rewire.it
Task

ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-SCTM: De novo backbones based sequence design, length 100 scTM

De novo backbones based sequence design, length 100 scTM. Scored with scTM on CASP, CAMEO and de novo backbones. Inverse folding: recover a sequence for a given backbone. Values are the median over repeated runs.

4 evaluations · 4 metric rows

Overview

De novo backbones based sequence design, length 100 scTM. Scored with scTM on CASP, CAMEO and de novo backbones. Inverse folding: recover a sequence for a given backbone. Values are the median over repeated runs.

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.

ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-SCTM: De novo backbones based sequence design, length 100 scTM

sctm (score) · Higher values are better for this metric.

Every method ProteinBench reports on De novo backbones based sequence design, length 100 scTM, scored with scTM on CASP, CAMEO and de novo backbones.

Evaluation protocol · CASP, CAMEO and de novo backbones (ProteinBench split)

  1. ProteinMPNN · Configuration · Author-reported evaluation0.962
  2. ESM-IF1 · Configuration · Author-reported evaluation0.810
  3. LM-Design · Configuration · Author-reported evaluation0.834
  4. ESM3 · Configuration · Author-reported evaluation0.942

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.

proteinbench primary benchmark evidence · Table 2, column(De novo backbones based sequence design, length 100 scTM ↑)
Values, uncertainty and evidence
sctm: original source values
Tested entityPrinted valueUncertaintyEvidence
ProteinMPNN · Configuration0.962 scoreNot reportedAuthor-reported evaluation · source checkedproteinbench primary benchmark evidence · Table 2, row(ProteinMPNN), column(De novo backbones based sequence design, length 100 scTM ↑)
ESM-IF1 · Configuration0.810 scoreNot reportedAuthor-reported evaluation · source checkedproteinbench primary benchmark evidence · Table 2, row(ESM-IF1), column(De novo backbones based sequence design, length 100 scTM ↑)
LM-Design · Configuration0.834 scoreNot reportedAuthor-reported evaluation · source checkedproteinbench primary benchmark evidence · Table 2, row(LM-Design), column(De novo backbones based sequence design, length 100 scTM ↑)
ESM3 · Configuration0.942 scoreNot reportedAuthor-reported evaluation · source checkedproteinbench primary benchmark evidence · Table 2, row(ESM3), column(De novo backbones based sequence design, length 100 scTM ↑)
Scope and limitations
  • Author-reported numbers, source checked but not independently reproduced.
  • Many of these metrics are better when lower, including scRMSD, perplexity and binding energy. The direction comes from the arrow in the paper's own header.
  • Rows such as Native PDBs and RAbD are the natural reference the authors include for scale, not a competing method.

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 · 4 evaluations · 4 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
ESM-IF1 on ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-SCTM: De novo backbones based sequence design, length 100 scTM

Inverse folding: recover a sequence for a given backbone. Values are the median over repeated runs.

Author-reported evaluation · Evaluation metadata: source checked

0.810 sctm

Unit: score · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedproteinbench primary benchmark evidence · Table 2, row(ESM-IF1), column(De novo backbones based sequence design, length 100 scTM ↑)

Source checking is not independent reproduction.

ESM3 on ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-SCTM: De novo backbones based sequence design, length 100 scTM

Inverse folding: recover a sequence for a given backbone. Values are the median over repeated runs.

Author-reported evaluation · Evaluation metadata: source checked

0.942 sctm

Unit: score · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedproteinbench primary benchmark evidence · Table 2, row(ESM3), column(De novo backbones based sequence design, length 100 scTM ↑)

Source checking is not independent reproduction.

LM-Design on ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-SCTM: De novo backbones based sequence design, length 100 scTM

Inverse folding: recover a sequence for a given backbone. Values are the median over repeated runs.

Author-reported evaluation · Evaluation metadata: source checked

0.834 sctm

Unit: score · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedproteinbench primary benchmark evidence · Table 2, row(LM-Design), column(De novo backbones based sequence design, length 100 scTM ↑)

Source checking is not independent reproduction.

ProteinMPNN on ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-SCTM: De novo backbones based sequence design, length 100 scTM

Inverse folding: recover a sequence for a given backbone. Values are the median over repeated runs.

Author-reported evaluation · Evaluation metadata: source checked

0.962 sctm

Unit: score · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedproteinbench primary benchmark evidence · Table 2, row(ProteinMPNN), column(De novo backbones based sequence design, length 100 scTM ↑)

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-proteinbench

Individual claims
proteinbench primary benchmark evidence

Original source ↗

Table 2, column(De novo backbones based sequence design, length 100 scTM ↑)

Version: 2409.06744v1
Retrieved: 2026-09-16T21:07:13.231727+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-proteinbench

Claim: proteinbench-association-if-de-novo-backbones-based-sequence-design-length-100-sctm

Source artifact SHA-256: 4334d636223ad42bfb9ae68aae03f5a255c29ba1cebe7b8f9588fb3b9b5453b2

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: proteinbench-task-if-de-novo-backbones-based-sequence-design-length-100-sctm

areas
proteins-complexes
tasks
De novo backbones based sequence design, length 100 scTM
metric
scTM
metric direction
higher
dataset
CASP, CAMEO and de novo backbones
protocol
Inverse folding: recover a sequence for a given backbone. Values are the median over repeated runs.
source locator
Table 2, column(De novo backbones based sequence design, length 100 scTM ↑)
comparison panels
id: proteinbench-panel-if-de-novo-backbones-based-sequence-design-length-100-sctm; title: ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-SCTM: De novo backbones based sequence design, length 100 scTM; protocol id: proteinbench-task-if-de-novo-backbones-based-sequence-design-length-100-sctm; dataset id: proteinbench-dataset-casp-cameo-and-de-novo-backbones; metric: sctm; unit: score; direction: higher; result ids: proteinbench-result-proteinmpnn-if-de-novo-backbones-based-sequence-design-length-100-sctm-sctm; proteinbench-result-esm-if1-if-de-novo-backbones-based-sequence-design-length-100-sctm-sctm; proteinbench-result-lm-design-if-de-novo-backbones-based-sequence-design-length-100-sctm-sctm; proteinbench-result-esm3-if-de-novo-backbones-based-sequence-design-length-100-sctm-sctm; source ids: expansion-p3-proteinbench; source locator: Table 2, column(De novo backbones based sequence design, length 100 scTM ↑); context: Every method ProteinBench reports on De novo backbones based sequence design, length 100 scTM, scored with scTM on CASP, CAMEO and de novo backbones.; caveats: Author-reported numbers, source checked but not independently reproduced.; Many of these metrics are better when lower, including scRMSD, perplexity and binding energy. The direction comes from the arrow in the paper's own header.; Rows such as Native PDBs and RAbD are the natural reference the authors include for scale, not a competing method.; review: method: automated_source_review; date: 2026-09-18
Related records

Suggest a correction