rewire.it
Task

Protein design / inverse folding

Inverse-folding evaluation asks whether a method can propose amino-acid sequences compatible with a specified protein structure.

Sourcesdauparas/ProteinMPNN official source · ProteinMPNN README: overview, scoring outputs and training documentation

0 evaluations · 0 metric rows

At a glance

Inputs, training, access and other details

Explanatory profile: source reviewed · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.

Data, procedure and scoring
PropertyDescription and evidence
Entity typeTask guide; concrete protocol identities remain separate.
Sourcesdauparas/ProteinMPNN official source · ProteinMPNN README: overview, scoring outputs and training documentation
DatasetsNo single dataset is fixed by this guide. Select a linked protocol and its versioned data release. · Not applicable
Sourcesdauparas/ProteinMPNN official source · ProteinMPNN README: overview, scoring outputs and training documentation
OrganismsNo shared organism population is defined at this guide level. Record it for each selected dataset. · Not applicable
Sourcesdauparas/ProteinMPNN official source · ProteinMPNN README: overview, scoring outputs and training documentation
AssaysNo single measurement assay is fixed by this guide; the endpoint and assay belong to the selected protocol. · Not applicable
Sourcesdauparas/ProteinMPNN official source · ProteinMPNN README: overview, scoring outputs and training documentation
SplitsNo executable split is attached to this task identity. Use the selected protocol’s split manifest. · Not applicable
Sourcesdauparas/ProteinMPNN official source · ProteinMPNN README: overview, scoring outputs and training documentation
Allowed inputsA target protein backbone and declared structural or sequence constraints for an inverse-folding protocol.
Sourcesdauparas/ProteinMPNN official source · ProteinMPNN README: overview, scoring outputs and training documentation
AdaptationNo common fitting regime is imposed here. Keep pretrained, frozen, probed, fine-tuned and conventional methods distinct where applicable. · Not applicable
Sourcesdauparas/ProteinMPNN official source · ProteinMPNN README: overview, scoring outputs and training documentation
MetricsProtocol-specific sequence recovery or structural assessment; experimental validation, when available, is a separate endpoint.
Sourcesdauparas/ProteinMPNN official source · ProteinMPNN README: overview, scoring outputs and training documentation
BaselinesUse inverse-folding comparators supplied with the selected benchmark and match structural inputs and constraints.
Sourcesdauparas/ProteinMPNN official source · ProteinMPNN README: overview, scoring outputs and training documentation

How it works

How it worksConceptual evaluation workflow
Conceptual evaluation workflow1. Select held-out structural targets. Then: 2. Declare allowed conditioning. Then: 3. Generate or score candidate sequences. Then: 4. Evaluate the specified endpointConceptual evaluation workflow1. Select held-out structural targets. Then: 2. Declare allowed conditioning. Then: 3. Generate or score candidate sequences. Then: 4. Evaluate the specified endpointConceptual evaluation workflow1. Select held-out structural targets. Then: 2. Declare allowed conditioning. Then: 3. Generate or score candidate sequences. Then: 4. Evaluate the specified endpoint

Conceptual task guide. Dataset preparation, parameters and scoring must come from a separately identified protocol.

Sourcesdauparas/ProteinMPNN official source · ProteinMPNN README: overview, scoring outputs and training documentation
Choosing an evaluation

Keep inverse folding separate from sequence-only generation and experimental function. ProteinMPNN takes structural context and produces sequence probabilities or candidate sequences. A concrete benchmark must state the held-out structures, permitted constraints and assessment. Recovery of a reference sequence and experimental success answer different questions.

Sourcesdauparas/ProteinMPNN official source · ProteinMPNN README: overview, scoring outputs and training documentation
Task scope

This is a task guide, not a single versioned benchmark protocol. The connected resources provide examples or concrete procedures. A candidate method or proposed control is not evidence that an evaluation has been completed.

Sourcesdauparas/ProteinMPNN official source · ProteinMPNN README: overview, scoring outputs and training documentation

Tested entities and results

Release 2026-09-17-d277315f7d76 · 0 evaluations · 0 metric rows. Different protocols are not a single leaderboard.

No evaluations linked in this release.

Papers and result coverage

Last literature check: 2026-09-17. Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.

Paper or primary resourceVersionReference
Robust deep learning based protein sequence design using ProteinMPNNPMC primary-source artifact, version pinned by SHA256Read source
DOI: 10.1126/science.add2187

What is still missing

  • Protein design is a broad task. ProteinMPNN reports native sequence recovery on 402 backbones and separate noisy-backbone/experimental design evaluations; no general protein-design ranking. New primary paper pinned, concrete protocol extraction required.
Search and extraction details

broad task requires concrete protocol links

Searches

  • Protein design / inverse folding primary paper benchmark results

Evidence locations

  • Native-backbone test in Results and Figure2A; Methods; Table1

Strengths and limitations

Strengths supported by sources

  • A specified structural target provides a clear conditioning context for evaluating sequence proposals.
    Sourcesdauparas/ProteinMPNN official source · ProteinMPNN README: overview, scoring outputs and training documentation

Limitations and conditions

  • Reference-sequence recovery does not by itself establish folding, function or experimental success.
    Sourcesdauparas/ProteinMPNN official source · ProteinMPNN README: overview, scoring outputs and training documentation
Profile review details

Reviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol.

Stable record: catalog-task-protein-design

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.

17 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-17-d277315f7d76
Property and statementOriginal source and locationReview and provenance
Diagram caption

Conceptual task guide. Dataset preparation, parameters and scoring must come from a separately identified protocol.

Individual claims
dauparas/ProteinMPNN official source

Original source ↗

ProteinMPNN README: overview, scoring outputs and training documentation

Version: 8907e6671bfbfc92303b5f79c4b5e6ce47cdef57
Retrieved: 2026-09-16T10:30:25.524269+00:00

source checked

automated source review · 2026-09-16

Audit details

Reviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol.

Field: attributes.profile.diagram.caption

Source artifact SHA-256: 772ebe52d2ba5100a28a888910c6f0c9fd4ded1d1372e3d89f6f1c48707e0365

Hash scope: Hash scope not separately documented; inspect source record

Diagram steps

["Select held-out structural targets","Declare allowed conditioning","Generate or score candidate sequences","Evaluate the specified endpoint"]

Individual claims
dauparas/ProteinMPNN official source

Original source ↗

ProteinMPNN README: overview, scoring outputs and training documentation

Version: 8907e6671bfbfc92303b5f79c4b5e6ce47cdef57
Retrieved: 2026-09-16T10:30:25.524269+00:00

source checked

automated source review · 2026-09-16

Audit details

Reviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol.

Field: attributes.profile.diagram.steps

Source artifact SHA-256: 772ebe52d2ba5100a28a888910c6f0c9fd4ded1d1372e3d89f6f1c48707e0365

Hash scope: Hash scope not separately documented; inspect source record

Diagram title

Conceptual evaluation workflow

Individual claims
dauparas/ProteinMPNN official source

Original source ↗

ProteinMPNN README: overview, scoring outputs and training documentation

Version: 8907e6671bfbfc92303b5f79c4b5e6ce47cdef57
Retrieved: 2026-09-16T10:30:25.524269+00:00

source checked

automated source review · 2026-09-16

Audit details

Reviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol.

Field: attributes.profile.diagram.title

Source artifact SHA-256: 772ebe52d2ba5100a28a888910c6f0c9fd4ded1d1372e3d89f6f1c48707e0365

Hash scope: Hash scope not separately documented; inspect source record

Entity type

Task guide; concrete protocol identities remain separate.

Individual claims
dauparas/ProteinMPNN official source

Original source ↗

ProteinMPNN README: overview, scoring outputs and training documentation

Version: 8907e6671bfbfc92303b5f79c4b5e6ce47cdef57
Retrieved: 2026-09-16T10:30:25.524269+00:00

source checked

automated source review · 2026-09-16

Audit details

Reviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol.

Field: attributes.profile.facts.0.value

Source artifact SHA-256: 772ebe52d2ba5100a28a888910c6f0c9fd4ded1d1372e3d89f6f1c48707e0365

Hash scope: Hash scope not separately documented; inspect source record

Datasets

No single dataset is fixed by this guide. Select a linked protocol and its versioned data release.

Individual claims
dauparas/ProteinMPNN official source

Original source ↗

ProteinMPNN README: overview, scoring outputs and training documentation

Version: 8907e6671bfbfc92303b5f79c4b5e6ce47cdef57
Retrieved: 2026-09-16T10:30:25.524269+00:00

inapplicable

automated source review · 2026-09-16

Audit details

Reviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol.

Field: attributes.profile.facts.1.value

Source artifact SHA-256: 772ebe52d2ba5100a28a888910c6f0c9fd4ded1d1372e3d89f6f1c48707e0365

Hash scope: Hash scope not separately documented; inspect source record

Organisms

No shared organism population is defined at this guide level. Record it for each selected dataset.

Individual claims
dauparas/ProteinMPNN official source

Original source ↗

ProteinMPNN README: overview, scoring outputs and training documentation

Version: 8907e6671bfbfc92303b5f79c4b5e6ce47cdef57
Retrieved: 2026-09-16T10:30:25.524269+00:00

inapplicable

automated source review · 2026-09-16

Audit details

Reviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol.

Field: attributes.profile.facts.2.value

Source artifact SHA-256: 772ebe52d2ba5100a28a888910c6f0c9fd4ded1d1372e3d89f6f1c48707e0365

Hash scope: Hash scope not separately documented; inspect source record

Assays

No single measurement assay is fixed by this guide; the endpoint and assay belong to the selected protocol.

Individual claims
dauparas/ProteinMPNN official source

Original source ↗

ProteinMPNN README: overview, scoring outputs and training documentation

Version: 8907e6671bfbfc92303b5f79c4b5e6ce47cdef57
Retrieved: 2026-09-16T10:30:25.524269+00:00

inapplicable

automated source review · 2026-09-16

Audit details

Reviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol.

Field: attributes.profile.facts.3.value

Source artifact SHA-256: 772ebe52d2ba5100a28a888910c6f0c9fd4ded1d1372e3d89f6f1c48707e0365

Hash scope: Hash scope not separately documented; inspect source record

Splits

No executable split is attached to this task identity. Use the selected protocol’s split manifest.

Individual claims
dauparas/ProteinMPNN official source

Original source ↗

ProteinMPNN README: overview, scoring outputs and training documentation

Version: 8907e6671bfbfc92303b5f79c4b5e6ce47cdef57
Retrieved: 2026-09-16T10:30:25.524269+00:00

inapplicable

automated source review · 2026-09-16

Audit details

Reviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol.

Field: attributes.profile.facts.4.value

Source artifact SHA-256: 772ebe52d2ba5100a28a888910c6f0c9fd4ded1d1372e3d89f6f1c48707e0365

Hash scope: Hash scope not separately documented; inspect source record

Allowed inputs

A target protein backbone and declared structural or sequence constraints for an inverse-folding protocol.

Individual claims
dauparas/ProteinMPNN official source

Original source ↗

ProteinMPNN README: overview, scoring outputs and training documentation

Version: 8907e6671bfbfc92303b5f79c4b5e6ce47cdef57
Retrieved: 2026-09-16T10:30:25.524269+00:00

source checked

automated source review · 2026-09-16

Audit details

Reviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol.

Field: attributes.profile.facts.5.value

Source artifact SHA-256: 772ebe52d2ba5100a28a888910c6f0c9fd4ded1d1372e3d89f6f1c48707e0365

Hash scope: Hash scope not separately documented; inspect source record

Adaptation

No common fitting regime is imposed here. Keep pretrained, frozen, probed, fine-tuned and conventional methods distinct where applicable.

Individual claims
dauparas/ProteinMPNN official source

Original source ↗

ProteinMPNN README: overview, scoring outputs and training documentation

Version: 8907e6671bfbfc92303b5f79c4b5e6ce47cdef57
Retrieved: 2026-09-16T10:30:25.524269+00:00

inapplicable

automated source review · 2026-09-16

Audit details

Reviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol.

Field: attributes.profile.facts.6.value

Source artifact SHA-256: 772ebe52d2ba5100a28a888910c6f0c9fd4ded1d1372e3d89f6f1c48707e0365

Hash scope: Hash scope not separately documented; inspect source record

Sources and history

Release 2026-09-17-d277315f7d76 · Record review: discovered

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

Stable ID: catalog-task-protein-design

areas
proteins-complexes
entity level
task
version
Not reported
task
Protein design / inverse folding
scope note
Score or design sequences conditional on a known structure.
benchmark research
review date: 2026-09-17; status: broad_task_requires_concrete_protocol_links; primary sources: evidence-expansion-p2-proteinmpnn-original-3e9042dc0ac2; inspected locators: Native-backbone test in Results and Figure2A; Methods; Table1; searched queries: Protein design / inverse folding primary paper benchmark results; gaps: Protein design is a broad task. ProteinMPNN reports native sequence recovery on 402 backbones and separate noisy-backbone/experimental design evaluations; no general protein-design ranking. New primary paper pinned, concrete protocol extraction required.; claim scope: Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
historical missing metadata
protocol version: not_yet_extracted
metadata review scope
historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
legacy kinds
benchmark
entity classification
review date: 2026-09-17; rationale: This record identifies the biological prediction question or a suite-specific task, rather than a uniquely fixed evaluated procedure. Preserve its task identity and leave split, model adaptation and scoring details on linked protocols/evaluations.; source ids: src-discovery-dauparas-proteinmpnn; source locator: ProteinMPNN README: overview, scoring outputs and training documentation; ambiguities: None recorded
Related records

    Suggest a correction