Inferring Sequence-Structure Preferences of RNA-Binding Proteins with Convolutional Residual Networks

Citations Over Time

Abstract

Abstract To infer the sequence and RNA structure specificities of RNA-binding proteins (RBPs) from experiments that enrich for bound sequences, we introduce a convolutional residual network which we call ResidualBind. ResidualBind significantly outperforms previous methods on experimental data from many RBP families. We interrogate ResidualBind to identify what features it has learned from high-affinity sequences with saliency analysis along with 1st-order and 2nd-order in silico mutagenesis. We show that in addition to sequence motifs, ResidualBind learns a model that includes the number of motifs, their spacing, and both positive and negative effects of RNA structure context. Strikingly, ResidualBind learns RNA structure context, including detailed base-pairing relationships, directly from sequence data, which we confirm on synthetic data. ResidualBind is a powerful, flexible, and interpretable model that can uncover cis -recognition preferences across a broad spectrum of RBPs.

Related Papers

• → Finding the target sites of RNA‐binding proteins(2013)99 cited
• → 2D Meets 4G: G-Quadruplexes in RNA Secondary Structure Prediction(2013)48 cited
• → Comparative analysis of RNA secondary structure accuracy on predicted RNA 3D models(2023)5 cited
• → FledFold: A Novel Software for RNA Secondary Structure Prediction(2017)8 cited
• → Mutational Patterns in RNA Secondary Structure Evolution Examined in Three RNA Families(2011)8 cited