Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

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

In Methods in molecular biology (Clifton, N.J.)

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.

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

2023

Deep learning, Global importance analysis, Model interpretability, Motif analysis, RNA-binding proteins, RNA-protein interactions, RNAcompete