CoChat
Sign Up
Cited by 44RNA Research and SplicingGenomics and Phylogenetic StudiesRNA and protein synthesis mechanisms

Inference of the human polyadenylation code

Open access
Leung, Michael K K, Delong, Andrew, Frey, Brendan J·2018·Bioinformatics
DOI 10.1093/bioinformatics/bty211PMC PMC6129302

Published version of a preprint

Open this paper in CoChat — free account

Abstract

Motivation: Processing of transcripts at the 3′-end involves cleavage at a polyadenylation site followed by the addition of a poly(A)-tail. By selecting which site is cleaved, the process of alternative polyadenylation enables genes to produce transcript isoforms with different 3′-ends. To facilitate the identification and treatment of disease-causing mutations that affect polyadenylation and to understand the sequence determinants underlying this regulatory process, a computational model that can accurately predict polyadenylation patterns from genomic features is desirable. Results: Previous works have focused on identifying candidate polyadenylation sites and classifying tissue-specific sites. By training on how multiple sites in genes are competitively selected for polyadenylation from 3′-end sequencing data, we developed a deep learning model that can predict the tissue-specific strength of a polyadenylation site in the 3′ untranslated region of the human genome given only its genomic sequence. We demonstrate the model’s broad utility on multiple tasks, without any application-specific training. The model can be used to predict which polyadenylation site is more likely to be selected in genes with multiple sites. It can be used to scan the 3′ untranslated region to find candidate polyadenylation sites. It can be used to classify the pathogenicity of variants near annotated polyadenylation sites in ClinVar. It can also be used to anticipate the effect of antisense oligonucleotide experiments to redirect polyadenylation. We provide analysis on how different features affect the model’s predictive performance and a method to identify sensitive regions of the genome at the single-based resolution that can affect polyadenylation regulation. Supplementary information: Supplementary data are available at Bioinformatics online.

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 · 10.1093/bioinformatics/bty211

Cites

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?

  • Sequence-based models of post-transcriptional regulation rely on genome annotations and transformed measurements extracted from RNA-seq to isolate each regulatory mechanism.

    “Similarly, sequence-based models of post-transcriptional regulation rely on genome annotations and transformed measurements extracted from RNA-seq to isolate each regulatory mechanism (for example, percent spliced-in for splicing)14–23.”

    From Predicting RNA-seq coverage from DNA sequence as a unifying model of gene regulation (2025) · cites this paper as [17]

Self-check

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

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

No citation lists for this paper

No citation lists for this paper yet — checked again daily.

References 62 · Cited by 44

Research works printed but not linked: 56

  1. Abadi M. et al (2015) Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv: 1603.04467. · arXiv
  2. Akhtar M.N. et al (2010) POLYAR, a new computer program for prediction of poly(A) sites in human sequences. BMC Genomics, 11, 646. 21092114 PMC3053588
  3. Alipanahi B. et al (2015) Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning. Nat. Biotechnol., 33, 831– 838. 26213851
  4. Angermueller C. et al (2017) DeepCpG: accurate prediction of single-cell DNA methylation states using deep learning. Genome Biol., 18, 67. 28395661 PMC5387360
  5. Blanchette M. (2004) Aligning multiple genomic sequences with the threaded blockset aligner. Genome Res., 14, 708– 715. 15060014 PMC383317
  6. Chang T.H. et al (2011) Characterization and prediction of mRNA polyadenylation sites in human genes. Med. Biol. Eng. Comput., 49, 463– 472. 21286831
  7. Cheng Y. et al (2006) Prediction of mRNA polyadenylation sites by support vector machine. Bioinformatics, 22, 2320– 2325. 16870936
  8. Cooper G.M. et al (2005) Distribution and intensity of constraint in mammalian genomic sequence. Genome Res., 15, 901– 913. 15965027 PMC1172034
  9. Danckwardt S. et al (2008) 3′ end mRNA processing: molecular mechanisms and implications for health and disease. Embo J., 27, 482– 498. 18256699 PMC2241648
  10. Derti A. et al (2012) A quantitative atlas of polyadenylation in five mammals. Genome Res., 22, 1173– 1183. 22454233 PMC3371698
  11. Di Giammartino D.C. et al (2011) Mechanisms and consequences of alternative polyadenylation. Mol. Cell., 43, 853– 866. 21925375 PMC3194005
  12. Elkon R. et al (2013) Alternative cleavage and polyadenylation: extent, regulation and function. Nat. Rev. Genet., 14, 496– 506. 23774734
  13. Gallego Romero I. et al (2014) RNA-seq: impact of RNA degradation on transcript quantification. BMC Biol., 12, 42. 24885439 PMC4071332
  14. Glorot X. et al (2011) Deep sparse rectifier neural networks. Proc. 14th Int. Conf. Artif. Intell. Stat., 315– 320.
  15. Glorot X., Bengio Y. (2010) Understanding the difficulty of training deep feedforward neural networks. Proc. 13th Int. Conf. Artif. Intell. Stat., 9, 249– 256.
  16. Hafez D. et al (2013) Genome-wide identification and predictive modeling of tissue-specific alternative polyadenylation. Bioinformatics, 29, i108– i116. 23812974 PMC3694680
  17. Harrow J. et al (2012) GENCODE: the reference human genome annotation for the ENCODE project. Genome Res., 22, 1760– 1774. 22955987 PMC3431492
  18. Hinton G.E. et al (2012) Improving neural networks by preventing co-adaptation of feature detectors. arXiv:1207.0580. · arXiv
  19. Ho E.S. et al (2013) A multispecies polyadenylation site model. BMC Bioinformatics, 14, S9. PMC3549828 23368518
  20. Hu J. (2005) Bioinformatic identification of candidate cis-regulatory elements involved in human mRNA polyadenylation. RNA, 11, 1485– 1493. 16131587 PMC1370832
  21. Ji G. et al (2015) Genome-wide identification and predictive modeling of polyadenylation sites in eukaryotes. Brief. Bioinf., 16, 304– 313. 24695098
  22. Kalkatawi M. et al (2012) Dragon PolyA Spotter: predictor of poly(A) motifs within human genomic DNA sequences. Bioinformatics, 28, 127– 129. 22088842 PMC3244764
  23. Kaneko S., Manley J.L. (2005) The mammalian RNA polymerase II C-terminal domain interacts with RNA to suppress transcription-coupled 3′ end formation. Mol. Cell., 20, 91– 103. 16209948
  24. Kelley D.R. et al (2016) Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks. Genome Res., 26, 990– 999. 27197224 PMC4937568
  25. Kent W.J. et al (2002) The human genome browser at UCSC. Genome Res., 12, 996– 1006. 12045153 PMC186604
  26. Kircher M. et al (2014) A general framework for estimating the relative pathogenicity of human genetic variants. Nat. Genet., 46, 310– 315. 24487276 PMC3992975
  27. Kole R. et al (2012) RNA therapeutics: beyond RNA interference and antisense oligonucleotides. Nat. Rev. Drug Discov., 11, 125– 140. 22262036 PMC4743652
  28. Landrum M.J. et al (2014) ClinVar: public archive of relationships among sequence variation and human phenotype. Nucleic Acids Res., 42, D980– D985. 24234437 PMC3965032
  29. LeCun Y. et al (1998) Gradient-based learning applied to document recognition. Proc. IEEE, 86, 2278– 2323.
  30. LeCun Y. et al (2015) Deep learning. Nature, 521, 436– 444. 26017442
  31. Lee J.Y. et al (2007) PolyA_DB 2: mRNA polyadenylation sites in vertebrate genes. Nucleic Acids Res., 35, D165– D168. 17202160 PMC1899096
  32. Leung M.K.K. et al (2014) Deep learning of the tissue-regulated splicing code. Bioinformatics, 30, i121– i129. 24931975 PMC4058935
  33. Leung M.K.K. et al (2016) Machine learning in genomic medicine: a review of computational problems and data sets. Proc. IEEE, 104, 176– 197.
  34. Lianoglou S. et al (2013) Ubiquitously transcribed genes use alternative polyadenylation to achieve tissue-specific expression. Genes Dev., 27, 2380– 2396. 24145798 PMC3828523
  35. Lin Y. et al (2012) An in-depth map of polyadenylation sites in cancer. Nucleic Acids Res., 40, 8460– 8471. 22753024 PMC3458571
  36. MacDonald C.C., McMahon K.W. (2010) Tissue-specific mechanisms of alternative polyadenylation: testis, brain, and beyond. Wiley Interdiscip. Rev. RNA, 1, 494– 501. 21956945 PMC5417544
  37. Manning K.S., Cooper T.A. (2016) The roles of RNA processing in translating genotype to phenotype. Nat. Rev. Mol. Cell Biol., 18, 102– 114. 27847391 PMC5544131
  38. Müller S. et al (2014) APADB: a database for alternative polyadenylation and microRNA regulation events. Database (Oxford), doi/10.1093/database/bau076/2634812. PMC4105710 25052703 · DOI
  39. Pollard K.S. et al (2010) Detection of nonneutral substitution rates on mammalian phylogenies. Genome Res., 20, 110– 121. 19858363 PMC2798823
  40. Proudfoot N.J. (2011) Ending the message: poly(A) signals then and now. Genes Dev., 25, 1770– 1782. 21896654 PMC3175714
  41. Pruitt K.D. (2004) NCBI Reference Sequence (RefSeq): a curated non-redundant sequence database of genomes, transcripts and proteins. Nucleic Acids Res., 33, D501– D504. PMC539979 15608248
  42. Rampasek L., Goldenberg A. (2016) TensorFlow: biology’s gateway to deep learning? Cell Syst., 2, 12– 14. 27136685
  43. Rund D. et al (1992) Two mutations in the beta-globin polyadenylylation signal reveal extended transcripts and new RNA polyadenylylation sites. Proc. Natl. Acad. Sci. USA, 89, 4324– 4328. 1374896 PMC49074
  44. Shaw G., Kamen R. (1986) A conserved AU sequence from the 3′ untranslated region of GM-CSF mRNA mediates selective mRNA degradation. Cell, 46, 659– 667. 3488815
  45. Shi Y. (2012) Alternative polyadenylation: new insights from global analyses. RNA, 18, 2105– 2117. 23097429 PMC3504663
  46. Simonyan K. et al (2014) Deep inside convolutional networks: visualising image classification models and saliency maps. In: Proc. of the Int. Conf. on Learn. Representations.
  47. Tian B., Graber J.H. (2012) Signals for pre-mRNA cleavage and polyadenylation. Wiley Interdiscip. Rev. RNA, 3, 385– 396. 22012871 PMC4451228
  48. Tian B., Manley J.L. (2017) Alternative polyadenylation of mRNA precursors. Nat. Rev. Mol. Cell Biol., 18, 18– 30. 27677860 PMC5483950
  49. van der Heijden T. et al (2012) Sequence-based prediction of single nucleosome positioning and genome-wide nucleosome occupancy. Proc. Natl. Acad. Sci. 109, E2514– E2522. PMC3458375 22908247
  50. Vickers T. et al (2001) Fully modified 2′ MOE oligonucleotides redirect polyadenylation. Nucleic Acids Res., 29, 1293– 1299. 11238995 PMC29745
  51. Weng L. et al (2016) Poly(A) code analyses reveal key determinants for tissue-specific mRNA alternative polyadenylation. RNA, 22, 813– 821. 27095026 PMC4878608
  52. Xie B. et al (2013) Poly(A) motif prediction using spectral latent features from human DNA sequences. Bioinformatics, 29, i316– i325. 23813000 PMC3694652
  53. Xiong H.Y. et al (2014) The human splicing code reveals new insights into the genetic determinants of disease. Science, 347, 1254806. PMC4362528 25525159
  54. Xiong H.Y. et al (2016) Probabilistic estimation of short sequence expression using RNA-Seq data and the positional bootstrap. bioRxiv:046474.
  55. Yates A. et al (2016) Ensembl 2016. Nucleic Acids Res., 44, D710– D716. 26687719 PMC4702834
  56. Zhou J., Troyanskaya O.G. (2015) Predicting effects of noncoding variants with deep learning–based sequence model. Nat. Methods, 12, 931. 26301843 PMC4768299

Authors
Leung, M. K. K., Delong, A., & Frey, B. J.
Affiliations
University of Toronto (CA)
Corresponding author
Frey, Brendan J
ORCID
Delong, Andrew
Venue
Bioinformatics
Publisher
Oxford University Press (OUP)
Published
2018-04-10
Volume
34
Issue
17
Pages
2889-2898
ISSN
  • 1367-4803 (ISSN-L)
  • 1367-4811
DOI
10.1093/bioinformatics/bty211
PMC
PMC6129302
OpenAlex
W2946841580
Cited by
44
References
62
Citations by year
2026: 1 · 2025: 7 · 2024: 5 · 2023: 4 · 2022: 10 · 2021: 5 · 2020: 2 · 2019: 8 · 2018: 2
FWCI
1.51
Type
journal article
Language
en
Open access
Licence
Locations
  • Bioinformatics (publishedVersion, cc-by-nc)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by-nc)
  • PubMed Central (publishedVersion, cc-by-nc)
  • PubMed (publishedVersion)
  • Research in Computational Molecular Biology
Funders
Natural Science and Engineering Research Council of Canada and Deep Genomics
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › RNA Research and Splicing
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Phylogenetic Studies
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › RNA and protein synthesis mechanisms
Keywords
polyadenylation site selection, alternative polyadenylation, poly(A) tail, 3' untranslated region, deep learning prediction, variant pathogenicity classification, antisense oligonucleotides
MeSH terms
Gene Expression Regulation, Humans, Poly A, Genome, Human, 3' Untranslated Regions, Genomics, Polyadenylation

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