Advancing Human Population Genomics with DNA Foundation Models
Bibliographic record
Abstract
Abstract DNA foundation models offer a new approach to interpret genetic variation, but their potential in population-scale genomics remains untapped. We introduce a novel analytical framework that integrates a genomic foundation model with human population genomics studies. We employed the Evo2 DNA foundation model to systematically score the functional impact of a variant and haplotype across diverse cohorts including people with Alzheimer’s Disease Neuroimaging Initiative (ADNI), the Human Pangenome Project, and the UK Biobank. As proof-of-concept, the analysis of the APOE locus confirmed the approach’s validity, with model-derived scores can help to prioritize putatively functional variants and quantify effects of both variants and haplotype onto Alzheimer’s Disease susceptibility or associated endophenotypes, including cognitive performance, brain structural change and amyloid load. Specifically, scoring multi-ancestry assembly sequences from the Human Pangenome Project revealed, for the first time, that genetic variation could nicely explains ancestry-specific differences in APOE expression and the impact of APOE -ε4 on Alzheimer’s disease risk. Overall, this study provides a scalable framework for mapping functional genetic variation, complementing conventional population-genomics approaches, enabling better interpretation of genetic effects in complex genomic regions at population scale.
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 | 0.010 | 0.029 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
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".