Additional file 6 of Systematic evaluation of supervised machine learning for sample origin prediction using metagenomic sequencing data
Bibliographic record
Abstract
Additional file 6: Figure S6. Inclusion of training data from a heterogeneous sequencing protocol affects model performance. This figure is analogous to Figs. 3, S3 and 5, with the distinction of including single-end data from Sacramento into training. Figures (A-C) provide global visualizations of the samples using Bray-Curtis dissimilarity matrix. Latitude (D) and longitude (E) predictions from the multivariate regression model on species abundance data are plotted against the true geographic coordinates on the x-axis. Each data point represents a sample. The dashed line shows where predictions would be exactly correct. (F) Predictions from the classification model are illustrated in comparison to true sources. Each entry shows the number of samples predicted to be the corresponding city (row) and originally from the corresponding source (column). Cities within the same continent with respect to reference are boxed in blue. Squared errors for latitude and longitude from the regression (G, H) and classification (I, J) are shown in boxplots for each city.
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 | 0.011 | 0.094 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.004 | 0.005 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.005 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.793 | 0.151 |
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".