rewirebio.iobenchmarks
Source

FramePool 2021 primary article

2021 journal article XML; PMC8136849.1

DOI: 10.1371/journal.pcbi.1008982Original source

What this source contributed

Records in this release that cite this source. A record can cite several sources.

Results

Values as the source printed them. Compare results only under compatible protocols, datasets and metrics.

Model or configurationMetricValueDatasetEvaluation
3mer_random_forestPearson0.616 unitlessSample MPRA Random 25-100nt3mer_random_forest random-25-100nt
3mer_random_forestPearson0.732 unitlessSample MPRA Random 50nt3mer_random_forest random-50nt
4mer_random_forestPearson0.647 unitlessSample MPRA Random 25-100nt4mer_random_forest random-25-100nt
4mer_random_forestPearson0.75 unitlessSample MPRA Random 50nt4mer_random_forest random-50nt
5mer_frame_forestPearson0.73 unitlessSample MPRA Random 25-100nt5mer_frame_forest random-25-100nt
5mer_frame_forestPearson0.803 unitlessSample MPRA Random 50nt5mer_frame_forest random-50nt
frame_forest (4mer)Pearson0.772 unitlessSample MPRA Random 25-100ntframe_forest (4mer) random-25-100nt
frame_forest (4mer)Pearson0.877 unitlessSample MPRA Random 50ntframe_forest (4mer) random-50nt
frame_forest_hyperoptPearson0.778 unitlessSample MPRA Random 25-100ntframe_forest_hyperopt random-25-100nt
frame_forest_hyperoptPearson0.876 unitlessSample MPRA Random 50ntframe_forest_hyperopt random-50nt
FramePool 50Pearson0.871 unitlessSample MPRA Human 25-100ntFramePool 50 Human 25-100nt
FramePool 50Pearson0.882 unitlessSample MPRA Human 50ntFramePool 50 Human 50nt
FramePool 50Pearson0.901 unitlessSample MPRA Random 25-100ntFramePool 50 Random 25-100nt
FramePool 50Pearson0.964 unitlessSample MPRA Random 50ntFramePool 50 Random 50nt
FramePool 100Pearson0.884 unitlessSample MPRA Human 25-100ntFramePool 100 Human 25-100nt
FramePool 100Pearson0.839 unitlessSample MPRA Human 50ntFramePool 100 Human 50nt
FramePool 100Pearson0.903 unitlessSample MPRA Random 25-100ntFramePool 100 Random 25-100nt
FramePool 100Pearson0.929 unitlessSample MPRA Random 50ntFramePool 100 Random 50nt
FramePool CombinedPearson0.894 unitlessSample MPRA Human 25-100ntFramePool Combined Human 25-100nt
FramePool CombinedPearson0.867 unitlessSample MPRA Human 50ntFramePool Combined Human 50nt
FramePool CombinedPearson0.914 unitlessSample MPRA Random 25-100ntFramePool Combined Random 25-100nt
FramePool CombinedPearson0.954 unitlessSample MPRA Random 50ntFramePool Combined Random 50nt
Optimus 50Pearson0.7 unitlessSample MPRA Human 25-100ntOptimus 50 Human 25-100nt
Optimus 50Pearson0.889 unitlessSample MPRA Human 50ntOptimus 50 Human 50nt
Optimus 50Pearson0.743 unitlessSample MPRA Random 25-100ntOptimus 50 Random 25-100nt
Optimus 50Pearson0.966 unitlessSample MPRA Random 50ntOptimus 50 Random 50nt
Optimus 100Pearson0.882 unitlessSample MPRA Human 25-100ntOptimus 100 Human 25-100nt
Optimus 100Pearson0.852 unitlessSample MPRA Human 50ntOptimus 100 Human 50nt
Optimus 100Pearson0.915 unitlessSample MPRA Random 25-100ntOptimus 100 Random 25-100nt
Optimus 100Pearson0.938 unitlessSample MPRA Random 50ntOptimus 100 Random 50nt

Claims

Statements this source supports, each with where in the source it was checked.

  • 3mer_random_forest family identity: Configuration of k-mer count random forest (S1/S4 Table; Methods Framepool model and Model training; S7–S8 figure captions)
  • 3mer_random_forest: facets.method_types: Facets: method types ["supervised_machine_learning"] (FramePool Methods: "we also trained random forest models which use k-mer counts as input features")
  • 4mer_random_forest family identity: Configuration of k-mer count random forest (S1/S4 Table; Methods Framepool model and Model training; S7–S8 figure captions)
  • 4mer_random_forest: facets.method_types: Facets: method types ["supervised_machine_learning"] (FramePool Methods: "we also trained random forest models which use k-mer counts as input features")
  • 5mer_frame_forest family identity: Configuration of Frame-aware k-mer random forest (S1/S4 Table; Methods Framepool model and Model training; S7–S8 figure captions)
  • 5mer_frame_forest: facets.method_types: Facets: method types ["supervised_machine_learning"] (FramePool Methods: "we also trained random forest models which use k-mer counts as input features")
  • Baseline: Set baselines for UTR translation experiments: Baseline k-mer random forests (uc20260930-source-framepool-2021: Methods 'Random forest models' (random forests on k-mer counts against deep learning))
  • Evidence summary: Set baselines for UTR translation experiments: Summary Only two sequence-only controls have been measured on the target split, both in Rewire's own runs, so there is no model comparison on it yet. On the 15,003 held-out records of the mRNABench designed-reporter test split, the composition ridge control reached a mean squared error of 1.914 against 2.366 for the training-mean control, and a Pearson correlation of 0.437; the training-mean control has no defined correlation, because its prediction is constant. The published FramePool panels are the only model comparison recorded here: neural models (FramePool and Optimus) reached Pearson 0.743 to 0.966 on the two random-sequence panels and 0.700 to 0.894 on the two human panels, while k-mer random forests, which were evaluated on the random panels only, reached 0.616 to 0.877. Those values are reported in the FramePool study on its own library, one split per panel with no uncertainty interval, and they are not measured on the designed-reporter split, so they are not baselines for it. Both Rewire controls are single runs on one split with no seed variability, and their automated audit checks the run itself, not a published score. (rewire-local-20260920 run outputs: metrics.mse and metrics.pearson for the composition and training-mean controls; uc20260930-source-framepool-s1: S1 Table rows Random 50nt, Random 25-100nt, Human 50nt and Human 25-100nt; uc20260930-source-framepool-s4: S4 Table columns B and C)
  • frame_forest (4mer) family identity: Configuration of Frame-aware k-mer random forest (S1/S4 Table; Methods Framepool model and Model training; S7–S8 figure captions)
  • frame_forest (4mer): facets.method_types: Facets: method types ["supervised_machine_learning"] (FramePool Methods: "we also trained random forest models which use k-mer counts as input features")
  • frame_forest_hyperopt family identity: Configuration of Frame-aware k-mer random forest (S1/S4 Table; Methods Framepool model and Model training; S7–S8 figure captions)
  • frame_forest_hyperopt: facets.method_types: Facets: method types ["supervised_machine_learning"] (FramePool Methods: "we also trained random forest models which use k-mer counts as input features")
  • Frame-aware k-mer random forest: description: Description Random forest whose input is the k-mer counts of the sequence computed separately for each of the three reading frames, trained on the same MPRA training set as FramePool50. (uc20260930-source-framepool-2021: Methods, Random forest models ('the framed_forest model. This random forest takes as input the k-mer-counts for each frame (giving a vector of length 3*(4^k))'); S7 Fig caption)
  • FramePool 50 family identity: Configuration of FramePool (S1/S4 Table; Methods Framepool model and Model training; S7–S8 figure captions)
  • FramePool 50: facets.method_types: Facets: method types ["supervised_machine_learning"] (FramePool Methods: convolutional networks trained on the MPRA library)
  • FramePool 100 family identity: Configuration of FramePool (S1/S4 Table; Methods Framepool model and Model training; S7–S8 figure captions)
  • FramePool 100: facets.method_types: Facets: method types ["supervised_machine_learning"] (FramePool Methods: convolutional networks trained on the MPRA library)
  • FramePool Combined family identity: Configuration of FramePool (S1/S4 Table; Methods Framepool model and Model training; S7–S8 figure captions)
  • FramePool Combined: facets.method_types: Facets: method types ["supervised_machine_learning"] (FramePool Methods: convolutional networks trained on the MPRA library)
  • FramePool study MRL: Human 25-100nt study membership: Part of FramePool translation-prediction study (Supplementary Tables S1 and S4; Model training and testing)
  • FramePool study MRL: Human 50nt study membership: Part of FramePool translation-prediction study (Supplementary Tables S1 and S4; Model training and testing)
  • FramePool study MRL: Random 25-100nt study membership: Part of FramePool translation-prediction study (Supplementary Tables S1 and S4; Model training and testing)
  • FramePool study MRL: Random 50nt study membership: Part of FramePool translation-prediction study (Supplementary Tables S1 and S4; Model training and testing)
  • FramePool: description: Description Neural network with frame pooling that predicts mean ribosome load, a proxy for translation efficiency, from 5' UTR sequences of any length. (uc20260930-source-framepool-2021: Abstract; Introduction paragraphs 5-7)
  • k-mer count random forest: description: Description Random forest whose input is a fixed-length vector of the sequence's 3-mer or 4-mer counts, with no reading-frame information, trained on the same MPRA training set as FramePool50. (uc20260930-source-framepool-2021: Methods, Random forest models ('random forest models which use k-mer counts as input features ... 3mer_random_forest and 4mer_random_forest'); S7 Fig caption ('offers no frame information'))

Models, benchmarks and other records

Models (2)

Methods (2)

Configurations (10)

Benchmarks (1)

Protocols (4)

Dataset subsets (4)

Baselines (5)

Evaluations (30)

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.

15 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
Artifact SHA-256
689af3ecab7b5a928eacc5a76d965960708cbb253fc7cdeae463b16d30ffd2e3
Source metadata
FramePool 2021 primary article

Original source ↗

No field-specific location recorded

Version: 2021 journal article XML; PMC8136849.1
Retrieved: 2026-09-30

catalogued

No individual claim review recorded

Audit details

Field: attributes.artifact_sha256

Source artifact SHA-256: 689af3ecab7b5a928eacc5a76d965960708cbb253fc7cdeae463b16d30ffd2e3

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Artifact url
https://www.ebi.ac.uk/europepmc/webservices/rest/PMC8136849/fullTextXML
Source metadata
FramePool 2021 primary article

Original source ↗

No field-specific location recorded

Version: 2021 journal article XML; PMC8136849.1
Retrieved: 2026-09-30

catalogued

No individual claim review recorded

Audit details

Field: attributes.artifact_url

Source artifact SHA-256: 689af3ecab7b5a928eacc5a76d965960708cbb253fc7cdeae463b16d30ffd2e3

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Doi
10.1371/journal.pcbi.1008982
Source metadata
FramePool 2021 primary article

Original source ↗

No field-specific location recorded

Version: 2021 journal article XML; PMC8136849.1
Retrieved: 2026-09-30

catalogued

No individual claim review recorded

Audit details

Field: attributes.doi

Source artifact SHA-256: 689af3ecab7b5a928eacc5a76d965960708cbb253fc7cdeae463b16d30ffd2e3

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Retrieved at
2026-09-30
Source metadata
FramePool 2021 primary article

Original source ↗

No field-specific location recorded

Version: 2021 journal article XML; PMC8136849.1
Retrieved: 2026-09-30

catalogued

No individual claim review recorded

Audit details

Field: attributes.retrieved_at

Source artifact SHA-256: 689af3ecab7b5a928eacc5a76d965960708cbb253fc7cdeae463b16d30ffd2e3

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Review method
1 values
  • automated-source-review
Source metadata
FramePool 2021 primary article

Original source ↗

No field-specific location recorded

Version: 2021 journal article XML; PMC8136849.1
Retrieved: 2026-09-30

catalogued

No individual claim review recorded

Audit details

Field: attributes.review.method

Source artifact SHA-256: 689af3ecab7b5a928eacc5a76d965960708cbb253fc7cdeae463b16d30ffd2e3

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Review: scope
Only explicitly extracted table rows and protocol methods; no execution.
Source metadata
FramePool 2021 primary article

Original source ↗

No field-specific location recorded

Version: 2021 journal article XML; PMC8136849.1
Retrieved: 2026-09-30

catalogued

No individual claim review recorded

Audit details

Field: attributes.review.scope

Source artifact SHA-256: 689af3ecab7b5a928eacc5a76d965960708cbb253fc7cdeae463b16d30ffd2e3

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Url
https://www.ebi.ac.uk/europepmc/webservices/rest/PMC8136849/fullTextXML
Source metadata
FramePool 2021 primary article

Original source ↗

No field-specific location recorded

Version: 2021 journal article XML; PMC8136849.1
Retrieved: 2026-09-30

catalogued

No individual claim review recorded

Audit details

Field: attributes.url

Source artifact SHA-256: 689af3ecab7b5a928eacc5a76d965960708cbb253fc7cdeae463b16d30ffd2e3

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Version
2021 journal article XML; PMC8136849.1
Source metadata
FramePool 2021 primary article

Original source ↗

No field-specific location recorded

Version: 2021 journal article XML; PMC8136849.1
Retrieved: 2026-09-30

catalogued

No individual claim review recorded

Audit details

Field: attributes.version

Source artifact SHA-256: 689af3ecab7b5a928eacc5a76d965960708cbb253fc7cdeae463b16d30ffd2e3

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Description
Primary source retrieved and inspected for this audit.
Source metadata
FramePool 2021 primary article

Original source ↗

No field-specific location recorded

Version: 2021 journal article XML; PMC8136849.1
Retrieved: 2026-09-30

catalogued

No individual claim review recorded

Audit details

Field: description

Source artifact SHA-256: 689af3ecab7b5a928eacc5a76d965960708cbb253fc7cdeae463b16d30ffd2e3

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Search facets
None recorded
Source metadata
FramePool 2021 primary article

Original source ↗

No field-specific location recorded

Version: 2021 journal article XML; PMC8136849.1
Retrieved: 2026-09-30

catalogued

No individual claim review recorded

Audit details

Field: facets

Source artifact SHA-256: 689af3ecab7b5a928eacc5a76d965960708cbb253fc7cdeae463b16d30ffd2e3

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

How to read the evidence

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: source checked

Primary source retrieved and inspected for this audit.

Release history

No supporting source is linked yet.

Read original source

Download this release (gzip)
Technical metadata and extraction receipts

Stable ID: uc20260930-source-framepool-2021

url
https://www.ebi.ac.uk/europepmc/webservices/rest/PMC8136849/fullTextXML
artifact url
https://www.ebi.ac.uk/europepmc/webservices/rest/PMC8136849/fullTextXML
retrieved at
2026-09-30
version
2021 journal article XML; PMC8136849.1
artifact sha256
689af3ecab7b5a928eacc5a76d965960708cbb253fc7cdeae463b16d30ffd2e3
doi
10.1371/journal.pcbi.1008982
review
method: automated-source-review; scope: Only explicitly extracted table rows and protocol methods; no execution.
Related records

    Suggest a correction