CoChat
Sign Up
Cited by 559Genetic Associations and EpidemiologyGenomics and Chromatin DynamicsGenomics and Rare Diseases

Deep learning sequence-based ab initio prediction of variant effects on expression and disease risk

Open access
Zhou, Jian, Theesfeld, Chandra L., Yao, Kevin, Chen, Kathleen M., Wong, Aaron K., Troyanskaya, Olga G.·2018·Nature Genetics
DOI 10.1038/s41588-018-0160-6PMC PMC6094955
Open this paper in CoChat — free account

Abstract

Key challenges for human genetics, precision medicine and evolutionary biology include deciphering the regulatory code of gene expression and understanding the transcriptional effects of genome variation. However, this is extremely difficult because of the enormous scale of the noncoding mutation space. We developed a deep learning-based framework, ExPecto, that can accurately predict, ab initio from a DNA sequence, the tissue-specific transcriptional effects of mutations, including those that are rare or that have not been observed. We prioritized causal variants within disease- or trait-associated loci from all publicly available genome-wide association studies and experimentally validated predictions for four immune-related diseases. By exploiting the scalability of ExPecto, we characterized the regulatory mutation space for human RNA polymerase II-transcribed genes by in silico saturation mutagenesis and profiled > 140 million promoter-proximal mutations. This enables probing of evolutionary constraints on gene expression and ab initio prediction of mutation disease effects, making ExPecto an end-to-end computational framework for the in silico prediction of expression and disease risk.

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 · 10.1038/s41588-018-0160-6

Cites

8 of 8 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?

  • Previous models have only attempted to work with RNA-seq after summarizing gene expression in a single statistic.

    “Previous models have only attempted to work with RNA-seq after summarizing gene expression in a single statistic.”

    From Predicting RNA-seq coverage from DNA sequence as a unifying model of gene regulation (2025) · cites this paper as [12]

    The Online Methods section on representative transcription start sites says most expression-profiling datasets were quantified at the gene level, including RNA-seq datasets. That supports the idea of summarizing expression, but it does not establish that all previous models worked with RNA-seq only after reducing expression to a single statistic. No page number is available in our copy. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

  • Deep convolutional neural networks (CNNs) achieve the current state of the art at predicting gene expression from DNA sequences for the human and mouse genomes.

    “Deep convolutional neural networks (CNNs) achieve the current state of the art at predicting gene expression from DNA sequences for the human and mouse genomes1–4.”

    From Effective gene expression prediction from sequence by integrating long-range interactions (2021) · cites this paper as [1]

    The Results section reports accurate gene-expression predictions from DNA sequence across 218 human tissues and cell types, and the Online Methods describe a convolutional neural network as part of the ExPecto framework. The paper does not establish that this approach is the current state of the art, and the passages address human rather than mouse expression prediction. Its final expression-prediction stage uses regularized linear models, not a CNN alone. (LLM, conf=0.86)

    Experimental — accuracy not yet measured

  • By processing a large region centered on the transcription start site, several models can predict normalized gene counts.

    “By processing a large region centered on the transcription start site (TSS), several models can predict normalized gene counts11–13.”

    From Predicting RNA-seq coverage from DNA sequence as a unifying model of gene regulation (2025) · cites this paper as [12]

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: 45

  1. [1]Pickrell JK Understanding mechanisms underlying human gene expression variation with RNA sequencing Nature 464 768 772 2010 20220758 PMC3089435
  2. [2]GTEx Consortium, T. Gte The Genotype-Tissue Expression (GTEx) project Nat Genet 45 580 5 2013 23715323 PMC4010069
  3. [3]Gamazon ER A gene-based association method for mapping traits using reference transcriptome data Nat Genet 47 1091 1098 2015 26258848 PMC4552594
  4. [4]Li X The impact of rare variation on gene expression across tissues bioRxiv 2016 10.1101/074443 PMC5877409 29022581 · DOI
  5. [5]Edwards SL Beesley J French JD Dunning M Beyond GWASs: Illuminating the dark road from association to function American Journal of Human Genetics 93 779 797 2013 24210251 PMC3824120
  6. [6]Segal E Raveh-Sadka T Schroeder M Unnerstall U Gaul U Predicting expression patterns from regulatory sequence in Drosophila segmentation Nature 451 535 540 2008 18172436
  7. [7]Beer MA Tavazoie S Predicting gene expression from sequence. TL - 117 Cell 117VN 185 198 2004 15084257
  8. [8]Yuan Y Guo L Shen L Liu JS Predicting gene expression from sequence: A reexamination PLoS Comput Biol 3 2391 2397 2007 PMC2098866 18052544
  9. [9]Bussemaker HJ Li H Siggia ED Regulatory element detection using correlation with expression Nat Genet 27 167 71 2001 11175784
  10. [10]Kreimer A Predicting gene expression in massively parallel reporter assays: A comparative study Human Mutation 2017 10.1002/humu.23197 PMC5560998 28220625 · DOI
  11. [11]Zhou J Troyanskaya OG Predicting effects of noncoding variants with deep learning-based sequence model Nat Methods 12 931 4 2015 26301843 PMC4768299
  12. [12]Aguet F Local genetic effects on gene expression across 44 human tissues bioRxiv 2016 10.1101/074450 · DOI
  13. [13]Aguet F Genetic effects on gene expression across human tissues Nature 550 204 213 2017 29022597 PMC5776756
  14. [14]Westra H-J Systematic identification of trans eQTLs as putative drivers of known disease associations Nat Genet 45 1238 43 2013 24013639 PMC3991562
  15. [16]Fairfax BP Genetics of gene expression in primary immune cells identifies cell type-specific master regulators and roles of HLA alleles Nat Genet 44 502 10 2012 22446964 PMC3437404
  16. [18]MacArthur J The new NHGRI-EBI Catalog of published genome-wide association studies (GWAS Catalog) Nucleic Acids Res 45 D896 D901 2017 27899670 PMC5210590
  17. [19]Germain M Genetics of Venous thrombosis: Insights from a new genome wide association study PLoS One 6 2011 PMC3181335 21980494
  18. [20]Tang W A Genome-Wide Association Study for Venous Thromboembolism: The Extended Cohorts for Heart and Aging Research in Genomic Epidemiology (CHARGE) Consortium Genet Epidemiol 37 512 521 2013 23650146 PMC3990406
  19. [21]Plagnol V Genome-wide association analysis of autoantibody positivity in type 1 diabetes cases PLoS Genet 7 2011 PMC3150451 21829393
  20. [22]Chu X A genome-wide association study identifies two new risk loci for Graves’ disease Nat Genet 43 897 901 2011 21841780
  21. [24]Graham RR Genetic variants near TNFAIP3 on 6q23 are associated with systemic lupus erythematosus Nat Genet 40 1059 61 2008 19165918 PMC2772171
  22. [25]Bentham J Genetic association analyses implicate aberrant regulation of innate and adaptive immunity genes in the pathogenesis of systemic lupus erythematosus Nat Genet 47 1457 1464 2015 26502338 PMC4668589
  23. [26]Lee Y-C Two new susceptibility loci for Kawasaki disease identified through genome-wide association analysis Nat Genet 44 522 5 2012 22446961
  24. [27]Xi H Analysis of overrepresented motifs in human core promoters reveals dual regulatory roles of YY1 Genome Res 17 798 806 2007 17567998 PMC1891339
  25. [29]Nagaizumi K Two double heterozygous mutations in the F7 gene show different manifestations Br J Haematol 119 1052 1058 2002 12472587
  26. [30]Feldmann J Munc13-4 Is Essential for Cytolytic Granules Fusion and Is Mutated in a Form of Familial Hemophagocytic Lymphohistiocytosis (FHL3) Cell 115 461 473 2003 14622600
  27. [31]Ng Y-S Wardemann H Chelnis J Cunningham-Rundles C Meffre E Bruton’s tyrosine kinase is essential for human B cell tolerance J Exp Med 200 927 34 2004 15466623 PMC2213290
  28. [32]Yamagata K Mutations in the hepatocyte nuclear factor-4alpha gene in maturity-onset diabetes of the young (MODY1) Nature 384 458 460 1996 8945471
  29. [33]Servitja J-M Hnf1alpha (MODY3) controls tissue-specific transcriptional programs and exerts opposed effects on cell growth in pancreatic islets and liver Mol Cell Biol 29 2945 59 2009 19289501 PMC2682018
  30. [34]Huang FW Highly recurrent TERT promoter mutations in human melanoma Science 339 957 9 2013 23348506 PMC4423787
  31. [35]Vinagre J Frequency of TERT promoter mutations in human cancers Nat Commun 4 2013 23887589
  32. [36]Pasaniuc B Price AL Dissecting the genetics of complex traits using summary association statistics Nature Reviews Genetics 18 117 127 2017 PMC5449190 27840428
  33. [37]Parkes M Sequence variants in the autophagy gene IRGM and multiple other replicating loci contribute to Crohn’s disease susceptibility Nat Genet 39 830 2 2007 17554261 PMC2628541
  34. [38]Wellcome T Case T Consortium, C. Genome-wide association study of 14,000 cases of seven common diseases and 3,000 shared controls Nature 447 661 78 2007 17554300 PMC2719288
  35. [39]Barrett JC Genome-wide association defines more than 30 distinct susceptibility loci for Crohn’s disease Nat Genet 40 955 962 2008 18587394 PMC2574810
  36. [40]Franke A Genome-wide meta-analysis increases to 71 the number of confirmed Crohn’s disease susceptibility loci Nat Genet 42 1118 25 2010 21102463 PMC3299551
  37. [41]Jostins L Host-microbe interactions have shaped the genetic architecture of inflammatory bowel disease Nature 491 119 24 2012 23128233 PMC3491803
  38. [42]Liu JZ Association analyses identify 38 susceptibility loci for inflammatory bowel disease and highlight shared genetic risk across populations Nat Genet 47 979 989 2015 26192919 PMC4881818
  39. [43]Kirino Y Genome-wide association analysis identifies new susceptibility loci for Behçet’s disease and epistasis between HLA-B*51 and ERAP1 Nat Genet 45 202 7 2013 23291587 PMC3810947
  40. [44]Jiang DK Genetic Variants in Five Novel Loci Including CFB and CD40 Predispose to Chronic Hepatitis B Hepatology 62 118 128 2015 25802187
  41. [45]de Souza N The ENCODE project Nat Methods 9 1046 1046 2012 23281567
  42. [46]Bernstein BE The NIH Roadmap Epigenomics Mapping Consortium Nat Biotechnol 28 1045 8 2010 20944595 PMC3607281
  43. [51]Kircher M A general framework for estimating the relative pathogenicity of human genetic variants Nat Genet 46 310 315 2014 24487276 PMC3992975
  44. [53]Uhlen M Tissue-based map of the human proteome Science (80-) 347 1260419 1260419 2015 25613900
  45. [54]Forrest ARR A promoter-level mammalian expression atlas Nature 507 462 470 2014 24670764 PMC4529748

Cited by

Sorted by citations

Authors
Zhou, J., Theesfeld, C. L., Yao, K., Chen, K. M., Wong, A. K., & Troyanskaya, O. G.
Affiliations
  • Princeton University (US)
  • Simons Foundation (US)
Corresponding author
Troyanskaya, Olga G.
ORCID
Venue
Nature Genetics
Publisher
Springer Science and Business Media LLC
Published
2018-07-16
Volume
50
Issue
8
Pages
1171-1179
ISSN
  • 1061-4036 (ISSN-L)
  • 1546-1718
DOI
10.1038/s41588-018-0160-6
PMC
PMC6094955
OpenAlex
W2883945062
Cited by
559
References
8
Citations by year
2026: 59 · 2025: 67 · 2024: 94 · 2023: 74 · 2022: 81 · 2021: 74 · 2020: 63 · 2019: 34 · 2018: 12 · 2013: 1
FWCI
28.00
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Genetics (publishedVersion)
  • PubMed (publishedVersion)
  • Europe PMC (PubMed Central) (acceptedVersion)
  • PubMed Central (acceptedVersion)
Funders
  • Princeton University
  • Canadian Institute for Advanced Research
  • National Heart, Lung, and Blood Institute (U54HL117798)
  • National Human Genome Research Institute (R01HG005998)
  • National Institute of General Medical Sciences (R01GM071966)
  • National Institute of Allergy and Infectious Diseases (HHSN272201000054C, U19AI117873)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Genetic Associations and Epidemiology
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Chromatin Dynamics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Genomics and Rare Diseases
Keywords
ab initio prediction, non-coding mutations, tissue-specific gene expression, disease risk prediction, causal variant prioritization, immune-related diseases
MeSH terms
Deep Learning, Algorithms, Computer Simulation, Humans, Models, Genetic, Mutation, Promoter Regions, Genetic, Gene Expression, Genetic Predisposition to Disease, Polymorphism, Single Nucleotide, Quantitative Trait Loci, Genome-Wide Association Study

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