CoChat
Sign Up
Cited by 228Genomics and Chromatin DynamicsGenetic Associations and EpidemiologyGene Regulatory Network Analysis

Cross-species regulatory sequence activity prediction

Open access
Kelley, David R.·2020·PLOS Computational Biology
DOI 10.1371/journal.pcbi.1008050PMC PMC7392335

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

Abstract Machine learning algorithms trained to predict the regulatory activity of nucleic acid sequences have revealed principles of gene regulation and guided genetic variation analysis. While the human genome has been extensively annotated and studied, model organisms have been less explored. Model organism genomes offer both additional training sequences and unique annotations describing tissue and cell states unavailable in humans. Here, we develop a strategy to train deep convolutional neural networks simultaneously on multiple genomes and apply it to learn sequence predictors for large compendia of human and mouse data. Training on both genomes improves gene expression prediction accuracy on held out sequences. We further demonstrate a novel and powerful transfer learning approach to use mouse regulatory models to analyze human genetic variants associated with molecular phenotypes and disease. Together these techniques unleash thousands of non-human epigenetic and transcriptional profiles toward more effective investigation of how gene regulation affects human 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 · 10.1371/journal.pcbi.1008050

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?

  • Thus far, sequence-based models have focused on assays in which measured activity is proportional to local sequencing read counts.

    “Thus far, such models have focused on assays in which measured activity is proportional to local sequencing read counts.”

    From Predicting RNA-seq coverage from DNA sequence as a unifying model of gene regulation (2025) · cites this paper as [9]

    The Materials and methods section (Functional genomics data; page not specified) says the models focused on sequencing assays and describes deriving local signal from aligned reads. But it also says the models used log-fold-change signal tracks for many datasets; those targets are not simply proportional to local read counts. (LLM, conf=0.85)

    Experimental — accuracy not yet measured

  • Machine-learning models trained to predict function from DNA sequences have been successful at characterizing regulatory syntax and interpreting genetic variant effects.

    “Machine-learning models trained to predict function from DNA sequences have been successful at characterizing regulatory syntax and interpreting genetic variant effects.”

    From Predicting RNA-seq coverage from DNA sequence as a unifying model of gene regulation (2025) · cites this paper as [9]

  • Models trained on data from multiple species have been shown to improve performance.

    “Models trained on data from multiple species have been shown to improve performance9, but chromatin profiling and the CAGE gene expression assays have been performed on far fewer species than RNA-seq.”

    From Predicting RNA-seq coverage from DNA sequence as a unifying model of gene regulation (2025) · cites this paper as [9]

  • Including experimental assays studied by Enformer and Basenji in training data helps the model use important sequence features for making RNA coverage predictions.

    “To help the model use important sequence features for making its RNA coverage predictions, we also included the experimental assays studied by the Enformer and Basenji models in the training data8,9,13.”

    From Predicting RNA-seq coverage from DNA sequence as a unifying model of gene regulation (2025) · cites this paper as [9]

  • 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 [2]

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: 51

  1. [1]Ghandi M, Lee D, Mohammad-Noori M, Beer MA. Enhanced regulatory sequence prediction using gapped k-mer features. PLoS Comput Biol. 2014; 10(7): e1003711 10.1371/journal.pcbi.1003711 25033408 PMC4102394 · DOI
  2. [2]Alipanahi B, Delong A, Weirauch MT, Frey BJ. Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning. Nature Biotechnology. 2015; 33: 831– 838. 10.1038/nbt.3300 26213851 · DOI · Paper page
  3. [3]Lee D, Gorkin DU, Baker M, Strober BJ, Asoni AL, McCallion AS, et al A method to predict the impact of regulatory variants from DNA sequence. Nature Genetics. 2015; 47: 955– 961. 10.1038/ng.3331 26075791 PMC4520745 · DOI
  4. [4]Kelley DR, Snoek J, Rinn JL. Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks. Genome research. 2016; 26(7): 990– 999. 10.1101/gr.200535.115 27197224 PMC4937568 · DOI · Paper page
  5. [5]Kelley DR, Reshef YA, Bileschi M, Belanger D, McLean CY, Snoek J. Sequential regulatory activity prediction across chromosomes with convolutional neural networks. Genome Research. 2018; 28(5): 739– 750. 10.1101/gr.227819.117 29588361 PMC5932613 · DOI · Paper page
  6. [6]Zhou J, Troyanskaya OG. Predicting effects of noncoding variants with deep learning–based sequence model. Nature methods. 2015; 12(10): 931 10.1038/nmeth.3547 26301843 PMC4768299 · DOI · Paper page
  7. [7]Zhou J, Theesfeld CL, Yao K, Chen KM, Wong AK, Troyanskaya OG. Deep learning sequence-based ab initio prediction of variant effects on expression and disease risk. Nature Genetics. 2018; 464: 1. PMC6094955 30013180
  8. [8]Reshef YA, Finucane HK, Kelley DR, Gusev A, Kotliar D, Ulirsch JC, et al Detecting genome-wide directional effects of transcription factor binding on polygenic disease risk. Nature genetics. 2018; 50(10): 1483 10.1038/s41588-018-0196-7 30177862 PMC6202062 · DOI · Paper page
  9. [9]Agarwal V, Shendure J. Predicting mRNA abundance directly from genomic sequence using deep convolutional neural networks. Cell Reports. 2020; 31(7): 107663 10.1016/j.celrep.2020.107663 32433972 · DOI · Paper page
  10. [10]Melnikov A, Murugan A, Zhang X, Tesileanu T, Wang L, Rogov P, et al Systematic dissection and optimization of inducible enhancers in human cells using a massively parallel reporter assay. Nature Biotechnology. 2012; 30(3): 271– 277. 10.1038/nbt.2137 22371084 PMC3297981 · DOI · Paper page
  11. [11]Sharon E, Kalma Y, Sharp A, Raveh-Sadka T, Levo M, Zeevi D, et al Inferring gene regulatory logic from high-throughput measurements of thousands of systematically designed promoters. Nature biotechnology. 2012; 30(6): 521 10.1038/nbt.2205 22609971 PMC3374032 · DOI · Paper page
  12. [12]Patwardhan RP, Hiatt JB, Witten DM, Kim MJ, Smith RP, May D, et al Massively parallel functional dissection of mammalian enhancers in vivo. Nature biotechnology. 2012; 30(3): 265 10.1038/nbt.2136 22371081 PMC3402344 · DOI · Paper page
  13. [13]Kwasnieski JC, Mogno I, Myers CA, Corbo JC, Cohen BA. Complex effects of nucleotide variants in a mammalian cis-regulatory element. Proceedings of the National Academy of Sciences. 2012; 109(47): 19498– 19503. 10.1073/pnas.1210678109 PMC3511131 23129659 · DOI
  14. [14]Rosenberg AB, Patwardhan RP, Shendure J, Seelig G. Learning the Sequence Determinants of Alternative Splicing from Millions of Random Sequences. Cell. 2015; 163(3): 698– 711. 10.1016/j.cell.2015.09.054 26496609 · DOI
  15. [15]Wilson MD, Barbosa-Morais NL, Schmidt D, Conboy CM, Vanes L, Tybulewicz VLJ, et al Species-Specific Transcription in Mice Carrying Human Chromosome 21. Science. 2008; 322(5900): 434– 438. 10.1126/science.1160930 18787134 PMC3717767 · DOI
  16. [16]Villar D, Flicek P, Odom DT. Evolution of transcription factor binding in metazoans—mechanisms and functional implications. Nature Reviews Genetics. 2014; 15(4): 221– 233. 10.1038/nrg3481 24590227 PMC4175440 · DOI
  17. [18]Chen L, Fish AE, Capra JA. Prediction of gene regulatory enhancers across species reveals evolutionarily conserved sequence properties. PLoS computational biology. 2018; 14(10): e1006484 10.1371/journal.pcbi.1006484 30286077 PMC6191148 · DOI
  18. [19]Cohn D, Zuk O, Kaplan T. Enhancer Identification using Transfer and Adversarial Deep Learning of DNA Sequences. bioRxiv. 2018; p. 264200.
  19. [20]Yue F, Cheng Y, Breschi A, Vierstra J, Wu W, Ryba T, et al A comparative encyclopedia of DNA elements in the mouse genome. Nature. 2014; 515(7527): 355 10.1038/nature13992 25409824 PMC4266106 · DOI · Paper page
  20. [22]Consortium EP. An integrated encyclopedia of DNA elements in the human genome. Nature. 2012; 489(7414): 57 10.1038/nature11247 22955616 PMC3439153 · DOI · Paper page
  21. [24]Forrest AR, Kawaji H, Rehli M, Baillie JK, De Hoon MJ, Haberle V, et al A promoter-level mammalian expression atlas. Nature. 2014; 507(7493): 462 10.1038/nature13182 24670764 PMC4529748 · DOI · Paper page
  22. [26]Meuleman W, Muratov A, Rynes E, Halow J, Lee K, Bates D, et al Index and biological spectrum of accessible DNA elements in the human genome. BioRxiv. 2019; p. 822510.
  23. [27]Nitta KR, Jolma A, Yin Y, Morgunova E, Kivioja T, Akhtar J, et al Conservation of transcription factor binding specificities across 600 million years of bilateria evolution. Elife. 2015; 4: e04837 10.7554/eLife.04837 PMC4362205 25779349 · DOI
  24. [28]Lan G, Zhou J, Xu R, Lu Q, Wang H. Cross-Cell-Type Prediction of TF-Binding Site by Integrating Convolutional Neural Network and Adversarial Network. International journal of molecular sciences. 2019; 20(14): 3425 10.3390/ijms20143425 PMC6679139 31336830 · DOI
  25. [29]Consortium G, et al Genetic effects on gene expression across human tissues. Nature. 2017; 550(7675): 204 10.1038/nature24277 29022597 PMC5776756 · DOI · Paper page
  26. [30]Sobel JA, Krier I, Andersin T, Raghav S, Canella D, Gilardi F, et al Transcriptional regulatory logic of the diurnal cycle in the mouse liver. PLoS biology. 2017; 15(4): e2001069 10.1371/journal.pbio.2001069 28414715 PMC5393560 · DOI
  27. [33]Stenson PD, Ball EV, Mort M, Phillips AD, Shiel JA, Thomas NS, et al Human gene mutation database (HGMD): 2003 update. Human mutation. 2003; 21(6): 577– 581. 10.1002/humu.10212 12754702 · DOI
  28. [34]Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research. 2011; 12: 2825– 2830.
  29. [35]Musunuru K, Strong A, Frank-Kamenetsky M, Lee NE, Ahfeldt T, Sachs KV, et al From noncoding variant to phenotype via SORT1 at the 1p13 cholesterol locus. Nature. 2010; 466(7307): 714 10.1038/nature09266 20686566 PMC3062476 · DOI · Paper page
  30. [36]Kim SS, Dey KK, Weissbrod O, Marquez-Luna C, Gazal S, Price AL. Improving the informativeness of Mendelian disease pathogenicity scores for common disease. bioRxiv. 2020;. PMC7721881 33288751
  31. [37]Wang G, Sarkar AK, Carbonetto P, Stephens M. A simple new approach to variable selection in regression, with application to genetic fine-mapping. bioRxiv. 2018; p. 501114. PMC10201948 37220626
  32. [39]Si-Tayeb K, Lemaigre FP, Duncan SA. Organogenesis and development of the liver. Developmental cell. 2010; 18(2): 175– 189. 10.1016/j.devcel.2010.01.011 20159590 · DOI · Paper page
  33. [40]Qu M, Duffy T, Hirota T, Kay SA. Nuclear receptor HNF4A transrepresses CLOCK: BMAL1 and modulates tissue-specific circadian networks. Proceedings of the National Academy of Sciences. 2018; 115(52): E12305– E12312. 10.1073/pnas.1816411115 PMC6310821 30530698 · DOI
  34. [42]Fischbach GD, Lord C. The Simons Simplex Collection: a resource for identification of autism genetic risk factors. Neuron. 2010; 68(2): 192– 195. 10.1016/j.neuron.2010.10.006 20955926 · DOI · Paper page
  35. [43]An JY, Lin K, Zhu L, Werling DM, Dong S, Brand H, et al Genome-wide de novo risk score implicates promoter variation in autism spectrum disorder. Science. 2018; 362(6420): eaat6576 10.1126/science.aat6576 30545852 PMC6432922 · DOI · Paper page
  36. [44]Zhou J, Park CY, Theesfeld CL, Wong AK, Yuan Y, Scheckel C, et al Whole-genome deep-learning analysis identifies contribution of noncoding mutations to autism risk. Nature genetics. 2019; 51(6): 973– 980. 10.1038/s41588-019-0420-0 31133750 PMC6758908 · DOI
  37. [45]Karczewski KJ, Francioli LC, Tiao G, Cummings BB, Alföldi J, Wang Q, et al The mutational constraint spectrum quantified from variation in 141,456 humans. Nature. 2020; 581(7809): 434– 443. 10.1038/s41586-020-2308-7 32461654 PMC7334197 · DOI · Paper page
  38. [46]Weintraub AS, Li CH, Zamudio AV, Sigova AA, Hannett NM, Day DS, et al YY1 is a structural regulator of enhancer-promoter loops. Cell. 2017; 171(7): 1573– 1588. 10.1016/j.cell.2017.11.008 29224777 PMC5785279 · DOI · Paper page
  39. [47]Fudenberg G, Kelley DR, Pollard KS. Predicting 3D genome folding from DNA sequence. bioRxiv. 2019; p. 800060. PMC8211359 33046897
  40. [48]Normand R, Du W, Briller M, Gaujoux R, Starosvetsky E, Ziv-Kenet A, et al Found In Translation: a machine learning model for mouse-to-human inference. Nature methods. 2018; 15(12): 1067 10.1038/s41592-018-0214-9 30478323 PMC12396630 · DOI
  41. [49]Earl D, Nguyen N, Hickey G, Harris RS, Fitzgerald S, Beal K, et al Alignathon: a competitive assessment of whole-genome alignment methods. Genome research. 2014; 24(12): 2077– 2089. 10.1101/gr.174920.114 25273068 PMC4248324 · DOI · Paper page
  42. [51]Chen S, Zhou Y, Chen Y, Gu J. fastp: an ultra-fast all-in-one FASTQ preprocessor. Bioinformatics. 2018; 34(17): i884– i890. 10.1093/bioinformatics/bty560 30423086 PMC6129281 · DOI
  43. [52]Li H, Durbin R. Fast and accurate short read alignment with Burrows–Wheeler transform. Bioinformatics. 2009; 25(14): 1754– 1760. 10.1093/bioinformatics/btp324 19451168 PMC2705234 · DOI · Paper page
  44. [53]Davis CA, Hitz BC, Sloan CA, Chan ET, Davidson JM, Gabdank I, et al The Encyclopedia of DNA elements (ENCODE): data portal update. Nucleic acids research. 2017; 46(D1): D794– D801. 10.1093/nar/gkx1081 PMC5753278 29126249 · DOI · Paper page
  45. [55]Pickrell JK, Gaffney DJ, Gilad Y, Pritchard JK. False positive peaks in ChIP-seq and other sequencing-based functional assays caused by unannotated high copy number regions. Bioinformatics. 2011; 27(15): 2144– 2146. 10.1093/bioinformatics/btr354 21690102 PMC3137225 · DOI
  46. [56]Karimzadeh M, Ernst C, Kundaje A, Hoffman MM. Umap and Bismap: quantifying genome and methylome mappability. Nucleic acids research. 2018; 46(20): e120– e120. 10.1093/nar/gky677 30169659 PMC6237805 · DOI
  47. [57]Hendrycks D, Gimpel K. Gaussian Error Linear Units (GELUs). arXiv preprint arXiv:160608415. 2016;.
  48. [58]Jaganathan K, Panagiotopoulou SK, McRae JF, Darbandi SF, Knowles D, Li YI, et al Predicting splicing from primary sequence with deep learning. Cell. 2019; 176(3): 535– 548. 10.1016/j.cell.2018.12.015 30661751 · DOI · Paper page
  49. [59]Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, et al. Tensorflow: A system for large-scale machine learning. In: 12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16); 2016. p. 265–283.
  50. [60]Schwartz S, Kent WJ, Smit A, Zhang Z, Baertsch R, Hardison RC, et al Human–mouse alignments with BLASTZ. Genome research. 2003; 13(1): 103– 107. 10.1101/gr.809403 12529312 PMC430961 · DOI
  51. [61]Di Iulio J, Bartha I, Wong EH, Yu HC, Lavrenko V, Yang D, et al The human noncoding genome defined by genetic diversity. Nature genetics. 2018; 50(3): 333– 337. 10.1038/s41588-018-0062-7 29483654 · DOI · Paper page

Cited by

Sorted by citations

Authors
Kelley, D. R.
Affiliations
Calico Life Sciences (US)
Corresponding author
Kelley, David R.
ORCID
Kelley, David R.
Venue
PLOS Computational Biology
Publisher
Public Library of Science (PLoS)
Published
2020-07-20
Volume
16
Issue
7
Pages
e1008050
ISSN
  • 1553-734X (ISSN-L)
  • 1553-7358
DOI
10.1371/journal.pcbi.1008050
PMC
PMC7392335
OpenAlex
W3042669608
Cited by
228
References
8
Citations by year
2026: 28 · 2025: 38 · 2024: 55 · 2023: 52 · 2022: 33 · 2021: 13 · 2020: 9
FWCI
8.68
Type
journal article
Language
en
Update notices
new_version (2020-07-30)
Open access
Licence
Locations
  • PLoS Computational Biology (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Chromatin Dynamics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Genetic Associations and Epidemiology
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene Regulatory Network Analysis
Keywords
gene expression prediction, interspecies transmission, deep convolutional neural networks, genetic variants, cis-regulatory elements, tissue-specific gene expression, epigenetic profiles, disease-associated variants, transcriptional regulation
MeSH terms
Machine Learning, Algorithms, Animals, Gene Expression Regulation, Humans, Models, Genetic, Mutation, Software, Species Specificity, Genetic Variation, Models, Statistical, Genome, Human, Neural Networks, Computer, Sequence Analysis, DNA, Computational Biology, Hepatocytes, Genomics, Databases, Genetic, Quantitative Trait Loci, Mice, Epigenomics

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