Comparison and benchmark of deep learning methods for non-coding RNA classification

Constance Creux (1, 2) , Farida Zehraoui (1) , François Radvanyi (2) , Fariza Tahi (1)

1 IBISC - Informatique, BioInformatique, Systèmes Complexes
2 Institut Curie [Paris]

The grouping of non-coding RNAs into functional classes started in the 1950s with housekeeping RNAs. Since, multiple additional classes were described. The involvement of non-coding RNAs in biological processes and diseases has made their characterization crucial, creating a need for computational methods that can classify large sets of non-coding RNAs. In recent years, the success of deep learning in various domains led to its application to non-coding RNA classification. Multiple novel architectures have been developed, but these advancements are not covered by current literature reviews. We propose a comparison of the different approaches and of non-coding RNA datasets proposed in the state-of-the-art. Then, we perform experiments to fairly evaluate the performance of various tools for non-coding RNA classification on two popular datasets. With regard to these results, we assess the relevance of the different architectural choices and provide recommendations to consider in future methods.

Keywords: Non-coding RNA; Non-coding RNA classification; Deep leaning; non-coding RNA non-coding rna classification deep learning; non-coding RNA; non-coding rna classification; deep learning

Domains: Bioinformatics [q-bio.QM]; Neural and Evolutionary Computing [cs.NE]

Constance Creux, Farida Zehraoui, François Radvanyi, Fariza Tahi. Comparison and benchmark of deep learning methods for non-coding RNA classification. 2024. ⟨hal-04437995⟩