Multi-view deep learning of highly multiplexed imaging data improves association of cell states with clinical outcomes
Bibliographic record
Abstract
Test data for manuscript titled: Multi-view deep learning of highly multiplexed imaging data improves association of cell states with clinical outcomes. This is a subset of 9 images taken from Jackson 2020 paper (PMID 31959985). `test_data_sample_paths.tsv` is an example tsv file containing the paths to each file and is in the format expected by the pipeline. The paper makes use of the full datasets available from: Jackson-BC (PMID 31959985) - Basel samples only Ali-BC (PMID 35122013) - IMC only Hoch-Melanoma (PMID 35363540) Details on how to run the model and get the images into the form expected by the model can be found in the associated repository. We add AnnData object files used in our pipeline to the folder preprocessed_anndatas.zip. These anndatas contain the single-cell data, along with all the extracted views and background covariates. The folder PDAC_tiff_and_ masks.zip contains the tiff files and mask files from 5 PDAC patient biopsies.
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 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 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 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.050 | 0.015 |
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".