rewire.itbenchmarks
← Back to results
Task

mRNABench HL: mRNA half life

mRNA half life. Scored with R on mRNABench HL. A linear probe over frozen embeddings, scored as the mean over ten random seeds.

21 evaluations · 21 results

Overview

mRNA half life. Scored with R on mRNABench HL. A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Results

Each comparison retains its reviewed evaluation scope, dataset and metric. Results are shown without a pooled ranking.

mRNABench HL: mRNA half life

pearson_r (correlation) · Higher values are better.

mRNABench HL: mRNA half life · mRNABench HL (mRNABench split)

Evidence origin: Author-reported evaluation.

mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, column(HL)
  • Metrics alternate between AUPRC on a percentage scale and Pearson R, so figures in different columns are on different scales.
  • Each row is the best checkpoint of a model family, chosen by the authors, not the family's average.
Comparison details and limitations

Every method mRNABench reports on mRNA half life, scored with R on mRNABench HL.

  • Author-reported numbers, source checked but not independently reproduced.

Automated source review: 2026-09-18. Numerical source review does not establish independent reproduction.

Dots show point estimates. Whiskers show only explicitly defined uncertainty (standard deviation, standard error or a labelled interval); their definitions remain in Table. Unresolved uncertainty is not plotted. Differences do not establish statistical significance.

Showing 12 of 21 matching rows.

Tested configuration
-1-0.500.51
Reported score
  1. Orthrus0.67
  2. Evo20.66
  3. Supervised CNN0.65
  4. Naive Mamba0.57
  5. AIDO.RNA0.57
  6. NT0.57
  7. RiNALMo0.53
  8. SpliceBERT0.53
  9. ERNIE-RNA0.52
  10. DNABERT20.48
  11. DNABERT-S0.47
  12. RNA-FM0.47

Methods and evaluation design

Procedure, tasks and evaluated configurations

Evaluation design

Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.

Benchmarks

These source-backed links do not make different protocols or scores interchangeable.

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Explore all linked results

Run instructions

No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.

Strengths, limitations and unresolved questions

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.

1 evidence row matching the loaded filters

Claims, original sources and review scope · Release 2026-09-29-06401fd5b220
Property and statementOriginal source and locationReview and provenance
Relationship: part of
discovery-benchmark-mrnabench
Individual claims		mRNABench: A curated benchmark for mature mRNA property and function prediction

Original source ↗

Table 2, column(HL)

Version: preprint archived 2025-07-08
Retrieved: 2026-09-16T10:41:16.497221+00:00

source checked

automated source review · 2026-09-18

Audit details

Primary-source transcription with no human sign-off and no independent reproduction.

Field: links:part_of:discovery-benchmark-mrnabench

Claim: mrnabench-association-hl

Source artifact SHA-256: 79f6264ee883535203c63a313547e7c57baa85585f76b42f8d899eb17fb7e600

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

All evidence (CSV)All evidence (JSONL)How to read the evidence

Sources and history

View linked audit checks and correction history

Release 2026-09-29-06401fd5b220 · Record review: source checked

1 source records and release historyDownload this release
Technical metadata and extraction receipts

Stable ID: mrnabench-task-hl

areas
rna-transcriptomes
tasks
mRNA half life
metric
R
metric direction
higher
dataset
mRNABench HL
protocol
A linear probe over frozen embeddings, scored as the mean over ten random seeds.
source locator
Table 2, column(HL)
comparison panels
id: mrnabench-panel-hl; title: mRNABench HL: mRNA half life; protocol id: mrnabench-task-hl; dataset id: mrnabench-dataset-mrnabench-hl; metric: pearson_r; unit: correlation; direction: higher; result ids: mrnabench-result-naive-baseline-hl-pearson-r; mrnabench-result-naive-mamba-hl-pearson-r; mrnabench-result-supervised-cnn-hl-pearson-r; mrnabench-result-3utrbert-hl-pearson-r; mrnabench-result-aido-rna-hl-pearson-r; mrnabench-result-dnabert-s-hl-pearson-r; mrnabench-result-dnabert2-hl-pearson-r; mrnabench-result-ernie-rna-hl-pearson-r; mrnabench-result-evo1-hl-pearson-r; mrnabench-result-evo2-hl-pearson-r; mrnabench-result-helix-mrna-hl-pearson-r; mrnabench-result-hyenadna-hl-pearson-r; mrnabench-result-nt-hl-pearson-r; mrnabench-result-orthrus-hl-pearson-r; mrnabench-result-rna-fm-hl-pearson-r; mrnabench-result-rna-msm-hl-pearson-r; mrnabench-result-rnabert-hl-pearson-r; mrnabench-result-rnaernie-hl-pearson-r; mrnabench-result-rinalmo-hl-pearson-r; mrnabench-result-splicebert-hl-pearson-r; mrnabench-result-utr-lm-hl-pearson-r; source ids: expansion-p3-mrnabench-2025; source locator: Table 2, column(HL); context: Every method mRNABench reports on mRNA half life, scored with R on mRNABench HL.; caveats: Author-reported numbers, source checked but not independently reproduced.; Metrics alternate between AUPRC on a percentage scale and Pearson R, so figures in different columns are on different scales.; Each row is the best checkpoint of a model family, chosen by the authors, not the family's average.; review: method: automated_source_review; date: 2026-09-18
Related records

Suggest a correction