YModPred: an interpretable prediction method for multi-type RNA modification sites in S. cerevisiae based on deep...

Area of Science:

• Molecular Biology
• Bioinformatics
• Computational Biology

Background:

• RNA post-transcriptional modifications alter RNA structure and function.
• These modifications impact crucial cellular processes like translation and stability.
• Accurate prediction of modification sites is key to understanding their mechanisms.

Purpose of the Study:

• To develop a novel deep learning model for predicting RNA modification sites.
• To accurately predict multiple types of RNA modification sites in S. cerevisiae based on RNA sequences.

Main Methods:

• Developed YModPred, a deep learning model utilizing convolution and self-attention mechanisms.
• Employed YModPred to capture global sequence information and local features for prediction.
• Predicted multi-type RNA modification sites in S. cerevisiae.

Main Results:

• YModPred demonstrated high accuracy in predicting various RNA modification types.
• The model outperformed existing state-of-the-art methods in comparative analyses.
• Prediction performance was validated through visualization and motif analysis.

Conclusions:

• YModPred effectively captures RNA sequence features for accurate prediction of multi-type modification sites.
• The model facilitates research into RNA modification mechanisms in S. cerevisiae.
• YModPred shows promise for advancing the study of RNA modifications.