rewire.it
Task

mRNABench MRL: Mean ribosome load

Mean ribosome load. Scored with R on mRNABench MRL. A linear probe over frozen embeddings, scored as the mean over ten random seeds.

21 evaluations · 21 metric rows

Overview

Mean ribosome load. Scored with R on mRNABench MRL. 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.

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.

Published comparisons

Explore the results reported under one evaluation protocol. Each figure keeps its source, dataset and metric together; it is not a ranking across studies. The pooled view gathers every source table that reports the same metric and names what it does not hold constant.

mRNABench MRL: Mean ribosome load

pearson_r (correlation) · Higher values are better for this metric.

Every method mRNABench reports on Mean ribosome load, scored with R on mRNABench MRL.

Evaluation protocol · mRNABench MRL (mRNABench split)

  1. Naive Baseline · Method · Author-reported evaluation0.14
  2. Naive Mamba · Method · Author-reported evaluation0.19
  3. Supervised CNN · Method · Author-reported evaluation0.45
  4. 3UTRBERT · Configuration · Author-reported evaluation0.19
  5. AIDO.RNA · Configuration · Author-reported evaluation0.38
  6. DNABERT-S · Configuration · Author-reported evaluation0.29
  7. DNABERT2 · Configuration · Author-reported evaluation0.29
  8. ERNIE-RNA · Configuration · Author-reported evaluation0.33
  9. Evo1 · Configuration · Author-reported evaluation0.19
  10. Evo2 · Configuration · Author-reported evaluation0.45
  11. Helix-mRNA · Configuration · Author-reported evaluation0.24
  12. HyenaDNA · Configuration · Author-reported evaluation0.28
  13. NT · Configuration · Author-reported evaluation0.34
  14. Orthrus · Configuration · Author-reported evaluation0.43
  15. RNA-FM · Configuration · Author-reported evaluation0.29
  16. RNA-MSM · Configuration · Author-reported evaluation0.16
  17. RNABERT · Configuration · Author-reported evaluation0.06
  18. RNAErnie · Configuration · Author-reported evaluation0.14
  19. RiNALMo · Configuration · Author-reported evaluation0.42
  20. SpliceBERT · Configuration · Author-reported evaluation0.34
  21. UTR-LM · Configuration · Author-reported evaluation0.25

Source order is preserved. Plotted marks show point estimates; uncertainty, where reported, is retained in the printed values and table. Differences do not establish statistical significance.

mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, column(MRL)
Values, uncertainty and evidence
pearson_r: original source values
Tested entityPrinted valueUncertaintyEvidence
Naive Baseline · Method0.14 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(Naive Baseline), column(MRL)
Naive Mamba · Method0.19 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(Naive Mamba), column(MRL)
Supervised CNN · Method0.45 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(Supervised CNN), column(MRL)
3UTRBERT · Configuration0.19 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(3UTRBERT), column(MRL)
AIDO.RNA · Configuration0.38 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(AIDO.RNA), column(MRL)
DNABERT-S · Configuration0.29 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(DNABERT-S), column(MRL)
DNABERT2 · Configuration0.29 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(DNABERT2), column(MRL)
ERNIE-RNA · Configuration0.33 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(ERNIE-RNA), column(MRL)
Evo1 · Configuration0.19 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(Evo1), column(MRL)
Evo2 · Configuration0.45 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(Evo2), column(MRL)
Helix-mRNA · Configuration0.24 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(Helix-mRNA), column(MRL)
HyenaDNA · Configuration0.28 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(HyenaDNA), column(MRL)
NT · Configuration0.34 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(NT), column(MRL)
Orthrus · Configuration0.43 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(Orthrus), column(MRL)
RNA-FM · Configuration0.29 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RNA-FM), column(MRL)
RNA-MSM · Configuration0.16 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RNA-MSM), column(MRL)
RNABERT · Configuration0.06 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RNABERT), column(MRL)
RNAErnie · Configuration0.14 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RNAErnie), column(MRL)
RiNALMo · Configuration0.42 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RiNALMo), column(MRL)
SpliceBERT · Configuration0.34 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(SpliceBERT), column(MRL)
UTR-LM · Configuration0.25 correlationNot reportedAuthor-reported evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(UTR-LM), column(MRL)
Scope and limitations
  • 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.

Source transcription and grouping reviewed by automated source review on 2026-09-18. These experiments were not independently reproduced by rewire.

Tested entities and results

Release 2026-09-17-134cd1815de8 · 21 evaluations · 21 metric rows. Different protocols are not a single leaderboard. Where several source tables report the same metric, the published comparisons above offer a pooled view that names what it does not hold constant.

Results grouped by the exact reported evaluation
Metric and findingCoverage and uncertaintyEvidence
3UTRBERT on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.19 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(3UTRBERT), column(MRL)

Source checking is not independent reproduction.

AIDO.RNA on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.38 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(AIDO.RNA), column(MRL)

Source checking is not independent reproduction.

DNABERT-S on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.29 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(DNABERT-S), column(MRL)

Source checking is not independent reproduction.

DNABERT2 on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.29 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(DNABERT2), column(MRL)

Source checking is not independent reproduction.

ERNIE-RNA on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.33 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(ERNIE-RNA), column(MRL)

Source checking is not independent reproduction.

Evo1 on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.19 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(Evo1), column(MRL)

Source checking is not independent reproduction.

Evo2 on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.45 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(Evo2), column(MRL)

Source checking is not independent reproduction.

Helix-mRNA on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.24 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(Helix-mRNA), column(MRL)

Source checking is not independent reproduction.

HyenaDNA on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.28 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(HyenaDNA), column(MRL)

Source checking is not independent reproduction.

Naive Baseline on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.14 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(Naive Baseline), column(MRL)

Source checking is not independent reproduction.

Naive Mamba on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.19 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(Naive Mamba), column(MRL)

Source checking is not independent reproduction.

NT on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.34 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(NT), column(MRL)

Source checking is not independent reproduction.

Orthrus on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.43 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(Orthrus), column(MRL)

Source checking is not independent reproduction.

RiNALMo on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.42 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RiNALMo), column(MRL)

Source checking is not independent reproduction.

RNA-FM on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.29 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RNA-FM), column(MRL)

Source checking is not independent reproduction.

RNA-MSM on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.16 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RNA-MSM), column(MRL)

Source checking is not independent reproduction.

RNABERT on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.06 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RNABERT), column(MRL)

Source checking is not independent reproduction.

RNAErnie on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.14 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RNAErnie), column(MRL)

Source checking is not independent reproduction.

SpliceBERT on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.34 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(SpliceBERT), column(MRL)

Source checking is not independent reproduction.

Supervised CNN on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.45 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(Supervised CNN), column(MRL)

Source checking is not independent reproduction.

UTR-LM on mRNABench MRL: Mean ribosome load

A linear probe over frozen embeddings, scored as the mean over ten random seeds.

Author-reported evaluation · Evaluation metadata: source checked

0.25 pearson_r

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(UTR-LM), column(MRL)

Source checking is not 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 2026-09-17-134cd1815de8
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(MRL)

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-mrl

Source artifact SHA-256: 79f6264ee883535203c63a313547e7c57baa85585f76b42f8d899eb17fb7e600

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Sources and history

Release 2026-09-17-134cd1815de8 · Record review: source checked

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

Stable ID: mrnabench-task-mrl

areas
rna-transcriptomes
tasks
Mean ribosome load
metric
R
metric direction
higher
dataset
mRNABench MRL
protocol
A linear probe over frozen embeddings, scored as the mean over ten random seeds.
source locator
Table 2, column(MRL)
comparison panels
id: mrnabench-panel-mrl; title: mRNABench MRL: Mean ribosome load; protocol id: mrnabench-task-mrl; dataset id: mrnabench-dataset-mrnabench-mrl; metric: pearson_r; unit: correlation; direction: higher; result ids: mrnabench-result-naive-baseline-mrl-pearson-r; mrnabench-result-naive-mamba-mrl-pearson-r; mrnabench-result-supervised-cnn-mrl-pearson-r; mrnabench-result-3utrbert-mrl-pearson-r; mrnabench-result-aido-rna-mrl-pearson-r; mrnabench-result-dnabert-s-mrl-pearson-r; mrnabench-result-dnabert2-mrl-pearson-r; mrnabench-result-ernie-rna-mrl-pearson-r; mrnabench-result-evo1-mrl-pearson-r; mrnabench-result-evo2-mrl-pearson-r; mrnabench-result-helix-mrna-mrl-pearson-r; mrnabench-result-hyenadna-mrl-pearson-r; mrnabench-result-nt-mrl-pearson-r; mrnabench-result-orthrus-mrl-pearson-r; mrnabench-result-rna-fm-mrl-pearson-r; mrnabench-result-rna-msm-mrl-pearson-r; mrnabench-result-rnabert-mrl-pearson-r; mrnabench-result-rnaernie-mrl-pearson-r; mrnabench-result-rinalmo-mrl-pearson-r; mrnabench-result-splicebert-mrl-pearson-r; mrnabench-result-utr-lm-mrl-pearson-r; source ids: expansion-p3-mrnabench-2025; source locator: Table 2, column(MRL); context: Every method mRNABench reports on Mean ribosome load, scored with R on mRNABench MRL.; 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