The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Leopard: fast decoding cell type-specific transcription factor binding landscape at single-nucleotide resolution
Open accessPreprint — published as 10.1101/gr.269613.120
Abstract
Decoding the cell type-specific transcription factor (TF) binding landscape at single-nucleotide resolution is crucial for understanding the regulatory mechanisms underlying many fundamental biological processes and human diseases. However, limits on time and resources restrict the high-resolution experimental measurements of TF binding profiles of all possible TF-cell type combinations. Previous computational approaches either can not distinguish the cell-context-dependent TF binding profiles across diverse cell types, or only provide a relatively low-resolution prediction. Here we present a novel deep learning approach, Leopard, for predicting TF-binding sites at single-nucleotide resolution, achieving the median area under receiver operating characteristic curve (AUROC) of 0.994. Our method substantially outperformed state-of-the-art methods Anchor and FactorNet, improving the performance by 19% and 27% respectively despite evaluated at a lower resolution. Meanwhile, by leveraging a many-to-many neural network architecture, Leopard features hundred-fold to thousand-fold speedup compared to current many-to-one machine learning methods.
Overview
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
Verification
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?
Distribution shifts between cell types are a significant problem for TF binding prediction.
“Overall, it is commonly understood that distribution shifts between cell types are a significant problem for TF binding prediction, and many methods have been developed to tackle these shifts (Balsubramani et al., 2017; Li et al., 2019a; Li and Guan, 2019; Keilwagen et al., 2019; Quang and Xie, 2019).”
From WILDS: A Benchmark of in-the-Wild Distribution Shifts (2020) · cites this paper as Li and Guan, 2019
The ERM baselines' OOD test performance is competitive with the original challenge results but lower than the state-of-the-art performance of Li and Guan (2019).
“Our ERM baselines' OOD test performance is competitive with the original challenge results, but lower than the state-of-the-art performance of Li and Guan (2019) because of the aforementioned differences in data processing, splits, and architecture, as well as the cross-domain training method employed by that paper and predecessor work (Li et al., 2019a).”
From WILDS: A Benchmark of in-the-Wild Distribution Shifts (2020) · cites this paper as Li and Guan (2019)
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
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
The chromatin accessibility landscape of primary human cancers
Corces, M. R., Granja, J. M., Shams, S., Louie, B. H., Seoane, J. A., Zhou, W., Silva, T. C., Groeneveld, C., Wong, C. K., Cho, S. W., et al. (2018) · Science · doi:10.1126/science.aav1898 · Cited by 1,230
The role of regulatory variation in complex traits and disease
Albert, F. W., & Kruglyak, L. (2015) · Nature Reviews Genetics · doi:10.1038/nrg3891 · Cited by 1,047
The selection and function of cell type-specific enhancers
Heinz, S., Romanoski, C. E., Benner, C., & Glass, C. K. (2015) · Nature Reviews Molecular Cell Biology · doi:10.1038/nrm3949 · Cited by 1,010
Flagged first, then by citations
Research works printed but not linked: 32
- 10.1126/science.1162327 · DOI
- 10.1016/j.cell.2012.12.009 · DOI
- 10.1038/nrg2538 · DOI · Paper page
- 10.1016/j.cell.2018.01.029 · DOI · Paper page
- 10.1016/j.cell.2011.11.013 · DOI
- 10.1093/nar/gkx1106 · DOI
- 10.1093/nar/gkx1126 · DOI
- 10.1038/nature11232 · DOI · Paper page
- 10.1038/nature11212 · DOI
- 10.1126/science.1141319 · DOI · Paper page
- Furey TS . ChIP–seq and beyond: new and improved methodologies to detect and characterize protein–DNA interactions [Internet]. Nature Reviews Genetics. 2012. p. 840–52. Available from: http://dx.doi.org/10.1038/nrg3306 · DOI
- 10.1038/nbt.3121 · DOI
- 10.1038/s41588-018-0295-5 · DOI · Paper page
- Zhou J , Troyanskaya OG . Predicting effects of noncoding variants with deep learning–based sequence model [Internet]. Nature Methods. 2015. p. 931–4. Available from: http://dx.doi.org/10.1038/nmeth.3547 · DOI · Paper page
- 10.1038/nbt.3300 · DOI · Paper page
- 10.1093/nar/gkw226 · DOI
- 10.1093/nar/gky215 · DOI
- 10.1101/gr.237156.118 · DOI
- 2019, FactorNet: A deep learning framework for predicting cell type specific transcription factor binding from nucleotide-resolution sequential data, Methods, 166, 40, 10.1016/j.ymeth.2019.03.020 · DOI · Paper page
- 10.1093/bioinformatics/btr064 · DOI · Paper page
- Zeiler MD , Fergus R. Visualizing and Understanding Convolutional Networks [Internet]. 2013 [cited 2019 Oct 7]. Available from: http://arxiv.org/abs/1311.2901 · arXiv
- 2019, Whole-genome deep-learning analysis identifies contribution of noncoding mutations to autism risk, Nat Genet, 51, 973, 10.1038/s41588-019-0420-0 · DOI
- 2019, Accurate prediction of cell type-specific transcription factor binding, Genome Biol, 20, 9, 10.1186/s13059-018-1614-y · DOI · Paper page
- 10.1158/1538-7445.AM2018-5446 · DOI
- Li H , Guan Y. Deepsleep: Fast and Accurate Delineation of Sleep Arousals at Millisecond Resolution by Deep Learning. 2019 [cited 2019 Oct 3]; Available from: https://papers.ssrn.com/abstract=3445559 · DOI
- Jiang YQ , Xiong JH , Li HY , Yang XH , Yu WT , Gao M , et al. Recognizing basal cell carcinoma on smartphone-captured digital histopathology images with a deep neural network. Br J Dermatol [Internet]. 2019; Available from: http://dx.doi.org/10.1111/bjd.18026 · DOI
- Xie S , Kirillov A , Girshick R , He K. Exploring Randomly Wired Neural Networks for Image Recognition [Internet]. 2019 [cited 2019 Oct 3]. Available from: http://arxiv.org/abs/1904.01569 · DOI
- 10.1093/bioinformatics/btp324 · DOI · Paper page
- 10.1038/nbt.1508 · DOI
- Li Q , Brown JB , Huang H , Bickel PJ . Measuring reproducibility of high-throughput experiments [Internet]. The Annals of Applied Statistics. 2011. p. 1752–79. Available from: http://dx.doi.org/10.1214/11-aoas466 · DOI
- 2008, Genome Biol, 9, 1
- 10.1093/nar/gku846 · DOI
Cited by
Sorted by citations
WILDS: A Benchmark of in-the-Wild Distribution Shifts
Koh, P. W., Sagawa, S., Marklund, H., Xie, S. M., Zhang, M., Balsubramani, A., Hu, W., Yasunaga, M., Phillips, R. L., Gao, I., et al. (2020) · arXiv · doi:10.48550/arxiv.2012.07421 · Cited by 518
Metadata
- Authors
- Li, H., & Guan, Y.
- Affiliations
- University of Michigan (US)
- Corresponding author
- Guan, Yuanfang
- Venue
- bioRxiv (Cold Spring Harbor Laboratory)
- Publisher
- openRxiv
- Published
- 2019-11-27
- OpenAlex
- W2991184346
- Cited by
- 3
- References
- 4
- Citations by year
- 2022: 1 · 2020: 2
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Licence
- cc-by-nc
- Locations
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc)
- Funders
- National Science Foundation (19AMTG34850176, 1452656, NSF-US14-PAF07599, CAREER)
- American Heart Association (19AMTG34850176)
- Nvidia (19AMTG34850176)
- Amazon Web Services (19AMTG34850176)
- 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 › Gene Regulatory Network Analysis
- Keywords
- transcription factor binding site prediction, cell type-specific binding, single-nucleotide resolution, deep learning, chromatin regulatory elements, computational genomics, leopard
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
