ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
Supervised substitutions, average over splits, MSE. Scored with MSE on ProteinGym substitution DMS assays. Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits.
Overview
Supervised substitutions, average over splits, MSE. Scored with MSE on ProteinGym substitution DMS assays. Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits.
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.
- Embed. ESM-1v on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
- Embed. MSAT on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
- Embed. Tranception on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
- NPT ProteinNPT on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
- OHE DeepSequence on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
- OHE ESM-1v on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
- OHE MSAT on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
- OHE None on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
- OHE TranceptEVE on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
- OHE Tranception on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
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.
ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
mse (error) · Lower values are better for this metric.
Every method ProteinGym reports on Supervised substitutions, average over splits, MSE, scored with MSE on ProteinGym substitution DMS assays.
Evaluation protocol · ProteinGym substitution DMS assays (ProteinGym split)
- OHE None · Configuration · Author-reported evaluation1.061
- OHE DeepSequence · Configuration · Author-reported evaluation0.891
- OHE ESM-1v · Configuration · Author-reported evaluation0.897
- OHE MSAT · Configuration · Author-reported evaluation0.882
- OHE Tranception · Configuration · Author-reported evaluation0.895
- OHE TranceptEVE · Configuration · Author-reported evaluation0.870
- Embed. ESM-1v · Configuration · Author-reported evaluation0.787
- Embed. MSAT · Configuration · Author-reported evaluation0.735
- Embed. Tranception · Configuration · Author-reported evaluation0.769
- NPT ProteinNPT · Configuration · Author-reported evaluation0.683
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.
ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, column(Supervised substitutions, average over splits, MSE)Values, uncertainty and evidence
| Tested entity | Printed value | Uncertainty | Evidence |
|---|---|---|---|
| OHE None · Configuration | 1.061 error | Not reported | Author-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(OHE None), column(Supervised substitutions, average over splits, MSE) |
| OHE DeepSequence · Configuration | 0.891 error | Not reported | Author-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(DeepSequence), column(Supervised substitutions, average over splits, MSE) |
| OHE ESM-1v · Configuration | 0.897 error | Not reported | Author-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(ESM-1v), column(Supervised substitutions, average over splits, MSE) |
| OHE MSAT · Configuration | 0.882 error | Not reported | Author-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(MSAT), column(Supervised substitutions, average over splits, MSE) |
| OHE Tranception · Configuration | 0.895 error | Not reported | Author-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(Tranception), column(Supervised substitutions, average over splits, MSE) |
| OHE TranceptEVE · Configuration | 0.870 error | Not reported | Author-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(TranceptEVE), column(Supervised substitutions, average over splits, MSE) |
| Embed. ESM-1v · Configuration | 0.787 error | Not reported | Author-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(Embed. ESM-1v), column(Supervised substitutions, average over splits, MSE) |
| Embed. MSAT · Configuration | 0.735 error | Not reported | Author-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(MSAT), column(Supervised substitutions, average over splits, MSE) |
| Embed. Tranception · Configuration | 0.769 error | Not reported | Author-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(Tranception), column(Supervised substitutions, average over splits, MSE) |
| NPT ProteinNPT · Configuration | 0.683 error | Not reported | Author-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(NPT ProteinNPT), column(Supervised substitutions, average over splits, MSE) |
Scope and limitations
- Author-reported numbers, source checked but not independently reproduced.
- MSE is better when lower; every other metric here is better when higher.
- Zero-shot, supervised and indel benchmarks use different protocols and assay sets, so their figures are not comparable to each other.
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 · 10 evaluations · 10 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.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| Embed. ESM-1v on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE Configuration: Embed. ESM-1vTask: ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSEDataset subset: ProteinGym substitution DMS assays (ProteinGym split) Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.787 mse Unit: error · Direction: lower | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(Embed. ESM-1v), column(Supervised substitutions, average over splits, MSE) Source checking is not independent reproduction. |
| Embed. MSAT on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE Configuration: Embed. MSATTask: ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSEDataset subset: ProteinGym substitution DMS assays (ProteinGym split) Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.735 mse Unit: error · Direction: lower | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(MSAT), column(Supervised substitutions, average over splits, MSE) Source checking is not independent reproduction. |
| Embed. Tranception on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE Configuration: Embed. TranceptionTask: ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSEDataset subset: ProteinGym substitution DMS assays (ProteinGym split) Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.769 mse Unit: error · Direction: lower | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(Tranception), column(Supervised substitutions, average over splits, MSE) Source checking is not independent reproduction. |
| NPT ProteinNPT on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE Configuration: NPT ProteinNPTTask: ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSEDataset subset: ProteinGym substitution DMS assays (ProteinGym split) Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.683 mse Unit: error · Direction: lower | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(NPT ProteinNPT), column(Supervised substitutions, average over splits, MSE) Source checking is not independent reproduction. |
| OHE DeepSequence on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE Configuration: OHE DeepSequenceTask: ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSEDataset subset: ProteinGym substitution DMS assays (ProteinGym split) Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.891 mse Unit: error · Direction: lower | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(DeepSequence), column(Supervised substitutions, average over splits, MSE) Source checking is not independent reproduction. |
| OHE ESM-1v on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE Configuration: OHE ESM-1vTask: ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSEDataset subset: ProteinGym substitution DMS assays (ProteinGym split) Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.897 mse Unit: error · Direction: lower | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(ESM-1v), column(Supervised substitutions, average over splits, MSE) Source checking is not independent reproduction. |
| OHE MSAT on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE Configuration: OHE MSATTask: ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSEDataset subset: ProteinGym substitution DMS assays (ProteinGym split) Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.882 mse Unit: error · Direction: lower | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(MSAT), column(Supervised substitutions, average over splits, MSE) Source checking is not independent reproduction. |
| OHE None on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE Configuration: OHE NoneTask: ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSEDataset subset: ProteinGym substitution DMS assays (ProteinGym split) Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits. Author-reported evaluation · Evaluation metadata: source checked | ||
| 1.061 mse Unit: error · Direction: lower | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(OHE None), column(Supervised substitutions, average over splits, MSE) Source checking is not independent reproduction. |
| OHE TranceptEVE on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE Configuration: OHE TranceptEVETask: ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSEDataset subset: ProteinGym substitution DMS assays (ProteinGym split) Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.870 mse Unit: error · Direction: lower | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(TranceptEVE), column(Supervised substitutions, average over splits, MSE) Source checking is not independent reproduction. |
| OHE Tranception on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE Configuration: OHE TranceptionTask: ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSEDataset subset: ProteinGym substitution DMS assays (ProteinGym split) Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.895 mse Unit: error · Direction: lower | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(Tranception), column(Supervised substitutions, average over splits, MSE) 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
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Relationship: part of discovery-benchmark-proteingym Individual claims | ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design Table 3, column(Supervised substitutions, average over splits, MSE) Version: Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256 | source checked automated source review · 2026-09-18 Audit detailsPrimary-source transcription with no human sign-off and no independent reproduction. Field: Claim: proteingym-association-sup-sub-mse-avg Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Sources and history
Release 2026-09-17-134cd1815de8 · Record review: source checked
1 source records and release history
- ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Original source · Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256
Technical metadata and extraction receipts
Stable ID: proteingym-task-sup-sub-mse-avg
- areas
- proteins-complexes
- tasks
- Supervised substitutions, average over splits, MSE
- metric
- MSE
- metric direction
- lower
- dataset
- ProteinGym substitution DMS assays
- protocol
- Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits.
- source locator
- Table 3, column(Supervised substitutions, average over splits, MSE)
- comparison panels
- id: proteingym-panel-sup-sub-mse-avg; title: ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE; protocol id: proteingym-task-sup-sub-mse-avg; dataset id: proteingym-dataset-proteingym-substitution-dms-assays; metric: mse; unit: error; direction: lower; result ids: proteingym-result-ohe-none-sup-sub-mse-avg-mse; proteingym-result-ohe-deepsequence-sup-sub-mse-avg-mse; proteingym-result-ohe-esm-1v-sup-sub-mse-avg-mse; proteingym-result-ohe-msat-sup-sub-mse-avg-mse; proteingym-result-ohe-tranception-sup-sub-mse-avg-mse; proteingym-result-ohe-trancepteve-sup-sub-mse-avg-mse; proteingym-result-embed-esm-1v-sup-sub-mse-avg-mse; proteingym-result-embed-msat-sup-sub-mse-avg-mse; proteingym-result-embed-tranception-sup-sub-mse-avg-mse; proteingym-result-npt-proteinnpt-sup-sub-mse-avg-mse; source ids: evidence-expansion-proteingym-a3b08cc4; source locator: Table 3, column(Supervised substitutions, average over splits, MSE); context: Every method ProteinGym reports on Supervised substitutions, average over splits, MSE, scored with MSE on ProteinGym substitution DMS assays.; caveats: Author-reported numbers, source checked but not independently reproduced.; MSE is better when lower; every other metric here is better when higher.; Zero-shot, supervised and indel benchmarks use different protocols and assay sets, so their figures are not comparable to each other.; review: method: automated_source_review; date: 2026-09-18
Related records
- part of: ProteinGym
- subject: ProteinGym SUP-SUB-MSE-AVG: part of discovery-benchmark-proteingym
- benchmark: Embed. ESM-1v on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
- benchmark: Embed. MSAT on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
- benchmark: Embed. Tranception on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
- benchmark: NPT ProteinNPT on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
- benchmark: OHE DeepSequence on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
- benchmark: OHE ESM-1v on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
- benchmark: OHE MSAT on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
- benchmark: OHE None on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
- benchmark: OHE TranceptEVE on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE
- benchmark: OHE Tranception on ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE