Rxivist logo

Deciphering the rules of mRNA structure differentiation in vivo and in vitro with deep neural networks in Saccharomyces cerevisiae

By Haopeng Yu, Wenjing Meng, Yuanhui Mao, Yi Zhang, Qing Sun, Shiheng Tao

Posted 03 Jun 2018
bioRxiv DOI: 10.1101/337733 (published DOI: 10.1080/15476286.2019.1612692)

In vivo mRNA structure is influenced by versatile factors in translation process, resulting in a significant differentiation of mRNA structure from that in vitro. Due to multiple factors caused the differentiation of in vivo and in vitro mRNA structures, it was tough to perform a further accuracy analysis of mRNA structures in previous studies. In this study, we elaborated a deep neural networks (DNN) model to predict structural stability of mRNA in vivo, by fitting six quantifiable features that may affect mRNA folding: ribosome density, minimum folding free energy, GC content, mRNA abundance, ribosomal initial density and position of mRNA structure. Simulation mutations of mRNA structure was designed and then fed into trained DNN model to compute their structural stability state. We found the unique effects of these six features on mRNA structural stability in vivo. Strikingly, a double-sided effect of ribosomal density on mRNA structural stability was identified. It could be speculated that higher stable structure leaded to an accumulation of ribosomes in the region of low ribosomal density, whereas higher ribosomal density resulted in unstable mRNA structure. Additionally, the trend and extent of these six features affecting mRNA structural stability in vivo could also be accurately predicted by DNN model. Recruitment of the deep neural networks provides a new paradigm to decipher the differentiation of mRNA structure in vivo and in vitro. This knowledge on mechanisms of influencing factors on mRNA structural stability will facilitate the design and functional analysis of mRNA structure in vivo.

Download data

  • Downloaded 480 times
  • Download rankings, all-time:
    • Site-wide: 45,793 out of 118,665
    • In bioinformatics: 4,882 out of 9,595
  • Year to date:
    • Site-wide: 70,435 out of 118,665
  • Since beginning of last month:
    • Site-wide: 60,951 out of 118,665

Altmetric data


Downloads over time

Distribution of downloads per paper, site-wide


PanLingua

Sign up for the Rxivist weekly newsletter! (Click here for more details.)


News