rewirebio.iobenchmarks
Evaluation

ProteinMPNN: novel and foldable designs per de novo backbone at matched diversity (HyInv report)

Author-reported comparison transcribed from the pinned technical report. Run by the team that released HyInv; not reproduced by Rewire.

Evaluation results

1 evaluation · 2 results. Different protocols are not a single leaderboard.

Protocol: Novel and foldable designs per de novo backbone at matched diversity (HyInv report) · Dataset: De novo backbones application panel (74 backbones)

Sorted by Count (Number of designs per backbone (of 4) that are both foldable (ESMFold2 scTM at least 0.9) and novel (sequence identity below 0.3 to the nearest UniRef50 sequence and to the nearest sequence of the pretraining library), at matched diversity; two readings, with and without the report's composition filter; the composition-filtered reading: sequence entropy at least 3.5 bits, hydrophobic fraction (AVILMFWY) 0.25 to 0.55, longest homopolymer run at most 6 The baselines are interpolated at the HyInv diversity from their own temperature grids, so 'at matched diversity' is the report's wording for an interpolated comparison and not a measurement of either baseline at HyInv's diversity.) (higher 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 configurationCount (Number of designs per backbone (of 4) that are both foldable (ESMFold2 scTM at least 0.9) and novel (sequence identity below 0.3 to the nearest UniRef50 sequence and to the nearest sequence of the pretraining library), at matched diversity; two readings, with and without the report's composition filter; the composition-filtered reading: sequence entropy at least 3.5 bits, hydrophobic fraction (AVILMFWY) 0.25 to 0.55, longest homopolymer run at most 6 The baselines are interpolated at the HyInv diversity from their own temperature grids, so 'at matched diversity' is the report's wording for an interpolated comparison and not a measurement of either baseline at HyInv's diversity.)Count (Number of designs per backbone (of 4) that are both foldable (ESMFold2 scTM at least 0.9) and novel (sequence identity below 0.3 to the nearest UniRef50 sequence and to the nearest sequence of the pretraining library), at matched diversity; two readings, with and without the report's composition filter; the unfiltered reading, over all designs The baselines are interpolated at the HyInv diversity from their own temperature grids, so 'at matched diversity' is the report's wording for an interpolated comparison and not a measurement of either baseline at HyInv's diversity.)
ProteinMPNN (HyInv report)Evaluation0.050.47
All 2 result rows with coverage, uncertainty and sources
Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: ProteinMPNN (HyInv report)Protocol: Novel and foldable designs per de novo backbone at matched diversity (HyInv report)
Dataset: De novo backbones application panel (74 backbones)
0.05 Count (Number of designs per backbone (of 4) that are both foldable (ESMFold2 scTM at least 0.9) and novel (sequence identity below 0.3 to the nearest UniRef50 sequence and to the nearest sequence of the pretraining library), at matched diversity; two readings, with and without the report's composition filter; the composition-filtered reading: sequence entropy at least 3.5 bits, hydrophobic fraction (AVILMFWY) 0.25 to 0.55, longest homopolymer run at most 6 The baselines are interpolated at the HyInv diversity from their own temperature grids, so 'at matched diversity' is the report's wording for an interpolated comparison and not a measurement of either baseline at HyInv's diversity.)
count · higher

Uncertainty: Not reported by the source

Coverage: 74/74 backbones scored (58 clusters of 30% sequence identity; 4 designs per backbone.)

Author-reported evaluation · Source checked
Methods, coverage and source

ProteinMPNN: novel and foldable designs per de novo backbone at matched diversity (HyInv report)

hyinv-20261106-protocol-novel-and-foldable-yield

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Section 6 'De novo backbones', sentence '0.68 unfiltered and 0.38 filtered per backbone, against 0.47 and 0.05 for ProteinMPNN and 0.45 and 0.11 for ProteinZero V2' (page 8 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: Novel and foldable designs per de novo backbone at matched diversity (HyInv report)
Dataset: De novo backbones application panel (74 backbones)
0.47 Count (Number of designs per backbone (of 4) that are both foldable (ESMFold2 scTM at least 0.9) and novel (sequence identity below 0.3 to the nearest UniRef50 sequence and to the nearest sequence of the pretraining library), at matched diversity; two readings, with and without the report's composition filter; the unfiltered reading, over all designs The baselines are interpolated at the HyInv diversity from their own temperature grids, so 'at matched diversity' is the report's wording for an interpolated comparison and not a measurement of either baseline at HyInv's diversity.)
count · higher

Uncertainty: Not reported by the source

Coverage: 74/74 backbones scored (58 clusters of 30% sequence identity; 4 designs per backbone.)

Author-reported evaluation · Source checked
Methods, coverage and source

ProteinMPNN: novel and foldable designs per de novo backbone at matched diversity (HyInv report)

hyinv-20261106-protocol-novel-and-foldable-yield

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Section 6 'De novo backbones', sentence '0.68 unfiltered and 0.38 filtered per backbone, against 0.47 and 0.05 for ProteinMPNN and 0.45 and 0.11 for ProteinZero V2' (page 8 of 21)

Source checking is not independent reproduction. Release 2026-11-21-c8bea25e5abb.

Research readiness

0 of 4 readiness checks met. These checks assess whether the evidence supports a reproducible investigation; a source-checked score alone does not meet them.

Readiness checks, gaps and artifacts

Release 2026-11-21-c8bea25e5abb · Evidence verified: Not verified

Evidence incomplete

Replay metrics

Exact outcomes, predictions, identifiers and evaluator are connected.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified

Verified: Not verified

Evidence incomplete

Investigate discrepancies

Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified
  • Sample annotations are recorded: not yet verified
  • Dependence between samples is assessed: not yet verified

Verified: Not verified

Evidence incomplete

Run locally

A pinned recipe describes the inputs, environment and resource requirements.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • A pinned run recipe exists: not yet verified
  • Compute requirements are estimated: not yet verified

Verified: Not verified

Evidence incomplete

Validate independently

Separate data and exposure records support an independent test.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Independent validation data exist: not yet verified
  • Overlap with training data is checked: not yet verified

Verified: Not verified

Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.

Artifacts and reproduction

No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.

Evaluation procedure

Novel and foldable designs per de novo backbone at matched diversity (HyInv report)

Configuration
ProteinMPNN (HyInv report)
Protocol
Novel and foldable designs per de novo backbone at matched diversity (HyInv report)
Dataset
De novo backbones application panel (74 backbones)
origin
Author-reported evaluation
configuration
HyInv technical report, 2026-10-14, retrieved at commit 0dcc533c
adaptation
HyInv runs its default setting. ProteinMPNN and ProteinZero V2 are interpolated at the HyInv diversity from their temperature grids, without extrapolating by more than 0.05, so the baseline side is interpolated rather than measured at HyInv's diversity
aggregation
Mean number of qualifying designs per backbone over the 74 backbones; the resampling unit is the cluster of 30% identity.
budget
4 designs per backbone
dataset version
As assembled for the HyInv technical report (2026-10-14); no chain list or split manifest is published
inputs
Backbone N, CA, C and O coordinates of the panel chain; no sequence, alignment, language model or structure predictor at design time
metric implementation
74 de novo backbones, 4 designs each. A design is foldable if its ESMFold2 scTM is at least 0.9 and novel if its identity to the nearest UniRef50 sequence and to the nearest pretraining-library sequence is below 0.3. The composition filter keeps sequences with entropy at least 3.5 bits, hydrophobic fraction (AVILMFWY) between 0.25 and 0.55 and longest homopolymer run at most 6, which excludes low-complexity sequences a structure predictor can fold to a high scTM. Both readings were fixed before designs were generated. HyInv is compared with ProteinMPNN and ProteinZero V2 over their temperature grids, interpolating each curve at the HyInv diversity without extrapolating by more than 0.05.
population
74 de novo backbones in 58 clusters of 30% sequence identity, none with a hit that passes the report's homology rule; 28 have partial hits below the coverage limit (Table 10)
protocol id
hyinv-20261106-protocol-novel-and-foldable-yield
split
application panel

Metadata review: source checked. Unreported conditions prevent automatic comparisons.

Reproduction

Split
application panel
Adaptation
HyInv runs its default setting. ProteinMPNN and ProteinZero V2 are interpolated at the HyInv diversity from their temperature grids, without extrapolating by more than 0.05, so the baseline side is interpolated rather than measured at HyInv's diversity
Scoring implementation
74 de novo backbones, 4 designs each. A design is foldable if its ESMFold2 scTM is at least 0.9 and novel if its identity to the nearest UniRef50 sequence and to the nearest pretraining-library sequence is below 0.3. The composition filter keeps sequences with entropy at least 3.5 bits, hydrophobic fraction (AVILMFWY) between 0.25 and 0.55 and longest homopolymer run at most 6, which excludes low-complexity sequences a structure predictor can fold to a high scTM. Both readings were fixed before designs were generated. HyInv is compared with ProteinMPNN and ProteinZero V2 over their temperature grids, interpolating each curve at the HyInv diversity without extrapolating by more than 0.05.

No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.

Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.

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.

18 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance
Comparison: adaptation
HyInv runs its default setting. ProteinMPNN and ProteinZero V2 are interpolated at the HyInv diversity from their temperature grids, without extrapolating by more than 0.05, so the baseline side is interpolated rather than measured at HyInv's diversity
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Section 6 'De novo backbones', sentence '0.68 unfiltered and 0.38 filtered per backbone, against 0.47 and 0.05 for ProteinMPNN and 0.45 and 0.11 for ProteinZero V2' (page 8 of 21)

Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages)
Retrieved: 2026-11-06T09:52:00Z

not individually reviewed

No individual claim review recorded

author reported

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.comparison.adaptation

Source artifact SHA-256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419

Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted.

Inspected artifact

Comparison: aggregation
Mean number of qualifying designs per backbone over the 74 backbones; the resampling unit is the cluster of 30% identity.
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Section 6 'De novo backbones', sentence '0.68 unfiltered and 0.38 filtered per backbone, against 0.47 and 0.05 for ProteinMPNN and 0.45 and 0.11 for ProteinZero V2' (page 8 of 21)

Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages)
Retrieved: 2026-11-06T09:52:00Z

not individually reviewed

No individual claim review recorded

author reported

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.comparison.aggregation

Source artifact SHA-256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419

Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted.

Inspected artifact

Comparison: budget
4 designs per backbone
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Section 6 'De novo backbones', sentence '0.68 unfiltered and 0.38 filtered per backbone, against 0.47 and 0.05 for ProteinMPNN and 0.45 and 0.11 for ProteinZero V2' (page 8 of 21)

Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages)
Retrieved: 2026-11-06T09:52:00Z

not individually reviewed

No individual claim review recorded

author reported

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.comparison.budget

Source artifact SHA-256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419

Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted.

Inspected artifact

Comparison: dataset version
As assembled for the HyInv technical report (2026-10-14); no chain list or split manifest is published
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Section 6 'De novo backbones', sentence '0.68 unfiltered and 0.38 filtered per backbone, against 0.47 and 0.05 for ProteinMPNN and 0.45 and 0.11 for ProteinZero V2' (page 8 of 21)

Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages)
Retrieved: 2026-11-06T09:52:00Z

not individually reviewed

No individual claim review recorded

author reported

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.comparison.dataset_version

Source artifact SHA-256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419

Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted.

Inspected artifact

Comparison: inputs
Backbone N, CA, C and O coordinates of the panel chain; no sequence, alignment, language model or structure predictor at design time
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Section 6 'De novo backbones', sentence '0.68 unfiltered and 0.38 filtered per backbone, against 0.47 and 0.05 for ProteinMPNN and 0.45 and 0.11 for ProteinZero V2' (page 8 of 21)

Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages)
Retrieved: 2026-11-06T09:52:00Z

not individually reviewed

No individual claim review recorded

author reported

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.comparison.inputs

Source artifact SHA-256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419

Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted.

Inspected artifact

Comparison: metric implementation
74 de novo backbones, 4 designs each. A design is foldable if its ESMFold2 scTM is at least 0.9 and novel if its identity to the nearest UniRef50 sequence and to the nearest pretraining-library sequence is below 0.3. The composition filter keeps sequences with entropy at least 3.5 bits, hydrophobic fraction (AVILMFWY) between 0.25 and 0.55 and longest homopolymer run at most 6, which excludes low-complexity sequences a structure predictor can fold to a high scTM. Both readings were fixed before designs were generated. HyInv is compared with ProteinMPNN and ProteinZero V2 over their temperature grids, interpolating each curve at the HyInv diversity without extrapolating by more than 0.05.
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Section 6 'De novo backbones', sentence '0.68 unfiltered and 0.38 filtered per backbone, against 0.47 and 0.05 for ProteinMPNN and 0.45 and 0.11 for ProteinZero V2' (page 8 of 21)

Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages)
Retrieved: 2026-11-06T09:52:00Z

not individually reviewed

No individual claim review recorded

author reported

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.comparison.metric_implementation

Source artifact SHA-256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419

Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted.

Inspected artifact

Comparison: population
74 de novo backbones in 58 clusters of 30% sequence identity, none with a hit that passes the report's homology rule; 28 have partial hits below the coverage limit (Table 10)
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Section 6 'De novo backbones', sentence '0.68 unfiltered and 0.38 filtered per backbone, against 0.47 and 0.05 for ProteinMPNN and 0.45 and 0.11 for ProteinZero V2' (page 8 of 21)

Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages)
Retrieved: 2026-11-06T09:52:00Z

not individually reviewed

No individual claim review recorded

author reported

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.comparison.population

Source artifact SHA-256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419

Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted.

Inspected artifact

Comparison: protocol id
hyinv-20261106-protocol-novel-and-foldable-yield
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Section 6 'De novo backbones', sentence '0.68 unfiltered and 0.38 filtered per backbone, against 0.47 and 0.05 for ProteinMPNN and 0.45 and 0.11 for ProteinZero V2' (page 8 of 21)

Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages)
Retrieved: 2026-11-06T09:52:00Z

not individually reviewed

No individual claim review recorded

author reported

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.comparison.protocol_id

Source artifact SHA-256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419

Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted.

Inspected artifact

Comparison: split
application panel
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Section 6 'De novo backbones', sentence '0.68 unfiltered and 0.38 filtered per backbone, against 0.47 and 0.05 for ProteinMPNN and 0.45 and 0.11 for ProteinZero V2' (page 8 of 21)

Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages)
Retrieved: 2026-11-06T09:52:00Z

not individually reviewed

No individual claim review recorded

author reported

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.comparison.split

Source artifact SHA-256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419

Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted.

Inspected artifact

Origin
author_reported
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Section 6 'De novo backbones', sentence '0.68 unfiltered and 0.38 filtered per backbone, against 0.47 and 0.05 for ProteinMPNN and 0.45 and 0.11 for ProteinZero V2' (page 8 of 21)

Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages)
Retrieved: 2026-11-06T09:52:00Z

not individually reviewed

No individual claim review recorded

author reported

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.origin

Source artifact SHA-256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419

Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted.

Inspected artifact

How to read the evidence

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: source checked

1 source record and release historyDownload this release (gzip)
Technical metadata and extraction receipts

Stable ID: hyinv-20261106-eval-novel-foldable-proteinmpnn-de-novo

areas
proteins-complexes; protein-structure
contexts
research
comparison
adaptation: HyInv runs its default setting. ProteinMPNN and ProteinZero V2 are interpolated at the HyInv diversity from their temperature grids, without extrapolating by more than 0.05, so the baseline side is interpolated rather than measured at HyInv's diversity; aggregation: Mean number of qualifying designs per backbone over the 74 backbones; the resampling unit is the cluster of 30% identity.; budget: 4 designs per backbone; dataset version: As assembled for the HyInv technical report (2026-10-14); no chain list or split manifest is published; inputs: Backbone N, CA, C and O coordinates of the panel chain; no sequence, alignment, language model or structure predictor at design time; metric implementation: 74 de novo backbones, 4 designs each. A design is foldable if its ESMFold2 scTM is at least 0.9 and novel if its identity to the nearest UniRef50 sequence and to the nearest pretraining-library sequence is below 0.3. The composition filter keeps sequences with entropy at least 3.5 bits, hydrophobic fraction (AVILMFWY) between 0.25 and 0.55 and longest homopolymer run at most 6, which excludes low-complexity sequences a structure predictor can fold to a high scTM. Both readings were fixed before designs were generated. HyInv is compared with ProteinMPNN and ProteinZero V2 over their temperature grids, interpolating each curve at the HyInv diversity without extrapolating by more than 0.05.; population: 74 de novo backbones in 58 clusters of 30% sequence identity, none with a hit that passes the report's homology rule; 28 have partial hits below the coverage limit (Table 10); protocol id: hyinv-20261106-protocol-novel-and-foldable-yield; split: application panel
origin
author_reported
protocol
hyinv-20261106-protocol-novel-and-foldable-yield
source locator
Section 6 'De novo backbones', sentence '0.68 unfiltered and 0.38 filtered per backbone, against 0.47 and 0.05 for ProteinMPNN and 0.45 and 0.11 for ProteinZero V2' (page 8 of 21)
version
HyInv technical report, 2026-10-14, retrieved at commit 0dcc533c
Related records

Suggest a correction