PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE; As published 2026

Overview

An explanatory profile has not yet been reviewed for this record.

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

21 recorded evaluations, 21 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

21 evaluations · 21 results. Different protocols are not a single leaderboard.

Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE · Dataset: SARS-CoV-2 RBD mutant binding and expression measurements

Sorted by RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, fine-tuned) (lower is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, fine-tuned)	RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, frozen)	RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, fine-tuned)	RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, frozen)	RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; one-hot mean representation)
ESM-C 600M, the CLS token embedding, fine-tuned (PRIME)Evaluation	1.6616 ± 0.05 (best in column)	Not reported	Not reported	Not reported	Not reported
ESM-C 300M, the CLS token embedding, fine-tuned (PRIME)Evaluation	1.7766 ± 0.04	Not reported	Not reported	Not reported	Not reported
ESM-2 650M, the CLS token embedding, fine-tuned (PRIME)Evaluation	1.8084 ± 0.06	Not reported	Not reported	Not reported	Not reported
ESM-2 8M, the CLS token embedding, fine-tuned (PRIME)Evaluation	1.9653 ± 0.03	Not reported	Not reported	Not reported	Not reported
ESM-2 150M, the CLS token embedding, fine-tuned (PRIME)Evaluation	2.0022 ± 0.04	Not reported	Not reported	Not reported	Not reported
ESM-2 150M, the CLS token embedding, not fine-tuned (PRIME)Evaluation	Not reported	1.9777 ± 0.03	Not reported	Not reported	Not reported
ESM-2 150M, the mean over residue embeddings, fine-tuned (PRIME)Evaluation	Not reported	Not reported	1.7863 ± 0.01	Not reported	Not reported
ESM-2 150M, the mean over residue embeddings, not fine-tuned (PRIME)Evaluation	Not reported	Not reported	Not reported	1.8359 ± 0.02	Not reported
ESM-2 650M, the CLS token embedding, not fine-tuned (PRIME)Evaluation	Not reported	1.9063 ± 0.02	Not reported	Not reported	Not reported
ESM-2 650M, the mean over residue embeddings, fine-tuned (PRIME)Evaluation	Not reported	Not reported	1.7200 ± 0.03	Not reported	Not reported
ESM-2 650M, the mean over residue embeddings, not fine-tuned (PRIME)Evaluation	Not reported	Not reported	Not reported	1.8488 ± 0.03	Not reported
ESM-2 8M, the CLS token embedding, not fine-tuned (PRIME)Evaluation	Not reported	1.9452 ± 0.04	Not reported	Not reported	Not reported
ESM-2 8M, the mean over residue embeddings, fine-tuned (PRIME)Evaluation	Not reported	Not reported	1.7688 ± 0.06	Not reported	Not reported
ESM-2 8M, the mean over residue embeddings, not fine-tuned (PRIME)Evaluation	Not reported	Not reported	Not reported	1.7519 ± 0.01 (best in column)	Not reported
ESM-C 300M, the CLS token embedding, not fine-tuned (PRIME)Evaluation	Not reported	1.9366 ± 0.04	Not reported	Not reported	Not reported
ESM-C 300M, the mean over residue embeddings, fine-tuned (PRIME)Evaluation	Not reported	Not reported	1.5918 ± 0.03	Not reported	Not reported
ESM-C 300M, the mean over residue embeddings, not fine-tuned (PRIME)Evaluation	Not reported	Not reported	Not reported	1.7874 ± 0.02	Not reported
ESM-C 600M, the CLS token embedding, not fine-tuned (PRIME)Evaluation	Not reported	1.8726 ± 0.00 (best in column)	Not reported	Not reported	Not reported
ESM-C 600M, the mean over residue embeddings, fine-tuned (PRIME)Evaluation	Not reported	Not reported	1.5745 ± 0.02 (best in column)	Not reported	Not reported
ESM-C 600M, the mean over residue embeddings, not fine-tuned (PRIME)Evaluation	Not reported	Not reported	Not reported	1.8558 ± 0.02	Not reported
One-hot mean representation (PRIME)Evaluation	Not reported	Not reported	Not reported	Not reported	1.9754 ± 0.00

All 21 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: ESM-2 150M, the CLS token embedding, fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	2.0022 ± 0.04 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, fine-tuned) unit-unreported · lower Uncertainty: SD 0.04 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-2 150M CLS finetuned: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-2 150M' / 'CLS' / '✓', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: ESM-2 150M, the CLS token embedding, not fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.9777 ± 0.03 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, frozen) unit-unreported · lower Uncertainty: SD 0.03 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-2 150M CLS frozen: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-2 150M' / 'CLS' / '×', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: ESM-2 150M, the mean over residue embeddings, fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.7863 ± 0.01 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, fine-tuned) unit-unreported · lower Uncertainty: SD 0.01 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-2 150M Mean finetuned: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-2 150M' / 'Mean' / '✓', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: ESM-2 150M, the mean over residue embeddings, not fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.8359 ± 0.02 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, frozen) unit-unreported · lower Uncertainty: SD 0.02 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-2 150M Mean frozen: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-2 150M' / 'Mean' / '×', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: ESM-2 650M, the CLS token embedding, fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.8084 ± 0.06 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, fine-tuned) unit-unreported · lower Uncertainty: SD 0.06 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-2 650M CLS finetuned: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-2 650M' / 'CLS' / '✓', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: ESM-2 650M, the CLS token embedding, not fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.9063 ± 0.02 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, frozen) unit-unreported · lower Uncertainty: SD 0.02 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-2 650M CLS frozen: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-2 650M' / 'CLS' / '×', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: ESM-2 650M, the mean over residue embeddings, fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.7200 ± 0.03 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, fine-tuned) unit-unreported · lower Uncertainty: SD 0.03 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-2 650M Mean finetuned: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-2 650M' / 'Mean' / '✓', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: ESM-2 650M, the mean over residue embeddings, not fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.8488 ± 0.03 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, frozen) unit-unreported · lower Uncertainty: SD 0.03 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-2 650M Mean frozen: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-2 650M' / 'Mean' / '×', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: ESM-2 8M, the CLS token embedding, fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.9653 ± 0.03 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, fine-tuned) unit-unreported · lower Uncertainty: SD 0.03 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-2 8M CLS finetuned: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-2 8M' / 'CLS' / '✓', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: ESM-2 8M, the CLS token embedding, not fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.9452 ± 0.04 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, frozen) unit-unreported · lower Uncertainty: SD 0.04 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-2 8M CLS frozen: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-2 8M' / 'CLS' / '×', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: ESM-2 8M, the mean over residue embeddings, fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.7688 ± 0.06 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, fine-tuned) unit-unreported · lower Uncertainty: SD 0.06 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-2 8M Mean finetuned: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-2 8M' / 'Mean' / '✓', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: ESM-2 8M, the mean over residue embeddings, not fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.7519 ± 0.01 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, frozen) unit-unreported · lower Uncertainty: SD 0.01 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-2 8M Mean frozen: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-2 8M' / 'Mean' / '×', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: ESM-C 300M, the CLS token embedding, fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.7766 ± 0.04 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, fine-tuned) unit-unreported · lower Uncertainty: SD 0.04 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-C 300M CLS finetuned: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-C 300M' / 'CLS' / '✓', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: ESM-C 300M, the CLS token embedding, not fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.9366 ± 0.04 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, frozen) unit-unreported · lower Uncertainty: SD 0.04 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-C 300M CLS frozen: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-C 300M' / 'CLS' / '×', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: ESM-C 300M, the mean over residue embeddings, fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.5918 ± 0.03 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, fine-tuned) unit-unreported · lower Uncertainty: SD 0.03 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-C 300M Mean finetuned: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-C 300M' / 'Mean' / '✓', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: ESM-C 300M, the mean over residue embeddings, not fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.7874 ± 0.02 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, frozen) unit-unreported · lower Uncertainty: SD 0.02 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-C 300M Mean frozen: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-C 300M' / 'Mean' / '×', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: ESM-C 600M, the CLS token embedding, fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.6616 ± 0.05 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, fine-tuned) unit-unreported · lower Uncertainty: SD 0.05 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-C 600M CLS finetuned: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-C 600M' / 'CLS' / '✓', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: ESM-C 600M, the CLS token embedding, not fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.8726 ± 0.00 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the CLS token embedding, frozen) unit-unreported · lower Uncertainty: SD 0.00 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-C 600M CLS frozen: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-C 600M' / 'CLS' / '×', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: ESM-C 600M, the mean over residue embeddings, fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.5745 ± 0.02 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, fine-tuned) unit-unreported · lower Uncertainty: SD 0.02 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-C 600M Mean finetuned: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-C 600M' / 'Mean' / '✓', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: ESM-C 600M, the mean over residue embeddings, not fine-tuned (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.8558 ± 0.02 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; the mean over residue embeddings, frozen) unit-unreported · lower Uncertainty: SD 0.02 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-C 600M Mean frozen: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-C 600M' / 'Mean' / '×', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
Configuration: One-hot mean representation (PRIME)	Protocol: PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE Dataset: SARS-CoV-2 RBD mutant binding and expression measurements	1.9754 ± 0.00 RMSE (ACE2 binding; Position-stratified split holding out whole mutated positions; one-hot mean representation) unit-unreported · lower Uncertainty: SD 0.00 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source One-Hot Mean: ACE2 binding RMSE, Position-stratified split holding out whole mutated positions lit-protein-20261011-prime-protocol-position-stratified-binding-rmse Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'One-Hot Mean', columns 'Position-Stratified Split' / 'Binding' / 'RMSE'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Methods and evaluation design

Procedure, tasks and evaluated configurations

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: 21

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 (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-10-22-1b7cf027e4f6. 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.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

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

1 source record and release history

PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Original source · Version of record, BMC Genomics 2026 (PMC13425921 JATS full text)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-protein-20261011-prime-protocol-position-stratified-binding-rmse

areas: protein-function
contexts: research
protocol: Representations of RBD mutants are fed to a supervised regression head and scored on held-out data under the position-stratified split holding out whole mutated positions. Binding and expression are predicted jointly by one multi-task fully connected network over the representations (Methods, Input features), so the two targets are not independent runs.
metric: root-mean-squared-error
metric direction: lower
unit: unit-unreported
metric qualifier: ACE2 binding; Position-stratified split holding out whole mutated positions
version: As published 2026
source locator: Table 1, columns 'Position-Stratified Split' / 'Binding' / 'RMSE'
limitations: Table 1 prints no unit for RMSE; the measurement scale is the assay's own.
uncertainty reporting: printed: mean plus or minus standard deviation across random seeds; runs: Five folds (Fig. 1C) and three seeds (Methods) are stated; which the printed spread is taken over is not

Related records