Parallel repulsive logic regression with biological adjacency
Bibliographic record
Abstract
Logic regression, an extension of generalized linear models with Boolean combinations of binary variables as predictors, is a useful tool in exploring interactions among single-nucleotide polymorphisms (SNPs) in genome-wide association studies. However, since the search space defined by all possible combinations of SNPs, their complements, and logical operators in Boolean expressions can be exceedingly large in such studies, objective function optimization is slow and likely to be trapped in many local solutions, resulting in model over-fitting. We introduce a new search algorithm, parallel repulsive logic regression (PRLR), to efficiently estimate parameters of a logic regression to find a best model within the large space of SNP interactions by incorporating: (i) relevant biological adjacency matrix between SNPs to define similarity of estimation paths or trees, which are derived from physical SNP positions on chromosomes and/or memberships in biological gene pathways; and (ii) two repulsive forces to counter the similarity between and within estimation paths considered in parallel, which are introduced as penalty terms in the objective function. We compare our method's performance for identifying biologically-meaningful SNP interactions through simulations and with real genetic-epidemiological data. PRLR's detection-accuracy measures outperform existing approaches, especially in terms of positive predictive value and sensitivity for detecting SNP-SNP interactions.
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 | 0.002 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".