DeepLINK: Deep learning inference using knockoffs with applications to genomics
DeepLINK: Deep learning inference using knockoffs with applications to genomics
复制标题
DOI：
10.1073/pnas.2104683118
复制
发表时间：
2021-09
期刊：
影响因子：
--
通讯作者：
Zifan Zhu;Yingying Fan;Yinfei Kong;Jinchi Lv;Fengzhu Sun
中科院分区：
文献类型：
--
作者：
Zifan Zhu;Yingying Fan;Yinfei Kong;Jinchi Lv;Fengzhu Sun
复杂的学习方法虽然具有很高的预测和分类能力，但往往缺乏可解释性和可重复性，限制了其科学应用。一种有用的补救办法是选择对感兴趣的反应有贡献的真正重要的变量。我们开发了一种使用仿制品DeepLINK进行深度学习推理的方法，以实现深度学习模型中错误率可控的变量选择的目标。我们表明，DeepLINK在变量选择方面也具有很高的功率，具有广泛的模型设计类别。然后，我们将DeepLINK应用于三个真实数据集，并产生具有可重复性和生物学意义的统计推断结果，展示了其在广泛的科学应用中的应用前景。我们提出了一个基于深度学习的仿制品推理框架DeepLINK，它保证了高维环境下的错误发现率（FDR）控制。DeepLINK适用于由可能的非线性潜在因素模型描述的广泛的协变量分布。它由两个主要部分组成：用于仿冒变量构造的自编码器网络和用于具有FDR控制的特征选择的多层感知器网络。通过广泛的仿真研究对DeepLINK的经验性能进行了研究，结果表明，DeepLINK在特征选择中实现了FDR控制，具有高选择能力和高预测精度。我们还将DeepLINK应用于三个实际数据应用中，以演示其实际效用。
Significance Although practically attractive with high prediction and classification power, complicated learning methods often lack interpretability and reproducibility, limiting their scientific usage. A useful remedy is to select truly important variables contributing to the response of interest. We develop a method for deep learning inference using knockoffs, DeepLINK, to achieve the goal of variable selection with controlled error rate in deep learning models. We show that DeepLINK can also have high power in variable selection with a broad class of model designs. We then apply DeepLINK to three real datasets and produce statistical inference results with both reproducibility and biological meanings, demonstrating its promising usage to a broad range of scientific applications. We propose a deep learning–based knockoffs inference framework, DeepLINK, that guarantees the false discovery rate (FDR) control in high-dimensional settings. DeepLINK is applicable to a broad class of covariate distributions described by the possibly nonlinear latent factor models. It consists of two major parts: an autoencoder network for the knockoff variable construction and a multilayer perceptron network for feature selection with the FDR control. The empirical performance of DeepLINK is investigated through extensive simulation studies, where it is shown to achieve FDR control in feature selection with both high selection power and high prediction accuracy. We also apply DeepLINK to three real data applications to demonstrate its practical utility.