Interpreting deep neural networks for the prediction of translation rates.

Journal: BMC genomics
PMID: 39522049

Abstract

BACKGROUND: The 5' untranslated region of mRNA strongly impacts the rate of translation initiation. A recent convolutional neural network (CNN) model accurately quantifies the relationship between massively parallel synthetic 5' untranslated regions (5'UTRs) and translation levels. However, the underlying biological features, which drive model predictions, remain elusive. Uncovering sequence determinants predictive of translation output may allow us to develop a more detailed understanding of translation regulation at the 5'UTR.

Authors

  • Frederick Korbel
    Max-Delbrück-Center for Molecular Medicine in the Helmholtz Association (MDC), Berlin Institute for Medical Systems Biology (BIMSB), Hannoversche Straße 28, Berlin, 10115, Germany.
  • Ekaterina Eroshok
    Max-Delbrück-Center for Molecular Medicine in the Helmholtz Association (MDC), Berlin Institute for Medical Systems Biology (BIMSB), Hannoversche Straße 28, Berlin, 10115, Germany.
  • Uwe Ohler
    Department of Biology, Humboldt Universität zu Berlin, 10117 Berlin, Germany; The Berlin Institute for Medical Systems Biology, Max Delbrück Center for Molecular Medicine, 10115 Berlin, Germany; Department of Computer Science, Humboldt Universität zu Berlin, 10117 Berlin, Germany. Electronic address: uwe.ohler@mdc-berlin.de.

Keywords

External Resources

Popular Topics
Recent Journals