An intrinsically interpretable neural network architecture for sequence-to-function learning.
An intrinsically interpretable neural network architecture for sequence-to-function learning.
复制标题
DOI：
10.1093/bioinformatics/btad271
复制
发表时间：
2023-06-30
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
基于序列的深度学习方法已被证明可以预测多种功能性基因组读数，包括开放染色质区域和基因的RNA表达。然而，目前的方法的一个主要限制是，模型解释依赖于计算要求的事后分析，即使这样，人们往往不能解释高度参数化模型的内部机制。在这里，我们介绍了一种深度学习架构，称为完全可解释的序列到功能模型（tiSFM）。tiSFM在使用更少参数的同时提高了标准多层卷积模型的性能。此外，虽然tiSFM本身在技术上是一个多层神经网络，但内部模型参数在相关序列基序方面本质上是可解释的。我们分析了已发表的造血谱系细胞类型的开放染色质测量结果，并证明了tiSFM优于为该数据集定制的最先进的卷积神经网络模型。我们还表明，它正确地识别了已知在造血分化中发挥作用的转录因子的上下文特异性活动，包括B细胞的Pax5和Ebf1，以及先天淋巴细胞的Rorc。tiSFM的模型参数具有生物学意义的解释，我们显示了我们的方法在预测表观遗传状态变化作为发育转变的函数的复杂任务上的实用性。源代码（包括用于分析关键发现的脚本）可在https：//github.com/boooooogey/ATAConv上找到，并用Python实现。
Sequence-based deep learning approaches have been shown to predict a multitude of functional genomic readouts, including regions of open chromatin and RNA expression of genes. However, a major limitation of current methods is that model interpretation relies on computationally demanding post hoc analyses, and even then, one can often not explain the internal mechanics of highly parameterized models. Here, we introduce a deep learning architecture called totally interpretable sequence-to-function model (tiSFM). tiSFM improves upon the performance of standard multilayer convolutional models while using fewer parameters. Additionally, while tiSFM is itself technically a multilayer neural network, internal model parameters are intrinsically interpretable in terms of relevant sequence motifs. We analyze published open chromatin measurements across hematopoietic lineage cell-types and demonstrate that tiSFM outperforms a state-of-the-art convolutional neural network model custom-tailored to this dataset. We also show that it correctly identifies context-specific activities of transcription factors with known roles in hematopoietic differentiation, including Pax5 and Ebf1 for B-cells, and Rorc for innate lymphoid cells. tiSFM’s model parameters have biologically meaningful interpretations, and we show the utility of our approach on a complex task of predicting the change in epigenetic state as a function of developmental transition. The source code, including scripts for the analysis of key findings, can be found at https://github.com/boooooogey/ATAConv, implemented in Python.
登录
查看更多内容
DOI：
10.1073/pnas.2011795117
发表时间：
2020-10-13
影响因子：
11.1
作者：
Maslova, Alexandra;Ramirez, Ricardo N.;Project, Immunological Genome
通讯作者：
Project, Immunological Genome
影响因子：
20.3
作者：
Ramos-Mejia, Veronica;Navarro-Montero, Oscar;Menendez, Pablo
通讯作者：
Menendez, Pablo
DOI：
10.4049/jimmunol.1003703
发表时间：
2011-06-15
期刊：
Journal of immunology (Baltimore, Md. : 1950)
影响因子：
--
作者：
Rothenberg EV
通讯作者：
Rothenberg EV
B淋巴细胞谱系规范，承诺和表观遗传学控制早期B细胞因子1。
影响因子：
--
作者：
Hagman, James;Ramirez, Julita;Lukin, Kara
通讯作者：
Lukin, Kara
DOI：
10.1038/nri2476
发表时间：
2009-02
期刊：
Nature reviews. Immunology
影响因子：
--
作者：
通讯作者：
--