Modeling chromatin state from sequence across angiosperms using recurrent convolutional neural networks

Travis Wrightsman, Alexandre P. Marand, Peter A. Crisp, Nathan M. Springer, Edward S. Buckler

Research output: Contribution to journalArticlepeer-review

Abstract

Accessible chromatin regions are critical components of gene regulation but modeling them directly from sequence remains challenging, especially within plants, whose mechanisms of chromatin remodeling are less understood than in animals. We trained an existing deep-learning architecture, DanQ, on data from 12 angiosperm species to predict the chromatin accessibility in leaf of sequence windows within and across species. We also trained DanQ on DNA methylation data from 10 angiosperms because unmethylated regions have been shown to overlap significantly with ACRs in some plants. The across-species models have comparable or even superior performance to a model trained within species, suggesting strong conservation of chromatin mechanisms across angiosperms. Testing a maize (Zea mays L.) held-out model on a multi-tissue chromatin accessibility panel revealed our models are best at predicting constitutively accessible chromatin regions, with diminishing performance as cell-type specificity increases. Using a combination of interpretation methods, we ranked JASPAR motifs by their importance to each model and saw that the TCP and AP2/ERF transcription factor (TF) families consistently ranked highly. We embedded the top three JASPAR motifs for each model at all possible positions on both strands in our sequence window and observed position- and strand-specific patterns in their importance to the model. With our publicly available across-species ‘a2z’ model it is now feasible to predict the chromatin accessibility and methylation landscape of any angiosperm genome.

Original languageEnglish (US)
Article numbere20249
JournalPlant Genome
Volume15
Issue number3
DOIs
StatePublished - Sep 2022

Bibliographical note

Funding Information:
This work was funded by an NSF Graduate Research Fellowship (DGE‐1650441) and the USDA–ARS to T.W., an NSF Postdoctoral Fellowship in Biology (DBI‐1905869) to A.P.M., an Australian Research Council (ARC) Discovery Early Career Award (DE200101748) to P.A.C., the NSF IOS‐1934384 to N.M.S., and the USDA–ARS to E.S.B. The Texas Advanced Computing Center supported a portion of the compute time for the analyses with their Frontera system. Peter Koo contributed helpful comments during the analyses.

Publisher Copyright:
© 2022 The Authors. The Plant Genome published by Wiley Periodicals LLC on behalf of Crop Science Society of America.

PubMed: MeSH publication types

  • Journal Article
  • Research Support, Non-U.S. Gov't
  • Research Support, U.S. Gov't, Non-P.H.S.

Fingerprint

Dive into the research topics of 'Modeling chromatin state from sequence across angiosperms using recurrent convolutional neural networks'. Together they form a unique fingerprint.

Cite this