Point-Wise Ribosome Translation Speed Prediction with Recurrent Neural Networks

Pietro Bongini (), Niccolò Pancino, Veronica Lachi, Caterina Graziani, Giorgia Giacomini, Paolo Andreini and Monica Bianchini
Additional contact information
Pietro Bongini: Department of Information Engineering and Mathematics, University of Siena, Via Roma 56, 53100 Siena, Italy
Niccolò Pancino: Department of Information Engineering and Mathematics, University of Siena, Via Roma 56, 53100 Siena, Italy
Veronica Lachi: Department of Information Engineering and Mathematics, University of Siena, Via Roma 56, 53100 Siena, Italy
Caterina Graziani: Department of Information Engineering and Mathematics, University of Siena, Via Roma 56, 53100 Siena, Italy
Giorgia Giacomini: IRCCS Ospedale San Raffaele, Via Olgettina 60, 20132 Milano, Italy
Paolo Andreini: Department of Information Engineering and Mathematics, University of Siena, Via Roma 56, 53100 Siena, Italy
Monica Bianchini: Department of Information Engineering and Mathematics, University of Siena, Via Roma 56, 53100 Siena, Italy

Mathematics, 2024, vol. 12, issue 3, 1-12

Abstract: Escherichia coli is a benchmark organism, which has been deeply studied by the scientific community for decades, obtaining a vast amount of metabolic and genetic data. Among these data, estimates of the translation speed of ribosomes over their genome are available. These estimates are based on Ribo-Seq profiles, where the abundance of a particular fragment of mRNA in a profile indicates that it was sampled many times inside a cell. Various measurements of Ribo-Seq profiles are available for Escherichia coli , yet they do not always show a high degree of correspondence, which means that they can vary significantly in different experimental setups, being characterized by poor reproducibility. Indeed, within Ribo-Seq profiles, the translation speed for some sequences is easier to estimate, while for others, an uneven distribution of consensus among the different estimates is evidenced. Our goal is to develop an artificial intelligence method that can be trained on a small pool of highly reproducible sequences to establish their translation rate, which can then be exploited to calculate a more reliable estimate of the translation speed on the rest of the genome.

Keywords: translation speed; ribosomes; Escherichia coli; Ribo-Seq profiles; neural networks; recurrent neural networks; translation speed prediction (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/3/465/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/3/465/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:3:p:465-:d:1330766

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().