Discovering epistatic feature interactions from neural network models of regulatory DNA sequences
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Motivation: Transcription factors bind regulatory DNA sequences in a combinatorial manner to modulate gene expression. Deep neural networks (DNNs) can learn the cis-regulatory grammars encoded in regulatory DNA sequences associated with transcription factor binding and chromatin accessibility. Several feature attribution methods have been developed for estimating the predictive importance of individual features (nucleotides or motifs) in any input DNA sequence to its associated output prediction from a DNN model. However, these methods do not reveal higher-order feature interactions encoded by the models. Results: We present a new method called Deep Feature Interaction Maps (DFIM) to efficiently estimate interactions between all pairs of features in any input DNA sequence. DFIM accurately identifies ground truth motif interactions embedded in simulated regulatory DNA sequences. DFIM identifies synergistic interactions between GATA1 and TAL1 motifs from in vivo TF binding models. DFIM reveals epistatic interactions involving nucleotides flanking the core motif of the Cbf1 TF in yeast from in vitro TF binding models. We also apply DFIM to regulatory sequence models of in vivo chromatin accessibility to reveal interactions between regulatory genetic variants and proximal motifs of target TFs as validated by TF binding quantitative trait loci. Our approach makes significant strides in improving the interpretability of deep learning models for genomics. Availability and implementation: Code is available at: https://github.com/kundajelab/dfim. Supplementary information: Supplementary data are available at Bioinformatics online.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370
Axiomatic attribution for deep networks
Sundararajan, M., Taly, A., & Yan, Q. (2017) · arXiv · doi:10.48550/arxiv.1703.01365 · Cited by 4,087
Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning
Alipanahi, B., Delong, A., Weirauch, M. T., & Frey, B. J. (2015) · Nature Biotechnology · doi:10.1038/nbt.3300 · Cited by 2,873
Learning Important Features Through Propagating Activation Differences
Shrikumar, A., Greenside, P., & Kundaje, A. (2017) · arXiv · doi:10.48550/arxiv.1704.02685 · Cited by 2,761
Self-citationAn improved ATAC-seq protocol reduces background and enables interrogation of frozen tissues
Corces, M. R., Trevino, A. E., Hamilton, E. G., Greenside, P. G., Sinnott-Armstrong, N. A., Vesuna, S., Satpathy, A. T., Rubin, A. J., Montine, K. S., Wu, B., et al. (2017) · Nature Methods · doi:10.1038/nmeth.4396 · Cited by 2,496
Self-citationPredicting effects of noncoding variants with deep learning–based sequence model
Zhou, J., & Troyanskaya, O. G. (2015) · Nature Methods · doi:10.1038/nmeth.3547 · Cited by 2,338
Consistent Individualized Feature Attribution for Tree Ensembles
Lundberg, S. M., Erion, G. G., & Lee, S.-I. (2018) · arXiv · doi:10.48550/arxiv.1802.03888 · Cited by 1,430
Corces, M. R., Buenrostro, J. D., Wu, B., Greenside, P. G., Chan, S. M., Koenig, J. L., Snyder, M. P., Pritchard, J. K., Kundaje, A., Greenleaf, W. J., et al. (2016) · Nature Genetics · doi:10.1038/ng.3646 · Cited by 1,151
Self-citationKelley, D. R., Snoek, J., & Rinn, J. L. (2016) · Genome Research · doi:10.1101/gr.200535.115 · Cited by 1,048
Sequential regulatory activity prediction across chromosomes with convolutional neural networks
Kelley, D. R., Reshef, Y. A., Bileschi, M., Belanger, D., McLean, C. Y., & Snoek, J. (2018) · Genome Research · doi:10.1101/gr.227819.117 · Cited by 537 · cited 1×
“the mutant sequence X0 ′ has X0 ′ [(2,3), s] = fGC 2 , X0 ′ [(1,4), s] = 1−fGC 2 ∀ s ∈ {sk .”
Cited by
Deep learning: new computational modelling techniques for genomics
Eraslan, G., Avsec, Ž., Gagneur, J., & Theis, F. J. (2019) · Nature Reviews Genetics · doi:10.1038/s41576-019-0122-6 · Cited by 1,203
Base-resolution models of transcription-factor binding reveal soft motif syntax
Avsec, Ž., Weilert, M., Shrikumar, A., Krueger, S., Alexandari, A., Dalal, K., Fropf, R., McAnany, C., Gagneur, J., Kundaje, A., et al. (2021) · Nature Genetics · doi:10.1038/s41588-021-00782-6 · Cited by 610
Self-citationObtaining genetics insights from deep learning via explainable artificial intelligence
Novakovsky, G., Dexter, N., Libbrecht, M. W., Wasserman, W. W., & Mostafavi, S. (2023) · Nature Reviews Genetics · doi:10.1038/s41576-022-00532-2 · Cited by 386
DeepSTARR predicts enhancer activity from DNA sequence and enables the de novo design of enhancers
de Almeida, B. P., Reiter, F., Pagani, M., & Stark, A. (2021) · doi:10.1101/2021.10.05.463203 · Cited by 284
de Almeida, B. P., Reiter, F., Pagani, M., & Stark, A. (2022) · Nature Genetics · doi:10.1038/s41588-022-01048-5 · Cited by 283
Linder, J., Bogard, N., Rosenberg, A. B., & Seelig, G. (2020) · Cell Systems · doi:10.1016/j.cels.2020.05.007 · Cited by 107
Detecting genetic interactions with visible neural networks
(2025) · doi:10.1038/s42003-025-08157-x · Cited by 5
Detecting Genetic Interactions with Visible Neural Networks
van Hilten, A., Melograna, F., Fan, B., Niessen, W., van Steen, K., & Roshchupkin, G. (2024) · doi:10.1101/2024.02.27.582086 · Cited by 3
A comprehensive evaluation of self-attention for detecting regulatory feature interactions
Jabeen, S., & Ben-Hur, A. (2026) · NAR Genomics and Bioinformatics · doi:10.1093/nargab/lqaf209 · Cited by 1
A Comprehensive Evaluation of Self Attention for Detecting Regulatory Feature Interactions
Jabeen, S., & Ben-Hur, A. (2024) · doi:10.1101/2024.08.23.609428 · Cited by 1
Metadata
- Authors
- Greenside, P., Shimko, T., Fordyce, P., & Kundaje, A.
- Venue
- Bioinformatics
- Publisher
- Oxford University Press (OUP)
- Published
- 2018-09-01
- Volume
- 34
- Issue
- 17
- Pages
- i629-i637
- ISSN
- 1367-4803 (ISSN-L)
- 1367-4811
- OpenAlex
- W2951212842
- Cited by
- 91
- References
- 11
- FWCI
- 3.45
- Type
- journal article
- Language
- en
- Open access
- hybrid
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.