CoChat
Sign Up
Cited by 142Genomics and Chromatin DynamicsCRISPR and Genetic EngineeringGene Regulatory Network Analysis

Machine-guided design of cell-type-targeting cis-regulatory elements

Open access
Gosai, Sager J., Castro, Rodrigo I., Fuentes, Natalia, Butts, John C., Mouri, Kousuke, Alasoadura, Michael, Kales, Susan, Nguyen, Thanh Thanh L. +6 more·2024·Nature
DOI 10.1038/s41586-024-08070-zPMC PMC11525185
Open this paper in CoChat — free account

Abstract

Abstract Cis -regulatory elements (CREs) control gene expression, orchestrating tissue identity, developmental timing and stimulus responses, which collectively define the thousands of unique cell types in the body 1–3 . While there is great potential for strategically incorporating CREs in therapeutic or biotechnology applications that require tissue specificity, there is no guarantee that an optimal CRE for these intended purposes has arisen naturally. Here we present a platform to engineer and validate synthetic CREs capable of driving gene expression with programmed cell-type specificity. We take advantage of innovations in deep neural network modelling of CRE activity across three cell types, efficient in silico optimization and massively parallel reporter assays to design and empirically test thousands of CREs 4–8 . Through large-scale in vitro validation, we show that synthetic sequences are more effective at driving cell-type-specific expression in three cell lines compared with natural sequences from the human genome and achieve specificity in analogous tissues when tested in vivo. Synthetic sequences exhibit distinct motif vocabulary associated with activity in the on-target cell type and a simultaneous reduction in the activity of off-target cells. Together, we provide a generalizable framework to prospectively engineer CREs from massively parallel reporter assay models and demonstrate the required literacy to write fit-for-purpose regulatory code.

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/s41586-024-08070-z

Cites

15 of 15 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 design rules identified here are transparent insights into pairwise interactions between TF motifs.

    “Unlike recent studies that used genomic data and deep learning for designing cell-type-specific enhancers in the fruit fly61,62 or in cancer cell lines,63 the design rules identified here are transparent insights into pairwise interactions between TF motifs.”

    From Design principles of cell-state-specific enhancers in hematopoiesis (2025) · cites this paper as [63]

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: 81

  1. [3]Donohue, L. K. H. et al. A cis -regulatory lexicon of DNA motif combinations mediating cell-type-specific gene regulation. Cell Genom. 2, 100191 (2022). 36742369 PMC9894309 · DOI
  2. [4]Kelley, D. R., Snoek, J. & Rinn, J. L. Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks. Genome Res. 26, 990–999 (2016). 27197224 PMC4937568 · DOI · Paper page
  3. [5]Linder, J. & Seelig, G. Fast activation maximization for molecular sequence design. BMC Bioinform. 22, 510 (2021). PMC8527647 34670493 · DOI
  4. [6]Sinai, S. et al. AdaLead: a simple and robust adaptive greedy search algorithm for sequence design. Preprint at arxiv.org/abs/2010.02141 (2020). · arXiv
  5. [7]van Laarhoven, P. J. M. & Aarts, E. H. L. in Simulated Annealing: Theory and Applications (eds van Laarhoven, P. J. M. & Aarts, E. H. L.) 7–15 (Springer, 1987).
  6. [10]Gasperini, M., Tome, J. M. & Shendure, J. Towards a comprehensive catalogue of validated and target-linked human enhancers. Nat. Rev. Genet. 21, 292–310 (2020). 31988385 PMC7845138 · DOI · Paper page
  7. [12]ENCODE Project Consortium et al. Expanded encyclopaedias of DNA elements in the human and mouse genomes. Nature 583, 699–710 (2020). 32728249 PMC7410828 · DOI · Paper page
  8. [13]Levo, M. & Segal, E. In pursuit of design principles of regulatory sequences. Nat. Rev. Genet. 15, 453–468 (2014). 24913666 · DOI · Paper page
  9. [15]Lambert, S. A. et al. The human transcription factors. Cell 172, 650–665 (2018). 29425488 PMC12908702 · DOI · Paper page
  10. [16]Kim, D. S. et al. The dynamic, combinatorial cis -regulatory lexicon of epidermal differentiation. Nat. Genet. 53, 1564–1576 (2021). 34650237 PMC8763320 · DOI
  11. [17]Shrikumar, A., Greenside, P. & Kundaje, A. Learning important features through propagating activation differences. In Proc. 34th International Conference on Machine Learning (eds Precup, D. & Teh, Y. W.) Vol. 70, 3145–3153 (JMLR.org, 2017).
  12. [18]Ulirsch, J. C. et al. Systematic functional dissection of common genetic variation affecting red blood cell traits. Cell 165, 1530–1545 (2016). 27259154 PMC4893171 · DOI · Paper page
  13. [20]Melnikov, A. et al. Systematic dissection and optimization of inducible enhancers in human cells using a massively parallel reporter assay. Nat. Biotechnol. 30, 271–277 (2012). 22371084 PMC3297981 · DOI · Paper page
  14. [22]Lawler, A. J. et al. Machine learning sequence prioritization for cell type-specific enhancer design. eLife 11, e69571 (2022). 35576146 PMC9110026 · DOI
  15. [23]Movva, R. et al. Deciphering regulatory DNA sequences and noncoding genetic variants using neural network models of massively parallel reporter assays. PLoS ONE 14, e0218073 (2019). 31206543 PMC6576758 · DOI
  16. [24]Vaishnav, E. D. et al. The evolution, evolvability and engineering of gene regulatory DNA. Nature 603, 455–463 (2022). 35264797 PMC8934302 · DOI
  17. [25]Agarwal, V. et al. Massively parallel characterization of transcriptional regulatory elements in three diverse human cell types. Preprint at bioRxiv10.1101/2023.03.05.531189 (2023).
  18. [26]Xue, J. R. et al. The functional and evolutionary impacts of human-specific deletions in conserved elements. Science 380, eabn2253 (2023). 37104592 PMC10202372 · DOI
  19. [27]Siraj, L. et al. Functional dissection of complex and molecular trait variants at single nucleotide resolution. Preprint at bioRxiv10.1101/2024.05.05.592437 (2024).
  20. [28]Rosenberg, A. B., Patwardhan, R. P., Shendure, J. & Seelig, G. Learning the sequence determinants of alternative splicing from millions of random sequences. Cell 163, 698–711 (2015). 26496609 · DOI
  21. [29]Bogard, N., Linder, J., Rosenberg, A. B. & Seelig, G. A deep neural network for predicting and engineering alternative polyadenylation. Cell 178, 91–106 (2019). 31178116 PMC6599575 · DOI · Paper page
  22. [31]Kelley, D. R. et al. Sequential regulatory activity prediction across chromosomes with convolutional neural networks. Genome Res. 28, 739–750 (2018). 29588361 PMC5932613 · DOI · Paper page
  23. [32]Zhou, J. & Troyanskaya, O. G. Predicting effects of noncoding variants with deep learning-based sequence model. Nat. Methods 12, 931–934 (2015). 26301843 PMC4768299 · DOI · Paper page
  24. [33]Quang, D. & Xie, X. DanQ: a hybrid convolutional and recurrent deep neural network for quantifying the function of DNA sequences. Nucleic Acids Res. 44, e107 (2016). 27084946 PMC4914104 · DOI
  25. [34]Jaganathan, K. et al. Predicting splicing from primary sequence with deep learning. Cell 176, 535–548 (2019). 30661751 · DOI · Paper page
  26. [36]Penzar, D. et al. LegNet: a best-in-class deep learning model for short DNA regulatory regions. Bioinformatics 39, btad457 (2023). 37490428 PMC10400376 · DOI
  27. [37]Avsec, Ž. et al. Effective gene expression prediction from sequence by integrating long-range interactions. Nat. Methods 18, 1196–1203 (2021). 34608324 PMC8490152 · DOI · Paper page
  28. [38]Sinai, S. & Kelsic, E. D. A primer on model-guided exploration of fitness landscapes for biological sequence design. Preprint at arxiv.org/abs/2010.10614 (2020). · arXiv
  29. [39]Zrimec, J. et al. Controlling gene expression with deep generative design of regulatory DNA. Nat. Commun. 13, 5099 (2022). 36042233 PMC9427793 · DOI
  30. [40]Gupta, A. & Kundaje, A. Targeted optimization of regulatory DNA sequences with neural editing architectures. Preprint at bioRxiv10.1101/714402 (2019).
  31. [41]Killoran, N., Lee, L. J., Delong, A., Duvenaud, D. & Frey, B. J. Generating and designing DNA with deep generative models. Preprint at arxiv.org/abs/1712.06148 (2017). · arXiv
  32. [42]Taskiran, I. I. et al. Cell-type-directed design of synthetic enhancers. Nature 626, 212–220 (2023). 38086419 PMC10830415 · DOI · Paper page
  33. [43]de Almeida, B. P. et al. Targeted design of synthetic enhancers for selected tissues in the Drosophila embryo. Nature 626, 207–211 (2024). 38086418 PMC10830412 · DOI · Paper page
  34. [44]Deverman, B. E., Ravina, B. M., Bankiewicz, K. S., Paul, S. M. & Sah, D. W. Y. Gene therapy for neurological disorders: progress and prospects. Nat. Rev. Drug Discov. 17, 767 (2018). 30206384 · DOI
  35. [45]Mitchell, M. J. et al. Engineering precision nanoparticles for drug delivery. Nat. Rev. Drug Discov. 20, 101–124 (2020). 33277608 PMC7717100 · DOI · Paper page
  36. [46]Tabebordbar, M. et al. Directed evolution of a family of AAV capsid variants enabling potent muscle-directed gene delivery across species. Cell 184, 4919–4938 (2021). 34506722 PMC9344975 · DOI
  37. [47]Stanton, A. C. et al. Systemic administration of novel engineered AAV capsids facilitates enhanced transgene expression in the macaque CNS. Med 4, 31–50 (2023). 36417917 PMC9840684 · DOI
  38. [48]Cazares, T. A. et al. maxATAC: genome-scale transcription-factor binding prediction from ATAC-seq with deep neural networks. PLoS Comput. Biol. 19, e1010863 (2023). 36719906 PMC9917285 · DOI
  39. [49]Golovin, D. et al. Google Vizier: a service for black-box optimization. In Proc. 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 1487–1495 (ACM, 2017).
  40. [50]Snoek, J., Larochelle, H. & Adams, R. P. Practical bayesian optimization of machine learning algorithms. In Proc. Advances in Neural Information Processing Systems 25 (eds. Pereira, F., Burges, C. J. C., Bottou, L. & Weinberger, K. Q.) 2951–2959 (Curran Associates, 2012).
  41. [51]Thurman, R. E. et al. The accessible chromatin landscape of the human genome. Nature 489, 75–82 (2012). 22955617 PMC3721348 · DOI · Paper page
  42. [53]Hardison, R. C. & Taylor, J. Genomic approaches towards finding cis-regulatory modules in animals. Nat. Rev. Genet. 13, 469–483 (2012). 22705667 PMC3541939 · DOI
  43. [55]Luo, Y. et al. New developments on the Encyclopedia of DNA Elements (ENCODE) data portal. Nucleic Acids Res. 48, D882–D889 (2020). 31713622 PMC7061942 · DOI
  44. [56]Kagda, M. S. et al. Data navigation on the ENCODE portal. Preprint at arxiv.org/abs/2305.00006 (2023). PMC12575607 41168159 · arXiv
  45. [57]Hitz, B. C. et al. The ENCODE uniform analysis pipelines. Preprint at bioRxiv10.1101/2023.04.04.535623 (2023).
  46. [58]Sundararajan, M., Taly, A. & Yan, Q. Axiomatic attribution for deep networks. In Proc. 34th International Conference on Machine Learning (eds Precup, D. & Teh, Y. W.) Vol. 70, 3319–3328 (JMLR.org, 2017).
  47. [60]Shrikumar, A. et al. Technical note on transcription factor motif discovery from importance scores (TF-MoDISco) version 0.5.6.5. Preprint at arxiv.org/abs/1811.00416 (2018). · arXiv
  48. [61]Castro-Mondragon, J. A. et al. JASPAR 2022: the 9th release of the open-access database of transcription factor binding profiles. Nucleic Acids Res. 50, D165–D173 (2022). 34850907 PMC8728201 · DOI · Paper page
  49. [62]Kulakovskiy, I. V. et al. HOCOMOCO: towards a complete collection of transcription factor binding models for human and mouse via large-scale ChIP-Seq analysis. Nucleic Acids Res. 46, D252–D259 (2018). 29140464 PMC5753240 · DOI
  50. [64]Parviz, F. et al. Hepatocyte nuclear factor 4α controls the development of a hepatic epithelium and liver morphogenesis. Nat. Genet. 34, 292–296 (2003). 12808453 · DOI · Paper page
  51. [65]Harries, L. W., Brown, J. E. & Gloyn, A. L. Species-specific differences in the expression of the HNF1A, HNF1B and HNF4A genes. PLoS ONE 4, e7855 (2009). 19924231 PMC2773013 · DOI
  52. [66]El-Khairi, R. & Vallier, L. The role of hepatocyte nuclear factor 1β in disease and development. Diabetes Obes. Metab. 18, 23–32 (2016). 27615128 · DOI
  53. [67]Odom, D. T. et al. Core transcriptional regulatory circuitry in human hepatocytes. Mol. Syst. Biol. 2, 2006.0017 (2006). 16738562 PMC1681491 · DOI
  54. [68]Zweidler-Mckay, P. A., Grimes, H. L., Flubacher, M. M. & Tsichlis, P. N. Gfi-1 encodes a nuclear zinc finger protein that binds DNA and functions as a transcriptional repressor. Mol. Cell. Biol. 16, 4024–4034 (1996). 8754800 PMC231398 · DOI
  55. [69]Huang, D.-Y., Kuo, Y.-Y. & Chang, Z.-F. GATA-1 mediates auto-regulation of Gfi-1B transcription in K562 cells. Nucleic Acids Res. 33, 5331–5342 (2005). 16177182 PMC1226314 · DOI
  56. [70]Beauchemin, H. & Möröy, T. Multifaceted actions of GFI1 and GFI1B in hematopoietic stem cell self-renewal and lineage commitment. Front. Genet. 11, 591099 (2020). 33193732 PMC7649360 · DOI
  57. [71]Agoston, Z. & Schulte, D. Meis2 competes with the Groucho co-repressor Tle4 for binding to Otx2 and specifies tectal fate without induction of a secondary midbrain-hindbrain boundary organizer. Development 136, 3311–3322 (2009). 19736326 · DOI
  58. [72]Machon, O., Masek, J., Machonova, O., Krauss, S. & Kozmik, Z. Meis2 is essential for cranial and cardiac neural crest development. BMC Dev. Biol. 15, 40 (2015). 26545946 PMC4636814 · DOI
  59. [73]Zha, Y. et al. MEIS2 is essential for neuroblastoma cell survival and proliferation by transcriptional control of M-phase progression. Cell Death Dis. 5, e1417 (2014). 25210800 PMC4540202 · DOI
  60. [74]Lee, D. D. & Seung, H. S. Learning the parts of objects by non-negative matrix factorization. Nature 401, 788–791 (1999). 10548103 · DOI
  61. [75]Birnbaum, R. Y. et al. Coding exons function as tissue-specific enhancers of nearby genes. Genome Res. 22, 1059–1068 (2012). 22442009 PMC3371700 · DOI
  62. [76]Kvon, E. Z. et al. Comprehensive in vivo interrogation reveals phenotypic impact of human enhancer variants. Cell 180, 1262–1271 (2020). 32169219 PMC7179509 · DOI
  63. [77]Chatterjee, R. et al. Overlapping ETS and CRE motifs ((G/C)CGGAAGTGACGTCA) preferentially bound by GABPα and CREB proteins. G3 2, 1243–1256 (2012). 23050235 PMC3464117 · DOI
  64. [78]Fornes, O. et al. OnTarget: in silico design of MiniPromoters for targeted delivery of expression. Nucleic Acids Res. 51, W379–W386 (2023). 37166953 PMC10320062 · DOI
  65. [79]Korecki, A. J. et al. Human MiniPromoters for ocular-rAAV expression in ON bipolar, cone, corneal, endothelial, Müller glial, and PAX6 cells. Gene Ther. 28, 351–372 (2021). 33531684 PMC8222000 · DOI
  66. [80]Hrvatin, S. et al. A scalable platform for the development of cell-type-specific viral drivers. eLife 8, e48089 (2019). 31545165 PMC6776442 · DOI · Paper page
  67. [82]Rafi, A. M. et al. Evaluation and optimization of sequence-based gene regulatory deep learning models. Preprint at bioRxiv10.1101/2023.04.26.538471 (2024).
  68. [83]Cock, P. J. A. et al. Biopython: freely available Python tools for computational molecular biology and bioinformatics. Bioinformatics 25, 1422–1423 (2009). 19304878 PMC2682512 · DOI · Paper page
  69. [84]Quinlan, A. R. & Hall, I. M. BEDTools: a flexible suite of utilities for comparing genomic features. Bioinformatics 26, 841–842 (2010). 20110278 PMC2832824 · DOI · Paper page
  70. [85]Dale, R. K., Pedersen, B. S. & Quinlan, A. R. Pybedtools: a flexible Python library for manipulating genomic datasets and annotations. Bioinformatics 27, 3423–3424 (2011). 21949271 PMC3232365 · DOI
  71. [86]Heinz, S. et al. Simple combinations of lineage-determining transcription factors prime cis-regulatory elements required for macrophage and B cell identities. Mol. Cell 38, 576–589 (2010). 20513432 PMC2898526 · DOI · Paper page
  72. [87]Bailey, T. L., Johnson, J., Grant, C. E. & Noble, W. S. The MEME Suite. Nucleic Acids Res. 43, W39–W49 (2015). 25953851 PMC4489269 · DOI
  73. [88]Grant, C. E., Bailey, T. L. & Noble, W. S. FIMO: scanning for occurrences of a given motif. Bioinformatics 27, 1017–1018 (2011). 21330290 PMC3065696 · DOI · Paper page
  74. [89]Kunes, R. Z., Walle, T., Land, M., Nawy, T. & Pe’er, D. Supervised discovery of interpretable gene programs from single-cell data. Nat. Biotechnol. 10.1038/s41587-023-01940-3 (2023). PMC10958532 37735262 · DOI
  75. [90]Kotliar, D. et al. Identifying gene expression programs of cell-type identity and cellular activity with single-cell RNA-seq. eLife 8, e43803 (2019). 31282856 PMC6639075 · DOI · Paper page
  76. [91]Owen, A. B. & Perry, P. O. Bi-cross-validation of the SVD and the nonnegative matrix factorization. Ann. Appl. Stat. 3, 564–594 (2009). · DOI
  77. [92]Kawakami, K. et al. A transposon-mediated gene trap approach identifies developmentally regulated genes in zebrafish. Dev. Cell 7, 133–144 (2004). 15239961 · DOI
  78. [93]Levitsky, K. L., Toledo-Aral, J. J., López-Barneo, J. & Villadiego, J. Direct confocal acquisition of fluorescence from X-gal staining on thick tissue sections. Sci. Rep. 3, 2937 (2013). 24121824 PMC3796308 · DOI
  79. [94]Dobin, A. et al. STAR: ultrafast universal RNA-seq aligner. Bioinformatics 29, 15–21 (2013). 23104886 PMC3530905 · DOI · Paper page
  80. [95]Love, M. I., Huber, W. & Anders, S. Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2. Genome Biol. 15, 550 (2014). 25516281 PMC4302049 · DOI · Paper page
  81. [96]Gosai, S. J. et al. Data for ‘Machine-guided design of cell type-targeting cis-regulatory elements’. Zenodo10.5281/zenodo.10698013 (2024). PMC11525185 39443793

Cited by

Sorted by citations

Authors
Gosai, S. J., Castro, R. I., Fuentes, N., Butts, J. C., Mouri, K., Alasoadura, M., Kales, S., Nguyen, T. T. L., Noche, R. R., Rao, A. S., Joy, M. T., Sabeti, P. C., Reilly, S. K., & Tewhey, R.
Affiliations
  • Broad Institute (US)
  • Jackson Laboratory (US)
  • Harvard University (US)
  • Yale University (US)
  • Tufts University (US)
Corresponding author
  • Gosai, Sager J.
  • Castro, Rodrigo I.
  • Reilly, Steven K.
  • Tewhey, Ryan
ORCID
Venue
Nature
Publisher
Springer Science and Business Media LLC
Published
2024-10-23
Volume
634
Issue
8036
Pages
1211-1220
ISSN
  • 0028-0836 (ISSN-L)
  • 1476-4687
DOI
10.1038/s41586-024-08070-z
PMC
PMC11525185
OpenAlex
W4403680549
Cited by
142
References
15
Citations by year
2026: 60 · 2025: 74 · 2024: 7 · 2023: 1
FWCI
19.19
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
  • The Mouseion at the JAXlibrary (Jackson Laboratory) (submittedVersion, cc-by)
Funders
  • National Institute of Mental Health (T32MH014276)
  • National Human Genome Research Institute (UM1HG009435, R00HG010669, R00HG008179, R01HG012872, R35HG011329)
  • National Institute of General Medical Sciences (T32GM144273)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Chromatin Dynamics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › CRISPR and Genetic Engineering
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene Regulatory Network Analysis
Keywords
cis-regulatory elements, synthetic gene regulation, cell type specificity, deep neural network, massively parallel reporter assay, transcription factor binding motifs, tissue-specific gene expression
MeSH terms
Machine Learning, Deep Learning, Animals, Cell Line, Cells, Computer Simulation, Female, Gene Expression Regulation, Genetic Engineering, Humans, Male, Organ Specificity, Regulatory Sequences, Nucleic Acid, Zebrafish, Reproducibility of Results, Genome, Human, Neural Networks, Computer, Genes, Reporter, Mice

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