rewire.it
Task

ProteinGym SUP-SUB-MSE-MOD: Supervised substitutions, modulo split, MSE

Supervised substitutions, modulo split, MSE. Scored with MSE on ProteinGym substitution DMS assays. Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits.

10 evaluations · 10 metric rows

Overview

Supervised substitutions, modulo split, 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.

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-MOD: Supervised substitutions, modulo split, MSE

mse (error) · Lower values are better for this metric.

Every method ProteinGym reports on Supervised substitutions, modulo split, MSE, scored with MSE on ProteinGym substitution DMS assays.

Evaluation protocol · ProteinGym substitution DMS assays (ProteinGym split)

  1. OHE None · Configuration · Author-reported evaluation1.125
  2. OHE DeepSequence · Configuration · Author-reported evaluation0.940
  3. OHE ESM-1v · Configuration · Author-reported evaluation0.949
  4. OHE MSAT · Configuration · Author-reported evaluation0.934
  5. OHE Tranception · Configuration · Author-reported evaluation0.934
  6. OHE TranceptEVE · Configuration · Author-reported evaluation0.914
  7. Embed. ESM-1v · Configuration · Author-reported evaluation0.861
  8. Embed. MSAT · Configuration · Author-reported evaluation0.795
  9. Embed. Tranception · Configuration · Author-reported evaluation0.833
  10. NPT ProteinNPT · Configuration · Author-reported evaluation0.771

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, modulo split, MSE)
Values, uncertainty and evidence
mse: original source values
Tested entityPrinted valueUncertaintyEvidence
OHE None · Configuration1.125 errorNot reportedAuthor-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(OHE None), column(Supervised substitutions, modulo split, MSE)
OHE DeepSequence · Configuration0.940 errorNot reportedAuthor-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(DeepSequence), column(Supervised substitutions, modulo split, MSE)
OHE ESM-1v · Configuration0.949 errorNot reportedAuthor-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(ESM-1v), column(Supervised substitutions, modulo split, MSE)
OHE MSAT · Configuration0.934 errorNot reportedAuthor-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(MSAT), column(Supervised substitutions, modulo split, MSE)
OHE Tranception · Configuration0.934 errorNot reportedAuthor-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(Tranception), column(Supervised substitutions, modulo split, MSE)
OHE TranceptEVE · Configuration0.914 errorNot reportedAuthor-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(TranceptEVE), column(Supervised substitutions, modulo split, MSE)
Embed. ESM-1v · Configuration0.861 errorNot reportedAuthor-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(Embed. ESM-1v), column(Supervised substitutions, modulo split, MSE)
Embed. MSAT · Configuration0.795 errorNot reportedAuthor-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(MSAT), column(Supervised substitutions, modulo split, MSE)
Embed. Tranception · Configuration0.833 errorNot reportedAuthor-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(Tranception), column(Supervised substitutions, modulo split, MSE)
NPT ProteinNPT · Configuration0.771 errorNot reportedAuthor-reported evaluation · source checkedProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 3, row(NPT ProteinNPT), column(Supervised substitutions, modulo split, 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.

Results grouped by the exact reported evaluation
Metric and findingCoverage and uncertaintyEvidence
Embed. ESM-1v on ProteinGym SUP-SUB-MSE-MOD: Supervised substitutions, modulo split, MSE

Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits.

Author-reported evaluation · Evaluation metadata: source checked

0.861 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, modulo split, MSE)

Source checking is not independent reproduction.

Embed. MSAT on ProteinGym SUP-SUB-MSE-MOD: Supervised substitutions, modulo split, MSE

Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits.

Author-reported evaluation · Evaluation metadata: source checked

0.795 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, modulo split, MSE)

Source checking is not independent reproduction.

Embed. Tranception on ProteinGym SUP-SUB-MSE-MOD: Supervised substitutions, modulo split, MSE

Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits.

Author-reported evaluation · Evaluation metadata: source checked

0.833 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, modulo split, MSE)

Source checking is not independent reproduction.

NPT ProteinNPT on ProteinGym SUP-SUB-MSE-MOD: Supervised substitutions, modulo split, MSE

Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits.

Author-reported evaluation · Evaluation metadata: source checked

0.771 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, modulo split, MSE)

Source checking is not independent reproduction.

OHE DeepSequence on ProteinGym SUP-SUB-MSE-MOD: Supervised substitutions, modulo split, MSE

Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits.

Author-reported evaluation · Evaluation metadata: source checked

0.940 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, modulo split, MSE)

Source checking is not independent reproduction.

OHE ESM-1v on ProteinGym SUP-SUB-MSE-MOD: Supervised substitutions, modulo split, MSE

Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits.

Author-reported evaluation · Evaluation metadata: source checked

0.949 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, modulo split, MSE)

Source checking is not independent reproduction.

OHE MSAT on ProteinGym SUP-SUB-MSE-MOD: Supervised substitutions, modulo split, MSE

Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits.

Author-reported evaluation · Evaluation metadata: source checked

0.934 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, modulo split, MSE)

Source checking is not independent reproduction.

OHE None on ProteinGym SUP-SUB-MSE-MOD: Supervised substitutions, modulo split, MSE

Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits.

Author-reported evaluation · Evaluation metadata: source checked

1.125 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, modulo split, MSE)

Source checking is not independent reproduction.

OHE TranceptEVE on ProteinGym SUP-SUB-MSE-MOD: Supervised substitutions, modulo split, MSE

Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits.

Author-reported evaluation · Evaluation metadata: source checked

0.914 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, modulo split, MSE)

Source checking is not independent reproduction.

OHE Tranception on ProteinGym SUP-SUB-MSE-MOD: Supervised substitutions, modulo split, MSE

Supervised fitness prediction under three cross-validation schemes: contiguous, modulo and random splits.

Author-reported evaluation · Evaluation metadata: source checked

0.934 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, modulo split, 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

Claims, original sources and review scope · Release 2026-09-17-134cd1815de8
Property and statementOriginal source and locationReview and provenance
Relationship: part of

discovery-benchmark-proteingym

Individual claims
ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design

Original source ↗

Table 3, column(Supervised substitutions, modulo split, MSE)

Version: Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256
Retrieved: 2026-09-17T08:06:28.522924+00:00

source checked

automated source review · 2026-09-18

Audit details

Primary-source transcription with no human sign-off and no independent reproduction.

Field: links:part_of:discovery-benchmark-proteingym

Claim: proteingym-association-sup-sub-mse-mod

Source artifact SHA-256: a3b08cc4a6befd64620cf0f287d78d55a36dc2639955f52c5655f83833c50104

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Sources and history

Release 2026-09-17-134cd1815de8 · Record review: source checked

1 source records and release historyDownload this release
Technical metadata and extraction receipts

Stable ID: proteingym-task-sup-sub-mse-mod

areas
proteins-complexes
tasks
Supervised substitutions, modulo split, 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, modulo split, MSE)
comparison panels
id: proteingym-panel-sup-sub-mse-mod; title: ProteinGym SUP-SUB-MSE-MOD: Supervised substitutions, modulo split, MSE; protocol id: proteingym-task-sup-sub-mse-mod; dataset id: proteingym-dataset-proteingym-substitution-dms-assays; metric: mse; unit: error; direction: lower; result ids: proteingym-result-ohe-none-sup-sub-mse-mod-mse; proteingym-result-ohe-deepsequence-sup-sub-mse-mod-mse; proteingym-result-ohe-esm-1v-sup-sub-mse-mod-mse; proteingym-result-ohe-msat-sup-sub-mse-mod-mse; proteingym-result-ohe-tranception-sup-sub-mse-mod-mse; proteingym-result-ohe-trancepteve-sup-sub-mse-mod-mse; proteingym-result-embed-esm-1v-sup-sub-mse-mod-mse; proteingym-result-embed-msat-sup-sub-mse-mod-mse; proteingym-result-embed-tranception-sup-sub-mse-mod-mse; proteingym-result-npt-proteinnpt-sup-sub-mse-mod-mse; source ids: evidence-expansion-proteingym-a3b08cc4; source locator: Table 3, column(Supervised substitutions, modulo split, MSE); context: Every method ProteinGym reports on Supervised substitutions, modulo split, 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

Suggest a correction