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.

Posted by Michael T. Wolfinger on in publications. updated Tags: ViennaRNA, AI.

Functional RNA structures in the 3'UTR of Mosquito-Borne Flaviviruses

The 3'UTR of Mosquito-Borne Flaviviruses (MBF) contain evolutionarily conserved functional elements, such as exoribonuclease-resistant RNAs (xrRNAs), dumbbell elements or terminal stem-loops. In this contribution we describe, annotate, and compare these elements within different serological groups of MBF

Mpulungu Virus: A glimpse into Africa's novel tick-borne flavivirus

The discovery of Mpulungu virus (MPFV), a novel tick-borne flavivirus in Zambia, expands our understanding of the geographical distribution and genetic diversity of flaviviruses across Africa. This study delves into the genetic details of MPFV, suggesting its potential to infect vertebrate hosts and underscoring the importance of a One Health approach in addressing emerging infectious diseases

« newer articles | page 4 | older articles »