rewirebio.iobenchmarks
Configuration

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.

3 evaluations · 7 results

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.

ParametersNot recorded
Minimum VRAMNot recorded
Inference LatencyNot recorded
Context WindowNot recorded
AccessNot recorded
LicenseNot 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 configurationProtocol and datasetConcordance 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)EvaluationPBMC deconvolution, pairwise ordering accuracy, mean over five lineages0.83Not reportedNot reportedNot reportedNot reportedNot reportedNot reported
Ladon, composition post-trained, PCA 64 + TabICL regressors (PBMC deconvolution)EvaluationPBMC deconvolution, per-lineage Pearson r of inferred against measured sharesNot reported0.880.90.79Not reported0.90.89
Ladon, composition post-trained, PCA 64 + TabICL regressors (PBMC deconvolution)EvaluationPBMC deconvolution, Pearson r of inferred against measured shares, mean over five lineagesNot reportedNot reportedNot reportedNot reported0.87Not reportedNot reported
All 7 result rows with coverage, uncertainty and sources
Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: Ladon, composition post-trained, PCA 64 + TabICL regressors (PBMC deconvolution)Protocol: PBMC deconvolution, per-lineage Pearson r of inferred against measured shares
Dataset subset: Giroux PBMC bulk RNA-seq test set for deconvolution (35 bulks, 17 donors)
0.88 Pearson (Pearson r between inferred and measured B/plasma share across 35 PBMC bulks)
unitless · higher

Uncertainty: Not reported by the source: No interval is printed for this value.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Ladon, PBMC deconvolution per-lineage Pearson r

ladon-20261115-protocol-pbmc-lineage-pearson

Aggregation: Not reported

Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF) · Figure 17 (page 33), top panel 'B/plasma', label 'r 0.88 0.39', first value (Ladon)
Configuration: Ladon, composition post-trained, PCA 64 + TabICL regressors (PBMC deconvolution)Protocol: PBMC deconvolution, per-lineage Pearson r of inferred against measured shares
Dataset subset: Giroux PBMC bulk RNA-seq test set for deconvolution (35 bulks, 17 donors)
0.9 Pearson (Pearson r between inferred and measured CD4 T share across 35 PBMC bulks)
unitless · higher

Uncertainty: Not reported by the source: No interval is printed for this value.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Ladon, PBMC deconvolution per-lineage Pearson r

ladon-20261115-protocol-pbmc-lineage-pearson

Aggregation: Not reported

Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF) · Figure 17 (page 33), top panel 'CD4 T', label 'r 0.90 0.78', first value (Ladon)
Configuration: Ladon, composition post-trained, PCA 64 + TabICL regressors (PBMC deconvolution)Protocol: PBMC deconvolution, per-lineage Pearson r of inferred against measured shares
Dataset subset: Giroux PBMC bulk RNA-seq test set for deconvolution (35 bulks, 17 donors)
0.79 Pearson (Pearson r between inferred and measured CD8 T share across 35 PBMC bulks)
unitless · higher

Uncertainty: Not reported by the source: No interval is printed for this value.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Ladon, PBMC deconvolution per-lineage Pearson r

ladon-20261115-protocol-pbmc-lineage-pearson

Aggregation: Not reported

Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF) · Figure 17 (page 33), top panel 'CD8 T', label 'r 0.79 0.77', first value (Ladon)
Configuration: Ladon, composition post-trained, PCA 64 + TabICL regressors (PBMC deconvolution)Protocol: PBMC deconvolution, per-lineage Pearson r of inferred against measured shares
Dataset subset: Giroux PBMC bulk RNA-seq test set for deconvolution (35 bulks, 17 donors)
0.9 Pearson (Pearson r between inferred and measured Monocyte share across 35 PBMC bulks)
unitless · higher

Uncertainty: Not reported by the source: No interval is printed for this value.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Ladon, PBMC deconvolution per-lineage Pearson r

ladon-20261115-protocol-pbmc-lineage-pearson

Aggregation: Not reported

Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF) · Figure 17 (page 33), top panel 'Monocyte', label 'r 0.90 0.76', first value (Ladon)
Configuration: Ladon, composition post-trained, PCA 64 + TabICL regressors (PBMC deconvolution)Protocol: PBMC deconvolution, per-lineage Pearson r of inferred against measured shares
Dataset subset: Giroux PBMC bulk RNA-seq test set for deconvolution (35 bulks, 17 donors)
0.89 Pearson (Pearson r between inferred and measured NK share across 35 PBMC bulks)
unitless · higher

Uncertainty: Not reported by the source: No interval is printed for this value.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Ladon, PBMC deconvolution per-lineage Pearson r

ladon-20261115-protocol-pbmc-lineage-pearson

Aggregation: Not reported

Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF) · Figure 17 (page 33), top panel 'NK', label 'r 0.89 0.27', first value (Ladon)
Configuration: Ladon, composition post-trained, PCA 64 + TabICL regressors (PBMC deconvolution)Protocol: PBMC deconvolution, pairwise ordering accuracy, mean over five lineages
Dataset subset: Giroux PBMC bulk RNA-seq test set for deconvolution (35 bulks, 17 donors)
0.83 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)
unitless · higher

Uncertainty: Not yet extracted: 95% intervals are drawn as bars; their values appear only in the web version's collapsed data table, not in the PDF.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Ladon, PBMC deconvolution, pairwise ordering accuracy

ladon-20261115-protocol-pbmc-pairwise-ordering

Aggregation: Not reported

Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF) · Figure 17 (page 33), bottom chart, row 'Ladon', column 'Pairwise ordering accuracy'
Configuration: Ladon, composition post-trained, PCA 64 + TabICL regressors (PBMC deconvolution)Protocol: PBMC deconvolution, Pearson r of inferred against measured shares, mean over five lineages
Dataset subset: Giroux PBMC bulk RNA-seq test set for deconvolution (35 bulks, 17 donors)
0.87 Pearson (Pearson r between inferred and measured lineage shares across 35 PBMC bulks, mean over five lineages)
unitless · higher

Uncertainty: Not yet extracted: 95% intervals are drawn as bars; their values appear only in the web version's collapsed data table, not in the PDF.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Ladon, PBMC deconvolution, pearson r

ladon-20261115-protocol-pbmc-mean-pearson

Aggregation: Not reported

Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF) · Figure 17 (page 33), bottom chart, row 'Ladon', column 'Pearson r'

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

Claims, original sources and review scope · Release 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview 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 historyDownload this release (gzip)
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

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

Suggest a correction