Deep learning of immune cell differentiation
Deep learning of immune cell differentiation
复制标题
DOI：
10.1073/pnas.2011795117
复制
发表时间：
2020-10-13
影响因子：
11.1
通讯作者：
Project, Immunological Genome
中科院分区：
文献类型：
--
作者：
Maslova, Alexandra;Ramirez, Ricardo N.;Project, Immunological Genome
虽然我们知道许多序列特异性转录因子（TF），但顺式调节元件的DNA序列如何在基因组规模上解码和编排以确定免疫细胞分化超出了我们的掌握范围。利用81种免疫细胞类型的染色质可及性的颗粒图谱，我们询问卷积神经网络（CNN）是否可以学习仅从调控DNA序列推断细胞类型特异性染色质可及性。通过定制的架构和CNN参数解释的集成方法，我们证明了我们的训练网络（“AI-TAC”）通过从头开始重新发现已知调节器和一些未知调节器的结合基序来做到这一点。基序的重要性是学习几乎作为功能上的重要重叠惊人的位置确定的染色质免疫沉淀的几个TF。AI-TAC建立了一个TF及其相互作用的层次结构，该层次结构驱动谱系规范，并识别阶段特异性相互作用，如Pax 5/Ebf 1与Pax 5/Prdm 1，或不同NF-κ B二聚体在不同细胞类型中的作用。AI-TAC将Spi 1/Cebp和Pax 5/Ebf 1分别指定为髓系和B系命运所必需的驱动因子，但似乎没有因子是T细胞分化所必需的，这可能代表了一种回退途径。经过老鼠训练的AI-TAC可以解析人类DNA，揭示了有影响力的TF的惊人相似的排名，并为AI-TAC是一种可推广的调控序列解码器提供了额外的支持。因此，深度学习可以揭示预测免疫系统完全分化复杂性的调控语法。
Although we know many sequence-specific transcription factors (TFs), how the DNA sequence of cis-regulatory elements is decoded and orchestrated on the genome scale to determine immune cell differentiation is beyond our grasp. Leveraging a granular atlas of chromatin accessibility across 81 immune cell types, we asked if a convolutional neural network (CNN) could learn to infer cell type-specific chromatin accessibility solely from regulatory DNA sequences. With a tailored architecture and an ensemble approach to CNN parameter interpretation, we show that our trained network ("AI-TAC") does so by rediscovering ab initio the binding motifs for known regulators and some unknown ones. Motifs whose importance is learned virtually as functionally important overlap strikingly well with positions determined by chromatin immunoprecipitation for several TFs. AI-TAC establishes a hierarchy of TFs and their interactions that drives lineage specification and also identifies stage-specific interactions, like Pax5/Ebf1 vs. Pax5/Prdm1, or the role of different NF-kappa B dimers in different cell types. AI-TAC assigns Spi1/Cebp and Pax5/Ebf1 as the drivers necessary for myeloid and B lineage fates, respectively, but no factors seemed as dominantly required for T cell differentiation, which may represent a fall-back pathway. Mouse-trained AI-TAC can parse human DNA, revealing a strikingly similar ranking of influential TFs and providing additional support that AI-TAC is a generalizable regulatory sequence decoder. Thus, deep learning can reveal the regulatory syntax predictive of the full differentiative complexity of the immune system.