Modeling chromatin state from sequence across angiosperms using recurrent convolutional neural networks
Modeling chromatin state from sequence across angiosperms using recurrent convolutional neural networks
复制标题
DOI：
10.1002/tpg2.20249
复制
发表时间：
2021-11
期刊：
影响因子：
--
通讯作者：
Travis Wrightsman;Alexandre P. Marand;Peter A. Crisp;Nathan M. Springer;E. Buckler
中科院分区：
文献类型：
--
作者：
Travis Wrightsman;Alexandre P. Marand;Peter A. Crisp;Nathan M. Springer;E. Buckler
可接近的染色质区域是基因调控的关键组成部分，但直接根据序列对其进行建模仍然具有挑战性，特别是在植物中，其染色质重塑机制比动物中的了解更少。我们利用来自 12 个被子植物物种的叶子 ATAC-seq 数据训练了现有的深度学习架构 DanQ，以预测物种内部和跨物种的序列窗口的染色质可及性。我们还利用 10 种被子植物的 DNA 甲基化数据对 DanQ 进行了训练，因为未甲基化区域已被证明与某些植物中可接近的染色质区域显着重叠。跨物种模型与物种内训练的模型具有相当甚至更好的性能，这表明被子植物染色质机制具有很强的保守性。在多组织 scATAC 面板上测试玉米保留模型表明，我们的模型最擅长预测组成型可及染色质区域，但随着细胞类型特异性的增加，其性能会下降。使用解释方法的组合，我们根据 JASPAR 基序对每个模型的重要性进行排名，发现 TCP 和 AP2/ERF 转录因子家族始终排名靠前。我们将每个模型的前三个 JASPAR 基序嵌入序列窗口中两条链上所有可能的位置，并观察位置和链特异性模式对模型的重要性。通过我们的跨物种“a2z”模型，现在可以预测任何被子植物基因组的染色质可及性和甲基化景观。
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 leaf ATAC-seq data from 12 angiosperm species to predict the chromatin accessibility 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 accessible chromatin regions 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 held out model on a multi-tissue scATAC 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 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 cross-species “a2z” model it is now feasible to predict the chromatin accessibility and methylation landscape of any angiosperm genome.