Experimental support for genomic prediction of climate maladaptation using the machine learning approach Gradient Forests
Experimental support for genomic prediction of climate maladaptation using the machine learning approach Gradient Forests
复制标题
DOI：
10.1111/1755-0998.13374
复制
发表时间：
2021-03-22
影响因子：
7.7
通讯作者：
Keller, Stephen R.
中科院分区：
文献类型：
--
作者：
Fitzpatrick, Matthew C.;Chhatre, Vikram E.;Keller, Stephen R.
梯度森林(GF)是一种机器学习算法，在研究基因组变异的环境驱动因素和将基因组信息纳入气候变化影响评估方面越来越受欢迎。在这里，我们(I)首次对“基因组偏移量”--一种来自梯度森林的气候适应不良的衡量标准--预测生物对环境变化的反应的能力进行了实验评估，并(Ii)探索了使用GF来确定候选SNPs的方法。我们使用高通量测序、基因组扫描和包括遗传算法在内的几种方法来确定与气候适应相关的候选基因座。在两个常见的园艺实验中，还种植了从苦瓜杨范围内收集的个体。我们使用遗传生长因子将候选基因座与环境梯度联系起来，并预测种群从其“家”环境移植到普通花园时的预期反应幅度(即，不适应的遗传补偿度量)。然后，我们将不同候选和随机选择的SNP集合的预测遗传偏移量与普通花园中种群表现的测量结果进行了比较。我们发现了遗传偏移量和性能之间的预期反向关系：预测遗传偏移量较大的种群在普通花园中的表现比偏移量较小的种群更差。此外，遗传因素抵消的预测效果也好于“天真”的气候转移距离。然而，随机选择的几组SNP预测的表现略好于候选SNPs。我们的研究提供了证据表明，遗传偏移量代表了暴露在快速环境变化中的种群预期适应不良程度的一阶估计，并表明GF作为一种识别候选SNP的方法可能有一定的前景。
Gradient Forests (GF) is a machine learning algorithm that is gaining in popularity for studying the environmental drivers of genomic variation and for incorporating genomic information into climate change impact assessments. Here we (i) provide the first experimental evaluation of the ability of "genomic offsets" - a metric of climate maladaptation derived from Gradient Forests - to predict organismal responses to environmental change, and (ii) explore the use of GF for identifying candidate SNPs. We used high-throughput sequencing, genome scans, and several methods, including GF, to identify candidate loci associated with climate adaptation in balsam poplar (Populus balsamifera L.). Individuals collected throughout balsam poplar's range also were planted in two common garden experiments. We used GF to relate candidate loci to environmental gradients and predict the expected magnitude of the response (i.e., the genetic offset metric of maladaptation) of populations when transplanted from their "home" environment to the common gardens. We then compared the predicted genetic offsets from different sets of candidate and randomly selected SNPs to measurements of population performance in the common gardens. We found the expected inverse relationship between genetic offset and performance: populations with larger predicted genetic offsets performed worse in the common gardens than populations with smaller offsets. Also, genetic offset better predicted performance than did "naive" climate transfer distances. However, sets of randomly selected SNPs predicted performance slightly better than did candidate SNPs. Our study provides evidence that genetic offsets represent a first order estimate of the degree of expected maladaptation of populations exposed to rapid environmental change and suggests GF may have some promise as a method for identifying candidate SNPs.