Dec 16 2021 Deep learning methods are unable to predict RNA secondary structures

RNA structure prediction might seem like an ideal fit for machine learning, but it's more challenging than you might think. In this paper, we explore these difficulties by using synthetic data generated by ViennaRNA's RNAfold, offering a controlled environment to study how neural networks handle RNA secondary structure prediction. What we found suggests that the limitations seen in artificial settings can directly translate to real-world data, raising important questions about the effectiveness of current machine learning approaches in this field.

May 06 2019 Musashi binding elements in Zika virus 3'UTR

Discovering the characteristic traits of Musashi Binding Elements (MBEs) in Flaviviruses with a Thermodynamic Model

Jul 01 2018 Co-transcriptional riboswitch modleing with ViennaRNA

Riboswitches are RNA molecules that regulate gene expression by sensing metabolites, presenting an interesting target for synthetic biology applications. We present a computational approach based on ViennaRNA tools to dissect and model RNA-ligand interaction dynamics under kinetic control, enabling simulation of riboswitch folding

Jul 01 2018 In silico design of ligand triggered RNA switches

In the world of synthetic biology, the design of RNA switches holds immense promise for various applications, ranging from diagnostics to therapeutics. This paper presents a comprehensive workflow for designing RNA switches that can dynamically alter their structural conformations in response to specific ligands

Jul 01 2016 RNA structural insights through prediction and probing

This review explores methods for predicting RNA secondary structures by integrating reactivity information from experimental probing data. It highlights the limitations of traditional RNA structure prediction, which typically relies solely on thermodynamic models based on sequences