Back

MettleRNASeq: Complex RNA-Seq Data Analysis and Gene Relationships Exploration Based on Machine Learning

Salles, S.; Brustolini, O.; Ciapina, L. P.; Ocana, K.

2025-05-10 bioinformatics
10.1101/2025.05.06.652387 bioRxiv
Show abstract

Typical differential gene expression (DGE) analysis might struggle when RNA-Seq datasets possess characteristics that hinder the power of statistical analyses and the obtention of accurate conclusions, such as a limited number of replicates and high variability. We present MettleRNASeq, a robust alternative for complex RNA-Seq data analysis that integrates machine learning techniques - a tailored classification approach, association rule mining, and complementary correlation analysis - to accurately identify key genes that distinguish experimental conditions and emphasize gene relationships. This approach provides full control over critical parameters, making it versatile for transcriptomic analyses and enhancing the comprehension of disease mechanisms, treatments, and their progression. MettleRNASeq was applied for the analysis of complex radiotherapy datasets. While popular DGE tools showed an inability to accurately differentiate the distinct radiotherapy treatments, MettleRNASeq effectively and consistently indicated relevant genes for condition discrimination and identified meaningful gene relationships related to radiotherapy, highlighting condition-specific and shared gene relationships. MettleRNASeq is implemented as an R package and available on GitHub at https://github.com/SamellaSalles/MettleRNASeq.

Matching journals

The top 11 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.