rewirebio.iobenchmarks
Configuration

BulkRNABert, published Hugging Face checkpoint (Ladon report comparator)

BulkRNABert embeddings from the published Hugging Face checkpoint with its published input processing, used as features for the same outcome heads as Ladon.

6 evaluations · 6 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 BulkRNABert, published Hugging Face checkpoint (Ladon report comparator). 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: Published Hugging Face checkpoint and input processing

Evaluations and results

6 evaluations · 6 results. Different protocols are not a single leaderboard.

Sorted by AUROC (AUROC for RECIST complete or partial response against other evaluable responses, immunotherapy arms, equal mean over six held-out trials) (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 datasetAUROC (AUROC for RECIST complete or partial response against other evaluable responses, immunotherapy arms, equal mean over six held-out trials)Concordance index (Uno's C-index, survival endpoint not specified beyond 'survival', equal mean over six CPTAC target cancers, predictor fitted on TCGA)Concordance index (Uno's C-index, survival endpoint not specified beyond 'survival', equal mean over six TCGA target cancers, predictor fitted on CPTAC)Concordance index (Uno's C-index, survival endpoint not specified beyond 'survival', pan-cancer (pairs across cancers counted), equal mean of the TCGA to CPTAC and CPTAC to TCGA transfers)Hazard ratio (hazard ratio, higher-risk half against lower-risk half at the median predicted risk, overall survival, Cox stratified by treatment arm, Efron ties, full follow-up; equal-trial geometric mean over six trials)Hazard ratio (hazard ratio, higher-risk half against lower-risk half at the median predicted risk, progression-free survival, Cox stratified by treatment arm, Efron ties, full follow-up; equal-trial geometric mean over three trials)
BulkRNABert, published Hugging Face checkpoint (Ladon report comparator)EvaluationHeld-out trials, immunotherapy response AUROC, equal mean over six trials, Immunotherapy arms of six held-out trials with evaluable response0.612Not reportedNot reportedNot reportedNot reportedNot reported
BulkRNABert, published Hugging Face checkpoint (Ladon report comparator)EvaluationSurvival transfer CPTAC to TCGA, mean Uno C-index over six cancers, TCGA six-cancer transfer target set (2,461 patients)Not reportedNot reported0.59Not reportedNot reportedNot reported
BulkRNABert, published Hugging Face checkpoint (Ladon report comparator)EvaluationSurvival transfer TCGA and CPTAC, pan-cancer Uno C-index, mean of two directions, TCGA and CPTAC transfer target sets combined (pan-cancer panel)Not reportedNot reportedNot reported0.68Not reportedNot reported
BulkRNABert, published Hugging Face checkpoint (Ladon report comparator)EvaluationSurvival transfer TCGA to CPTAC, mean Uno C-index over six cancers, CPTAC six-cancer transfer target set (1,128 patients)Not reported0.63Not reportedNot reportedNot reportedNot reported
BulkRNABert, published Hugging Face checkpoint (Ladon report comparator)EvaluationHeld-out trials, OS hazard ratio of higher- against lower-risk half, geometric mean over six trials, Six held-out trials with overall survivalNot reportedNot reportedNot reportedNot reported1.55Not reported
BulkRNABert, published Hugging Face checkpoint (Ladon report comparator)EvaluationHeld-out trials, PFS hazard ratio of higher- against lower-risk half, geometric mean over three trials, Three held-out trials with progression-free survivalNot reportedNot reportedNot reportedNot reportedNot reported1.6
All 6 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: BulkRNABert, published Hugging Face checkpoint (Ladon report comparator)Protocol: Survival transfer CPTAC to TCGA, mean Uno C-index over six cancers
Dataset subset: TCGA six-cancer transfer target set (2,461 patients)
0.59 Concordance index (Uno's C-index, survival endpoint not specified beyond 'survival', equal mean over six TCGA target cancers, predictor fitted on CPTAC)
unitless · higher

Uncertainty: Not reported by the source: Dots and bars only; no interval is printed.

Coverage: Not reported scored / Not reported eligible

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

BulkRNABert, survival transfer CPTAC to TCGA, Uno C-index

ladon-20261115-protocol-transfer-cptac-to-tcga

Aggregation: Not reported

Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF) · Figure 2 (page 6), row 'BulkRNABert', panel 'CPTAC → TCGA' ('6 cancer cohorts'), bar label
Configuration: BulkRNABert, published Hugging Face checkpoint (Ladon report comparator)Protocol: Survival transfer TCGA and CPTAC, pan-cancer Uno C-index, mean of two directions
Dataset subset: TCGA and CPTAC transfer target sets combined (pan-cancer panel)
0.68 Concordance index (Uno's C-index, survival endpoint not specified beyond 'survival', pan-cancer (pairs across cancers counted), equal mean of the TCGA to CPTAC and CPTAC to TCGA transfers)
unitless · higher

Uncertainty: Not reported by the source: Dots and bars only; no interval is printed.

Coverage: Not reported scored / Not reported eligible

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

BulkRNABert, survival transfer pan-cancer, Uno C-index

ladon-20261115-protocol-transfer-pan-cancer

Aggregation: Not reported

Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF) · Figure 2 (page 6), row 'BulkRNABert', panel 'Pan-Cancer' ('Mean of 2 transfers'), bar label
Configuration: BulkRNABert, published Hugging Face checkpoint (Ladon report comparator)Protocol: Survival transfer TCGA to CPTAC, mean Uno C-index over six cancers
Dataset subset: CPTAC six-cancer transfer target set (1,128 patients)
0.63 Concordance index (Uno's C-index, survival endpoint not specified beyond 'survival', equal mean over six CPTAC target cancers, predictor fitted on TCGA)
unitless · higher

Uncertainty: Not reported by the source: Dots and bars only; no interval is printed.

Coverage: Not reported scored / Not reported eligible

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

BulkRNABert, survival transfer TCGA to CPTAC, Uno C-index

ladon-20261115-protocol-transfer-tcga-to-cptac

Aggregation: Not reported

Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF) · Figure 2 (page 6), row 'BulkRNABert', panel 'TCGA → CPTAC' ('6 cancer cohorts'), bar label
Configuration: BulkRNABert, published Hugging Face checkpoint (Ladon report comparator)Protocol: Held-out trials, OS hazard ratio of higher- against lower-risk half, geometric mean over six trials
Dataset subset: Six held-out trials with overall survival
1.55 Hazard ratio (hazard ratio, higher-risk half against lower-risk half at the median predicted risk, overall survival, Cox stratified by treatment arm, Efron ties, full follow-up; equal-trial geometric mean over six trials)
unitless · higher

Uncertainty: Not reported by the source: Per-trial dots and a bar only; no interval is printed.

Coverage: 6/6 trials scored (All trials estimable.)

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

BulkRNABert, held-out trials OS hazard ratio

ladon-20261115-protocol-trials-os-hazard-ratio

Aggregation: Not reported

Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF) · Figure 3 (page 7), row 'BulkRNABert', label 'OS 1.55'
Configuration: BulkRNABert, published Hugging Face checkpoint (Ladon report comparator)Protocol: Held-out trials, PFS hazard ratio of higher- against lower-risk half, geometric mean over three trials
Dataset subset: Three held-out trials with progression-free survival
1.6 Hazard ratio (hazard ratio, higher-risk half against lower-risk half at the median predicted risk, progression-free survival, Cox stratified by treatment arm, Efron ties, full follow-up; equal-trial geometric mean over three trials)
unitless · higher

Uncertainty: Not reported by the source: Per-trial dots and a bar only; no interval is printed.

Coverage: 3/3 trials scored (All trials estimable.)

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

BulkRNABert, held-out trials PFS hazard ratio

ladon-20261115-protocol-trials-pfs-hazard-ratio

Aggregation: Not reported

Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF) · Figure 3 (page 7), row 'BulkRNABert', label 'PFS 1.60'
Configuration: BulkRNABert, published Hugging Face checkpoint (Ladon report comparator)Protocol: Held-out trials, immunotherapy response AUROC, equal mean over six trials
Dataset subset: Immunotherapy arms of six held-out trials with evaluable response
0.612 AUROC (AUROC for RECIST complete or partial response against other evaluable responses, immunotherapy arms, equal mean over six held-out trials)
unitless · higher

Uncertainty: Not reported by the source: Per-trial dots and a bar only; no interval is printed.

Coverage: Not reported scored / Not reported eligible

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

BulkRNABert, held-out trials immunotherapy response AUROC

ladon-20261115-protocol-trials-response-auroc

Aggregation: Not reported

Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF) · Figure 6 (page 10), row 'BulkRNABert', bar label

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-bulkrnabert-hf.

Source locator: Page 11, Comparators table; pages 12, 13 and 16 for the heads

Related records

How to cite

BulkRNABert, published Hugging Face checkpoint (Ladon report comparator). Rewire biological model benchmark database, release 2026-11-21-c8bea25e5abb. https://benchmarks.rewirebio.io/database/configuration/ladon-20261115-config-bulkrnabert-hf/

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