Experimental support for genomic prediction of climate maladaptation
using the machine learning approach Gradient Forests
Abstract
Gradient Forests 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 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. We used high-throughput sequencing, genome scans, and several
methods (including Gradient Forests) 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 Gradient Forests to
relate candidate loci to environmental gradients and to predict the
expected magnitude of response (i.e., the genetic offset) of populations
when transplanted from their “home” environment to the new
environments in the common gardens. We then compared the predicted
genetic offsets to measurements of population performance in the common
gardens. We found the expected inverse relationship between genetic
offset and performance in the common gardens: populations with larger
predicted genetic offsets performed worse in the common gardens than
populations with smaller offsets. Also, genetic offset better predicted
performance in the common gardens than did ‘naive’ climate distances.
Our results provide preliminary evidence that genomic offsets may
provide a first order estimate of the degree of expected maladaptation
of populations exposed to rapid environmental change.