A trainable language model with potential to modulate translation rates in non-model organisms by generating upstream untranslated region sequence libraries.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος:	A trainable language model with potential to modulate translation rates in non-model organisms by generating upstream untranslated region sequence libraries.
Συγγραφείς:	Duggan AD; Department of Chemical and Physical Sciences, University of Toronto Mississauga, Mississauga, Ontario, Canada.; Department of Cell and Systems Biology, University of Toronto, Toronto, Ontario, Canada., Newman MP; Department of Chemical and Physical Sciences, University of Toronto Mississauga, Mississauga, Ontario, Canada.; Department of Chemistry, University of Toronto, Toronto, Ontario, Canada., McMillen DR; Department of Chemical and Physical Sciences, University of Toronto Mississauga, Mississauga, Ontario, Canada.; Department of Cell and Systems Biology, University of Toronto, Toronto, Ontario, Canada.; Department of Chemistry, University of Toronto, Toronto, Ontario, Canada.
Πηγή:	PloS one [PLoS One] 2026 Sep 17; Vol. 21 (9), pp. e0348455. Date of Electronic Publication: 2026 Sep 17 (Print Publication: 2026).
Τύπος έκδοσης:	Journal Article
Γλώσσα:	English
Στοιχεία περιοδικού:	Publisher: Public Library of Science Country of Publication: United States NLM ID: 101285081 Publication Model: eCollection Cited Medium: Internet ISSN: 1932-6203 (Electronic) Linking ISSN: 19326203 NLM ISO Abbreviation: PLoS One Subsets: MEDLINE
Imprint Name(s):	Original Publication: San Francisco, CA : Public Library of Science
Ιατρικοί όροι (MeSH):	5' Untranslated Regions/genetics , Protein Biosynthesis , Gene Library* , Models, Genetic*, Escherichia coli/genetics ; Large Language Models ; Base Sequence
Περίληψη:	Tuning protein expression in non-model organisms is often constrained by the lack of validated genetic parts and predictive design tools. Translational tuning through the modulation of upstream untranslated regions (5'-UTRs) offers a potentially organism-agnostic route, but existing methods typically rely on mechanistic assumptions, prior knowledge that may not be available in non-model contexts, or the screening of sequence libraries. Here, we present a simple generative approach for creating synthetic 5'-UTR libraries based solely on the genomic sequence statistics of any desired organism. The method uses a sliding-window n-gram language model applied to native 5'-UTR sequences to produce novel sequences that preserve organism-specific base distributions and motifs without hard-coding specific motifs or mechanistic rules into inflexible statistical templates. We have applied this approach to the model bacterium Escherichia coli and the non-model probiotic Limosilactobacillus reuteri. Libraries of approximately 1,000 sequences were generated for each organism, from which about 100 unique sequences were experimentally tested for translation of a fluorescent reporter protein. In both organisms, the synthetic libraries yielded a broad range of translation levels from this relatively small number of tested variants. Sequences derived from an organism's own genomic statistics provided a more uniformly distributed range of translation rates in that organism than sequences derived from the other species. Correlations of individual sequence performance across the two species were weak, and thermodynamic predictions of ribosome binding strength showed very little predictive power, especially in the non-model L. reuteri. The results demonstrate that simple statistical language model approaches applied to genomic data can generate functional translational regulatory sequence libraries without detailed mechanistic knowledge or explicit reference to consensus motifs. The approach requires minimal computational resources, avoids reproducing native sequences, and can be readily applied to any organism with a sequenced genome. This strategy may lower technical barriers to expression tuning in non-model organisms. (Copyright: © 2026 Duggan et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
Competing Interests:	The authors have declared that no competing interests exist.
References:	Appl Environ Microbiol. 2024 Nov 20;90(11):e0031224. (PMID: 39480094) Genes Dis. 2025 Jun 22;13(1):101729. (PMID: 41069576) Nucleic Acids Res. 2020 Aug 20;48(14):e81. (PMID: 32504488) Bioinformatics. 2010 Oct 15;26(20):2633-4. (PMID: 20702394) Nat Biotechnol. 2018 Nov;36(10):1005-1015. (PMID: 30247489) Biotechnol Adv. 2022 Jan-Feb;54:107853. (PMID: 34637919) ACS Synth Biol. 2021 Feb 19;10(2):318-332. (PMID: 33464822) Nucleic Acids Res. 2024 Jul 22;52(13):e58. (PMID: 38864396) Nat Methods. 2013 Apr;10(4):347-53. (PMID: 23474467) Microb Biotechnol. 2021 Nov;14(6):2291-2315. (PMID: 34171170) ACS Synth Biol. 2020 Nov 20;9(11):3145-3156. (PMID: 33054181) ACS Synth Biol. 2025 Oct 17;14(10):3815-3821. (PMID: 40964802) Genome Res. 2017 Dec;27(12):2015-2024. (PMID: 29097404) J Vis Exp. 2023 Jun 23;(196):. (PMID: 37427913) J Proteome Res. 2020 Sep 4;19(9):3595-3606. (PMID: 32786681) Cell Rep. 2025 Oct 28;44(10):116434. (PMID: 41118765) Nat Commun. 2016 Mar 31;7:11163. (PMID: 27029461) Proc Natl Acad Sci U S A. 2013 Aug 20;110(34):14024-9. (PMID: 23924614) Nucleic Acids Res. 1998 Jan 15;26(2):544-8. (PMID: 9421513) J Open Source Softw. 2021;6(64):. (PMID: 36177308) Nucleic Acids Res. 2017 May 19;45(9):5437-5448. (PMID: 28158713) Nature. 2024 Sep;633(8029):371-379. (PMID: 39232160) Nucleic Acids Res. 1994 Nov 11;22(22):4768-78. (PMID: 7984429) Mol Biol Evol. 2012 Jan;29(1):81-9. (PMID: 21965341) J Bacteriol. 2008 Apr;190(7):2597-606. (PMID: 18245285) Microbiol Resour Announc. 2018 Nov 1;7(17):. (PMID: 30533759) Nat Biotechnol. 2026 May;44(5):783-796. (PMID: 40715456) Nat Methods. 2013 Apr;10(4):354-60. (PMID: 23474465) Nat Biotechnol. 2009 Oct;27(10):946-50. (PMID: 19801975) BMC Syst Biol. 2010 May 26;4:71. (PMID: 20504310) ACS Synth Biol. 2013 Oct 18;2(10):547-67. (PMID: 23905721) Microbiology (Reading). 2013 Jul;159(Pt 7):1236-1253. (PMID: 23704788)
Substance Nomenclature:	0 (5' Untranslated Regions)
Entry Date(s):	Date Created: 20260917 Date Completed: 20260917 Latest Revision: 20260922
Update Code:	20260922
PubMed Central ID:	PMC13585243
DOI:	10.1371/journal.pone.0348455
PMID:	42752596
Βάση Δεδομένων:	MEDLINE

Full Text Finder

Περιγραφή
ISSN:	1932-6203
DOI:	10.1371/journal.pone.0348455