A synergistic DNA logic predicts genome-wide chromatin accessibility
Name
Hashimoto_A synergistic DNA lo.pdf
Size
1.29 MB
Format
Adobe PDF
Checksum (MD5)
81e9405856b4d077e841a4229ed4f67a
Author(s)
Sherwood, Richard I.
Emons, Bart J.M.
Hashimoto, Tatsunori Benjamin
Kang, Daniel D.
Rajagopal, Nisha
Barkal, Amira
Zeng, Haoyang
Srinivasan, Sharanya
Jaakkola, Tommi S.
Gifford, David K.
Date Issued
August 206
Journal
Genome Research
Publisher
Cold Spring Harbor Laboratory Press
Citation
Hashimoto, Tatsunori et al. “A Synergistic DNA Logic Predicts Genome-Wide Chromatin Accessibility.” Genome Research 26.10 (2016): 1430–1440.
Version
Final published version
Abstract
Enhancers and promoters commonly occur in accessible chromatin characterized by depleted nucleosome contact; however, it is unclear how chromatin accessibility is governed. We show that log-additive cis-acting DNA sequence features can predict chromatin accessibility at high spatial resolution. We develop a new type of high-dimensional machine learning model, the Synergistic Chromatin Model (SCM), which when trained with DNase-seq data for a cell type is capable of predicting expected read counts of genome-wide chromatin accessibility at every base from DNA sequence alone, with the highest accuracy at hypersensitive sites shared across cell types. We confirm that a SCM accurately predicts chromatin accessibility for thousands of synthetic DNA sequences using a novel CRISPR-based method of highly efficient site-specific DNA library integration. SCMs are directly interpretable and reveal that a logic based on local, nonspecific synergistic effects, largely among pioneer TFs, is sufficient to predict a large fraction of cellular chromatin accessibility in a wide variety of cell types.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-NonCommercial 4.0 International
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1101/gr.199778.115
