Knowledge Discovery in Variant Databases Using Inductive Logic Programming
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Understanding the effects of genetic variation on the phenotype of an individual is a major goal of biomedical research, especially for the development of diagnostics and effective therapeutic solutions. In this work, we describe the use of a recent knowledge discovery from database (KDD) approach using inductive logic programming (ILP) to automatically extract knowledge about human monogenic diseases. We extracted background knowledge from MSV3d, a database of all human missense variants mapped to 3D protein structure. In this study, we identified 8,117 mutations in 805 proteins with known three-dimensional structures that were known to be involved in human monogenic disease. Our results help to improve our understanding of the relationships between structural, functional or evolutionary features and deleterious mutations. Our inferred rules can also be applied to predict the impact of any single amino acid replacement on the function of a protein. The interpretable rules are available at http://decrypthon.igbmc.fr/kd4v/.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| 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 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it