A directed learning strategy integrating multiple omic data improves genomic prediction
A directed learning strategy integrating multiple omic data improves genomic prediction
复制标题
整合多个组学数据的定向学习策略改善了基因组预测
DOI：
10.1111/pbi.13117
复制
发表时间：
2019-10-01
影响因子：
13.8
通讯作者：
Xu, Shizhong
中科院分区：
文献类型：
--
作者：
Hu, Xuehai;Xie, Weibo;Xu, Shizhong
基因组预测（GP）是利用全基因组标记构建一个预测表型的统计模型，是加速植物分子育种的一个有前途的策略。然而，目前仅使用基因组数据进行表型预测的进展已经达到了瓶颈，并且先前的转录组学和代谢组学预测的研究忽略了基因组信息。在这里，我们设计了一种称为多层最小绝对收缩和选择算子（MLLASSO）的GP新策略，将多个组学数据整合到一个模型中，该模型迭代学习由观察到的转录组和代谢组监督的三层遗传特征（GF）。值得注意的是，MLLASSO学习基因互作的高阶信息，这使我们能够实现水稻产量的可预测性从0.1588（单独GP）到0.2451（MLLASSO）的显著提高。在前两层的预测中，发现一些基因是遗传可预测基因（GPGs），因为它们的表达被遗传标记准确预测。有趣的是，我们对GPG有三个引人注目的发现：（i）GPG是高度复杂性状（如产量）的良好预测因子;（ii）GPG大多是eQTL基因（顺式或反式）;（iii）性状相关转录因子家族富含GPG。这些发现支持了这样一种观点，即学习型GF不仅是性状的良好预测因子，而且在基因表达调控方面具有特定的生物学意义。为了将新方法与传统的GP模型区分开来，我们将MLLASSO称为由中间组学数据监督的定向学习策略。这种新的预测模型似乎比传统的GP模型更可靠，更强大。
Genomic prediction (GP) aims to construct a statistical model for predicting phenotypes using genome-wide markers and is a promising strategy for accelerating molecular plant breeding. However, current progress of phenotype prediction using genomic data alone has reached a bottleneck, and previous studies on transcriptomic and metabolomic predictions ignored genomic information. Here, we designed a novel strategy of GP called multilayered least absolute shrinkage and selection operator (MLLASSO) by integrating multiple omic data into a single model that iteratively learns three layers of genetic features (GFs) supervised by observed transcriptome and metabolome. Significantly, MLLASSO learns higher order information of gene interactions, which enables us to achieve a significant improvement of predictability of yield in rice from 0.1588 (GP alone) to 0.2451 (MLLASSO). In the prediction of the first two layers, some genes were found to be genetically predictable genes (GPGs) as their expressions were accurately predicted with genetic markers. Interestingly, we made three dramatic discoveries for the GPGs: (i) GPGs are good predictors for highly complex traits like yield; (ii) GPGs are mostly eQTL genes (cis or trans); and (iii) trait-related transcriptional factor families are enriched in GPGs. These findings support the notion that learned GFs not only are good predictors for traits but also have specific biological implications regarding regulation of gene expressions. To differentiate the new method from conventional GP models, we called MLLASSO a directed learning strategy supervised by intermediate omic data. This new prediction model appears to be more reliable and more robust than conventional GP models.