Home LiteratureArticle Details
PMID: 26213851 Published · ppublish English Journal Article Research Support, Non-U.S. Gov't

Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning.

Nature biotechnology ·Vol. 33 ·No. 8 ·2015-08-00 ·Pages 831-8

Alipanahi B, Delong A, Weirauch MT, Frey BJ

Abstract

Knowing the sequence specificities of DNA- and RNA-binding proteins is essential for developing models of the regulatory processes in biological systems and for identifying causal disease variants. Here we show that sequence specificities can be ascertained from experimental data with 'deep learning' techniques, which offer a scalable, flexible and unified computational approach for pattern discovery. Using a diverse array of experimental data and evaluation metrics, we find that deep learning outperforms other state-of-the-art methods, even when training on in vitro data and testing on in vivo data. We call this approach DeepBind and have built a stand-alone software tool that is fully automatic and handles millions of sequences per experiment. Specificities determined by DeepBind are readily visualized as a weighted ensemble of position weight matrices or as a 'mutation map' that indicates how variations affect binding within a specific sequence.

MeSH Terms
Computational Biology/methods DNA-Binding Proteins/chemistry Position-Specific Scoring Matrices RNA-Binding Proteins/chemistry Sequence Analysis, Protein/methods Software
Chemicals
DNA-Binding Proteins RNA-Binding Proteins
Authors & Affiliations
4 authors, click to expand affiliations / ORCID
Alipanahi Babak
1] Department of Electrical and Computer Engineering, University of Toronto, Toronto, Ontario, Canada. [2] Donnelly Centre for Cellular and Biomolecular Research, University of Toronto, Toronto, Ontario, Canada.
Delong Andrew
Department of Electrical and Computer Engineering, University of Toronto, Toronto, Ontario, Canada.
Weirauch Matthew T
1] Canadian Institute for Advanced Research, Programs on Genetic Networks and Neural Computation, Toronto, Ontario, Canada. [2] Center for Autoimmune Genomics and Etiology, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, USA. [3] Divisions of Biomedical Informatics and Developmental Biology, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, USA.
Frey Brendan J
1] Department of Electrical and Computer Engineering, University of Toronto, Toronto, Ontario, Canada. [2] Donnelly Centre for Cellular and Biomolecular Research, University of Toronto, Toronto, Ontario, Canada. [3] Canadian Institute for Advanced Research, Programs on Genetic Networks and Neural Computation, Toronto, Ontario, Canada.
References (45)
45 references, click to expand
  1. Design and analysis of ChIP-seq experiments for DNA-binding proteins.
    Nat Biotechnol. 2008 Dec;26(12):1351-9 PMID: 19029915
  2. DNA binding sites: representation and discovery.
    Bioinformatics. 2000 Jan;16(1):16-23 PMID: 10812473
  3. Evolutionarily dynamic alternative splicing of GPR56 regulates regional cerebral cortical patterning.
    Science. 2014 Feb 14;343(6172):764-8 PMID: 24531968
  4. Compact, universal DNA microarrays to comprehensively determine transcription-factor binding site specificities.
    Nat Biotechnol. 2006 Nov;24(11):1429-35 PMID: 16998473
  5. RankMotif++: a motif-search algorithm that accounts for relative ranks of K-mers in binding transcription factors.
    Bioinformatics. 2007 Jul 1;23(13):i72-9 PMID: 17646348
  6. RBFOX1 regulates both splicing and transcriptional networks in human neuronal development.
    Hum Mol Genet. 2012 Oct 1;21(19):4171-86 PMID: 22730494
  7. Multiplexed massively parallel SELEX for characterization of human transcription factor binding specificities.
    Genome Res. 2010 Jun;20(6):861-73 PMID: 20378718
  8. Evaluation of methods for modeling transcription factor sequence specificity.
    Nat Biotechnol. 2013 Feb;31(2):126-34 PMID: 23354101
  9. Direct measurement of DNA affinity landscapes on a high-throughput sequencing instrument.
    Nat Biotechnol. 2011 Jun 26;29(7):659-64 PMID: 21706015
  10. Origins of specificity in protein-DNA recognition.
    Annu Rev Biochem. 2010;79:233-69 PMID: 20334529
  11. Transcriptional regulation and its misregulation in disease.
    Cell. 2013 Mar 14;152(6):1237-51 PMID: 23498934
  12. The Human Gene Mutation Database: building a comprehensive mutation repository for clinical and molecular genetics, diagnostic testing and personalized genomic medicine.
    Hum Genet. 2014 Jan;133(1):1-9 PMID: 24077912
  13. Cancer. The transcription factor GABP selectively binds and activates the mutant TERT promoter in cancer.
    Science. 2015 May 29;348(6238):1036-9 PMID: 25977370
  14. MEME-ChIP: motif analysis of large DNA datasets.
    Bioinformatics. 2011 Jun 15;27(12):1696-7 PMID: 21486936
  15. Statistical mechanical modeling of genome-wide transcription factor occupancy data by MatrixREDUCE.
    Bioinformatics. 2006 Jul 15;22(14):e141-9 PMID: 16873464
  16. Rapid analysis of the DNA-binding specificities of transcription factors with DNA microarrays.
    Nat Genet. 2004 Dec;36(12):1331-9 PMID: 15543148
  17. TRANSFAC and its module TRANSCompel: transcriptional gene regulation in eukaryotes.
    Nucleic Acids Res. 2006 Jan 1;34(Database issue):D108-10 PMID: 16381825
  18. A compendium of RNA-binding motifs for decoding gene regulation.
    Nature. 2013 Jul 11;499(7457):172-7 PMID: 23846655
  19. COSMIC: mining complete cancer genomes in the Catalogue of Somatic Mutations in Cancer.
    Nucleic Acids Res. 2011 Jan;39(Database issue):D945-50 PMID: 20952405
  20. RNAcontext: a new method for learning the sequence and structure binding preferences of RNA-binding proteins.
    PLoS Comput Biol. 2010 Jul 01;6:e1000832 PMID: 20617199
  21. ChIP-seq guidelines and practices of the ENCODE and modENCODE consortia.
    Genome Res. 2012 Sep;22(9):1813-31 PMID: 22955991
  22. The 8q24 cancer risk variant rs6983267 shows long-range interaction with MYC in colorectal cancer.
    Nat Genet. 2009 Aug;41(8):882-4 PMID: 19561607
  23. Diversity and complexity in DNA recognition by transcription factors.
    Science. 2009 Jun 26;324(5935):1720-3 PMID: 19443739
  24. JASPAR 2014: an extensively expanded and updated open-access database of transcription factor binding profiles.
    Nucleic Acids Res. 2014 Jan;42(Database issue):D142-7 PMID: 24194598
  25. DNA-binding specificities of human transcription factors.
    Cell. 2013 Jan 17;152(1-2):327-39 PMID: 23332764
  26. Application of experimentally verified transcription factor binding sites models for computational analysis of ChIP-Seq data.
    BMC Genomics. 2014 Jan 29;15:80 PMID: 24472686
  27. Protein-DNA binding: complexities and multi-protein codes.
    Nucleic Acids Res. 2014 Feb;42(4):2099-111 PMID: 24243859
  28. Shape-specific recognition in the structure of the Vts1p SAM domain with RNA.
    Nat Struct Mol Biol. 2006 Feb;13(2):160-7 PMID: 16429156
  29. The role of RNA sequence and structure in RNA--protein interactions.
    J Mol Biol. 2011 Jun 17;409(4):574-87 PMID: 21514302
  30. Genome-wide analysis of PTB-RNA interactions reveals a strategy used by the general splicing repressor to modulate exon inclusion or skipping.
    Mol Cell. 2009 Dec 25;36(6):996-1006 PMID: 20064465
  31. TERT promoter mutations in familial and sporadic melanoma.
    Science. 2013 Feb 22;339(6122):959-61 PMID: 23348503
  32. Highly expressed loci are vulnerable to misleading ChIP localization of multiple unrelated proteins.
    Proc Natl Acad Sci U S A. 2013 Nov 12;110(46):18602-7 PMID: 24173036
  33. Highly recurrent TERT promoter mutations in human melanoma.
    Science. 2013 Feb 22;339(6122):957-9 PMID: 23348506
  34. A general framework for estimating the relative pathogenicity of human genetic variants.
    Nat Genet. 2014 Mar;46(3):310-5 PMID: 24487276
  35. RRM-RNA recognition: NMR or crystallography…and new findings.
    Curr Opin Struct Biol. 2013 Feb;23 (1):100-8 PMID: 23253355
  36. Rapid and systematic analysis of the RNA recognition specificities of RNA-binding proteins.
    Nat Biotechnol. 2009 Jul;27(7):667-70 PMID: 19561594
  37. Quantitative analysis demonstrates most transcription factors require only simple models of specificity.
    Nat Biotechnol. 2011 Jun 07;29(6):480-3 PMID: 21654662
  38. GATA-4 regulates Bcl-2 expression in ovarian granulosa cell tumors.
    Endocrinology. 2008 Nov;149(11):5635-42 PMID: 18653721
  39. Deep surveying of alternative splicing complexity in the human transcriptome by high-throughput sequencing.
    Nat Genet. 2008 Dec;40(12):1413-5 PMID: 18978789
  40. MBNL proteins repress ES-cell-specific alternative splicing and reprogramming.
    Nature. 2013 Jun 13;498(7453):241-5 PMID: 23739326
  41. An RNA map predicting Nova-dependent splicing regulation.
    Nature. 2006 Nov 30;444(7119):580-6 PMID: 17065982
  42. Sequence features and chromatin structure around the genomic regions bound by 119 human transcription factors.
    Genome Res. 2012 Sep;22(9):1798-812 PMID: 22955990
  43. A regulatory SNP causes a human genetic disease by creating a new transcriptional promoter.
    Science. 2006 May 26;312(5777):1215-7 PMID: 16728641
  44. The RNA-binding protein TIA-1 is a novel mammalian splicing regulator acting through intron sequences adjacent to a 5' splice site.
    Mol Cell Biol. 2000 Sep;20(17):6287-99 PMID: 10938105
  45. Functional analysis of LDLR promoter and 5' UTR mutations in subjects with clinical diagnosis of familial hypercholesterolemia.
    Hum Mutat. 2011 Aug;32(8):868-72 PMID: 21538688
Article Info
Journal
Nature biotechnology
Abbr.
Nat Biotechnol
ISSN
1546-1696
Published
2015-08-00
Epub
2015-00-27
Pages
831-8
Language
English
Region
United States
NLM ID
9604648
Subset
IM
Grants
Canadian Institutes of Health Research · OGP-106690 · Canada
Corrections
CommentIn
Analysis Services
Analysis Services

Contact

No. 2 Wenbo Road, Zhangqiu District, Jinan, Shandong

Qilu Normal University · Genelibs Bioinformatics Lab

750 Shunhua Rd, Jinan

2F, Bldg F, University Science Park

Tel: 0531-88819269

WeChat Official Account

Follow our WeChat subscription account for real-time updates and the latest in medical and biological research.


Business Email

E-mail: [email protected]