Deep learning of immune cell differentiation
Authors:
- Ricardo N. RamirezRRRicardo N. Ramirez
- Chendi WangCWChendi Wang
- Bernard NgBNBernard Ng
- Christophe BenoistCBChristophe Benoist
- Sara MostafaviSMSara Mostafavi
- Immunological Genome ProjectIPImmunological Genome Project
- 25 September 2020
- journal article
- research article
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 117 (41) , 25655-25666
Abstract
Significance: Applying artificial intelligence tools to a highly complex question of immunology, we show that a deep neural network can learn to predict the patterns of chromatin opening across 81 stem and differentiated cells across the immune system, solely from the DNA sequence of regulatory regions. It does so by discovering ab initio the binding motifs for known master regulators, along with some unknown ones, and their combinatorial operation. These predictions validated biochemically, and a mouse-trained neural network predicts human enhancer/promoter activity much better than sequence comparisons would. Beyond serving as a trove of testable functional frameworks, this work is important in showing how massively complex integrated questions of immunology can be handled with such tools.Keywords
Funding Information
- HHS | NIH | National Institute of Allergy and Infectious Diseases (AI072073)
- Division of Intramural Research (AI116834-03S1)
- Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada (CREATE scholarship)
- Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada (Undergraduate Student Research Award)
This publication has 48 references indexed in Scilit:
- Foxp3 Exploits a Pre-Existent Enhancer Landscape for Regulatory T Cell Lineage SpecificationCell, 2012
- Pioneer transcription factors: establishing competence for gene expressionGenes & Development, 2011
- Simple Combinations of Lineage-Determining Transcription Factors Prime cis-Regulatory Elements Required for Macrophage and B Cell IdentitiesMolecular Cell, 2010
- Noncooperative Interactions between Transcription Factors and Clustered DNA Binding Sites Enable Graded Transcriptional Responses to Environmental InputsMolecular Cell, 2010
- Genome-Wide Mapping of in Vivo Protein-DNA InteractionsScience, 2007
- The Transcriptional Regulation of B Cell Lineage CommitmentImmunity, 2007
- Quantifying similarity between motifsGenome Biology, 2007
- Effector and memory CD8+ T cell fate coupled by T-bet and eomesoderminNature Immunology, 2005
- Bcl11: sibling rivalry in lymphoid developmentNature Immunology, 2003
- Multiple specific contacts between a mammalian transcription factor and its cognate promotersNature, 1984