Transfer learning identifies sequence determinants of regulatory element accessibility
Open accessPreprint — published as 10.1093/nargab/lqad026 · Paper page
Abstract
Dysfunction of regulatory elements through genetic variants is a central mechanism in the pathogenesis of disease. To better understand disease etiology, there is consequently a need to understand how DNA encodes regulatory activity. Deep learning methods show great promise for modeling of biomolecular data from DNA sequence but are limited to large input data for training. Here, we develop ChromTransfer, a transfer learning method that uses a pre-trained, cell-type agnostic model of open chromatin regions as a basis for fine-tuning on regulatory sequences. We demonstrate superior performances with ChromTransfer for learning cell-type specific chromatin accessibility from sequence compared to models not informed by a pre-trained model. Importantly, ChromTransfer enables fine-tuning on small input data with minimal decrease in accuracy. We show that ChromTransfer uses sequence features matching binding site sequences of key transcription factors for prediction. Together, these results demonstrate ChromTransfer as a promising tool for learning the regulatory code.
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.
Integrity signals
Registry
Cites
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.
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?
Transfer learning from sequence models trained with large data sets has been recently shown as a robust alternative.
“While training on small data sets may lead to overfitting, transfer learning from sequence models trained with large data sets has been recently shown as a robust alternative75,”
From Enhancer grammar of liver cell types and hepatocyte zonation states (2022) · cites this paper as [75]
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
No references could be resolved yet.
Research works printed but not linked: 10
- Janssens,J., Aibar,S., Taskiran,I.I., Ismail,J.N., Gomez,A.E., Aughey,G., Spanier,K.I., De Rop,F.V., González-Blas,C.B., Dionne,M. et al. (2022) Decoding gene regulation in the fly brain. Nature, 601, 630-636. 10 NAR Genomics and Bioinformatics, 2023, Vol. 5, No. 2
- Chen,Z., Badrinarayanan,V., Lee,C.-Y. and Rabinovich,A. (2018) GradNorm: gradient normalization for adaptive loss balancing in deep multitask networks. In: Proceedings of the 35th International Conference on Machine Learning. PMLR, Vol. 80, pp. 794-803.
- Yosinski,J., Clune,J., Bengio,Y. and Lipson,H. (2014) How transferable are features in deep neural networks? In: Advances in Neural Information Processing Systems.
- He,K., Zhang,X., Ren,S. and Sun,J. (2015) Deep residual learning for image recognition. arXiv doi: https://arxiv.org/abs/1512.03385, 10 December 2015, preprint: not peer reviewed. · arXiv
- Agarap,A.F. (2019) Deep learning using rectified linear units (ReLU). arXiv doi: https://arxiv.org/abs/1803.08375, 07 February 2019, preprint: not peer reviewed. · arXiv
- Abadi,M., Agarwal,A., Barham,P., Brevdo,E., Chen,Z., Citro,C., Corrado,G.S., Davis,A., Dean,J., Devin,M. et al. (2016) TensorFlow: large-scale machine learning on heterogeneous distributed systems. arXiv doi: https://arxiv.org/abs/1603.04467, 16 March 2016, preprint: not peer reviewed. · arXiv
- Kingma,D.P. and Ba,J. (2017) Adam: a method for stochastic optimization. arXiv doi: https://doi.org/10.48550/arXiv.1412.6980, 30 January 2017, preprint: not peer reviewed. · DOI · Paper page
- Shrikumar,A., Greenside,P. and Kundaje,A. (2017) Learning important features through propagating activation differences. In: Proceedings of the 34th International Conference on Machine Learning. PMLR, Vol. 70, pp. 3145-3153.
- Wickham,H. (2016) In: ggplot2: Elegant Graphics for Data Analysis. Springer International Publishing.
- Taskiran,I.I., Spanier,K.I., Christiaens,V., Mauduit,D. and Aerts,S. (2022) Cell type directed design of synthetic enhancers. bioRxiv doi: https://doi.org/10.1101/2022.07.26.501466, 27 July 2022, preprint: not peer reviewed. · DOI
Cited by
Sorted by citations
Enhancer grammar of liver cell types and hepatocyte zonation states
González-Blas, C. B., Matetovici, I., Hillen, H., Taskiran, I. I., Vandepoel, R., Christiaens, V., Sansores-García, L., Verboven, E., Hulselmans, G., Poovathingal, S., et al. (2022) · doi:10.1101/2022.12.08.519575 · Cited by 5 · see citing works
- Authors
- Salvatore, M., Horlacher, M., Marsico, A., Winther, O., & Andersson, R.
- Affiliations
- University of Copenhagen (DK)
- Helmholtz Munich (DE)
- Broad Institute (US)
- Corresponding author
- Andersson, Robin
- Venue
- NAR Genomics and Bioinformatics
- Publisher
- openRxiv
- Published
- 2022-08-05
- Volume
- 5
- Issue
- 2
- Pages
- lqad026-lqad026
- ISSN
- 2631-9268 (ISSN-L)
- PMC
- PMC10052367
- OpenAlex
- W4361853159
- Cited by
- 13
- References
- 0
- Citations by year
- 2026: 2 · 2025: 3 · 2024: 6 · 2023: 1 · 2022: 1
- FWCI
- 0.90
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by-nc
- Locations
- NAR Genomics and Bioinformatics (publishedVersion, cc-by-nc)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- Research at the University of Copenhagen (University of Copenhagen) (publishedVersion, cc-by-nc)
- Research at the University of Copenhagen (University of Copenhagen) (submittedVersion, cc-by-nc-nd)
- mediaTUM (Technical University of Munich) (submittedVersion, other-oa)
- Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU) (submittedVersion, cc-by-nc)
- PuSH - Publication Server of Helmholtz Zentrum München (submittedVersion)
- Funders
- Novo Nordisk (NNF21SA0072102)
- Novo Nordisk Fonden (NNF20OC0059796, NNF18OC0052570, NNF21SA0072102, NNF20OC0062606)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Chromatin Dynamics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Chromatin Remodeling and Cancer
- Keywords
- chromatin accessibility, cell type-specific gene regulation, transfer learning, deep learning, transcription factor binding sites, open chromatin, limited training data, genetic variants, etiology
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
