CoChat
Sign Up
Cited by 37RNA Research and SplicingGenomics and Phylogenetic StudiesCancer-related molecular mechanisms research

DeeReCT-APA: Prediction of Alternative Polyadenylation Site Usage Through Deep Learning

Open access
Li, Zhongxiao, Li, Yisheng, Zhang, Bin, Li, Yu, Long, Yongkang, Zhou, Juexiao, Zou, Xudong, Zhang, Min +3 more·2022·Genomics, Proteomics & Bioinformatics
DOI 10.1016/j.gpb.2020.05.004PMC PMC9801043

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

Alternative polyadenylation (APA) is a crucial step in post-transcriptional regulation. Previous bioinformatic studies have mainly focused on the recognition of polyadenylation sites (PASs) in a given genomic sequence, which is a binary classification problem. Recently, computational methods for predicting the usage level of alternative PASs in the same gene have been proposed. However, all of them cast the problem as a non-quantitative pairwise comparison task and do not take the competition among multiple PASs into account. To address this, here we propose a deep learning architecture, Deep Regulatory Code and Tools for Alternative Polyadenylation (DeeReCT-APA), to quantitatively predict the usage of all alternative PASs of a given gene. To accommodate different genes with potentially different numbers of PASs, DeeReCT-APA treats the problem as a regression task with a variable-length target. Based on a convolutional neural network-long short-term memory (CNN-LSTM) architecture, DeeReCT-APA extracts sequence features with CNN layers, uses bidirectional LSTM to explicitly model the interactions among competing PASs, and outputs percentage scores representing the usage levels of all PASs of a gene. In addition to the fact that only our method can quantitatively predict the usage of all the PASs within a gene, we show that our method consistently outperforms other existing methods on three different tasks for which they are trained: pairwise comparison task, highest usage prediction task, and ranking task. Finally, we demonstrate that our method can be used to predict the effect of genetic variations on APA patterns and sheds light on future mechanistic understanding in APA regulation. Our code and data are available at https://github.com/lzx325/DeeReCT-APA-repo.

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 · 10.1016/j.gpb.2020.05.004

Cites

3 of 3 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?

  • 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 [20]

    The Methods section ('A genome-wide PAS quantification dataset'; page unavailable) describes a sequence-based model trained on PAS usage values calculated from 3′-mRNA sequencing reads, using a reference of identified PASs. This supports the claim for alternative polyadenylation, but the paper does not establish that sequence-based models generally rely on genome annotations and RNA-seq-derived measurements to isolate each post-transcriptional mechanism. (LLM, conf=0.83)

    Experimental — accuracy not yet measured

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: 38

  1. [1]Barreau C. Paillard L. Osborne H.B. AU-rich elements and associated factors: are there unifying principles? Nucleic Acids Res 33 2005 7138 7150 16391004 PMC1325018
  2. [4]Lau A.G. Irier H.A. Gu J. Tian D. Ku L. Liu G. Distinct 3ʹUTRs differentially regulate activity-dependent translation of brain-derived neurotrophic factor (BDNF) Proc Natl Acad Sci U S A 107 2010 15945 15950 20733072 PMC2936648
  3. [5]Bertrand E. Chartrand P. Schaefer M. Shenoy S.M. Singer R.H. Long R.M. Localization of ASH1 mRNA particles in living yeast Mol Cell 2 1998 437 445 9809065
  4. [6]Ephrussi A. Dickinson L.K. Lehmann R. Oskar organizes the germ plasm and directs localization of the posterior determinant nanos Cell 66 1991 37 50 2070417
  5. [7]Niedner A. Edelmann F.T. Niessing D. Of social molecules: the interactive assembly of ASH1 mRNA-transport complexes in yeast RNA Biol 11 2014 998 1009 25482892 PMC4615550
  6. [9]Yasuda M. Shabbeer J. Osawa M. Desnick R.J. Fabry disease: novel alpha-galactosidase A 3ʹ-terminal mutations result in multiple transcripts due to aberrant 3ʹ-end formation Am J Hum Genet 73 2003 162 173 12796853 PMC1180577
  7. [10]Bennett C.L. Brunkow M.E. Ramsdell F. O'Briant K.C. Zhu Q. Fuleihan R.L. A rare polyadenylation signal mutation of the FOXP3 gene (AAUAAA→AAUGAA) leads to the IPEX syndrome Immunogenetics 53 2001 435 439 11685453
  8. [11]Higgs D.R. Goodbourn S.E. Lamb J. Clegg J.B. Weatherall D.J. Proudfoot N.J. Alpha-thalassaemia caused by a polyadenylation signal mutation Nature 306 1983 398 400 6646217
  9. [12]Orkin S.H. Cheng T.C. Antonarakis S.E. Kazazian H.H. Jr Thalassemia due to a mutation in the cleavage-polyadenylation signal of the human beta-globin gene EMBO J 4 1985 453 456 4018033 PMC554207
  10. [13]Elkon R. Ugalde A.P. Agami R. Alternative cleavage and polyadenylation: extent, regulation and function Nat Rev Genet 14 2013 496 506 23774734
  11. [14]Mandel C.R. Bai Y. Tong L. Protein factors in pre-mRNA 3ʹ-end processing Cell Mol Life Sci 65 2008 1099 1122 18158581 PMC2742908
  12. [15]Shi Y. Alternative polyadenylation: new insights from global analyses RNA 18 2012 2105 2117 23097429 PMC3504663
  13. [16]Hoque M. Ji Z. Zheng D. Luo W. Li W. You B. Analysis of alternative cleavage and polyadenylation by 3ʹ region extraction and deep sequencing Nat Methods 10 2013 133 139 23241633 PMC3560312
  14. [17]Kalkatawi M. Rangkuti F. Schramm M. Jankovic B.R. Kamau A. Chowdhary R. Dragon PolyA Spotter: predictor of poly(A) motifs within human genomic DNA sequences Bioinformatics 29 2013 1484 23616439
  15. [18]Magana-Mora A. Kalkatawi M. Bajic V.B. Omni-PolyA: a method and tool for accurate recognition of Poly(A) signals in human genomic DNA BMC Genomics 18 2017 620 28810905 PMC5558757
  16. [19]Xie B. Jankovic B.R. Bajic V.B. Song L. Gao X. Poly(A) motif prediction using spectral latent features from human DNA sequences Bioinformatics 29 2013 i316 i325 23813000 PMC3694652
  17. [20]Leung M.K.K. Delong A. Frey B.J. Inference of the human polyadenylation code Bioinformatics 34 2018 2889 2898 29648582 PMC6129302
  18. [21]Arefeen A. Xiao X. Jiang T. DeepPASTA: deep neural network based polyadenylation site analysis Bioinformatics 35 2019 4577 4585 31081512 PMC6853695
  19. [22]LeCun Y. Bengio Y. Hinton G. Deep learning Nature 521 2015 436 444 26017442
  20. [23]Alipanahi B. Delong A. Weirauch M.T. Frey B.J. Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning Nat Biotechnol 33 2015 831 838 26213851
  21. [24]Leung M.K. Xiong H.Y. Lee L.J. Frey B.J. Deep learning of the tissue-regulated splicing code Bioinformatics 30 2014 i121 i129 24931975 PMC4058935
  22. [25]Li Y. Wang S. Umarov R. Xie B. Fan M. Li L. DEEPre: sequence-based enzyme EC number prediction by deep learning Bioinformatics 34 2018 760 769 29069344 PMC6030869
  23. [26]Zou Z. Tian S. Gao X. Li Y. mlDEEPre: multi-functional enzyme function prediction with hierarchical multi-label deep learning Front Genet 9 2019 714 30723495 PMC6349967
  24. [27]Han R. Li Y. Wang S. Gao X. Bi C. Li M. DeepSimulator: a deep simulator for Nanopore sequencing Bioinformatics 34 2018 2899 2908 29659695 PMC6129308
  25. [29]Umarov R. Kuwahara H. Li Y. Gao X. Solovyev V. Promoter analysis and prediction in the human genome using sequence-based deep learning models Bioinformatics 35 2019 2730 2737 30601980
  26. [30]Xia Z. Li Y. Zhang B. Li Z. Hu Y. Chen W. DeeReCT-PolyA: a robust and generic deep learning method for PAS identification Bioinformatics 35 2019 2371 2379 30500881 PMC6612895
  27. [31]Xiao M.S. Zhang B. Li Y.S. Gao Q. Sun W. Chen W. Global analysis of regulatory divergence in the evolution of mouse alternative polyadenylation Mol Syst Biol 12 2016 890 27932516 PMC5199128
  28. [32]Hochreiter S. Schmidhuber J. Long short-term memory Neural Comput 9 1997 1735 1780 9377276
  29. [33]Hu J. Lutz C.S. Wilusz J. Tian B. Bioinformatic identification of candidate cis-regulatory elements involved in human mRNA polyadenylation RNA 11 2005 1485 1493 16131587 PMC1370832
  30. [34]Gao Q. Sun W. Ballegeer M. Libert C. Chen W. Predominant contribution of cis-regulatory divergence in the evolution of mouse alternative splicing Mol Syst Biol 11 2015 816 26134616 PMC4547845
  31. [35]Hou J. Wang X. McShane E. Zauber H. Sun W. Selbach M. Extensive allele-specific translational regulation in hybrid mice Mol Syst Biol 11 2015 825 26253569 PMC4562498
  32. [36]Kingma DP, Ba J. Adam: a method for stochastic optimization. arXiv 2014;1412.6980.
  33. [37]Paszke A. Gross S. Massa F. Lerer A. Bradbury J. Chanan G. PyTorch: an imperative style, high-performance deep learning library Adv Neural Inf Process Syst 2019 8024 8035
  34. [38]Bogard N. Linder J. Rosenberg A.B. Seelig G. A deep neural network for predicting and engineering alternative polyadenylation Cell 178 2019 91 106.e23 31178116 PMC6599575
  35. [39]Zuberi K. Gandhi S. Bretschneider H. Frey B.J. Deshwar A.G. COSSMO: predicting competitive alternative splice site selection using deep learning Bioinformatics 34 2018 i429 i437 29949959 PMC6022534
  36. [40]Pinto P.A.B. Henriques T. Freitas M.O. Martins T. Domingues R.G. Wyrzykowska P.S. RNA polymerase II kinetics in polo polyadenylation signal selection EMBO J 30 2011 2431 2444 21602789 PMC3116286
  37. [41]Gruber A.J. Zavolan M. Alternative cleavage and polyadenylation in health and disease Nat Rev Genet 20 2019 599 614 31267064
  38. [42]Zhang Z. Pan Z. Ying Y. Xie Z. Adhikari S. Phillips J. Deep-learning augmented RNA-seq analysis of transcript splicing Nat Methods 16 2019 307 310 30923373 PMC7605494

Cited by

Sorted by citations

Authors
Li, Z., Li, Y., Zhang, B., Li, Y., Long, Y., Zhou, J., Zou, X., Zhang, M., Hu, Y., Chen, W., & Gao, X.
Affiliations
  • King Abdullah University of Science and Technology (SA)
  • Southern University of Science and Technology (CN)
  • Cancer Science Institute of Singapore (SG)
Corresponding author
  • Hu, Yuhui
  • Chen, Wei
  • Gao, Xin
ORCID
Venue
Genomics, Proteomics & Bioinformatics
Publisher
Oxford University Press (OUP)
Published
2021-03-02
Volume
20
Issue
3
Pages
483-495
ISSN
  • 1672-0229 (ISSN-L)
  • 2210-3244
DOI
10.1016/j.gpb.2020.05.004
PMC
PMC9801043
OpenAlex
W3159968191
Cited by
37
References
3
Citations by year
2025: 11 · 2024: 7 · 2023: 2 · 2022: 11 · 2021: 5 · 2020: 1
FWCI
1.96
Type
journal article
Language
en
Open access
Licence
Locations
  • Genomics Proteomics & Bioinformatics (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology) (submittedVersion, other-oa)
Funders
  • King Abdullah University of Science and Technology (URF/1/4098-01-01, BAS/1/1624-01, FCC/1/1976-18-01, FCC/1/1976-23-01, FCC/1/1976-25-01, FCC/1/1976-26-01, FCS/1/4102-02-01)
  • Science and Technology Innovation Commission of Shenzhen Municipal Government, China (GJHZ20170310161947503)
  • Shenzhen Science and Technology Program, China (KQTD20180411143432337)
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 › Cancer Research › Cancer-related molecular mechanisms research
Keywords
alternative polyadenylation, CNN-LSTM, post-transcriptional regulation
MeSH terms
Deep Learning, Gene Expression Regulation, Neural Networks, Computer, Computational Biology, 3' Untranslated Regions, 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