Cargando…

Deep learning of the regulatory grammar of yeast 5′ untranslated regions from 500,000 random sequences

Our ability to predict protein expression from DNA sequence alone remains poor, reflecting our limited understanding of cis-regulatory grammar and hampering the design of engineered genes for synthetic biology applications. Here, we generate a model that predicts the protein expression of the 5′ unt...

Descripción completa

Detalles Bibliográficos
Autores principales: Cuperus, Josh T., Groves, Benjamin, Kuchina, Anna, Rosenberg, Alexander B., Jojic, Nebojsa, Fields, Stanley, Seelig, Georg
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Cold Spring Harbor Laboratory Press 2017
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5741052/
https://www.ncbi.nlm.nih.gov/pubmed/29097404
http://dx.doi.org/10.1101/gr.224964.117
_version_ 1783288135884472320
author Cuperus, Josh T.
Groves, Benjamin
Kuchina, Anna
Rosenberg, Alexander B.
Jojic, Nebojsa
Fields, Stanley
Seelig, Georg
author_facet Cuperus, Josh T.
Groves, Benjamin
Kuchina, Anna
Rosenberg, Alexander B.
Jojic, Nebojsa
Fields, Stanley
Seelig, Georg
author_sort Cuperus, Josh T.
collection PubMed
description Our ability to predict protein expression from DNA sequence alone remains poor, reflecting our limited understanding of cis-regulatory grammar and hampering the design of engineered genes for synthetic biology applications. Here, we generate a model that predicts the protein expression of the 5′ untranslated region (UTR) of mRNAs in the yeast Saccharomyces cerevisiae. We constructed a library of half a million 50-nucleotide-long random 5′ UTRs and assayed their activity in a massively parallel growth selection experiment. The resulting data allow us to quantify the impact on protein expression of Kozak sequence composition, upstream open reading frames (uORFs), and secondary structure. We trained a convolutional neural network (CNN) on the random library and showed that it performs well at predicting the protein expression of both a held-out set of the random 5′ UTRs as well as native S. cerevisiae 5′ UTRs. The model additionally was used to computationally evolve highly active 5′ UTRs. We confirmed experimentally that the great majority of the evolved sequences led to higher protein expression rates than the starting sequences, demonstrating the predictive power of this model.
format Online
Article
Text
id pubmed-5741052
institution National Center for Biotechnology Information
language English
publishDate 2017
publisher Cold Spring Harbor Laboratory Press
record_format MEDLINE/PubMed
spelling pubmed-57410522018-06-01 Deep learning of the regulatory grammar of yeast 5′ untranslated regions from 500,000 random sequences Cuperus, Josh T. Groves, Benjamin Kuchina, Anna Rosenberg, Alexander B. Jojic, Nebojsa Fields, Stanley Seelig, Georg Genome Res Research Our ability to predict protein expression from DNA sequence alone remains poor, reflecting our limited understanding of cis-regulatory grammar and hampering the design of engineered genes for synthetic biology applications. Here, we generate a model that predicts the protein expression of the 5′ untranslated region (UTR) of mRNAs in the yeast Saccharomyces cerevisiae. We constructed a library of half a million 50-nucleotide-long random 5′ UTRs and assayed their activity in a massively parallel growth selection experiment. The resulting data allow us to quantify the impact on protein expression of Kozak sequence composition, upstream open reading frames (uORFs), and secondary structure. We trained a convolutional neural network (CNN) on the random library and showed that it performs well at predicting the protein expression of both a held-out set of the random 5′ UTRs as well as native S. cerevisiae 5′ UTRs. The model additionally was used to computationally evolve highly active 5′ UTRs. We confirmed experimentally that the great majority of the evolved sequences led to higher protein expression rates than the starting sequences, demonstrating the predictive power of this model. Cold Spring Harbor Laboratory Press 2017-12 /pmc/articles/PMC5741052/ /pubmed/29097404 http://dx.doi.org/10.1101/gr.224964.117 Text en © 2017 Cuperus et al.; Published by Cold Spring Harbor Laboratory Press http://creativecommons.org/licenses/by-nc/4.0/ This article is distributed exclusively by Cold Spring Harbor Laboratory Press for the first six months after the full-issue publication date (see http://genome.cshlp.org/site/misc/terms.xhtml). After six months, it is available under a Creative Commons License (Attribution-NonCommercial 4.0 International), as described at http://creativecommons.org/licenses/by-nc/4.0/.
spellingShingle Research
Cuperus, Josh T.
Groves, Benjamin
Kuchina, Anna
Rosenberg, Alexander B.
Jojic, Nebojsa
Fields, Stanley
Seelig, Georg
Deep learning of the regulatory grammar of yeast 5′ untranslated regions from 500,000 random sequences
title Deep learning of the regulatory grammar of yeast 5′ untranslated regions from 500,000 random sequences
title_full Deep learning of the regulatory grammar of yeast 5′ untranslated regions from 500,000 random sequences
title_fullStr Deep learning of the regulatory grammar of yeast 5′ untranslated regions from 500,000 random sequences
title_full_unstemmed Deep learning of the regulatory grammar of yeast 5′ untranslated regions from 500,000 random sequences
title_short Deep learning of the regulatory grammar of yeast 5′ untranslated regions from 500,000 random sequences
title_sort deep learning of the regulatory grammar of yeast 5′ untranslated regions from 500,000 random sequences
topic Research
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5741052/
https://www.ncbi.nlm.nih.gov/pubmed/29097404
http://dx.doi.org/10.1101/gr.224964.117
work_keys_str_mv AT cuperusjosht deeplearningoftheregulatorygrammarofyeast5untranslatedregionsfrom500000randomsequences
AT grovesbenjamin deeplearningoftheregulatorygrammarofyeast5untranslatedregionsfrom500000randomsequences
AT kuchinaanna deeplearningoftheregulatorygrammarofyeast5untranslatedregionsfrom500000randomsequences
AT rosenbergalexanderb deeplearningoftheregulatorygrammarofyeast5untranslatedregionsfrom500000randomsequences
AT jojicnebojsa deeplearningoftheregulatorygrammarofyeast5untranslatedregionsfrom500000randomsequences
AT fieldsstanley deeplearningoftheregulatorygrammarofyeast5untranslatedregionsfrom500000randomsequences
AT seeliggeorg deeplearningoftheregulatorygrammarofyeast5untranslatedregionsfrom500000randomsequences