An image database of <i>Drosophila melanogaster</i> wings for phenomic and biometric analysis
Bibliographic record
Abstract
BACKGROUND: Extracting important descriptors and features from images of biological specimens is an ongoing challenge. Features are often defined using landmarks and semi-landmarks that are determined a priori based on criteria such as homology or some other measure of biological significance. An alternative, widely used strategy uses computational pattern recognition, in which features are acquired from the image de novo. Subsets of these features are then selected based on objective criteria. Computational pattern recognition has been extensively developed primarily for the classification of samples into groups, whereas landmark methods have been broadly applied to biological inference. RESULTS: To compare these approaches and to provide a general community resource, we have constructed an image database of Drosophila melanogaster wings - individually identifiable and organized by sex, genotype and replicate imaging system - for the development and testing of measurement and classification tools for biological images. We have used this database to evaluate the relative performance of current classification strategies. Several supervised parametric and nonparametric machine learning algorithms were used on principal components extracted from geometric morphometric shape data (landmarks and semi-landmarks). For comparison, we also classified phenotypes based on de novo features extracted from wing images using several computer vision and pattern recognition methods as implemented in the Bioimage Classification and Annotation Tool (BioCAT). CONCLUSIONS: Because we were able to thoroughly evaluate these strategies using the publicly available Drosophila wing database, we believe that this resource will facilitate the development and testing of new tools for the measurement and classification of complex biological phenotypes.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.009 | 0.005 |
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".