rewirebio.iobenchmarks
Configuration

ProteinMPNN (HyInv report)

ProteinMPNN at its published setting: autoregressive decoding at temperature 0.1.

41 evaluations · 44 results

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.

Model Capabilities & Hardware Requirements

Deployment facts recorded for ProteinMPNN (HyInv report). Fields the record does not carry are marked not recorded.

ParametersNot recorded
Minimum VRAMNot recorded
Inference LatencyNot recorded
Context WindowNot recorded
AccessNot recorded
LicenseNot recorded

Evaluated Checkpoint: Released weights at the published setting, as run in the HyInv technical report; no checkpoint revision printed

Evaluations and results

41 evaluations · 44 results. Different protocols are not a single leaderboard.

Sorted by lDDT (CA-only lDDT-style score without superposition, over all CA pairs below 15 Angstrom in the native structure, as the fraction whose distance error is below 0.5, 1, 2 and 4 Angstrom averaged over the four thresholds with the pairs pooled over the whole design; between 0 and 1) (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 configurationProtocol and datasetlDDT (CA-only lDDT-style score without superposition, over all CA pairs below 15 Angstrom in the native structure, as the fraction whose distance error is below 0.5, 1, 2 and 4 Angstrom averaged over the four thresholds with the pairs pooled over the whole design; between 0 and 1)Plddt (ESMFold2 mean per-residue confidence over valid sites on a scale from 0 to 100, averaged over the designs of a target and then over targets; from a second fold of the same sequences with the confidence head on)Scrmsd (CA RMSD between the ESMFold2 prediction of a design and the native backbone at valid sites after optimal Kabsch superposition with the residue correspondence fixed by position, averaged over the designs of a target and then over targets)Sctm (Mean TM-score of the predicted structure to the native backbone, averaged over the designs of a target and then over targets (macro-average); computed on the CA trace at valid sites, normalised by the native length and clipped at one; ESMFold2 as the structure predictor, which is also the reinforcement-learning reward of HyInv)Sctm difference (HyInv default minus the baseline, paired by chain on the same panel with shared folding randomness, printed in units of 10^-3 scTM with a 95% percentile interval; ESMFold2 as the structure predictor; the reference system is the HyInv default setting; the baseline is ProteinMPNN)Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)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 (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.)Runtime (Median wall-clock time of one design request on one NVIDIA H20, 128 candidates per request with a maximum candidate batch of 32 unless the request is the 10,000-design library; the timed region excludes model loading, CUDA graph capture and kernel compilation; the backbone length is named per result; the request is 128 designs for a 148-residue backbone)Runtime (Median wall-clock time of one design request on one NVIDIA H20, 128 candidates per request with a maximum candidate batch of 32 unless the request is the 10,000-design library; the timed region excludes model loading, CUDA graph capture and kernel compilation; the backbone length is named per result; the request is 128 designs for a 402-residue backbone)Runtime (Median wall-clock time of one design request on one NVIDIA H20, 128 candidates per request with a maximum candidate batch of 32 unless the request is the 10,000-design library; the timed region excludes model loading, CUDA graph capture and kernel compilation; the backbone length is named per result; the request is a library of 10,000 designs for a 250-residue backbone)Sctm (Mean TM-score of the predicted structure to the native backbone, averaged over the designs of a target and then over targets; Boltz2 as the structure predictor, with the alignment built from the designed sequence by MMseqs2 against UniRef50; RecentPDB only)Sctm (Mean TM-score of the predicted structure to the native backbone, averaged over the designs of a target and then over targets; Protenix2 as the structure predictor, with the alignment built from the designed sequence by MMseqs2 against UniRef50; RecentPDB only)Sctm difference (HyInv default minus the baseline, paired by chain on RecentPDB with shared folding randomness, printed in units of 10^-3 scTM with a 95% percentile interval; Boltz2 as the structure predictor; the reference system is the HyInv default setting; the baseline is ProteinMPNN)Sctm difference (HyInv default minus the baseline, paired by chain on RecentPDB with shared folding randomness, printed in units of 10^-3 scTM with a 95% percentile interval; Protenix2 as the structure predictor; the reference system is the HyInv default setting; the baseline is ProteinMPNN)Sequence diversity (Mean pairwise normalised Hamming distance between the K designs of a chain over valid sites, then a macro-average over targets; counted at valid sites for every method, because baseline sequences carry X at invalid sites and counting those as identical would lower their diversity)
ProteinMPNN (HyInv report)EvaluationCA-lDDT of designed sequences under ESMFold2 (HyInv report), TS500 (500 chains)0.896 (best in column)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationCA-lDDT of designed sequences under ESMFold2 (HyInv report), TS50 (50 chains)0.892Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationCA-lDDT of designed sequences under ESMFold2 (HyInv report), RecentPDB (121 chains from 111 recent PDB entries)0.865Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationCA-lDDT of designed sequences under ESMFold2 (HyInv report), CATH4.2 test (1,120 chains)0.863Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationCA-lDDT of designed sequences under ESMFold2 (HyInv report), CATH4.3 test (1,882 chains)0.861Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationLatency of a design request on one NVIDIA H20 (HyInv report), Timing backbones for the HyInv inference-time measurementsNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported1,0712,907142Not reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationNovel and foldable designs per de novo backbone at matched diversity (HyInv report), De novo backbones application panel (74 backbones)Not reportedNot reportedNot reportedNot reportedNot reportedNot reported0.050.47Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationpLDDT of ESMFold2 predictions of designed sequences (HyInv report), CATH4.2 test (1,120 chains)Not reported81.5Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationpLDDT of ESMFold2 predictions of designed sequences (HyInv report), CATH4.3 test (1,882 chains)Not reported81.3Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationpLDDT of ESMFold2 predictions of designed sequences (HyInv report), RecentPDB (121 chains from 111 recent PDB entries)Not reported84.3Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationpLDDT of ESMFold2 predictions of designed sequences (HyInv report), TS50 (50 chains)Not reported84.4Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationpLDDT of ESMFold2 predictions of designed sequences (HyInv report), TS500 (500 chains)Not reported90.3 (best in column)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationSelf-consistency RMSD of designed sequences under ESMFold2 (HyInv report), CATH4.2 test (1,120 chains)Not reportedNot reported3.96Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationSelf-consistency RMSD of designed sequences under ESMFold2 (HyInv report), CATH4.3 test (1,882 chains)Not reportedNot reported4.18Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationSelf-consistency RMSD of designed sequences under ESMFold2 (HyInv report), RecentPDB (121 chains from 111 recent PDB entries)Not reportedNot reported4.81Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationSelf-consistency RMSD of designed sequences under ESMFold2 (HyInv report), TS50 (50 chains)Not reportedNot reported2.33 (best in column)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationSelf-consistency RMSD of designed sequences under ESMFold2 (HyInv report), TS500 (500 chains)Not reportedNot reported3.94Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationscTM of designed sequences under Boltz2 (HyInv report), RecentPDB (121 chains from 111 recent PDB entries)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.862Not reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationPaired scTM difference from HyInv under Boltz2 (HyInv report), RecentPDB (121 chains from 111 recent PDB entries)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported+12.3 [3.8, 21.6]Not reportedNot reported
ProteinMPNN (HyInv report)EvaluationPaired scTM difference from HyInv under ESMFold2 (HyInv report), CATH4.2 test (1,120 chains)Not reportedNot reportedNot reportedNot reported+11.0 [2.2, 22.5]Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationPaired scTM difference from HyInv under ESMFold2 (HyInv report), CATH4.3 test (1,882 chains)Not reportedNot reportedNot reportedNot reported+13.6 [2.3, 24.6]Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationPaired scTM difference from HyInv under ESMFold2 (HyInv report), RecentPDB (121 chains from 111 recent PDB entries)Not reportedNot reportedNot reportedNot reported+18.5 [7.3, 30.1] (best in column)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationPaired scTM difference from HyInv under ESMFold2 (HyInv report), TS50 (50 chains)Not reportedNot reportedNot reportedNot reported+13.8 [−6.6, 37.0]Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationPaired scTM difference from HyInv under ESMFold2 (HyInv report), TS500 (500 chains)Not reportedNot reportedNot reportedNot reported+3.7 [−0.5, 7.8]Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationPaired scTM difference from HyInv under Protenix2 (HyInv report), RecentPDB (121 chains from 111 recent PDB entries)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported+16.0 [5.2, 28.0]Not reported
ProteinMPNN (HyInv report)EvaluationscTM of designed sequences under ESMFold2 (HyInv report), CATH4.2 test (1,120 chains)Not reportedNot reportedNot reported0.844Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationscTM of designed sequences under ESMFold2 (HyInv report), CATH4.3 test (1,882 chains)Not reportedNot reportedNot reported0.826Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationscTM of designed sequences under ESMFold2 (HyInv report), RecentPDB (121 chains from 111 recent PDB entries)Not reportedNot reportedNot reported0.842Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationscTM of designed sequences under ESMFold2 (HyInv report), TS50 (50 chains)Not reportedNot reportedNot reported0.906 (best in column)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationscTM of designed sequences under ESMFold2 (HyInv report), TS500 (500 chains)Not reportedNot reportedNot reported0.895Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationscTM of designed sequences under Protenix2 (HyInv report), RecentPDB (121 chains from 111 recent PDB entries)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.862Not reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationSequence diversity of a design set (HyInv report), CATH4.2 test (1,120 chains)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.312
ProteinMPNN (HyInv report)EvaluationSequence diversity of a design set (HyInv report), CATH4.3 test (1,882 chains)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.314
ProteinMPNN (HyInv report)EvaluationSequence diversity of a design set (HyInv report), RecentPDB (121 chains from 111 recent PDB entries)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.307
ProteinMPNN (HyInv report)EvaluationSequence diversity of a design set (HyInv report), TS50 (50 chains)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.272
ProteinMPNN (HyInv report)EvaluationSequence diversity of a design set (HyInv report), TS500 (500 chains)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.264
ProteinMPNN (HyInv report)EvaluationNative sequence recovery of designed sequences (HyInv report), CATH4.2 test (1,120 chains)Not reportedNot reportedNot reportedNot reportedNot reported0.398Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationNative sequence recovery of designed sequences (HyInv report), CATH4.3 test (1,882 chains)Not reportedNot reportedNot reportedNot reportedNot reported0.387Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationNative sequence recovery of designed sequences (HyInv report), RecentPDB (121 chains from 111 recent PDB entries)Not reportedNot reportedNot reportedNot reportedNot reported0.428Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationNative sequence recovery of designed sequences (HyInv report), TS50 (50 chains)Not reportedNot reportedNot reportedNot reportedNot reported0.445Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
ProteinMPNN (HyInv report)EvaluationNative sequence recovery of designed sequences (HyInv report), TS500 (500 chains)Not reportedNot reportedNot reportedNot reportedNot reported0.466 (best in column)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
All 44 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: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
1,071 Runtime (Median wall-clock time of one design request on one NVIDIA H20, 128 candidates per request with a maximum candidate batch of 32 unless the request is the 10,000-design library; the timed region excludes model loading, CUDA graph capture and kernel compilation; the backbone length is named per result; the request is 128 designs for a 148-residue backbone)
millisecond · lower

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

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

Latency of a design request for proteinmpnn on one NVIDIA H20 (HyInv report)

hyinv-20261106-protocol-design-latency-h20

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Table 1, row 'ProteinMPNN', column '128 designs (ms), 148 res.' (page 5 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
2,907 Runtime (Median wall-clock time of one design request on one NVIDIA H20, 128 candidates per request with a maximum candidate batch of 32 unless the request is the 10,000-design library; the timed region excludes model loading, CUDA graph capture and kernel compilation; the backbone length is named per result; the request is 128 designs for a 402-residue backbone)
millisecond · lower

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

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

Latency of a design request for proteinmpnn on one NVIDIA H20 (HyInv report)

hyinv-20261106-protocol-design-latency-h20

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Table 1, row 'ProteinMPNN', column '128 designs (ms), 402 res.' (page 5 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
142 Runtime (Median wall-clock time of one design request on one NVIDIA H20, 128 candidates per request with a maximum candidate batch of 32 unless the request is the 10,000-design library; the timed region excludes model loading, CUDA graph capture and kernel compilation; the backbone length is named per result; the request is a library of 10,000 designs for a 250-residue backbone)
second · lower

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

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

Latency of a design request for proteinmpnn on one NVIDIA H20 (HyInv report)

hyinv-20261106-protocol-design-latency-h20

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Table 1, row 'ProteinMPNN', column '10,000 designs (s)' (page 5 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: CA-lDDT of designed sequences under ESMFold2 (HyInv report)
Dataset: CATH4.2 test (1,120 chains)
0.863 lDDT (CA-only lDDT-style score without superposition, over all CA pairs below 15 Angstrom in the native structure, as the fraction whose distance error is below 0.5, 1, 2 and 4 Angstrom averaged over the four thresholds with the pairs pooled over the whole design; between 0 and 1)
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

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

ProteinMPNN on CATH4.2 test (CA-lDDT of designed sequences under ESMFold2, HyInv report)

hyinv-20261106-protocol-lddt-esmfold2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 15, 'CA-lDDT' block, row 'ProteinMPNN', column 'CATH4.2 test' (page 17 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: CA-lDDT of designed sequences under ESMFold2 (HyInv report)
Dataset: CATH4.3 test (1,882 chains)
0.861 lDDT (CA-only lDDT-style score without superposition, over all CA pairs below 15 Angstrom in the native structure, as the fraction whose distance error is below 0.5, 1, 2 and 4 Angstrom averaged over the four thresholds with the pairs pooled over the whole design; between 0 and 1)
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

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

ProteinMPNN on CATH4.3 test (CA-lDDT of designed sequences under ESMFold2, HyInv report)

hyinv-20261106-protocol-lddt-esmfold2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 15, 'CA-lDDT' block, row 'ProteinMPNN', column 'CATH4.3 test' (page 17 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: CA-lDDT of designed sequences under ESMFold2 (HyInv report)
Dataset: RecentPDB (121 chains from 111 recent PDB entries)
0.865 lDDT (CA-only lDDT-style score without superposition, over all CA pairs below 15 Angstrom in the native structure, as the fraction whose distance error is below 0.5, 1, 2 and 4 Angstrom averaged over the four thresholds with the pairs pooled over the whole design; between 0 and 1)
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

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

ProteinMPNN on RecentPDB (CA-lDDT of designed sequences under ESMFold2, HyInv report)

hyinv-20261106-protocol-lddt-esmfold2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 15, 'CA-lDDT' block, row 'ProteinMPNN', column 'RecentPDB' (page 17 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: CA-lDDT of designed sequences under ESMFold2 (HyInv report)
Dataset: TS50 (50 chains)
0.892 lDDT (CA-only lDDT-style score without superposition, over all CA pairs below 15 Angstrom in the native structure, as the fraction whose distance error is below 0.5, 1, 2 and 4 Angstrom averaged over the four thresholds with the pairs pooled over the whole design; between 0 and 1)
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

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

ProteinMPNN on TS50 (CA-lDDT of designed sequences under ESMFold2, HyInv report)

hyinv-20261106-protocol-lddt-esmfold2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 15, 'CA-lDDT' block, row 'ProteinMPNN', column 'TS50' (page 17 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: CA-lDDT of designed sequences under ESMFold2 (HyInv report)
Dataset: TS500 (500 chains)
0.896 lDDT (CA-only lDDT-style score without superposition, over all CA pairs below 15 Angstrom in the native structure, as the fraction whose distance error is below 0.5, 1, 2 and 4 Angstrom averaged over the four thresholds with the pairs pooled over the whole design; between 0 and 1)
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

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

ProteinMPNN on TS500 (CA-lDDT of designed sequences under ESMFold2, HyInv report)

hyinv-20261106-protocol-lddt-esmfold2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 15, 'CA-lDDT' block, row 'ProteinMPNN', column 'TS500' (page 17 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)
0.05 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)
Configuration: ProteinMPNN (HyInv report)Protocol: pLDDT of ESMFold2 predictions of designed sequences (HyInv report)
Dataset: CATH4.2 test (1,120 chains)
81.5 Plddt (ESMFold2 mean per-residue confidence over valid sites on a scale from 0 to 100, averaged over the designs of a target and then over targets; from a second fold of the same sequences with the confidence head on)
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

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

ProteinMPNN on CATH4.2 test (pLDDT of ESMFold2 predictions of designed sequences, HyInv report)

hyinv-20261106-protocol-plddt-esmfold2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 15, 'pLDDT' block, row 'ProteinMPNN', column 'CATH4.2 test' (page 17 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: pLDDT of ESMFold2 predictions of designed sequences (HyInv report)
Dataset: CATH4.3 test (1,882 chains)
81.3 Plddt (ESMFold2 mean per-residue confidence over valid sites on a scale from 0 to 100, averaged over the designs of a target and then over targets; from a second fold of the same sequences with the confidence head on)
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

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

ProteinMPNN on CATH4.3 test (pLDDT of ESMFold2 predictions of designed sequences, HyInv report)

hyinv-20261106-protocol-plddt-esmfold2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 15, 'pLDDT' block, row 'ProteinMPNN', column 'CATH4.3 test' (page 17 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: pLDDT of ESMFold2 predictions of designed sequences (HyInv report)
Dataset: RecentPDB (121 chains from 111 recent PDB entries)
84.3 Plddt (ESMFold2 mean per-residue confidence over valid sites on a scale from 0 to 100, averaged over the designs of a target and then over targets; from a second fold of the same sequences with the confidence head on)
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

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

ProteinMPNN on RecentPDB (pLDDT of ESMFold2 predictions of designed sequences, HyInv report)

hyinv-20261106-protocol-plddt-esmfold2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 15, 'pLDDT' block, row 'ProteinMPNN', column 'RecentPDB' (page 17 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: pLDDT of ESMFold2 predictions of designed sequences (HyInv report)
Dataset: TS50 (50 chains)
84.4 Plddt (ESMFold2 mean per-residue confidence over valid sites on a scale from 0 to 100, averaged over the designs of a target and then over targets; from a second fold of the same sequences with the confidence head on)
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

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

ProteinMPNN on TS50 (pLDDT of ESMFold2 predictions of designed sequences, HyInv report)

hyinv-20261106-protocol-plddt-esmfold2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 15, 'pLDDT' block, row 'ProteinMPNN', column 'TS50' (page 17 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: pLDDT of ESMFold2 predictions of designed sequences (HyInv report)
Dataset: TS500 (500 chains)
90.3 Plddt (ESMFold2 mean per-residue confidence over valid sites on a scale from 0 to 100, averaged over the designs of a target and then over targets; from a second fold of the same sequences with the confidence head on)
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

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

ProteinMPNN on TS500 (pLDDT of ESMFold2 predictions of designed sequences, HyInv report)

hyinv-20261106-protocol-plddt-esmfold2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 15, 'pLDDT' block, row 'ProteinMPNN', column 'TS500' (page 17 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: Self-consistency RMSD of designed sequences under ESMFold2 (HyInv report)
Dataset: CATH4.2 test (1,120 chains)
3.96 Scrmsd (CA RMSD between the ESMFold2 prediction of a design and the native backbone at valid sites after optimal Kabsch superposition with the residue correspondence fixed by position, averaged over the designs of a target and then over targets)
angstrom · lower

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

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

ProteinMPNN on CATH4.2 test (Self-consistency RMSD of designed sequences under ESMFold2, HyInv report)

hyinv-20261106-protocol-scrmsd-esmfold2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 15, 'scRMSD' block, row 'ProteinMPNN', column 'CATH4.2 test' (page 17 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: Self-consistency RMSD of designed sequences under ESMFold2 (HyInv report)
Dataset: CATH4.3 test (1,882 chains)
4.18 Scrmsd (CA RMSD between the ESMFold2 prediction of a design and the native backbone at valid sites after optimal Kabsch superposition with the residue correspondence fixed by position, averaged over the designs of a target and then over targets)
angstrom · lower

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

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

ProteinMPNN on CATH4.3 test (Self-consistency RMSD of designed sequences under ESMFold2, HyInv report)

hyinv-20261106-protocol-scrmsd-esmfold2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 15, 'scRMSD' block, row 'ProteinMPNN', column 'CATH4.3 test' (page 17 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: Self-consistency RMSD of designed sequences under ESMFold2 (HyInv report)
Dataset: RecentPDB (121 chains from 111 recent PDB entries)
4.81 Scrmsd (CA RMSD between the ESMFold2 prediction of a design and the native backbone at valid sites after optimal Kabsch superposition with the residue correspondence fixed by position, averaged over the designs of a target and then over targets)
angstrom · lower

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

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

ProteinMPNN on RecentPDB (Self-consistency RMSD of designed sequences under ESMFold2, HyInv report)

hyinv-20261106-protocol-scrmsd-esmfold2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 15, 'scRMSD' block, row 'ProteinMPNN', column 'RecentPDB' (page 17 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: Self-consistency RMSD of designed sequences under ESMFold2 (HyInv report)
Dataset: TS50 (50 chains)
2.33 Scrmsd (CA RMSD between the ESMFold2 prediction of a design and the native backbone at valid sites after optimal Kabsch superposition with the residue correspondence fixed by position, averaged over the designs of a target and then over targets)
angstrom · lower

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

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

ProteinMPNN on TS50 (Self-consistency RMSD of designed sequences under ESMFold2, HyInv report)

hyinv-20261106-protocol-scrmsd-esmfold2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 15, 'scRMSD' block, row 'ProteinMPNN', column 'TS50' (page 17 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: Self-consistency RMSD of designed sequences under ESMFold2 (HyInv report)
Dataset: TS500 (500 chains)
3.94 Scrmsd (CA RMSD between the ESMFold2 prediction of a design and the native backbone at valid sites after optimal Kabsch superposition with the residue correspondence fixed by position, averaged over the designs of a target and then over targets)
angstrom · lower

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

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

ProteinMPNN on TS500 (Self-consistency RMSD of designed sequences under ESMFold2, HyInv report)

hyinv-20261106-protocol-scrmsd-esmfold2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 15, 'scRMSD' block, row 'ProteinMPNN', column 'TS500' (page 17 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: scTM of designed sequences under Boltz2 (HyInv report)
Dataset: RecentPDB (121 chains from 111 recent PDB entries)
0.862 Sctm (Mean TM-score of the predicted structure to the native backbone, averaged over the designs of a target and then over targets; Boltz2 as the structure predictor, with the alignment built from the designed sequence by MMseqs2 against UniRef50; RecentPDB only)
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

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

ProteinMPNN on RecentPDB Boltz2 (scTM of designed sequences under Boltz2, HyInv report)

hyinv-20261106-protocol-sctm-boltz2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Table 6, row 'ProteinMPNN', column 'RecentPDB, Boltz2' (page 16 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: Paired scTM difference from HyInv under Boltz2 (HyInv report)
Dataset: RecentPDB (121 chains from 111 recent PDB entries)
+12.3 [3.8, 21.6] Sctm difference (HyInv default minus the baseline, paired by chain on RecentPDB with shared folding randomness, printed in units of 10^-3 scTM with a 95% percentile interval; Boltz2 as the structure predictor; the reference system is the HyInv default setting; the baseline is ProteinMPNN)
unitless · higher

Uncertainty: 95% CI 3.8 to 21.6. Printed in units of 10^-3 scTM, as the point estimate is. The interval excludes zero.

Coverage: Not reported scored / Not reported eligible

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

HyInv minus ProteinMPNN on RecentPDB Boltz2 (paired scTM difference, HyInv report)

hyinv-20261106-protocol-sctm-difference-boltz2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Table 7, row 'ProteinMPNN', column 'RecentPDB, Boltz2' (page 16 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: Paired scTM difference from HyInv under ESMFold2 (HyInv report)
Dataset: CATH4.2 test (1,120 chains)
+11.0 [2.2, 22.5] Sctm difference (HyInv default minus the baseline, paired by chain on the same panel with shared folding randomness, printed in units of 10^-3 scTM with a 95% percentile interval; ESMFold2 as the structure predictor; the reference system is the HyInv default setting; the baseline is ProteinMPNN)
unitless · higher

Uncertainty: 95% CI 2.2 to 22.5. Printed in units of 10^-3 scTM, as the point estimate is. The interval excludes zero.

Coverage: Not reported scored / Not reported eligible

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

HyInv minus ProteinMPNN on CATH4.2 test (paired scTM difference, HyInv report)

hyinv-20261106-protocol-sctm-difference-esmfold2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Table 7, row 'ProteinMPNN', column 'CATH4.2 test' (page 16 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: Paired scTM difference from HyInv under ESMFold2 (HyInv report)
Dataset: CATH4.3 test (1,882 chains)
+13.6 [2.3, 24.6] Sctm difference (HyInv default minus the baseline, paired by chain on the same panel with shared folding randomness, printed in units of 10^-3 scTM with a 95% percentile interval; ESMFold2 as the structure predictor; the reference system is the HyInv default setting; the baseline is ProteinMPNN)
unitless · higher

Uncertainty: 95% CI 2.3 to 24.6. Printed in units of 10^-3 scTM, as the point estimate is. The interval excludes zero.

Coverage: Not reported scored / Not reported eligible

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

HyInv minus ProteinMPNN on CATH4.3 test (paired scTM difference, HyInv report)

hyinv-20261106-protocol-sctm-difference-esmfold2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Table 7, row 'ProteinMPNN', column 'CATH4.3 test' (page 16 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: Paired scTM difference from HyInv under ESMFold2 (HyInv report)
Dataset: RecentPDB (121 chains from 111 recent PDB entries)
+18.5 [7.3, 30.1] Sctm difference (HyInv default minus the baseline, paired by chain on the same panel with shared folding randomness, printed in units of 10^-3 scTM with a 95% percentile interval; ESMFold2 as the structure predictor; the reference system is the HyInv default setting; the baseline is ProteinMPNN)
unitless · higher

Uncertainty: 95% CI 7.3 to 30.1. Printed in units of 10^-3 scTM, as the point estimate is. The interval excludes zero.

Coverage: Not reported scored / Not reported eligible

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

HyInv minus ProteinMPNN on RecentPDB (paired scTM difference, HyInv report)

hyinv-20261106-protocol-sctm-difference-esmfold2

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Table 7, row 'ProteinMPNN', column 'RecentPDB, ESMFold2' (page 16 of 21)

Source checking is not independent reproduction. Release 2026-11-21-adc15377fab2.

Use this configuration

How it works, versions and access

Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this configuration. Consult the linked sources and evaluation records below.

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 2026-11-21-adc15377fab2
Property and statementOriginal source and locationReview and provenance

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

Sources and history

Release 2026-11-21-adc15377fab2 · Record review: source checked

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

Technical metadata for this record is tracked under stable ID hyinv-20261106-config-proteinmpnn.

Source locator: Table 5 row 'ProteinMPNN'; Section 5.1 'Baselines'; Appendix D.1

Related records

How to cite

ProteinMPNN (HyInv report). Rewire biological model benchmark database, release 2026-11-21-adc15377fab2. https://benchmarks.rewirebio.io/database/configuration/hyinv-20261106-config-proteinmpnn/

Release 2026-11-21-adc15377fab2. Rankings and values change between releases, so keep the release id in the citation. Cite the original publication as well for any value you reuse: each result links its source.

The compilation and annotations made by Rewire in this release are offered under CC BY 4.0; values and text taken from cited sources stay under the terms of those sources and are not covered by this licence. Data licence

Suggest a correction