CoChat
Sign Up
Cited by 215RNA Research and SplicingRNA regulation and diseaseGenomics and Phylogenetic Studies

A Deep Neural Network for Predicting and Engineering Alternative Polyadenylation

Open access
Bogard, Nicholas, Linder, Johannes, Rosenberg, Alexander B., Seelig, Georg·2019·Cell
DOI 10.1016/j.cell.2019.04.046PMC PMC6599575

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

Alternative polyadenylation (APA) is a major driver of transcriptome diversity in human cells. Here, we use deep learning to predict APA from DNA sequence alone. We trained our model (APARENT, APA REgression NeT) on isoform expression data from over 3 million APA reporters. APARENT's predictions are highly accurate when tasked with inferring APA in synthetic and human 3'UTRs. Visualizing features learned across all network layers reveals that APARENT recognizes sequence motifs known to recruit APA regulators, discovers previously unknown sequence determinants of 3' end processing, and integrates these features into a comprehensive, interpretable, cis-regulatory code. We apply APARENT to forward engineer functional polyadenylation signals with precisely defined cleavage position and isoform usage and validate predictions experimentally. Finally, we use APARENT to quantify the impact of genetic variants on APA. Our approach detects pathogenic variants in a wide range of disease contexts, expanding our understanding of the genetic origins of disease.

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.cell.2019.04.046

Cites

10 of 10 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 [21]

    The “APARENT Accurately Predicts Native APA” section (page unavailable) uses annotated APA events and RNA-seq read counts to estimate isoform proportions. But the Abstract and “A Massively Parallel Reporter Assay for APA” section say APARENT itself was trained on sequenced synthetic reporter constructs, not that it relies on genome annotations and transformed RNA-seq measurements to isolate each regulatory mechanism. The paper therefore supports an example of using those data, not the broader claim of reliance. (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: 71

  1. Alipanahi B, Delong A, Weirauch MT, and Frey BJ (2015). Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning. Nat. Biotechnol 33, 831– 838. 26213851
  2. Ausländer S, Ausländer D, Müller M, Wieland M, and Fussenegger M (2012). Programmable single-cell mammalian biocomputers. Nature 487, 123– 127. 22722847
  3. Bennett CL, Brunkow ME, Ramsdell F, O’Briant KC, Zhu Q, Fuleihan RL, Shigeoka AO, Ochs HD, and Chance PF (2001). A rare polyadenylation signal mutation of the FOXP3 gene (AAUAAA-->AAUGAA) leads to the IPEX syndrome. Immunogenetics 53, 435– 439. 11685453
  4. Biswas S, Kuznetsov G, Ogden PJ, Conway NJ, Adams RP, and Church GM (2018). Toward machine-guided design of proteins (bioRxiv).
  5. Chen F, MacDonald CC, and Wilusz J (1995). Cleavage site determinants in the mammalian polyadenylation signal. Nucleic Acids Res. 23, 2614– 2620. 7651822 PMC307082
  6. Cheng Y, Miura RM, and Tian B (2006). Prediction of mRNA polyadenylation sites by support vector machine. Bioinformatics 22, 2320– 2325. 16870936
  7. Cooper GM, Stone EA, Asimenos G, NISC Comparative Sequencing Program, Green ED, Batzoglou S, and Sidow A (2005). Distribution and intensity of constraint in mammalian genomic sequence. Genome Res. 15, 901– 913. 15965027 PMC1172034
  8. Cuperus JT, Groves B, Kuchina A, Rosenberg AB, Jojic N, Fields S, and Seelig G (2017). Deep learning of the regulatory grammar of yeast 5’ untranslated regions from 500,000 random sequences. Genome Res. 27, 2015– 2024. 29097404 PMC5741052
  9. Danckwardt S, Gehring NH, Neu-Yilik G, Hundsdoerfer P, Pforsich M, Frede U, Hentze MW, and Kulozik AE (2004). The prothrombin 3′ end formation signal reveals a unique architecture that is sensitive to thrombophilic gain-of-function mutations. Blood 104, 428– 435. 15059842
  10. Danckwardt S, Hentze MW, and Kulozik AE (2008). 3’ end mRNA processing: molecular mechanisms and implications for health and disease. EMBO J. 27, 482– 498. 18256699 PMC2241648
  11. Derti A, Garrett-Engele P, Macisaac KD, Stevens RC, Sriram S, Chen R, Rohl CA, Johnson JM, and Babak T (2012). A quantitative atlas of polyadenylation in five mammals. Genome Res. 22, 1173– 1183. 22454233 PMC3371698
  12. DeZazzo JD, and Imperiale MJ (1989). Sequences upstream of AAUAAA influence poly(A) site selection in a complex transcription unit. Mol. Cell. Biol 9, 4951– 4961. 2601703 PMC363646
  13. Di Giammartino DC, Nishida K, and Manley JL (2011). Mechanisms and consequences of alternative polyadenylation. Mol. Cell 43, 853– 866. 21925375 PMC3194005
  14. Elkon R, Ugalde AP, and Agami R (2013). Alternative cleavage and polyadenylation: extent, regulation and function. Nat. Rev. Genet 14, 496– 506. 23774734
  15. Findlay GM, Boyle EA, Hause RJ, Klein JC, and Shendure J (2014). Saturation editing of genomic regions by multiplex homology-directed repair. Nature 513, 120– 123. 25141179 PMC4156553
  16. Freyhult E, Gardner PP, and Moulton V (2005). A comparison of RNA folding measures. BMC Bioinformatics 6, 241. 16202126 PMC1274297
  17. Fu Y, Liu Z, Lou S, Bedford J, Mu XJ, Yip KY, Khurana E, and Gerstein M (2014). FunSeq2: a framework for prioritizing noncoding regulatory variants in cancer. Genome Biol. 15, 480. 25273974 PMC4203974
  18. Gazda HT, Sheen MR, Vlachos A, Choesmel V, O’Donohue M-F, Schneider H, Darras N, Hasman C, Sieff CA, Newburger PE, (2008). Ribosomal protein L5 and L11 mutations are associated with cleft palate and abnormal thumbs in Diamond-Blackfan anemia patients. Am. J. Hum. Genet 83, 769– 780. 19061985 PMC2668101
  19. Gehring NH, Frede U, Neu-Yilik G, Hundsdoerfer P, Vetter B, Hentze MW, and Kulozik AE (2001). Increased efficiency of mRNA 3’ end formation: a new genetic mechanism contributing to hereditary thrombophilia. Nat. Genet 28, 389– 392. 11443298
  20. Gruber AJ, Schmidt R, Gruber AR, Martin G, Ghosh S, Belmadani M, Keller W, and Zavolan M (2016). A comprehensive analysis of 3’ end sequencing data sets reveals novel polyadenylation signals and the repressive role of heterogeneous ribonucleoprotein C on cleavage and polyadenylation. Genome Res. 26, 1145– 1159. 27382025 PMC4971764
  21. Gupta S, Stamatoyannopoulos JA, Bailey TL, and Noble WS (2007). Quantifying similarity between motifs. Genome Biol. 8, R24. 17324271 PMC1852410
  22. Higgs DR, Goodbourn SEY, Lamb J, Clegg JB, Weatherall DJ, and Proudfoot NJ (1983). α-Thalassaemia caused by a polyadenylation signal mutation. Nature 306, 398– 400. 6646217
  23. Hu J, Lutz CS, Wilusz J, and Tian B (2005). Bioinformatic identification of candidate cis-regulatory elements involved in human mRNA polyadenylation. RNA 11, 1485– 1493. 16131587 PMC1370832
  24. Huang Y-F, Gulko B, and Siepel A (2017). Fast, scalable prediction of deleterious noncoding variants from functional and population genomic data. Nat. Genet 49, 618– 624. 28288115 PMC5395419
  25. Jaganathan K, Kyriazopoulou Panagiotopoulou S, McRae JF, Darbandi SF, Knowles D, Li YI, Kosmicki JA, Arbelaez J, Cui W, Schwartz GB, (2019). Predicting Splicing from Primary Sequence with Deep Learning. Cell 176, 535– 548.e24. 30661751
  26. Jenkinson EM, Rodero MP, Kasher PR, Uggenti C, Oojageer A, Goosey LC, Rose Y, Kershaw CJ, Urquhart JE, Williams SG, (2016). Mutations in SNORD118 cause the cerebral microangiopathy leukoencephalopathy with calcifications and cysts. Nat. Genet 48, 1185– 1192. 27571260 PMC5045717
  27. Kalia SS, Adelman K, Bale SJ, Chung WK, Eng C, Evans JP, Herman GE, Hufnagel SB, Klein TE, Korf BR, (2017). Recommendations for reporting of secondary findings in clinical exome and genome sequencing, 2016 update (ACMG sF v2.0): a policy statement of the American College of Medical Genetics and Genomics. Genet. Med 19, 249– 255. 27854360
  28. Kaufmann I, Martin G, Friedlein A, Langen H, and Keller W (2004). Human Fip1 is a subunit of CPSF that binds to U-rich RNA elements and stimulates poly(A) polymerase. EMBO J. 23, 616– 626. 14749727 PMC1271804
  29. Kelley DR, Snoek J, and Rinn JL (2016). Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks. Genome Res. 26, 990– 999. 27197224 PMC4937568
  30. Lackford B, Yao C, Charles GM, Weng L, Zheng X, Choi E, Xie X, Wan J, Xing Y, Freudenberg JM, (2014). Fip1 regulates mRNA alternative polyadenylation to promote stem cell self-renewal. EMBO J. 33, 878– 889. 24596251 PMC4194112
  31. Landrum MJ, Lee JM, Riley GR, Jang W, Rubinstein WS, Church DM, and Maglott DR (2014). ClinVar: public archive of relationships among sequence variation and human phenotype. Nucleic Acids Res. 42, D980– D985. 24234437 PMC3965032
  32. Landrum MJ, Lee JM, Benson M, Brown G, Chao C, Chitipiralla S, Gu B, Hart J, Hoffman D, Hoover J, (2016). ClinVar: public archive of interpretations of clinically relevant variants. Nucleic Acids Res. 44, D862– D868. 26582918 PMC4702865
  33. Lappalainen T, Sammeth M, Friedländer MR, ‘t Hoen PAC, Monlong J, Rivas MA, Gonzàlez-Porta M, Kurbatova N, Griebel T, Ferreira PG, (2013). Transcriptome and genome sequencing uncovers functional variation in humans. Nature 501, 506– 511. 24037378 PMC3918453
  34. Leung MKK, Delong A, and Frey BJ (2017). Inference Of The Human Polyadenylation Code. PMC6129302 29648582
  35. Li X-Q, and Du D (2013). RNA polyadenylation sites on the genomes of microorganisms, animals, and plants. pLoS One 8, e79511. 24260238 PMC3832601
  36. Li W, You B, Hoque M, Zheng D, Luo W, Ji Z, Park JY, Gunderson SI, Kalsotra A, Manley JL, (2015). Systematic Profiling of Poly(A) Transcripts Modulated by Core 3’ End Processing and Splicing Factors Reveals Regulatory Rules of Alternative Cleavage and Polyadenylation. PlOS Genetics 11, e1005166. 25906188 PMC4407891
  37. Lianoglou S, Garg V, Yang JL, Leslie CS, and Mayr C (2013). Ubiquitously transcribed genes use alternative polyadenylation to achieve tissue-specific expression. Genes Dev. 27, 2380– 2396. 24145798 PMC3828523
  38. Martin G, Gruber AR, Keller W, and Zavolan M (2012). Genome-wide analysis of pre-mRNA 3’ end processing reveals a decisive role of human cleavage factor I in the regulation of 3’ UTR length. Cell Rep. 1, 753– 763. 22813749
  39. Masamha CP, Xia Z, Yang J, Albrecht TR, Li M, Shyu A-B, Li W, and Wagner EJ (2014). CFIm25 links alternative polyadenylation to glioblastoma tumour suppression. Nature 510, 412– 416. 24814343 PMC4128630
  40. Matreyek KA, Starita LM, Stephany JJ, Martin B, Chiasson MA, Gray VE, Kircher M, Khechaduri A, Dines JN, Hause RJ, (2018). Multiplex assessment of protein variant abundance by massively parallel sequencing. Nat. Genet 50, 874– 882. 29785012 PMC5980760
  41. Medina-Trillo C, Aroca-Aguilar J-D, Méndez-Hernández C-D, Morales L, García-Antón M, García-Feijoo J, and Escribano J (2016). Rare FOXC1 variants in congenital glaucoma: identification of translation regulatory sequences. Eur. J. Hum. Genet 24, 672– 680. 26220699 PMC4930079
  42. Melnikov A, Murugan A, Zhang X, Tesileanu T, Wang L, Rogov P, Feizi S, Gnirke A, Callan CG Jr, Kinney JB, (2012). Systematic dissection and optimization of inducible enhancers in human cells using a massively parallel reporter assay. Nat. Biotechnol 30, 271– 277. 22371084 PMC3297981
  43. Müller S, Rycak L, Afonso-Grunz F, Winter P, Zawada AM, Damrath E, Scheider J, Schmäh J, Koch I, Kahl G, (2014). APADB: a database for alternative polyadenylation and microRNA regulation events. Database 2014. PMC4105710 25052703
  44. Patwardhan RP, Lee C, Litvin O, Young DL, Pe’er D, and Shendure J (2009). High-resolution analysis of DNA regulatory elements by synthetic saturation mutagenesis. Nat. Biotechnol 27, 1173– 1175. 19915551 PMC2849652
  45. Pérez Cañadillas JM, and Varani G (2003). Recognition of GU-rich polyadenylation regulatory elements by human CstF-64 protein. EMBO J. 22, 2821– 2830. 12773396 PMC156756
  46. Pollard KS, Hubisz MJ, Rosenbloom KR, and Siepel A (2010). Detection of nonneutral substitution rates on mammalian phylogenies. Genome Res. 20, 110– 121. 19858363 PMC2798823
  47. Poller W, Merklein F, Schneider-Rasp S, Haack A, Fechner H, Wang H, Anagnostopoulos I, and Weidinger S (1999). Molecular characterisation of the defective α1-antitrypsin alleles PI Mwürzburg (Pro369Ser), Mheerlen (Pro369Leu), and Q0lisbon (Thr68lle). Eur. J. Hum. Genet 7, 321. 10234508
  48. Rabani M, Pieper L, Chew G-L, and Schier AF (2017). A Massively Parallel Reporter Assay of 3’ UtR Sequences Identifies In Vivo Rules for mRNA Degradation. Mol. Cell 68, 1083– 1094.e5. 29225039 PMC5994907
  49. Rosenberg AB, Patwardhan RP, Shendure J, and Seelig G (2015). Learning the sequence determinants of alternative splicing from millions of random sequences. Cell 163, 698– 711. 26496609
  50. Ruder WC, Lu T, and Collins JJ (2011). Synthetic biology moving into the clinic. Science 333, 1248– 1252. 21885773
  51. Schönemann L, Kühn U, Martin G, Schäfer P, Gruber AR, Keller W, Zavolan M, and Wahle E (2014). Reconstitution of CPSF active in polyadenylation: recognition of the polyadenylation signal by WDR33. Genes Dev. 28, 2381– 2393. 25301781 PMC4215183
  52. Sharon E, Kalma Y, Sharp A, Raveh-Sadka T, Levo M, Zeevi D, Keren L, Yakhini Z, Weinberger A, and Segal E (2012). Inferring gene regulatory logic from high-throughput measurements of thousands of systematically designed promoters. Nat. Biotechnol 30, 521– 530. 22609971 PMC3374032
  53. Smith RP, Taher L, Patwardhan RP, Kim MJ, Inoue F, Shendure J, Ovcharenko I, and Ahituv N (2013). Massively parallel decoding of mammalian regulatory sequences supports a flexible organizational model. Nat. Genet 45, 1021– 1028. 23892608 PMC3775494
  54. Stacey SN, Sulem P, Jonasdottir A, Masson G, Gudmundsson J, Gudbjartsson DF, Magnusson OT, Gudjonsson SA, Sigurgeirsson B, Thorisdottir K, (2011). A germline variant in the TP53 polyadenylation signal confers cancer susceptibility. Nat. Genet 43, 1098– 1103. 21946351 PMC3263694
  55. Stapenhorst L, Wielckens K, Wylenzek M, Geisen C, and Klingler K (2001). A Novel Point Mutation in the 3’ Region of the Prothrombin Gene at Position 20221 in a Lebanese/Syrian Family. Thrombosis and Haemostasis 85, 943– 944. 11372696
  56. Stenson PD, Mort M, Ball EV, Evans K, Hayden M, Heywood S, Hussain M, Phillips AD, and Cooper DN (2017). The Human Gene Mutation Database: towards a comprehensive repository of inherited mutation data for medical research, genetic diagnosis and next-generation sequencing studies. Human Genetics 136, 665– 677. 28349240 PMC5429360
  57. Strovas TJ, Rosenberg AB, Kuypers BE, Muscat RA, and Seelig G (2014). MicroRNA-based single-gene circuits buffer protein synthesis rates against perturbations. ACS Synth. Biol. 3, 324– 331. 24847681
  58. Sun Y, Zhang Y, Hamilton K, Manley JL, Shi Y, Walz T, and Tong L (2018). Molecular basis for the recognition of the human AAUAAA polyadenylation signal. Proc. Natl. Acad. Sci. U. S. A. 115, E1419– E1428. 29208711 PMC5816196
  59. Tian B, and Manley JL (2017). Alternative polyadenylation of mRNA precursors. Nat. Rev. Mol. Cell Biol. 18, 18– 30. 27677860 PMC5483950
  60. Wang R, Zheng D, Yehia G, and Tian B (2018). A compendium of conserved cleavage and polyadenylation events in mammalian genes. Genome Res. 28, 1427– 1441. 30143597 PMC6169888
  61. White MA, Myers CA, Corbo JC, and Cohen BA (2013). Massively parallel in vivo enhancer assay reveals that highly local features determine the cis-regulatory function of ChIP-seq peaks. Proc. Natl. Acad. Sci. U. S. A. 110, 11952– 11957. 23818646 PMC3718143
  62. Wiestner A, Tehrani M, Chiorazzi M, Wright G, Gibellini F, Nakayama K, Liu H, Rosenwald A, Muller-Hermelink HK, Ott G, (2007). Point mutations and genomic deletions in CCND1 create stable truncated cyclin D1 mRNAs that are associated with increased proliferation rate and shorter survival. Blood 109, 4599– 4606. 17299095 PMC1885523
  63. Wroblewska L, Kitada T, Endo K, Siciliano V, Stillo B, Saito H, and Weiss R (2015). Mammalian synthetic circuits with RNA binding proteins for RNA-only delivery. Nat. Biotechnol. 33, 839– 841. 26237515 PMC4532950
  64. Wu X, and Bartel DP (2017). Widespread Influence of 3’-End Structures on Mammalian mRNA Processing and Stability. Cell 169, 905– 917.e11. 28525757 PMC5546744
  65. Xie Z, Wroblewska L, Prochazka L, Weiss R, and Benenson Y (2011). Multi-input RNAi-based logic circuit for identification of specific cancer cells. Science 333, 1307– 1311. 21885784
  66. Xiong HY, Alipanahi B, Lee LJ, Bretschneider H, Merico D, Yuen RKC, Hua Y, Gueroussov S, Najafabadi HS, Hughes TR, (2015). RNA splicing. The human splicing code reveals new insights into the genetic determinants of disease. Science 347, 1254806. 25525159 PMC4362528
  67. Yang Q, Gilmartin GM, and Doublié S (2010). Structural basis of UGUA recognition by the Nudix protein CFI(m)25 and implications for a regulatory role in mRNA 3’ processing. Proc. Natl. Acad. Sci. U. S. A. 107, 10062– 10067. 20479262 PMC2890493
  68. Yang Q, Coseno M, Gilmartin GM, and Doublie S (2011). Crystal structure of a human cleavage factor CFI(m)25/CFI(m)68/RNA complex provides an insight into poly(A) site recognition and RNA looping. Structure 19, 368– 377. 21295486 PMC3056899
  69. Zhao W, Pollack JL, Blagev DP, Zaitlen N, McManus MT, and Erle DJ (2014). Massively parallel functional annotation of 3’ untranslated regions. Nature Biotechnology 32, 387– 391. PMC3981918 24633241
  70. Zhou J, and Troyanskaya OG (2015). Predicting effects of noncoding variants with deep learning-based sequence model. Nat. Methods 12, 931– 934. 26301843 PMC4768299
  71. Zhu Y, Wang X, Forouzmand E, Jeong J, Qiao F, Sowd GA, Engelman AN, Xie X, Hertel KJ, and Shi Y (2018). Molecular Mechanisms for CFIm-Mediated Regulation of mRNA Alternative Polyadenylation. Mol. Cell 69, 62– 74.e4. 29276085 PMC5756121

Cited by

Sorted by citations

Authors
Bogard, N., Linder, J., Rosenberg, A. B., & Seelig, G.
Affiliations
University of Washington (US)
Corresponding author
Seelig, Georg
ORCID
Venue
Cell
Publisher
Elsevier BV
Published
2019-06
Volume
178
Issue
1
Pages
91-106.e23
ISSN
0092-8674 (ISSN-L)
DOI
10.1016/j.cell.2019.04.046
PMC
PMC6599575
OpenAlex
W2948558658
Cited by
215
References
10
Citations by year
2026: 16 · 2025: 36 · 2024: 42 · 2023: 28 · 2022: 35 · 2021: 32 · 2020: 17 · 2019: 8 · 2018: 1
FWCI
7.61
Type
journal article
Language
en
Open access
Licence
Locations
  • Cell (publishedVersion)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • PubMed Central (acceptedVersion)
Funders
National Institutes of Health
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › RNA Research and Splicing
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › RNA regulation and disease
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Phylogenetic Studies
Keywords
alternative polyadenylation, deep neural network, 3' untranslated region, isoform expression, sequence motifs, genetic variants, pathogenic variants, transcriptome diversity
MeSH terms
Deep Learning, RNA-Seq, Base Sequence, Humans, Models, Genetic, RNA, Messenger, Gene Expression, Mutagenesis, 3' Untranslated Regions, Polyadenylation, Databases, Genetic, HEK293 Cells, Synthetic Biology, RNA Cleavage, Transcriptome

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