Automatic classification of sub-microlitre protein-crystallization trials in 1536-well plates
Bibliographic record
Abstract
A technique for automatically evaluating microbatch (400 nl) protein-crystallization trials is described. This method addresses analysis problems introduced at the sub-microlitre scale, including non-uniform lighting and irregular droplet boundaries. The droplet is segmented from the well using a loopy probabilistic graphical model with a two-layered grid topology. A vector of 23 features is extracted from the droplet image using the Radon transform for straight-edge features and a bank of correlation filters for microcrystalline features. Image classification is achieved by linear discriminant analysis of its feature vector. The results of the automatic method are compared with those of a human expert on 32 1536-well plates. Using the human-labeled images as ground truth, this method classifies images with 85% accuracy and a ROC score of 0.84. This result compares well with the experimental repeatability rate, assessed at 87%. Images falsely classified as crystal-positive variously contain speckled precipitate resembling microcrystals, skin effects or genuine crystals falsely labeled by the human expert. Many images falsely classified as crystal-negative variously contain very fine crystal features or dendrites lacking straight edges. Characterization of these misclassifications suggests directions for improving the method.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".