Experimental support for genomic prediction of climate maladaptation using the machine learning approach Gradient Forests
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.019 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".