Genome-Wide Association Mapping for Intelligence in Military Working Dogs: Development of Advanced Classification Algorithm for Genome-Wide Single Nucleotide Polymorphism (SNP) Data Analysis
Bibliographic record
Abstract
Abstract : This project collected data to genetically map superior intelligence in the military working dog. A behavioral testing regimen was developed by canine cognitive expert Dr Karen Overall (UPENN) which enabled quantitative intelligence testing of individual dogs and blood samples were taken, and genome-wide SNP typing completed by means of the Affymetrix Canine SNP (single nucleotide polymorphism) Array v2. In order to identify SNP markers for mapping of small-effect-sized genes that contribute to highly complex polygenic traits, it is necessary to develop a more robust computational method for the analysis of SNP profile data. To accomplish this, we are undertaking two parallel efforts, Biologically Guided Feature Selection and Computational Based Feature Synthesis and Classification. As a proof-of-concept, we conducted a classification analysis focused on a subset of tested canines consisting of German Shepherds, Labrador Retrievers, and Belgian Malinois. Using this new classification technique, samples from the three breeds clustered into the correct breed with an accuracy ranging from 89 - 100 %. Classification accuracy was not significantly affected by data process methods (including data cleanup methods) or SNP annotation quality, thus suggesting that this algorithm is highly robust. With further refinement and optimization, this technique could be used to classify complex phenotypes in an unsupervised manner and allow identification of associated SNP markers.
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 | 0.003 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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".