Assigning protein subcellular distributions of vesicle associated tail‐anchored membrane proteins by image‐based machine learning
Bibliographic record
Abstract
Subcellular localization of proteins is a key feature of eukaryotes. Traditionally, co‐staining with known marker proteins (antibody based or fluorescence fusion protein) or organelle‐specific dyes (e.g., MitoTracker TM ) have been used to study subcellular localization of proteins of interest, followed by, a final inspection of the fluorescence microscope images by an experimentalist. However, human visual examination is inclined to bias and membrane proteins are trafficked in vesicles between subcellular locations such that assignment to a specific organelle can be misleading. As an alternative way to assign localization we generated a reference library of confocal micrographs of EGFP fusion proteins localized at key subcellular organelles in murine and human cell lines. Rather than assign the localization of an unknown protein to a specific organelle we consider which reference protein has the most similar subcellular distribution from image sets that are optically validated and comprise 789,011 and 523,319 individual human and murine cell images, respectively. Both morphology and statistical features were computed to enable automated assignment of the subcellular distribution for query proteins by machine learning algorithms with high accuracy. By means of this tool we investigate subcellular transport and distribution for model tail‐anchored proteins with randomly mutated C‐terminal targeting sequences for the endoplasmic reticulum and through out the secretory pathway.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| 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".