Ladon, composition post-trained, PCA 64 + TabICL regressors (PBMC deconvolution)
Composition-post-trained Ladon representations of synthetic bulks from four PBMC single-cell references, reduced to 64 principal components, with one TabICL regressor per lineage predicting its share in real bulk samples.
Overview
An explanatory profile has not yet been reviewed for this record.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
Model Capabilities & Hardware Requirements
Deployment facts recorded for Ladon, composition post-trained, PCA 64 + TabICL regressors (PBMC deconvolution). Fields the record does not carry are marked not recorded.
Evaluated Checkpoint: Pretrained model post-trained on bulk transcriptomes (pretraining objective) and synthetic bulks from scBaseCount pseudobulks (pretraining plus linear composition objective); a random subset of single-cell studies, including the study paired with the PBMC test bulks, contributed no synthetic bulks
Evaluations and results
3 evaluations · 7 results. Different protocols are not a single leaderboard.
Dataset subset: Giroux PBMC bulk RNA-seq test set for deconvolution (35 bulks, 17 donors)
Sorted by Concordance index (pairwise ordering accuracy: fraction of pairs of test bulks with different measured lineage shares put in the measured order, ties in inferred shares counted as half; mean over five lineages; 0.5 is chance) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.
| Tested configuration | Protocol and dataset | Concordance index (pairwise ordering accuracy: fraction of pairs of test bulks with different measured lineage shares put in the measured order, ties in inferred shares counted as half; mean over five lineages; 0.5 is chance) | Pearson (Pearson r between inferred and measured B/plasma share across 35 PBMC bulks) | Pearson (Pearson r between inferred and measured CD4 T share across 35 PBMC bulks) | Pearson (Pearson r between inferred and measured CD8 T share across 35 PBMC bulks) | Pearson (Pearson r between inferred and measured lineage shares across 35 PBMC bulks, mean over five lineages) | Pearson (Pearson r between inferred and measured Monocyte share across 35 PBMC bulks) | Pearson (Pearson r between inferred and measured NK share across 35 PBMC bulks) |
|---|---|---|---|---|---|---|---|---|
| Ladon, composition post-trained, PCA 64 + TabICL regressors (PBMC deconvolution)Evaluation | PBMC deconvolution, pairwise ordering accuracy, mean over five lineages | 0.83 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| Ladon, composition post-trained, PCA 64 + TabICL regressors (PBMC deconvolution)Evaluation | PBMC deconvolution, per-lineage Pearson r of inferred against measured shares | Not reported | 0.88 | 0.9 | 0.79 | Not reported | 0.9 | 0.89 |
| Ladon, composition post-trained, PCA 64 + TabICL regressors (PBMC deconvolution)Evaluation | PBMC deconvolution, Pearson r of inferred against measured shares, mean over five lineages | Not reported | Not reported | Not reported | Not reported | 0.87 | Not reported | Not reported |
All 7 result rows with coverage, uncertainty and sources
Filter evaluations
Applied filters: All linked evaluations
Source checking is not independent reproduction. Release 2026-11-21-c8bea25e5abb.
Use this configuration
How it works, versions and access
Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this configuration. Consult the linked sources and evaluation records below.
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
0 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
Sources and history
Release 2026-11-21-c8bea25e5abb · Record review: source checked
1 source record and release history
- Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF) · Original source · Zenodo record 24157116 (version DOI 10.5281/zenodo.24157116; concept DOI 10.5281/zenodo.24157115), file Ladon-An-RNA-Foundation-Model-for-Predicting-Patient-Outcomes.pdf, 47 pages, dated 12 November 2026
Technical metadata and record identifiers
Technical metadata for this record is tracked under stable ID ladon-20261115-config-ladon-deconvolution-pbmc.
Source locator: Pages 38, 39 and 40, Methods 'Ladon post-training', 'Deconvolution model' and 'PBMC deconvolution benchmark'
Related records
- configuration of: Ladon
- system: Ladon, PBMC deconvolution per-lineage Pearson r
- system: Ladon, PBMC deconvolution, pairwise ordering accuracy
- system: Ladon, PBMC deconvolution, pearson r
How to cite
Ladon, composition post-trained, PCA 64 + TabICL regressors (PBMC deconvolution). Rewire biological model benchmark database, release 2026-11-21-c8bea25e5abb. https://benchmarks.rewirebio.io/database/configuration/ladon-20261115-config-ladon-deconvolution-pbmc/
Release 2026-11-21-c8bea25e5abb. Rankings and values change between releases, so keep the release id in the citation. Cite the original publication as well for any value you reuse: each result links its source.
The compilation and annotations made by Rewire in this release are offered under CC BY 4.0; values and text taken from cited sources stay under the terms of those sources and are not covered by this licence. Data licence