Academic Journal
Προβολή σε EDS

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
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:cmedm&genre=article&issn=19326203&ISBN=&volume=21&issue=9&date=20260917&spage=e0348455&pages=e0348455&title=PloS one&atitle=A%20trainable%20language%20model%20with%20potential%20to%20modulate%20translation%20rates%20in%20non-model%20organisms%20by%20generating%20upstream%20untranslated%20region%20sequence%20libraries.&aulast=Duggan%20AD&id=DOI:10.1371/journal.pone.0348455
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: cmedm
DbLabel: MEDLINE
An: 42752596
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A trainable language model with potential to modulate translation rates in non-model organisms by generating upstream untranslated region sequence libraries.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Duggan+AD%22">Duggan AD</searchLink>; 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.<br /><searchLink fieldCode="AU" term="%22Newman+MP%22">Newman MP</searchLink>; Department of Chemical and Physical Sciences, University of Toronto Mississauga, Mississauga, Ontario, Canada.; Department of Chemistry, University of Toronto, Toronto, Ontario, Canada.<br /><searchLink fieldCode="AU" term="%22McMillen+DR%22">McMillen DR</searchLink>; 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.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22101285081%22">PloS one</searchLink> [PLoS One] 2026 Sep 17; Vol. 21 (9), pp. e0348455. <i>Date of Electronic Publication: </i>2026 Sep 17 (<i>Print Publication: </i>2026).
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22Public+Library+of+Science%22">Public Library of Science </searchLink><i>Country of Publication: </i>United States <i>NLM ID: </i>101285081 <i>Publication Model: </i>eCollection <i>Cited Medium: </i>Internet <i>ISSN: </i>1932-6203 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2219326203%22">19326203 </searchLink><i>NLM ISO Abbreviation: </i>PLoS One <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Original Publication</i>: San Francisco, CA : Public Library of Science
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%225'+Untranslated+Regions%22">5' Untranslated Regions*</searchLink>/<searchLink fieldCode="MM" term="%225'+Untranslated+Regions+genetics%22">genetics</searchLink> <br /><searchLink fieldCode="MM" term="%22Protein+Biosynthesis%22">Protein Biosynthesis*</searchLink> <br /><searchLink fieldCode="MM" term="%22Gene+Library%22">Gene Library*</searchLink> <br /><searchLink fieldCode="MM" term="%22Models%2C+Genetic%22">Models, Genetic*</searchLink><br /><searchLink fieldCode="MH" term="%22Escherichia+coli%22">Escherichia coli</searchLink>/<searchLink fieldCode="MH" term="%22Escherichia+coli+genetics%22">genetics</searchLink> ; <searchLink fieldCode="MH" term="%22Large+Language+Models%22">Large Language Models</searchLink> ; <searchLink fieldCode="MH" term="%22Base+Sequence%22">Base Sequence</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: 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.<br /> (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.)
– Name: Abstract
  Label: Competing Interests
  Group: Ab
  Data: The authors have declared that no competing interests exist.
– Name: Ref
  Label: References
  Group: RefInfo
  Data: Appl Environ Microbiol. 2024 Nov 20;90(11):e0031224. (PMID: <searchLink fieldCode="PM" term="%2239480094%22">39480094)</searchLink><br />Genes Dis. 2025 Jun 22;13(1):101729. (PMID: <searchLink fieldCode="PM" term="%2241069576%22">41069576)</searchLink><br />Nucleic Acids Res. 2020 Aug 20;48(14):e81. (PMID: <searchLink fieldCode="PM" term="%2232504488%22">32504488)</searchLink><br />Bioinformatics. 2010 Oct 15;26(20):2633-4. (PMID: <searchLink fieldCode="PM" term="%2220702394%22">20702394)</searchLink><br />Nat Biotechnol. 2018 Nov;36(10):1005-1015. (PMID: <searchLink fieldCode="PM" term="%2230247489%22">30247489)</searchLink><br />Biotechnol Adv. 2022 Jan-Feb;54:107853. (PMID: <searchLink fieldCode="PM" term="%2234637919%22">34637919)</searchLink><br />ACS Synth Biol. 2021 Feb 19;10(2):318-332. (PMID: <searchLink fieldCode="PM" term="%2233464822%22">33464822)</searchLink><br />Nucleic Acids Res. 2024 Jul 22;52(13):e58. (PMID: <searchLink fieldCode="PM" term="%2238864396%22">38864396)</searchLink><br />Nat Methods. 2013 Apr;10(4):347-53. (PMID: <searchLink fieldCode="PM" term="%2223474467%22">23474467)</searchLink><br />Microb Biotechnol. 2021 Nov;14(6):2291-2315. (PMID: <searchLink fieldCode="PM" term="%2234171170%22">34171170)</searchLink><br />ACS Synth Biol. 2020 Nov 20;9(11):3145-3156. (PMID: <searchLink fieldCode="PM" term="%2233054181%22">33054181)</searchLink><br />ACS Synth Biol. 2025 Oct 17;14(10):3815-3821. (PMID: <searchLink fieldCode="PM" term="%2240964802%22">40964802)</searchLink><br />Genome Res. 2017 Dec;27(12):2015-2024. (PMID: <searchLink fieldCode="PM" term="%2229097404%22">29097404)</searchLink><br />J Vis Exp. 2023 Jun 23;(196):. (PMID: <searchLink fieldCode="PM" term="%2237427913%22">37427913)</searchLink><br />J Proteome Res. 2020 Sep 4;19(9):3595-3606. (PMID: <searchLink fieldCode="PM" term="%2232786681%22">32786681)</searchLink><br />Cell Rep. 2025 Oct 28;44(10):116434. (PMID: <searchLink fieldCode="PM" term="%2241118765%22">41118765)</searchLink><br />Nat Commun. 2016 Mar 31;7:11163. (PMID: <searchLink fieldCode="PM" term="%2227029461%22">27029461)</searchLink><br />Proc Natl Acad Sci U S A. 2013 Aug 20;110(34):14024-9. (PMID: <searchLink fieldCode="PM" term="%2223924614%22">23924614)</searchLink><br />Nucleic Acids Res. 1998 Jan 15;26(2):544-8. (PMID: <searchLink fieldCode="PM" term="%229421513%22">9421513)</searchLink><br />J Open Source Softw. 2021;6(64):. (PMID: <searchLink fieldCode="PM" term="%2236177308%22">36177308)</searchLink><br />Nucleic Acids Res. 2017 May 19;45(9):5437-5448. (PMID: <searchLink fieldCode="PM" term="%2228158713%22">28158713)</searchLink><br />Nature. 2024 Sep;633(8029):371-379. (PMID: <searchLink fieldCode="PM" term="%2239232160%22">39232160)</searchLink><br />Nucleic Acids Res. 1994 Nov 11;22(22):4768-78. (PMID: <searchLink fieldCode="PM" term="%227984429%22">7984429)</searchLink><br />Mol Biol Evol. 2012 Jan;29(1):81-9. (PMID: <searchLink fieldCode="PM" term="%2221965341%22">21965341)</searchLink><br />J Bacteriol. 2008 Apr;190(7):2597-606. (PMID: <searchLink fieldCode="PM" term="%2218245285%22">18245285)</searchLink><br />Microbiol Resour Announc. 2018 Nov 1;7(17):. (PMID: <searchLink fieldCode="PM" term="%2230533759%22">30533759)</searchLink><br />Nat Biotechnol. 2026 May;44(5):783-796. (PMID: <searchLink fieldCode="PM" term="%2240715456%22">40715456)</searchLink><br />Nat Methods. 2013 Apr;10(4):354-60. (PMID: <searchLink fieldCode="PM" term="%2223474465%22">23474465)</searchLink><br />Nat Biotechnol. 2009 Oct;27(10):946-50. (PMID: <searchLink fieldCode="PM" term="%2219801975%22">19801975)</searchLink><br />BMC Syst Biol. 2010 May 26;4:71. (PMID: <searchLink fieldCode="PM" term="%2220504310%22">20504310)</searchLink><br />ACS Synth Biol. 2013 Oct 18;2(10):547-67. (PMID: <searchLink fieldCode="PM" term="%2223905721%22">23905721)</searchLink><br />Microbiology (Reading). 2013 Jul;159(Pt 7):1236-1253. (PMID: <searchLink fieldCode="PM" term="%2223704788%22">23704788)</searchLink>
– Name: NumberCAS
  Label: Substance Nomenclature
  Group: ID
  Data: 0 (5' Untranslated Regions)
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20260917 <i>Date Completed: </i>20260917 <i>Latest Revision: </i>20260922
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260922
– Name: PubmedCentralID
  Label: PubMed Central ID
  Group: ID
  Data: PMC13585243
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1371/journal.pone.0348455
– Name: AN
  Label: PMID
  Group: ID
  Data: 42752596
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=42752596
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1371/journal.pone.0348455
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        StartPage: e0348455
    Subjects:
      – SubjectFull: Escherichia coli genetics
        Type: general
      – SubjectFull: Large Language Models
        Type: general
      – SubjectFull: Base Sequence
        Type: general
      – SubjectFull: 5' Untranslated Regions genetics
        Type: general
      – SubjectFull: Protein Biosynthesis
        Type: general
      – SubjectFull: Gene Library
        Type: general
      – SubjectFull: Models, Genetic
        Type: general
    Titles:
      – TitleFull: A trainable language model with potential to modulate translation rates in non-model organisms by generating upstream untranslated region sequence libraries.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Duggan AD
      – PersonEntity:
          Name:
            NameFull: Newman MP
      – PersonEntity:
          Name:
            NameFull: McMillen DR
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 17
              M: 09
              Text: 2026 Sep 17
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1932-6203
          Numbering:
            – Type: volume
              Value: 21
            – Type: issue
              Value: 9
          Titles:
            – TitleFull: PloS one
              Type: main
ResultId 1