Classification and regression trees clarify the role of epistasis and environment in genotype–phenotype maps
Bibliographic record
Abstract
Understanding how genetic variation translates into phenotypic outcomes is central to various sub-fields of genetics. This task is complicated by a range of forces–including epistasis, environmental modulation of mutation effects, and ecological influences–that complicate the process of mapping from genotype to phenotype. In this study, we apply a unified decision tree approach, classification and regression trees (CART), to model genotype-phenotype relationships across protein fitness landscapes across a diversity of organisms: (i) a fluorescent protein isolated from Entacmaea quadricolor (bubble-tip anemone), (ii) antifolate resistance in Plasmodium falciparum (malaria parasite) dihydrofolate reductase (DHFR) under drug concentration gradients, (iii) allelic variants from the long-term evolution experiment (LTEE) in Escherichia coli, (iv) proteostasis-modulated drug resistance phenotypes in three bacterial orthologues of DHFR, and (v) chemotypic diversification of sesquiterpene synthases in Nicotiana tabacum (cultivated tobacco). Our results demonstrate that decision trees can effectively capture higher-order interactions between mutations and environments, uncovering nonlinear dependencies and contingencies that are often missed by traditional parametric models. By enabling clear visualization of interaction hierarchies, CART serves as both a predictive tool and an explanatory framework for genotype-phenotype mapping. This approach has use cases across the spectrum, from resolving the genomic architecture of biological traits, to personalized medicine, and varied applications in bioengineering.
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 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| 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".