rewirebio.iobenchmarks
← Browse all sources
Source

PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

BMC Genomics · 2026 · Version of record, BMC Genomics 2026 (PMC13425921 JATS full text) · Peer-reviewed

DOI: 10.1186/s12864-026-12976-5Original 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.

ValueMetricModel or configurationDatasetEvaluation
-0.2294 ± 0.03 unitlessR² (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, fine-tuned)ESM-2 8M, the CLS token embedding, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M CLS finetuned: ACE2 binding R², Position-stratified split holding out whole mutated positions
0.5897 ± 0.03 unitlessR² (ACE2 binding; Random split over RBD mutants; the CLS token embedding, fine-tuned)ESM-2 8M, the CLS token embedding, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M CLS finetuned: ACE2 binding R², Random split over RBD mutants
1.9653 ± 0.03 unit-unreportedRMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, fine-tuned)ESM-2 8M, the CLS token embedding, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M CLS finetuned: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions
1.2194 ± 0.04 unit-unreportedRMSE (ACE2 binding; Random split over RBD mutants; the CLS token embedding, fine-tuned)ESM-2 8M, the CLS token embedding, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M CLS finetuned: ACE2 binding RMSE, Random split over RBD mutants
-0.1928 ± 0.02 unitlessR² (RBD expression; Position-stratified split holding out whole mutated positions; the CLS token embedding, fine-tuned)ESM-2 8M, the CLS token embedding, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M CLS finetuned: RBD expression R², Position-stratified split holding out whole mutated positions
0.5302 ± 0.03 unitlessR² (RBD expression; Random split over RBD mutants; the CLS token embedding, fine-tuned)ESM-2 8M, the CLS token embedding, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M CLS finetuned: RBD expression R², Random split over RBD mutants
1.1756 ± 0.01 unit-unreportedRMSE (RBD expression; Position-stratified split holding out whole mutated positions; the CLS token embedding, fine-tuned)ESM-2 8M, the CLS token embedding, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M CLS finetuned: RBD expression RMSE, Position-stratified split holding out whole mutated positions
0.6808 ± 0.02 unit-unreportedRMSE (RBD expression; Random split over RBD mutants; the CLS token embedding, fine-tuned)ESM-2 8M, the CLS token embedding, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M CLS finetuned: RBD expression RMSE, Random split over RBD mutants
-0.2018 ± 0.04 unitlessR² (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, frozen)ESM-2 8M, the CLS token embedding, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M CLS frozen: ACE2 binding R², Position-stratified split holding out whole mutated positions
0.5876 ± 0.07 unitlessR² (ACE2 binding; Random split over RBD mutants; the CLS token embedding, frozen)ESM-2 8M, the CLS token embedding, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M CLS frozen: ACE2 binding R², Random split over RBD mutants
1.9452 ± 0.04 unit-unreportedRMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, frozen)ESM-2 8M, the CLS token embedding, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M CLS frozen: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions
1.2191 ± 0.10 unit-unreportedRMSE (ACE2 binding; Random split over RBD mutants; the CLS token embedding, frozen)ESM-2 8M, the CLS token embedding, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M CLS frozen: ACE2 binding RMSE, Random split over RBD mutants
-0.0324 ± 0.05 unitlessR² (RBD expression; Position-stratified split holding out whole mutated positions; the CLS token embedding, frozen)ESM-2 8M, the CLS token embedding, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M CLS frozen: RBD expression R², Position-stratified split holding out whole mutated positions
0.5984 ± 0.07 unitlessR² (RBD expression; Random split over RBD mutants; the CLS token embedding, frozen)ESM-2 8M, the CLS token embedding, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M CLS frozen: RBD expression R², Random split over RBD mutants
1.0916 ± 0.02 unit-unreportedRMSE (RBD expression; Position-stratified split holding out whole mutated positions; the CLS token embedding, frozen)ESM-2 8M, the CLS token embedding, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M CLS frozen: RBD expression RMSE, Position-stratified split holding out whole mutated positions
0.6272 ± 0.05 unit-unreportedRMSE (RBD expression; Random split over RBD mutants; the CLS token embedding, frozen)ESM-2 8M, the CLS token embedding, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M CLS frozen: RBD expression RMSE, Random split over RBD mutants
0.0071 ± 0.05 unitlessR² (ACE2 binding; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, fine-tuned)ESM-2 8M, the mean over residue embeddings, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M Mean finetuned: ACE2 binding R², Position-stratified split holding out whole mutated positions
0.6225 ± 0.07 unitlessR² (ACE2 binding; Random split over RBD mutants; the mean over residue embeddings, fine-tuned)ESM-2 8M, the mean over residue embeddings, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M Mean finetuned: ACE2 binding R², Random split over RBD mutants
1.7688 ± 0.06 unit-unreportedRMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, fine-tuned)ESM-2 8M, the mean over residue embeddings, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M Mean finetuned: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions
1.1659 ± 0.10 unit-unreportedRMSE (ACE2 binding; Random split over RBD mutants; the mean over residue embeddings, fine-tuned)ESM-2 8M, the mean over residue embeddings, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M Mean finetuned: ACE2 binding RMSE, Random split over RBD mutants
0.1013 ± 0.06 unitlessR² (RBD expression; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, fine-tuned)ESM-2 8M, the mean over residue embeddings, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M Mean finetuned: RBD expression R², Position-stratified split holding out whole mutated positions
0.5545 ± 0.07 unitlessR² (RBD expression; Random split over RBD mutants; the mean over residue embeddings, fine-tuned)ESM-2 8M, the mean over residue embeddings, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M Mean finetuned: RBD expression R², Random split over RBD mutants
1.0213 ± 0.03 unit-unreportedRMSE (RBD expression; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, fine-tuned)ESM-2 8M, the mean over residue embeddings, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M Mean finetuned: RBD expression RMSE, Position-stratified split holding out whole mutated positions
0.6613 ± 0.05 unit-unreportedRMSE (RBD expression; Random split over RBD mutants; the mean over residue embeddings, fine-tuned)ESM-2 8M, the mean over residue embeddings, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M Mean finetuned: RBD expression RMSE, Random split over RBD mutants
0.0248 ± 0.01 unitlessR² (ACE2 binding; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, frozen)ESM-2 8M, the mean over residue embeddings, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M Mean frozen: ACE2 binding R², Position-stratified split holding out whole mutated positions
0.6794 ± 0.02 unitlessR² (ACE2 binding; Random split over RBD mutants; the mean over residue embeddings, frozen)ESM-2 8M, the mean over residue embeddings, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M Mean frozen: ACE2 binding R², Random split over RBD mutants
1.7519 ± 0.01 unit-unreportedRMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, frozen)ESM-2 8M, the mean over residue embeddings, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M Mean frozen: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions
1.0777 ± 0.04 unit-unreportedRMSE (ACE2 binding; Random split over RBD mutants; the mean over residue embeddings, frozen)ESM-2 8M, the mean over residue embeddings, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M Mean frozen: ACE2 binding RMSE, Random split over RBD mutants
0.0967 ± 0.02 unitlessR² (RBD expression; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, frozen)ESM-2 8M, the mean over residue embeddings, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M Mean frozen: RBD expression R², Position-stratified split holding out whole mutated positions
0.6576 ± 0.04 unitlessR² (RBD expression; Random split over RBD mutants; the mean over residue embeddings, frozen)ESM-2 8M, the mean over residue embeddings, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M Mean frozen: RBD expression R², Random split over RBD mutants
1.0221 ± 0.01 unit-unreportedRMSE (RBD expression; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, frozen)ESM-2 8M, the mean over residue embeddings, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M Mean frozen: RBD expression RMSE, Position-stratified split holding out whole mutated positions
0.5807 ± 0.03 unit-unreportedRMSE (RBD expression; Random split over RBD mutants; the mean over residue embeddings, frozen)ESM-2 8M, the mean over residue embeddings, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 8M Mean frozen: RBD expression RMSE, Random split over RBD mutants
-0.2675 ± 0.07 unitlessR² (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, fine-tuned)ESM-2 150M, the CLS token embedding, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 150M CLS finetuned: ACE2 binding R², Position-stratified split holding out whole mutated positions
0.5836 ± 0.28 unitlessR² (ACE2 binding; Random split over RBD mutants; the CLS token embedding, fine-tuned)ESM-2 150M, the CLS token embedding, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 150M CLS finetuned: ACE2 binding R², Random split over RBD mutants
2.0022 ± 0.04 unit-unreportedRMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, fine-tuned)ESM-2 150M, the CLS token embedding, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 150M CLS finetuned: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions
1.1639 ± 0.40 unit-unreportedRMSE (ACE2 binding; Random split over RBD mutants; the CLS token embedding, fine-tuned)ESM-2 150M, the CLS token embedding, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 150M CLS finetuned: ACE2 binding RMSE, Random split over RBD mutants
-0.3805 ± 0.04 unitlessR² (RBD expression; Position-stratified split holding out whole mutated positions; the CLS token embedding, fine-tuned)ESM-2 150M, the CLS token embedding, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 150M CLS finetuned: RBD expression R², Position-stratified split holding out whole mutated positions
0.3354 ± 0.45 unitlessR² (RBD expression; Random split over RBD mutants; the CLS token embedding, fine-tuned)ESM-2 150M, the CLS token embedding, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 150M CLS finetuned: RBD expression R², Random split over RBD mutants
1.2480 ± 0.02 unit-unreportedRMSE (RBD expression; Position-stratified split holding out whole mutated positions; the CLS token embedding, fine-tuned)ESM-2 150M, the CLS token embedding, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 150M CLS finetuned: RBD expression RMSE, Position-stratified split holding out whole mutated positions
0.7664 ± 0.26 unit-unreportedRMSE (RBD expression; Random split over RBD mutants; the CLS token embedding, fine-tuned)ESM-2 150M, the CLS token embedding, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 150M CLS finetuned: RBD expression RMSE, Random split over RBD mutants
-0.2449 ± 0.06 unitlessR² (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, frozen)ESM-2 150M, the CLS token embedding, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 150M CLS frozen: ACE2 binding R², Position-stratified split holding out whole mutated positions
0.5788 ± 0.14 unitlessR² (ACE2 binding; Random split over RBD mutants; the CLS token embedding, frozen)ESM-2 150M, the CLS token embedding, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 150M CLS frozen: ACE2 binding R², Random split over RBD mutants
1.9777 ± 0.03 unit-unreportedRMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, frozen)ESM-2 150M, the CLS token embedding, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 150M CLS frozen: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions
1.2167 ± 0.22 unit-unreportedRMSE (ACE2 binding; Random split over RBD mutants; the CLS token embedding, frozen)ESM-2 150M, the CLS token embedding, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 150M CLS frozen: ACE2 binding RMSE, Random split over RBD mutants
-0.0754 ± 0.04 unitlessR² (RBD expression; Position-stratified split holding out whole mutated positions; the CLS token embedding, frozen)ESM-2 150M, the CLS token embedding, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 150M CLS frozen: RBD expression R², Position-stratified split holding out whole mutated positions
0.5409 ± 0.08 unitlessR² (RBD expression; Random split over RBD mutants; the CLS token embedding, frozen)ESM-2 150M, the CLS token embedding, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 150M CLS frozen: RBD expression R², Random split over RBD mutants
1.1169 ± 0.02 unit-unreportedRMSE (RBD expression; Position-stratified split holding out whole mutated positions; the CLS token embedding, frozen)ESM-2 150M, the CLS token embedding, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 150M CLS frozen: RBD expression RMSE, Position-stratified split holding out whole mutated positions
0.6709 ± 0.06 unit-unreportedRMSE (RBD expression; Random split over RBD mutants; the CLS token embedding, frozen)ESM-2 150M, the CLS token embedding, not fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 150M CLS frozen: RBD expression RMSE, Random split over RBD mutants
-0.0080 ± 0.00 unitlessR² (ACE2 binding; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, fine-tuned)ESM-2 150M, the mean over residue embeddings, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 150M Mean finetuned: ACE2 binding R², Position-stratified split holding out whole mutated positions
0.7461 ± 0.08 unitlessR² (ACE2 binding; Random split over RBD mutants; the mean over residue embeddings, fine-tuned)ESM-2 150M, the mean over residue embeddings, fine-tuned (PRIME)SARS-CoV-2 RBD mutant binding and expression measurementsESM-2 150M Mean finetuned: ACE2 binding R², Random split over RBD mutants

Models, benchmarks and other records

Models (1)

Methods (1)

Configurations (21)

Benchmarks (1)

Protocols (8)

Datasets (1)

Evaluations (168)

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.

27 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statementOriginal source and locationReview and provenance
attributes.artifact_sha256
f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971
Source metadata		PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

Original source ↗

No field-specific location recorded

Version: Version of record, BMC Genomics 2026 (PMC13425921 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.artifact_sha256

Source artifact SHA-256: f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971

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

Inspected artifact

Artifact url
https://www.ebi.ac.uk/europepmc/webservices/rest/PMC13425921/fullTextXML
Source metadata		PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

Original source ↗

No field-specific location recorded

Version: Version of record, BMC Genomics 2026 (PMC13425921 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.artifact_url

Source artifact SHA-256: f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971

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

Inspected artifact

Doi
10.1186/s12864-026-12976-5
Source metadata		PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

Original source ↗

No field-specific location recorded

Version: Version of record, BMC Genomics 2026 (PMC13425921 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.doi

Source artifact SHA-256: f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971

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

Inspected artifact

Licence
CC BY 4.0
Source metadata		PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

Original source ↗

No field-specific location recorded

Version: Version of record, BMC Genomics 2026 (PMC13425921 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.licence

Source artifact SHA-256: f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971

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

Inspected artifact

Limitations
3 values
  • Table 1 only. The lineage-clustering, temporal-dynamics and attention analyses are figures and were not extracted.
  • The One-Hot Mean row has no embedding or fine-tuning setting; its three leading cells repeat the row label in the XML and are recorded as a single baseline configuration.
  • The plus-minus values are the standard deviation across random seeds (Table 1 footnote, pointing at Supplementary Table 6, which was not retrieved). Table 1 uses five folds and the Methods name three seeds, so the sample count behind each spread is not determined by the article.
Source metadata		PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

Original source ↗

No field-specific location recorded

Version: Version of record, BMC Genomics 2026 (PMC13425921 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.limitations

Source artifact SHA-256: f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971

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

Inspected artifact

Media type
application/xml
Source metadata		PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

Original source ↗

No field-specific location recorded

Version: Version of record, BMC Genomics 2026 (PMC13425921 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.media_type

Source artifact SHA-256: f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971

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

Inspected artifact

Publication status
peer_reviewed
Source metadata		PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

Original source ↗

No field-specific location recorded

Version: Version of record, BMC Genomics 2026 (PMC13425921 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.publication_status

Source artifact SHA-256: f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971

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

Inspected artifact

Retrieved at
2026-10-11T21:30:00Z
Source metadata		PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

Original source ↗

No field-specific location recorded

Version: Version of record, BMC Genomics 2026 (PMC13425921 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.retrieved_at

Source artifact SHA-256: f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971

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

Inspected artifact

Review: date
2026-10-11
Source metadata		PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

Original source ↗

No field-specific location recorded

Version: Version of record, BMC Genomics 2026 (PMC13425921 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.review.date

Source artifact SHA-256: f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971

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

Inspected artifact

Review: method note
Artifact re-retrieved from Europe PMC and SHA-256 matched.
Source metadata		PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

Original source ↗

No field-specific location recorded

Version: Version of record, BMC Genomics 2026 (PMC13425921 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.review.method_note

Source artifact SHA-256: f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971

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

Inspected artifact

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

Primary source retrieved and hashed for the 2026-10-11 protein and structure literature pass.

Release history

No supporting source is linked yet.

Supersedes PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

Supersedes PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

Read original source

Download this release (gzip)
Technical metadata and extraction receipts

Stable ID: lit-protein-20261011-prime-source-prime2026

areas
protein-function
contexts
research
url
https://pmc.ncbi.nlm.nih.gov/articles/PMC13425921/
artifact url
https://www.ebi.ac.uk/europepmc/webservices/rest/PMC13425921/fullTextXML
doi
10.1186/s12864-026-12976-5
version
Version of record, BMC Genomics 2026 (PMC13425921 JATS full text)
retrieved at
2026-10-11T21:30:00Z
artifact sha256
f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971
publication status
peer_reviewed
licence
CC BY 4.0
media type
application/xml
venue
BMC Genomics
year
2026
limitations
Table 1 only. The lineage-clustering, temporal-dynamics and attention analyses are figures and were not extracted.; The One-Hot Mean row has no embedding or fine-tuning setting; its three leading cells repeat the row label in the XML and are recorded as a single baseline configuration.; The plus-minus values are the standard deviation across random seeds (Table 1 footnote, pointing at Supplementary Table 6, which was not retrieved). Table 1 uses five folds and the Methods name three seeds, so the sample count behind each spread is not determined by the article.
review
method: source-hash-verification; method note: Artifact re-retrieved from Europe PMC and SHA-256 matched.; reviewer: claude; reviewer note: Claude review agent reviewer-ps-1, independent of the extractor lit-protein-structure; no human review claimed; date: 2026-10-11
Related records

Suggest a correction