CAEN

CAEN (Category Encoding) for RNA-Seq Data Classification. The software tool uses bulk and single-cell RNA-seq data to detect differentially expressed (DE) genes. The tool employs several statistical methods for the classification of these data. However, many genes are not differentially expressed and are therefore irrelevant for class distinction. Thus, the tool aims to remove these unrelated genes to improve the classification performance and reduce computation time.
The CAEN method proposes a new way of selecting feature genes for classification by encoding categories based on the rank of sequence samples for each gene in each class. The tool considers correlation coefficients between genes and classes with the rank of the sample to determine the most compelling feature genes. The Sure Screening method is also established to ensure consistency in the ranking process.