Details

Autor(en) / Beteiligte

• Koo, Peter K
• Ploenzke, Matt
• Anand, Praveen
• Paul, Steffan
• Majdandzic, Antonio

Titel

ResidualBind: Uncovering Sequence-Structure Preferences of RNA-Binding Proteins with Deep Neural Networks

Ist Teil von

• Methods in molecular biology (Clifton, N.J.), 2023, Vol.2586, p.197

Ort / Verlag

United States

Erscheinungsjahr

2023

Quelle

MEDLINE

Beschreibungen/Notizen

• Deep neural networks have demonstrated improved performance at predicting sequence specificities of DNA- and RNA-binding proteins. However, it remains unclear why they perform better than previous methods that rely on k-mers and position weight matrices. Here, we highlight a recent deep learning-based software package, called ResidualBind, that analyzes RNA-protein interactions using only RNA sequence as an input feature and performs global importance analysis for model interpretability. We discuss practical considerations for model interpretability to uncover learned sequence motifs and their secondary structure preferences.