mRNABench variant probes MRL-MPRA: Mean ribosome load on an MPRA library

Overview

Mean ribosome load on an MPRA library. Scored with Pearson R on mRNABench MRL MPRA (mRNABench split). Frozen transcript representations with task-specific linear probes, or named supervised/naive controls. Homology splits where possible; random splits for MRL-MPRA, MRL-HL-Pair and VEP. Reported mean over ten splits; Appendix C enumerates nine seeds. Table captions say ten random splits, while Methods specify homology splits where possible. This source ambiguity and the nine explicitly listed seeds are retained; exact split manifests remain unextracted. Appendix C uses micro-averaged multilabel metrics.

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.

Evaluation scope and datasetMetric and reported setup

mRNABench variant probes MRL-MPRA: Mean ribosome load on an MPRA library

pearson_r (correlation) · Higher values are better.

Every method mRNABench variant probes reports on Mean ribosome load on an MPRA library, scored with Pearson R on mRNABench MRL MPRA (mRNABench split).

mRNABench variant probes MRL-MPRA: Mean ribosome load on an MPRA library · mRNABench MRL MPRA (mRNABench split)

Evidence origin: Author-reported evaluation. Numerical source review does not establish independent reproduction.

mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 6 (XML T3), MRL-MPRA column; Methods S17/S18; Appendix C (APP3)

These are configuration-level details of the experiment set summarized by the paper’s Table 2; they are not new independent experiments.

All comparison limitations (5)

These are configuration-level details of the experiment set summarized by the paper’s Table 2; they are not new independent experiments.
Tables report means over ten splits and 95% confidence intervals. Appendix C lists only nine seeds; the missing seed is not inferred.
Two localization columns are excluded because Table 2 and Table 5 disagree about their metric.
Supervised CNN and naive feature controls are retained; not every method is a pretrained model.
Table captions say ten random splits, while Methods specify homology splits where possible. This source ambiguity and the nine explicitly listed seeds are retained; exact split manifests remain unextracted.

Automated source review: 2026-09-23.

Find a tested model or method

No unavailable values; missing scores remain labelled and are never plotted as zero.

Showing 12 of 50 matching rows.

Zoom to observed range

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.

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

mRNABench

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

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

Author-reported evaluations: 50

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Training-set mean where supervised fitting is permitted

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Simple features with train-only ridge regression

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV · Model evaluation matrix · Source table · Release and checksums

Coverage is derived from release 2026-09-23-2b89723c6dd9. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run instructions

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

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 2026-09-23-2b89723c6dd9
Property and statement	Original source and location	Review and provenance
Relationship: part of discovery-benchmark-mrnabench Individual claims	mRNABench: A curated benchmark for mature mRNA property and function prediction Original source ↗ Table 6 (XML T3), MRL-MPRA column; Methods S17/S18; Appendix C (APP3) Version: preprint archived 2025-07-08 Retrieved: 2026-09-16T10:41:16.497221+00:00	source checked automated source review · 2026-09-23 Audit details Primary-source transcription with no human sign-off and no independent reproduction. Field: `links:part_of:discovery-benchmark-mrnabench` Claim: mrnabench-variants-2025-association-mrl-mpra 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 2026-09-23-2b89723c6dd9 · Record review: source checked

1 source records and release history

mRNABench: A curated benchmark for mature mRNA property and function prediction · Original source · preprint archived 2025-07-08

Download this release

Technical metadata and extraction receipts

Stable ID: mrnabench-variants-2025-task-mrl-mpra

areas: rna-transcriptomics
tasks: Mean ribosome load on an MPRA library
metric: Pearson R
metric direction: higher
dataset: mRNABench MRL MPRA (mRNABench split)
protocol: Frozen transcript representations with task-specific linear probes, or named supervised/naive controls. Homology splits where possible; random splits for MRL-MPRA, MRL-HL-Pair and VEP. Reported mean over ten splits; Appendix C enumerates nine seeds. Table captions say ten random splits, while Methods specify homology splits where possible. This source ambiguity and the nine explicitly listed seeds are retained; exact split manifests remain unextracted. Appendix C uses micro-averaged multilabel metrics.
source locator: Table 6 (XML T3), MRL-MPRA column; Methods S17/S18; Appendix C (APP3)
comparison panels: id: mrnabench-variants-2025-panel-mrl-mpra; title: mRNABench variant probes MRL-MPRA: Mean ribosome load on an MPRA library; protocol id: mrnabench-variants-2025-task-mrl-mpra; dataset id: mrnabench-dataset-mrnabench-mrl-mpra; metric: pearson_r; unit: correlation; direction: higher; result ids: mrnabench-variants-2025-result-aido-rna-1b600m-mrl-mpra-pearson-r; mrnabench-variants-2025-result-aido-rna-1b600m-cds-mrl-mpra-pearson-r; mrnabench-variants-2025-result-aido-rna-650m-mrl-mpra-pearson-r; mrnabench-variants-2025-result-aido-rna-650m-cds-mrl-mpra-pearson-r; mrnabench-variants-2025-result-dnabert-s-mrl-mpra-pearson-r; mrnabench-variants-2025-result-dnabert2-mrl-mpra-pearson-r; mrnabench-variants-2025-result-ernierna-mrl-mpra-pearson-r; mrnabench-variants-2025-result-ernierna-ss-mrl-mpra-pearson-r; mrnabench-variants-2025-result-evo-1-131k-base-mrl-mpra-pearson-r; mrnabench-variants-2025-result-evo-1-8k-base-mrl-mpra-pearson-r; mrnabench-variants-2025-result-evo-1-5-8k-base-mrl-mpra-pearson-r; mrnabench-variants-2025-result-evo2-1b-base-mrl-mpra-pearson-r; mrnabench-variants-2025-result-evo2-7b-mrl-mpra-pearson-r; mrnabench-variants-2025-result-evo2-7b-base-mrl-mpra-pearson-r; mrnabench-variants-2025-result-helix-mrna-mrl-mpra-pearson-r; mrnabench-variants-2025-result-hyenadna-large-1m-mrl-mpra-pearson-r; mrnabench-variants-2025-result-hyenadna-medium-160k-mrl-mpra-pearson-r; mrnabench-variants-2025-result-hyenadna-medium-450k-mrl-mpra-pearson-r; mrnabench-variants-2025-result-hyenadna-small-32k-mrl-mpra-pearson-r; mrnabench-variants-2025-result-hyenadna-tiny-16k-d128-mrl-mpra-pearson-r; mrnabench-variants-2025-result-mrna-fm-mrl-mpra-pearson-r; mrnabench-variants-2025-result-naive-4-mrl-mpra-pearson-r; mrnabench-variants-2025-result-naive-6-mrl-mpra-pearson-r; mrnabench-variants-2025-result-naive-mamba-mrl-mpra-pearson-r; mrnabench-variants-2025-result-nt-2-5b-1000g-mrl-mpra-pearson-r; mrnabench-variants-2025-result-nt-2-5b-multi-species-mrl-mpra-pearson-r; mrnabench-variants-2025-result-nt-500m-1000g-mrl-mpra-pearson-r; mrnabench-variants-2025-result-nt-500m-human-ref-mrl-mpra-pearson-r; mrnabench-variants-2025-result-nt-v2-100m-multi-species-mrl-mpra-pearson-r; mrnabench-variants-2025-result-nt-v2-250m-multi-species-mrl-mpra-pearson-r; mrnabench-variants-2025-result-nt-v2-500m-multi-species-mrl-mpra-pearson-r; mrnabench-variants-2025-result-nt-v2-50m-multi-species-mrl-mpra-pearson-r; mrnabench-variants-2025-result-orthrus-base-4-mrl-mpra-pearson-r; mrnabench-variants-2025-result-orthrus-large-6-mrl-mpra-pearson-r; mrnabench-variants-2025-result-orthrus-mlm-mrl-mpra-pearson-r; mrnabench-variants-2025-result-rinalmo-mrl-mpra-pearson-r; mrnabench-variants-2025-result-rna-fm-mrl-mpra-pearson-r; mrnabench-variants-2025-result-rnabert-mrl-mpra-pearson-r; mrnabench-variants-2025-result-rnaernie-mrl-mpra-pearson-r; mrnabench-variants-2025-result-rnamsm-mrl-mpra-pearson-r; mrnabench-variants-2025-result-splicebert-h-510nt-mrl-mpra-pearson-r; mrnabench-variants-2025-result-splicebert-v-1024nt-mrl-mpra-pearson-r; mrnabench-variants-2025-result-splicebert-v-510nt-mrl-mpra-pearson-r; mrnabench-variants-2025-result-supervised-cnn-mrl-mpra-pearson-r; mrnabench-variants-2025-result-utrbert-3mer-mrl-mpra-pearson-r; mrnabench-variants-2025-result-utrbert-4mer-mrl-mpra-pearson-r; mrnabench-variants-2025-result-utrbert-5mer-mrl-mpra-pearson-r; mrnabench-variants-2025-result-utrbert-6mer-mrl-mpra-pearson-r; mrnabench-variants-2025-result-utrlm-mrl-mrl-mpra-pearson-r; mrnabench-variants-2025-result-utrlm-te-el-mrl-mpra-pearson-r; source ids: expansion-p3-mrnabench-2025; source locator: Table 6 (XML T3), MRL-MPRA column; Methods S17/S18; Appendix C (APP3); context: Every method mRNABench variant probes reports on Mean ribosome load on an MPRA library, scored with Pearson R on mRNABench MRL MPRA (mRNABench split).; caveats: These are configuration-level details of the experiment set summarized by the paper’s Table 2; they are not new independent experiments.; Tables report means over ten splits and 95% confidence intervals. Appendix C lists only nine seeds; the missing seed is not inferred.; Two localization columns are excluded because Table 2 and Table 5 disagree about their metric.; Supervised CNN and naive feature controls are retained; not every method is a pretrained model.; Table captions say ten random splits, while Methods specify homology splits where possible. This source ambiguity and the nine explicitly listed seeds are retained; exact split manifests remain unextracted.; review: method: automated_source_review; date: 2026-09-23
entity level: protocol

Related records