucleotide sequences followed by random forest classification to predict open reading frames. The implementation combines R with C++.