CoChat
Sign Up
Cited by 98RNA and protein synthesis mechanismsRNA Interference and Gene DeliveryRNA regulation and disease

Optimizing 5’UTRs for mRNA-delivered gene editing using deep learning

Open access
Castillo-Hair, Sebastian, Fedak, Stephen, Wang, Ban, Linder, Johannes, Havens, Kyle, Certo, Michael, Seelig, Georg·2024·Nature Communications
DOI 10.1038/s41467-024-49508-2PMC PMC11189900

Published version of a preprint

Open this paper in CoChat — free account

Abstract

mRNA therapeutics are revolutionizing the pharmaceutical industry, but methods to optimize the primary sequence for increased expression are still lacking. Here, we design 5’UTRs for efficient mRNA translation using deep learning. We perform polysome profiling of fully or partially randomized 5’UTR libraries in three cell types and find that UTR performance is highly correlated across cell types. We train models on our datasets and use them to guide the design of high-performing 5’UTRs using gradient descent and generative neural networks. We experimentally test designed 5’UTRs with mRNA encoding megaTAL TM gene editing enzymes for two different gene targets and in two different cell lines. We find that the designed 5’UTRs support strong gene editing activity. Editing efficiency is correlated between cell types and gene targets, although the best performing UTR was specific to one cargo and cell type. Our results highlight the potential of model-based sequence design for mRNA therapeutics.

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 · 10.1038/s41467-024-49508-2

Cites

17 of 17 references verified0 citation errors · 0 not checkable

Statistics

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

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The Pfizer-BioNTech mRNA vaccine contains the 5′ UTR of human α-globin and the 3′ UTR AES-mtRNR1 combination.

    “the Pfizer-BioNTech mRNA vaccine contains the 5′ UTR of human α-globin, which was identified as one of the top 20% 5′ UTRs in massive screening studies,10,11,13 and the 3′ UTR AES-mtRNR1 combination of two genes, AES (Amino Enhancer of Split) and mtRNR1 (12S mitochondrial RNA).12”

    From Evaluation of synthetic mRNA with selected UTR sequences and alternative poly(A) tail, in vitro and in vivo (2025) · cites this paper as [10]

    The Introduction says many mRNA therapies use alpha- or beta-globin UTRs. The Results section on de novo designed 5′UTRs places the commonly used beta-globin UTR—not alpha-globin—in the top ~20% of short endogenous UTRs. This paper therefore does not establish the cited ranking for alpha-globin or identify it as the Pfizer-BioNTech vaccine’s 5′UTR; the sentence cites a different source for the 3′UTR combination. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

  • It is widely suggested that cell-type specificity of mRNA translation is primarily dictated by 3′ UTR, but emerging evidence points to significant regulatory role of 5′ UTR as well.

    “While it is widely suggested that the cell-type specificity of mRNA translation is primarily dictated by the 3′ UTR [31], emerging evidence points to a significant regulatory role of the 5′ UTR as well.”

    From Identification of novel 5’ UTR variants for enhanced mRNA translation and vaccine immunogenicity (2026) · cites this paper as [31]

Self-check

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

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

Cites

Flagged first, then by citations

Research works printed but not linked: 51

  1. [1]Weng Y The challenge and prospect of mRNA therapeutics landscape Biotechnol. Adv. 2020 40 107534 10.1016/j.biotechadv.2020.107534 32088327 · DOI · Paper page
  2. [2]Rosa SS Prazeres DMF Azevedo AM Marques MPC mRNA vaccines manufacturing: Challenges and bottlenecks Vaccine 2021 39 2190 2200 10.1016/j.vaccine.2021.03.038 33771389 PMC7987532 · DOI · Paper page
  3. [3]Zhang H-X Zhang Y Yin H Genome Editing with mRNA Encoding ZFN, TALEN, and Cas9 Mol. Ther. 2019 27 735 746 10.1016/j.ymthe.2019.01.014 30803822 PMC6453514 · DOI
  4. [4]van Haasteren J Li J Scheideler OJ Murthy N Schaffer DV The delivery challenge: fulfilling the promise of therapeutic genome editing Nat. Biotechnol. 2020 38 845 855 10.1038/s41587-020-0565-5 32601435 · DOI · Paper page
  5. [7]Magadum A Kaur K Zangi L mRNA-Based Protein Replacement Therapy for the Heart Mol. Ther. 2019 27 785 793 10.1016/j.ymthe.2018.11.018 30611663 PMC6453506 · DOI · Paper page
  6. [8]Trepotec Z Lichtenegger E Plank C Aneja MK Rudolph C Delivery of mRNA Therapeutics for the Treatment of Hepatic Diseases Mol. Ther. 2019 27 794 802 10.1016/j.ymthe.2018.12.012 30655211 PMC6453508 · DOI · Paper page
  7. [10]Chanda PK Sukhovershin R Cooke JP mRNA-Enhanced Cell Therapy and Cardiovascular Regeneration Cells 2021 10 187 10.3390/cells10010187 33477787 PMC7832270 · DOI
  8. [11]Soundara Rajan T Gugliandolo A Bramanti P Mazzon E In Vitro-Transcribed mRNA Chimeric Antigen Receptor T Cell (IVT mRNA CAR T) Therapy in Hematologic and Solid Tumor Management: A Preclinical Update Int. J. Mol. Sci. 2020 21 6514 10.3390/ijms21186514 32899932 PMC7556036 · DOI
  9. [12]Beck JD mRNA therapeutics in cancer immunotherapy Mol. Cancer 2021 20 69 10.1186/s12943-021-01348-0 33858437 PMC8047518 · DOI · Paper page
  10. [13]Rohner E Yang R Foo KS Goedel A Chien KR Unlocking the promise of mRNA therapeutics Nat. Biotechnol. 2022 40 1586 1600 10.1038/s41587-022-01491-z 36329321 · DOI · Paper page
  11. [14]Zabaleta N Torella L Weber ND Gonzalez-Aseguinolaza G mRNA and gene editing: Late breaking therapies in liver diseases Hepatology 2022 76 869 887 10.1002/hep.32441 35243655 PMC9546265 · DOI
  12. [16]Boissel S megaTALs: a rare-cleaving nuclease architecture for therapeutic genome engineering Nucleic Acids Res. 2014 42 2591 2601 10.1093/nar/gkt1224 24285304 PMC3936731 · DOI
  13. [17]Sather BD Efficient modification of CCR5 in primary human hematopoietic cells using a megaTAL nuclease and AAV donor template Sci. Transl. Med. 2015 7 307ra156 307ra156 10.1126/scitranslmed.aac5530 26424571 PMC4790757 · DOI · Paper page
  14. [18]Romano Ibarra GS Efficient Modification of the CCR5 Locus in Primary Human T Cells With megaTAL Nuclease Establishes HIV-1 Resistance Mol. Ther. - Nucleic Acids 2016 5 e352 10.1038/mtna.2016.56 27741222 PMC5023401 · DOI
  15. [22]Andries O N1-methylpseudouridine-incorporated mRNA outperforms pseudouridine-incorporated mRNA by providing enhanced protein expression and reduced immunogenicity in mammalian cell lines and mice J. Control. Release 2015 217 337 344 10.1016/j.jconrel.2015.08.051 26342664 · DOI · Paper page
  16. [25]Asrani KH Optimization of mRNA untranslated regions for improved expression of therapeutic mRNA RNA Biol. 2018 15 756 762 29578372 PMC6152433
  17. [29]Jia L Decoding mRNA translatability and stability from the 5′ UTR Nat. Struct. Mol. Biol. 2020 27 814 821 10.1038/s41594-020-0465-x 32719458 · DOI · Paper page
  18. [30]Gerstberger S Hafner M Tuschl T A census of human RNA-binding proteins Nat. Rev. Genet. 2014 15 829 845 10.1038/nrg3813 25365966 PMC11148870 · DOI · Paper page
  19. [31]Sood P Krek A Zavolan M Macino G Rajewsky N Cell-type-specific signatures of microRNAs on target mRNA expression Proc. Natl Acad. Sci. 2006 103 2746 2751 10.1073/pnas.0511045103 16477010 PMC1413820 · DOI · Paper page
  20. [32]Guo Z Genome-wide survey of tissue-specific microRNA and transcription factor regulatory networks in 12 tissues Sci. Rep. 2014 4 5150 10.1038/srep05150 24889152 PMC5381490 · DOI
  21. [34]Karollus A Avsec Ž Gagneur J Predicting mean ribosome load for 5’UTR of any length using deep learning PLOS Comput. Biol. 2021 17 e1008982 10.1371/journal.pcbi.1008982 33970899 PMC8136849 · DOI · Paper page
  22. [36]Castillo-Hair SM Seelig G Machine Learning for Designing Next-Generation mRNA Therapeutics Acc. Chem. Res. 2022 55 24 34 10.1021/acs.accounts.1c00621 34905691 · DOI
  23. [37]Jackson RJ Hellen CUT Pestova TV The mechanism of eukaryotic translation initiation and principles of its regulation Nat. Rev. Mol. Cell Biol. 2010 11 113 127 10.1038/nrm2838 20094052 PMC4461372 · DOI · Paper page
  24. [38]Hinnebusch, A. G., Ivanov, I. P. & Sonenberg, N. Translational control by 5′-untranslated regions of eukaryotic mRNAs. Science352, 1413–1416 (2016). PMC7422601 27313038
  25. [39]Leppek K Das R Barna M Functional 5′ UTR mRNA structures in eukaryotic translation regulation and how to find them Nat. Rev. Mol. Cell Biol. 2018 19 158 174 10.1038/nrm.2017.103 29165424 PMC5820134 · DOI · Paper page
  26. [40]Kochetov AV Sarai A Rogozin IB Shumny VK Kolchanov NA The role of alternative translation start sites in the generation of human protein diversity Mol. Genet. Genom. 2005 273 491 496 10.1007/s00438-005-1152-7 15959805 · DOI
  27. [41]Spriggs KA Stoneley M Bushell M Willis AE Re-programming of translation following cell stress allows IRES-mediated translation to predominate Biol. Cell 2008 100 27 38 10.1042/BC20070098 18072942 · DOI
  28. [42]Avni D Biberman Y Meyuhas O The 5′ Terminal Oligopyrimidine Tract Confers Translational Control on Top Mrnas in a Cell Type-and Sequence Context-Dependent Manner Nucleic Acids Res. 1997 25 995 1001 10.1093/nar/25.5.995 9023110 PMC146534 · DOI
  29. [43]Thoreen CC A unifying model for mTORC1-mediated regulation of mRNA translation Nature 2012 485 109 113 10.1038/nature11083 22552098 PMC3347774 · DOI · Paper page
  30. [45]Lim Y Multiplexed functional genomic analysis of 5’ untranslated region mutations across the spectrum of prostate cancer Nat. Commun. 2021 12 4217 10.1038/s41467-021-24445-6 34244513 PMC8270899 · DOI
  31. [46]Floor SN Doudna JA Tunable protein synthesis by transcript isoforms in human cells eLife 2016 5 e10921 10.7554/eLife.10921 26735365 PMC4764583 · DOI · Paper page
  32. [47]Blair JD Hockemeyer D Doudna JA Bateup HS Floor SN Widespread Translational Remodeling during Human Neuronal Differentiation Cell Rep. 2017 21 2005 2016 10.1016/j.celrep.2017.10.095 29141229 PMC5759054 · DOI
  33. [48]Zimmer A Zimmer AM Reynolds K Tissue specific expression of the retinoic acid receptor-beta 2: regulation by short open reading frames in the 5’-noncoding region J. Cell Biol. 1994 127 1111 1119 10.1083/jcb.127.4.1111 7962071 PMC2200052 · DOI
  34. [49]Xue S RNA regulons in Hox 5′ UTRs confer ribosome specificity to gene regulation Nature 2015 517 33 38 10.1038/nature14010 25409156 PMC4353651 · DOI
  35. [50]Rizvi F Murine liver repair via transient activation of regenerative pathways in hepatocytes using lipid nanoparticle-complexed nucleoside-modified mRNA Nat. Commun. 2021 12 613 10.1038/s41467-021-20903-3 33504774 PMC7840919 · DOI
  36. [52]Rurik JG CAR T cells produced in vivo to treat cardiac injury Science 2022 375 91 96 10.1126/science.abm0594 34990237 PMC9983611 · DOI · Paper page
  37. [53]Benjamin R Genome-edited, donor-derived allogeneic anti-CD19 chimeric antigen receptor T cells in paediatric and adult B-cell acute lymphoblastic leukaemia: results of two phase 1 studies Lancet 2020 396 1885 1894 10.1016/S0140-6736(20)32334-5 33308471 PMC11773457 · DOI
  38. [54]Linder J Seelig G Fast activation maximization for molecular sequence design BMC Bioinforma. 2021 22 510 10.1186/s12859-021-04437-5 PMC8527647 34670493 · DOI
  39. [55]Linder J Bogard N Rosenberg AB Seelig G A Generative Neural Network for Maximizing Fitness and Diversity of Synthetic DNA and Protein Sequences Cell Syst. 2020 11 49 62.e16 10.1016/j.cels.2020.05.007 32711843 PMC8694568 · DOI · Paper page
  40. [56]Stadtmauer EA CRISPR-engineered T cells in patients with refractory cancer Science 2020 367 eaba7365 10.1126/science.aba7365 32029687 PMC11249135 · DOI · Paper page
  41. [57]Tang, N. et al. TGF-β inhibition via CRISPR promotes the long-term efficacy of CAR T cells against solid tumors. JCI Insight5, e133977 (2020). PMC7101140 31999649
  42. [58]David CJ Massagué J Contextual determinants of TGFβ action in development, immunity and cancer Nat. Rev. Mol. Cell Biol. 2018 19 419 435 10.1038/s41580-018-0007-0 29643418 PMC7457231 · DOI · Paper page
  43. [59]Batlle E Massagué J Transforming Growth Factor-β Signaling in Immunity and Cancer Immunity 2019 50 924 940 10.1016/j.immuni.2019.03.024 30995507 PMC7507121 · DOI · Paper page
  44. [60]Sharpe AH Pauken KE The diverse functions of the PD1 inhibitory pathway Nat. Rev. Immunol. 2018 18 153 167 10.1038/nri.2017.108 28990585 · DOI
  45. [61]Kozak M Point mutations define a sequence flanking the AUG initiator codon that modulates translation by eukaryotic ribosomes Cell 1986 44 283 292 10.1016/0092-8674(86)90762-2 3943125 · DOI · Paper page
  46. [62]Kingma, D. P. & Welling, M. Auto-encoding variational Bayes. Preprint at https://arxiv.org/abs/1312.6114 (2014). · arXiv
  47. [63]Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. Preprint at https://arxiv.org/abs/1409.1556 (2015). · arXiv
  48. [64]Plassmeyer, S. P. et al. A massively parallel screen of 5′UTR mutations identifies variants impacting translation and protein production in neurodevelopmental disorder genes. Preprint at medRxiv 10.1101/2023.11.02.23297961 (2023). · DOI
  49. [65]Cao J High-throughput 5′ UTR engineering for enhanced protein production in non-viral gene therapies Nat. Commun. 2021 12 4138 10.1038/s41467-021-24436-7 34230498 PMC8260622 · DOI · Paper page
  50. [66]Dave P Single-molecule imaging reveals translation-dependent destabilization of mRNAs Mol. Cell 2023 83 589 606.e6 10.1016/j.molcel.2023.01.013 36731471 PMC9957601 · DOI
  51. [67]Bailey TL Elkan C Fitting a mixture model by expectation maximization to discover motifs in biopolymers Proc. Int. Conf. Intell. Syst. Mol. Biol. 1994 2 28 36 7584402

Cited by

Sorted by citations

Authors
Castillo-Hair, S., Fedak, S., Wang, B., Linder, J., Havens, K., Certo, M., & Seelig, G.
Affiliations
  • University of Washington (US)
  • Stanford University (US)
Corresponding author
Seelig, Georg
ORCID
Venue
Nature Communications
Publisher
Springer Science and Business Media LLC
Published
2024-06-20
Volume
15
Issue
1
Pages
5284-5284
ISSN
2041-1723 (ISSN-L)
DOI
10.1038/s41467-024-49508-2
PMC
PMC11189900
OpenAlex
W4399848621
Cited by
98
References
17
Citations by year
2026: 55 · 2025: 36 · 2024: 7
FWCI
12.68
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Communications (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • U.S. Department of Health & Human Services | NIH | National Institute of General Medical Sciences (R01GM149631)
  • National Science Foundation (2021552)
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 Interference and Gene Delivery
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › RNA regulation and disease
Keywords
5' untranslated region, mRNA therapeutics, genome editing, mRNA delivery, deep learning, sequence design, generative neural networks, polysome profiling, translation efficiency, TALEN, cell type specificity
MeSH terms
Gene Editing, Deep Learning, Cell Line, Humans, Polyribosomes, RNA, Messenger, Protein Biosynthesis, 5' Untranslated Regions, HEK293 Cells

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