Learning Causal Biological Networks With the Principle of Mendelian Randomization
Learning Causal Biological Networks With the Principle of Mendelian Randomization
复制标题
DOI：
10.3389/fgene.2019.00460
复制
发表时间：
2019-05-21
影响因子：
3.7
通讯作者：
Fu, Audrey Qiuyan
中科院分区：
文献类型：
--
作者：
Badsha, Md Bahadur;Fu, Audrey Qiuyan
尽管可以获得大量基因组数据，但可靠地推断分子表型（例如基因表达）之间的因果（即调节）关系仍然是一个挑战，特别是当涉及多个表型时。我们扩展了孟德尔随机化原理 (PMR) 的解释，并提出了 MRPC，这是一种新颖的机器学习算法，它将 PMR 融入到 PC 算法中，PC 算法是计算机科学中学习因果图的经典算法。 MRPC 通过整合个体水平的基因型和分子表型数据来高效、稳健地学习因果生物网络，其中有向边指示因果方向。我们通过仿真证明 MRPC 优于几种流行的通用网络推理方法和基于 PMR 的方法。我们应用 MRPC 来区分与表达数量性状位点相关的多个基因中的直接和间接目标。我们的方法在 R 包 MRPC 中实现，可在 GRAN 上找到（https://cran.r-project.org/web/packages/MRPC/index.html）。
Although large amounts of genomic data are available, it remains a challenge to reliably infer causal (i. e., regulatory) relationships among molecular phenotypes (such as gene expression), especially when multiple phenotypes are involved. We extend the interpretation of the Principle of Mendelian randomization (PMR) and present MRPC, a novel machine learning algorithm that incorporates the PMR in the PC algorithm, a classical algorithm for learning causal graphs in computer science. MRPC learns a causal biological network efficiently and robustly from integrating individual-level genotype and molecular phenotype data, in which directed edges indicate causal directions. We demonstrate through simulation that MRPC outperforms several popular general-purpose network inference methods and PMR-based methods. We apply MRPC to distinguish direct and indirect targets among multiple genes associated with expression quantitative trait loci. Our method is implemented in the R package MRPC, available on GRAN (https://cran.r-project.org/web/packages/MRPC/index.html).