Predictive modeling in case-control single-nucleotide polymorphism studies in the presence of population stratification: a case study using Genetic Analysis Workshop 16 Problem 1 dataset
Bibliographic record
Abstract
In this paper, we apply the gradient-boosting machine predictive model to the rheumatoid arthritis data for predicting the case-control status. QQ-plot suggests severe population stratification. In univariate genome-wide association studies, a correction factor for ethnicity confounding can be derived. Here we propose a novel strategy to deal with population stratification in the context of multivariate predictive modeling. We address the problem by clustering the subjects on the axes of genetic variations, and building a predictive model separately in each cluster. This allows us to control ethnicity without explicitly including it in the model, which could marginalize the genetic signal we are trying to discover. Clustering not only leads to more similar ethnicity groups but also, as our results show, increases the accuracy of our model when compared to the non-clustered approach. The highest accuracy is achieved with the model adjusted for population stratification, when the genetic axes of variation are included among the set of predictors, although this may be misleading given the confounding effects.
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 | 0.019 | 0.031 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.003 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".