A Caltech Library Service

Accurate design of translational output by a neural network model of ribosome distribution

Tunney, Robert and McGlincy, Nicholas J. and Graham, Monica E. and Naddaf, Nicki and Pachter, Lior and Lareau, Liana F. (2018) Accurate design of translational output by a neural network model of ribosome distribution. Nature Structural & Molecular Biology, 25 (7). pp. 577-582. ISSN 1545-9985. PMCID PMC6457438.

[img] PDF - Accepted Version
See Usage Policy.

[img] PDF - Submitted Version
Creative Commons Attribution.

[img] PDF (Supplementary Figures 1–7, Supplementary Notes 1–3 and Supplementary Tables 1 and 2) - Supplemental Material
See Usage Policy.

[img] PDF (Reporting Summary) - Supplemental Material
See Usage Policy.

[img] MS Excel (Supplementary Table 3) - Supplemental Material
See Usage Policy.

[img] Plain Text (Supplementary Dataset 1) - Supplemental Material
See Usage Policy.

[img] PDF - Supplemental Material
Creative Commons Attribution.

[img] Plain Text (Supplemental Table 1 - codon scores) - Supplemental Material
Creative Commons Attribution.

[img] Plain Text (Supplemental Table 2 - oligos) - Supplemental Material
Creative Commons Attribution.

[img] Plain Text (Supplemental File 2 - plasmid sequences) - Supplemental Material
Creative Commons Attribution.


Use this Persistent URL to link to this item:


Synonymous codon choice can have dramatic effects on ribosome speed and protein expression. Ribosome profiling experiments have underscored that ribosomes do not move uniformly along mRNAs. Here, we have modeled this variation in translation elongation by using a feed-forward neural network to predict the ribosome density at each codon as a function of its sequence neighborhood. Our approach revealed sequence features affecting translation elongation and characterized large technical biases in ribosome profiling. We applied our model to design synonymous variants of a fluorescent protein spanning the range of translation speeds predicted with our model. Levels of the fluorescent protein in budding yeast closely tracked the predicted translation speeds across their full range. We therefore demonstrate that our model captures information determining translation dynamics in vivo; that this information can be harnessed to design coding sequences; and that control of translation elongation alone is sufficient to produce large quantitative differences in protein output.

Item Type:Article
Related URLs:
URLURL TypeDescription ReadCube access Paper CentralArticle
McGlincy, Nicholas J.0000-0003-1412-2298
Pachter, Lior0000-0002-9164-6231
Lareau, Liana F.0000-0003-3223-3426
Additional Information:© 2018 Springer Nature Limited. Received 21 November 2017; Accepted 11 May 2018; Published 02 July 2018. We are grateful to N. Ingolia and S. McCurdy for discussion. This work was supported by the National Cancer Institute of the National Institutes of Health, under award R21CA202960 to L.F.L., and by the National Institute of General Medical Sciences of the National Institutes of Health, under award P50GM102706 to the Berkeley Center for RNA Systems Biology. R.T. was supported by the Department of Defense through the National Defense Science & Engineering Graduate Fellowship (NDSEG) Program. This work made use of the Vincent J. Coates Genomics Sequencing Laboratory at the University of California, Berkeley, supported by National Institutes of Health S10 Instrumentation grant OD018174, and the UC Berkeley flow cytometry core facilities. Author Contributions: L.F.L., R.T., and N.J.M. designed the study, with input from L.P. R.T. developed the software and performed modeling, and R.T., L.P., and L.F.L. analyzed and interpreted the computational results. N.J.M. designed and created the yeast strains and performed expression experiments, with assistance from M.E.G. and N.N. M.E.G. performed yeast ribosome profiling. N.J.M. and L.F.L. analyzed and interpreted the experimental data. R.T. and L.F.L. wrote the manuscript, with input from all authors. The authors declare no competing interests. Data availability: Ribosome profiling sequence data generated in this study have been deposited in the NCBI GEO database under accession number GSE106572. All Iχnos software and analysis scripts, including a complete workflow of analyses in this paper and all analyzed data used to create figures, can be found at
Funding AgencyGrant Number
National Defense Science and Engineering Graduate (NDSEG) FellowshipUNSPECIFIED
Issue or Number:7
PubMed Central ID:PMC6457438
Record Number:CaltechAUTHORS:20180423-152534642
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:86015
Deposited By: Katherine Johnson
Deposited On:25 Apr 2018 19:43
Last Modified:03 Oct 2019 19:38

Repository Staff Only: item control page