journal article·2024-10Open access

Deciphering 3'UTR Mediated Gene Regulation Using Interpretable Deep Representation Learning

Yuning Yang, Gen Li, Kuan Pang, Wuxinhao Cao, Zhaolei Zhang, Xiangtao Li

Advanced Science· Volume 11· Issue 39

Abstract

Abstract The 3' untranslated regions (3'UTRs) of messenger RNAs contain many important cis‐regulatory elements that are under functional and evolutionary constraints. It is hypothesized that these constraints are similar to grammars and syntaxes in human languages and can be modeled by advanced natural language techniques such as Transformers, which has been very effective in modeling complex protein sequence and structures. Here 3UTRBERT is described, which implements an attention‐based language model, i.e., Bidirectional Encoder Representations from Transformers (BERT). 3UTRBERT is pre‐trained on aggregated 3'UTR sequences of human mRNAs in a task‐agnostic manner; the pre‐trained model is then fine‐tuned for specific downstream tasks such as identifying RBP binding sites, m6A RNA modification sites, and predicting RNA sub‐cellular localizations. Benchmark results show that 3UTRBERT generally outperformed other contemporary methods in each of these tasks. More importantly, the self‐attention mechanism within 3UTRBERT allows direct visualization of the semantic relationship between sequence elements and effectively identifies regions with important regulatory potential. It is expected that 3UTRBERT model can serve as the foundational tool to analyze various sequence labeling tasks within the 3'UTR fields, thus enhancing the decipherability of post‐transcriptional regulatory mechanisms.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: RNA modifications and cancer · Cancer-related molecular mechanisms research · RNA Research and Splicing

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

School of Information Science and Technology Northeast Normal University Changchun Jilin 130117 China

Donnelly Centre for Cellular and Biomolecular Research University of Toronto Toronto ON M5S 3E1 Canada

Department of Computer Science University of Toronto Toronto ON M5S 3E1 Canada

Department of Molecular Genetics University of Toronto Toronto ON M5S 3E1 Canada

School of Artificial Intelligence Jilin University Changchun Jilin 130012 China

Funding

Natural Sciences and Engineering Research Council of Canada · National Natural Science Foundation of China · Fundamental Research Funds for the Central Universities

References (85)

Show source-provided references
1. 10.1016/j.cell.2016.03.01410.1016/j.cell.2016.03.014 ↗
2. 10.1016/j.cell.2012.04.03110.1016/j.cell.2012.04.031 ↗
3. 10.1126/science.117648810.1126/science.1176488 ↗
4. 10.1038/nature1423410.1038/nature14234 ↗
5. 10.1038/nature0164410.1038/nature01644 ↗
6. 10.1038/nature0344110.1038/nature03441 ↗
7. 10.1101/gr.371500510.1101/gr.3715005 ↗
8. 10.1101/gr.097857.10910.1101/gr.097857.109 ↗
9. 10.1038/nbt.330010.1038/nbt.3300 ↗
10. 10.1038/s41467-023-42547-110.1038/s41467-023-42547-1 ↗
11. 10.1093/bioinformatics/btaa15510.1093/bioinformatics/btaa155 ↗
12. 10.1093/nar/gkab01610.1093/nar/gkab016 ↗
13. 10.1093/nar/gky56710.1093/nar/gky567 ↗
14. Grønning A. G. B. · Nucleic Acids Res. · 2020 · 48 · 7099
15. 10.1093/bib/bbaa27410.1093/bib/bbaa274 ↗
16. 10.1093/bioinformatics/bty36410.1093/bioinformatics/bty364 ↗
17. 10.1093/bioinformatics/btaa45610.1093/bioinformatics/btaa456 ↗
18. M.Uhl V. D.Tran F.Heyl R.Backofen BioRxiv2021 850024.
19. 10.1016/j.tcb.2015.10.01210.1016/j.tcb.2015.10.012 ↗
20. A.Vaswani N.Shazeer N.Parmar J.Uszkoreit L.Jones A. N.Gomez Ł.Kaiser I.Polosukhin inProc. Conf. Neural Inform. Process. Syst. (NIPS) Long Beach CA USA 2017 pp.5998–6008.
21. J.Devlin M.‐W.Chang K.Lee K.Toutanova arXiv preprint arXiv:1810.048052018.
22. 10.1093/bioinformatics/btab08310.1093/bioinformatics/btab083 ↗
23. 10.1093/bioinformatics/btac02010.1093/bioinformatics/btac020 ↗
24. 10.1109/TPAMI.2021.309538110.1109/TPAMI.2021.3095381 ↗
25. Akiyama M. · NAR Genom. Bioinform. · 2022 · 4 · 012
26. J.Chen Z.Hu S.Sun Q.Tan Y.Wang Q.Yu L.Zong L.Hong J.Xiao T.Shen I.King Y.Li arXiv preprint arXiv:2204.003002022.
27. 10.1038/s41587-022-01432-w10.1038/s41587-022-01432-w ↗
28. 10.1126/science.ade257410.1126/science.ade2574 ↗
29. 10.1093/nar/gkad103110.1093/nar/gkad1031 ↗
30. 10.1016/j.compbiomed.2023.10723810.1016/j.compbiomed.2023.107238 ↗
31. 10.1093/bioadv/vbac02310.1093/bioadv/vbac023 ↗
32. 10.1038/nrm.2017.13010.1038/nrm.2017.130 ↗
33. 10.1093/bioinformatics/btw00310.1093/bioinformatics/btw003 ↗
34. 10.1016/j.molcel.2019.02.00210.1016/j.molcel.2019.02.002 ↗
35. 10.1038/nature1934210.1038/nature19342 ↗
36. Giudice G. · Database(Oxford) · 2016 · 2016 · 035
37. 10.1186/gb-2007-8-2-r2410.1186/gb-2007-8-2-r24 ↗
38. 10.1038/nrm217810.1038/nrm2178 ↗
39. 10.1016/j.canlet.2014.06.01910.1016/j.canlet.2014.06.019 ↗
40. 10.1016/j.celrep.2021.10917810.1016/j.celrep.2021.109178 ↗
41. 10.1074/jbc.M111.30148110.1074/jbc.M111.301481 ↗
42. 10.1016/j.molcel.2011.06.00810.1016/j.molcel.2011.06.008 ↗
43. 10.7554/eLife.4726110.7554/eLife.47261 ↗
44. 10.1093/nar/gkab106110.1093/nar/gkab1061 ↗
45. R.Pearce G. S.Omenn Y.Zhang bioRxiv2022 2022–05.
46. 10.1038/nprot.2016.16910.1038/nprot.2016.169 ↗
47. 10.1002/jcc.2128710.1002/jcc.21287 ↗
48. 10.1093/nar/gkn41110.1093/nar/gkn411 ↗
49. 10.1038/ncb290210.1038/ncb2902 ↗
50. 10.1371/journal.pgen.100814110.1371/journal.pgen.1008141 ↗
51. 10.1093/nar/gkaa69210.1093/nar/gkaa692 ↗
52. 10.1093/nar/gkw10410.1093/nar/gkw104 ↗
53. 10.1093/nar/gkz07410.1093/nar/gkz074 ↗
54. 10.1186/s12859-017-2006-010.1186/s12859-017-2006-0 ↗
55. 10.1093/nar/gkx32310.1093/nar/gkx323 ↗
56. 10.1016/j.cell.2012.05.00310.1016/j.cell.2012.05.003 ↗
57. 10.1038/nature1111210.1038/nature11112 ↗
58. 10.1016/j.tcb.2009.06.00110.1016/j.tcb.2009.06.001 ↗
59. 10.1093/nar/gkx53310.1093/nar/gkx533 ↗
60. 10.1093/nar/gkab82510.1093/nar/gkab825 ↗
61. 10.1093/bioinformatics/btz33710.1093/bioinformatics/btz337 ↗
62. 10.1093/nar/gkaa38510.1093/nar/gkaa385 ↗
63. 10.1093/bib/bbz17710.1093/bib/bbz177 ↗
64. 10.1074/jbc.M90102620010.1074/jbc.M901026200 ↗
65. 10.1038/nature1231110.1038/nature12311 ↗
66. 10.1083/jcb.20191207410.1083/jcb.201912074 ↗
67. 10.1093/bioinformatics/btae06510.1093/bioinformatics/btae065 ↗
68. 10.1038/s41467-019-09234-610.1038/s41467-019-09234-6 ↗
69. L.McInnes J.Healy J.Melville arXiv preprint arXiv:1802.034262018.
70. Yang Y. · Brief. Bioinform. · 2022 · 23 · 2
71. 10.1038/s42003-023-04462-510.1038/s42003-023-04462-5 ↗
72. Z. J.Wang R.Turko D. H.Chau arXiv preprint arXiv:2103.146252021.
73. 10.1093/bioinformatics/btp16310.1093/bioinformatics/btp163 ↗
74. 10.1016/S0022-2836(05)80360-210.1016/S0022-2836(05)80360-2 ↗
75. G.Attanasio E.Pastor C.Di Bonaventura D.Nozza arXiv preprint arXiv:2208.015752022.
76. S. M.Lundberg S.‐I.Lee inProceedings of the Advances in Neural Information Processing Systems Curran Associates Inc. Red Hook NY USA2017 pp.4765–4774.
77. M.Sundararajan A.Taly Q.Yan inProceedings of Machine Learning Research (PMLR) 2017 pp.3319–3328.
78. M. T.Ribeiro S.Singh C.Guestrin inProc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min. ACM San Francisco2016 pp.1135–1144.10.1145/2939672.2939778 ↗
79. 10.1101/gr.135350.11110.1101/gr.135350.111 ↗
80. 10.1093/nar/gkr100710.1093/nar/gkr1007 ↗
81. 10.1371/journal.pcbi.101029310.1371/journal.pcbi.1010293 ↗
82. 10.1038/s41586-020-2077-310.1038/s41586-020-2077-3 ↗
83. 10.1093/bioinformatics/bts56510.1093/bioinformatics/bts565 ↗
84. 10.1093/nar/gkac32610.1093/nar/gkac326 ↗
85. 10.1007/3-540-44696-6_2210.1007/3-540-44696-6_22 ↗