CoChat
Sign Up
PreprintCited by 57RNA and protein synthesis mechanismsRNA Research and SplicingGenomics and Phylogenetic Studies

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

Predicting Mean Ribosome Load for 5’UTR of any length using Deep Learning

Open access
Karollus, Alexander, Avsec, Žiga, Gagneur, Julien·2020·PLoS Computational Biology
DOI 10.1101/2020.06.15.152728PMC PMC8136849

Preprint — published as 10.1371/journal.pcbi.1008982 · Paper page

Open this paper in CoChat — free accountOpen PDF

Abstract

The 5’ untranslated region plays a key role in regulating mRNA translation and consequently protein abundance. Therefore, accurate modeling of 5’UTR regulatory sequences shall provide insights into translational control mechanisms and help interpret genetic variants. Recently, a model was trained on a massively parallel reporter assay to predict mean ribosome load (MRL) - a proxy for translation rate - directly from 5’UTR sequence with a high degree of accuracy. However, this model is restricted to sequence lengths investigated in the reporter assay and therefore cannot be applied to the majority of human sequences without a substantial loss of information. Here, we introduced frame pooling, a novel neural network operation that enabled the development of an MRL prediction model for 5’UTRs of any length. Our model shows state-of-the-art performance on fixed length randomized sequences, while offering better generalization performance on longer sequences and on a variety of translation-related genome-wide datasets. Variant interpretation is demonstrated on a 5’UTR variant of the gene HBB associated with beta-thalassemia. Frame pooling could find applications in other bioinformatics predictive tasks. Moreover, our model, released open source, could help pinpoint pathogenic genetic variants.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1101/2020.06.15.152728

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 47

  1. 10.1016/j.cell.2016.03.014 · DOI · Paper page
  2. 10.1371/journal.pcbi.1005535 · DOI · Paper page
  3. Eraslan B , Wang D , Gusic M , Prokisch H , Hallström BM , Uhlén M , et al. Quantification and discovery of sequence determinants of protein-Maximilians-Universitätper-Maximilians-UniversitätmRNA amount in 29 human tissues. Mol Syst Biol [Internet]. John Wiley & Sons, Ltd; 2019 [cited 2019 Sep 5];15. Available from: https://www.embopress.org/doi/abs/10.15252/msb.20188513 · DOI
  4. 10.1038/nature22293 · DOI · Paper page
  5. 10.1038/nrm2838 · DOI · Paper page
  6. 10.1016/0092-8674(78)90039-9 · DOI
  7. 10.1146/annurev-biochem-060713-035802 · DOI · Paper page
  8. Noderer WL , Flockhart RJ , Bhaduri A , de Arce AJD , Zhang J , Khavari PA , et al. Quantitative analysis of mammalian translation initiation sites by FACS -Maximilians-Universitätseq [Internet]. Molecular Systems Biology. 2014. p. 748. Available from: http://dx.doi.org/10.15252/msb.20145136 · DOI · Paper page
  9. 10.1093/nar/15.20.8125 · DOI
  10. 10.1073/pnas.83.9.2850 · DOI · Paper page
  11. 10.1073/pnas.87.21.8301 · DOI · Paper page
  12. 10.1073/pnas.0810916106 · DOI · Paper page
  13. 10.1101/gr.193342.115 · DOI · Paper page
  14. Hou J , Wang X , McShane E , Zauber H , Sun W , Selbach M , et al. Extensive allele-specific translational regulation in hybrid mice. Mol Syst Biol [Internet]. John Wiley & Sons, Ltd; 2015;11. Available from: https://www.embopress.org/doi/abs/10.15252/msb.156240 · DOI
  15. Whiffin N , Karczewski KJ , Zhang X , Chothani S. Characterising the loss-of-function impact of 5’untranslated region variants in whole genome sequence data from 15,708 individuals. BioRxiv [Internet]. biorxiv.org; 2019; Available from: https://www.biorxiv.org/content/10.1101/543504v1.abstract · DOI
  16. 10.1038/5082 · DOI
  17. 2018, Genetic variants in mRNA untranslated regions, Wiley Interdiscip Rev RNA, 9, e1474, 10.1002/wrna.1474 · DOI
  18. 1997, Neural network prediction of translation initiation sites in eukaryotes: perspectives for EST and genome analysis, Proc Int Conf Intell Syst Mol Biol, 5, 226
  19. 10.1093/bioinformatics/16.9.799 · DOI
  20. Reuter K , Biehl A , Koch L , Helms V. PreTIS: A Tool to Predict Non-canonical 5’ UTR Translational Initiation Sites in Human and Mouse [Internet]. PLOS Computational Biology. 2016. p. e1005170. Available from: http://dx.doi.org/10.1371/journal.pcbi.1005170 · DOI
  21. 10.1038/ncomms11663 · DOI
  22. 2017, TITER: predicting translation initiation sites by deep learning, Bioinformatics, 33, i234, 10.1093/bioinformatics/btx247 · DOI
  23. 10.1089/cmb.2005.12.702 · DOI
  24. 2019, Human 5′ UTR design and variant effect prediction from a massively parallel translation assay, Nat Biotechnol, 37, 803, 10.1038/s41587-019-0164-5 · DOI · Paper page
  25. 2002, Untranslated regions of mRNAs, Genome Biol, 3, REVIEWS0004
  26. Lin M , Chen Q , Yan S. Network In Network [Internet]. arXiv [cs.NE]. 2013. Available from: http://arxiv.org/abs/1312.4400 · arXiv
  27. Springenberg JT , Dosovitskiy A , Brox T , Riedmiller M. Striving for Simplicity: The All Convolutional Net [Internet]. arXiv [cs.LG]. 2014. Available from: http://arxiv.org/abs/1412.6806 · arXiv
  28. 2019, The Kipoi repository accelerates community exchange and reuse of predictive models for genomics, Nat Biotechnol, 37, 592, 10.1038/s41587-019-0140-0 · DOI
  29. Diaz de Arce AJ , de Arce AJD , Noderer WL , Wang CL . Complete motif analysis of sequence requirements for translation initiation at non-AUG start codons [Internet]. Nucleic Acids Research. 2018. p. 985–94. Available from: http://dx.doi.org/10.1093/nar/gkx1114 · DOI
  30. 10.1126/science.1168978 · DOI · Paper page
  31. Vogel C , de Sousa Abreu R , Ko D , Le S-Y , Shapiro BA , Burns SC , et al. Sequence signatures and mRNA concentration can explain two-thirds of protein abundance variation in a human cell line. Mol Syst Biol [Internet]. John Wiley & Sons, Ltd; 2010;6. Available from: https://www.embopress.org/doi/abs/10.1038/msb.2010.59 · DOI · Paper page
  32. 10.7554/eLife.10921 · DOI · Paper page
  33. 10.7554/eLife.03971 · DOI
  34. 10.1016/j.molcel.2014.08.028 · DOI · Paper page
  35. 2016, Genome-wide assessment of differential translations with ribosome profiling data, Nat Commun. The Author(s), 7, 11194, 10.1038/ncomms11194 · DOI
  36. 10.1038/nature13319 · DOI · Paper page
  37. 10.1101/gr.097857.109 · DOI · Paper page
  38. 10.1046/j.1365-2141.2003.04754.x · DOI
  39. 1991, The G A mutation at position+ 22 3’to the Cap site of the beta-globin gene as a possible cause for a beta-thalassemia, Hemoglobin, 15, 67, 10.3109/03630269109072485 · DOI
  40. Shrikumar A , Greenside P , Kundaje A. Reverse-complement parameter sharing improves deep learning models for genomics. bioRxiv [Internet]. biorxiv.org; 2017; Available from: https://www.biorxiv.org/content/10.1101/103663v1.abstract · DOI
  41. 10.1162/neco.1997.9.8.1735 · DOI · Paper page
  42. Weingarten-Gabbay S , Elias-Kirma S , Nir R , Gritsenko AA , Stern-Ginossar N , Yakhini Z , et al. Comparative genetics. Systematic discovery of cap-independent translation sequences in human and viral genomes. Science [Internet]. 2016;351. Available from: http://dx.doi.org/10.1126/science.aad4939 · DOI · Paper page
  43. 2016, Toward a systematic understanding of translational regulatory elements in human and viruses, RNA Biol, 13, 927, 10.1080/15476286.2016.1212802 · DOI
  44. He K , Zhang X , Ren S , Sun J. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. p. 770–8. · DOI · Paper page
  45. Karczewski KJ , Francioli LC , Tiao G , Cummings BB . Variation across 141,456 human exomes and genomes reveals the spectrum of loss-of-function intolerance across human protein-coding genes. BioRxiv [Internet]. biorxiv.org; 2019; Available from: https://www.biorxiv.org/content/10.1101/531210v2.abstract · DOI
  46. Shrikumar A , Greenside P , Kundaje A. Learning Important Features Through Propagating Activation Differences. Proceedings of the 34th International Conference on Machine Learning - Volume 70. Sydney, NSW, Australia: JMLR.org; 2017. p. 3145–53.
  47. 10.1093/bioinformatics/btx727 · DOI

Metadata

Authors
Karollus, A., Avsec, Ž., & Gagneur, J.
Affiliations
  • Technical University of Munich (DE)
  • Helmholtz Munich (DE)
Corresponding author
Gagneur, Julien
ORCID
Venue
PLoS Computational Biology
Publisher
openRxiv
Published
2020-06-16
Volume
17
Issue
5
Pages
e1008982-e1008982
ISSN
1553-734X (ISSN-L)
DOI
10.1101/2020.06.15.152728
PMC
PMC8136849
OpenAlex
W3163562839
Cited by
57
References
1
Citations by year
2026: 16 · 2025: 16 · 2024: 12 · 2023: 7 · 2022: 1 · 2021: 5
FWCI
2.04
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • PLoS Computational Biology (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • PuSH - Publication Server of Helmholtz Zentrum München (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • mediaTUM (Technical University of Munich) (submittedVersion, other-oa)
Funders
Bundesministerium für Bildung und Forschung (01IS18053F)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › RNA and protein synthesis mechanisms
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › RNA Research and Splicing
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Phylogenetic Studies
Keywords
5' untranslated region, translation rate, neural network architecture, massively parallel reporter assay, translational regulation, variant interpretation, beta-thalassemia, HBB, protein abundance
MeSH terms
Deep Learning, Humans, Ribosomes, RNA, Messenger, 5' Untranslated Regions

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review