| Method: ABIS | 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) | 0.76 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 checkedMethods, coverage and sourceABIS, 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 'ABIS', column 'Pairwise ordering accuracy' |
|---|
| Method: ABIS | 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) | 0.79 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 checkedMethods, coverage and sourceABIS, 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 'ABIS', column 'Pearson r' |
|---|
| Method: BayesPrism (single-cell PBMC references) | 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) | 0.74 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 checkedMethods, coverage and sourceBayesPrism, 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 'BayesPrism', column 'Pairwise ordering accuracy' |
|---|
| Method: BayesPrism (single-cell PBMC references) | 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) | 0.66 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 checkedMethods, coverage and sourceBayesPrism, 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 'BayesPrism', column 'Pearson r' |
|---|
| Method: CIBERSORT reimplementation (Ladon report) | 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) | 0.39 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 checkedMethods, coverage and sourceCIBERSORT, 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', second value (CIBERSORT) |
|---|
| Method: CIBERSORT reimplementation (Ladon report) | 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) | 0.78 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 checkedMethods, coverage and sourceCIBERSORT, 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', second value (CIBERSORT) |
|---|
| Method: CIBERSORT reimplementation (Ladon report) | 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) | 0.77 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 checkedMethods, coverage and sourceCIBERSORT, 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', second value (CIBERSORT) |
|---|
| Method: CIBERSORT reimplementation (Ladon report) | 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) | 0.76 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 checkedMethods, coverage and sourceCIBERSORT, 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', second value (CIBERSORT) |
|---|
| Method: CIBERSORT reimplementation (Ladon report) | 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) | 0.27 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 checkedMethods, coverage and sourceCIBERSORT, 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', second value (CIBERSORT) |
|---|
| Method: CIBERSORT reimplementation (Ladon report) | 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) | 0.7 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 checkedMethods, coverage and sourceCIBERSORT, 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 'CIBERSORT', column 'Pairwise ordering accuracy' |
|---|
| Method: CIBERSORT reimplementation (Ladon report) | 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) | 0.6 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 checkedMethods, coverage and sourceCIBERSORT, 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 'CIBERSORT', column 'Pearson r' |
|---|
| Method: DWLS reimplementation (Ladon report) | 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) | 0.65 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 checkedMethods, coverage and sourceDWLS, 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 'DWLS', column 'Pairwise ordering accuracy' |
|---|
| Method: DWLS reimplementation (Ladon report) | 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) | 0.57 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 checkedMethods, coverage and sourceDWLS, 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 'DWLS', column 'Pearson r' |
|---|
| Method: EPIC (BRef reference) | 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) | 0.76 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 checkedMethods, coverage and sourceEPIC, 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 'EPIC', column 'Pairwise ordering accuracy' |
|---|
| Method: EPIC (BRef reference) | 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) | 0.8 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 checkedMethods, coverage and sourceEPIC, 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 'EPIC', column 'Pearson r' |
|---|
| 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 checkedMethods, coverage and sourceLadon, 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 checkedMethods, coverage and sourceLadon, 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 checkedMethods, coverage and sourceLadon, 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 checkedMethods, coverage and sourceLadon, 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 checkedMethods, coverage and sourceLadon, 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 checkedMethods, coverage and sourceLadon, 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 checkedMethods, coverage and sourceLadon, 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' |
|---|