rewire.itbenchmarks
Configuration

ESM-IF1 [ProteinGym 144fe22b snapshot]

ESM-IF1 designs protein sequences conditioned on backbone coordinates.

Sourcesfacebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models

1 evaluation · 1 result

How it worksESM-IF1 workflow
ESM-IF1 workflow1. Backbone coordinates. Then: 2. Geometric processing. Then: 3. Sequence transformer. Then: 4. Designed sequence or likelihoodESM-IF1 workflow1. Backbone coordinates. Then: 2. Geometric processing. Then: 3. Sequence transformer. Then: 4. Designed sequence or likelihoodESM-IF1 workflow1. Backbone coordinates. Then: 2. Geometric processing. Then: 3. Sequence transformer. Then: 4. Designed sequence or likelihood

Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation.

Sourcesfacebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models

Overview

Model type

Geometric encoder and inverse-folding transformer

Inputs

Protein backbone atom coordinates; the model supports missing backbone spans.

Outputs

Sampled protein sequences or conditional sequence likelihoods.

Sourcesfacebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models

limited source coverage · Automated source review, 2026-09-16. All specifications and missing details

Evaluations and results

1 evaluation · 1 result. Different protocols are not a single leaderboard.

Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: ESM-IF1 [ProteinGym 144fe22b snapshot]Protocol: ProteinGym AMFR official zero-shot Spearman snapshot
Dataset subset: ProteinGym AMFR 4G3O official snapshot cohort
0.433 spearman_rho
correlation · higher

Uncertainty: type: unreported

Coverage: Not reported scored / Not reported eligible

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

ESM-IF1 AMFR official snapshot

Not reported

Aggregation: Not reported

ProteinGym AMFR assay-level Spearman comparison · DMS_substitutions_Spearman_DMS_level.csv line 15, DMS ID=AMFR_HUMAN_Tsuboyama_2023_4G3O, column=ESM-IF1

Source checking is not independent reproduction. Release 2026-09-30-e37e3ab1284d.

Use this model

How it works, versions and access

Related profile: ESM-IF1. This page retains the exact record and its evaluation context.

This configuration

Exact official CSV source-label configuration; checkpoint and per-assay scoring details are not inferred from similarly named methods.

record
ESM-IF1 [ProteinGym 144fe22b snapshot]
configuration
144fe22b07dfaeec2b366f2346203a9838a55b4c
entity type
Configuration

How it works

How it works

ESM-IF1 designs protein sequences conditioned on backbone coordinates. Geometric-vector-perceptron input processing followed by a sequence-to-sequence transformer. The documented inputs are protein backbone atom coordinates; the model supports missing backbone spans. The output consists of sampled protein sequences or conditional sequence likelihoods.

Sourcesfacebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
Versions and reproducibility

esm_if1_gvp4_t16_142M_UR50. The applicable input limits require configuration-specific checking.

Sourcesfacebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
Strengths, limitations and unresolved questions

Strengths and limitations

Strengths and considerations

  • Structure-conditioned design can use partially missing backbones because training included span masking.
    Sourcesfacebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models

Limitations and conditions

  • The public checkpoint name contains 142M but the README parameter table reports 124M. This discrepancy is retained rather than silently selecting a total.
    Sourcesfacebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
Profile review details

Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied.

Stable record: discovery-model-esm-if1

Specifications

Inputs, training, access and other details

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

Inputs, outputs and configuration
PropertyDescription and evidence
Model typeGeometric encoder and inverse-folding transformer
Sourcesfacebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
ArchitectureGeometric-vector-perceptron input processing followed by a sequence-to-sequence transformer.
Sourcesfacebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
InputsProtein backbone atom coordinates; the model supports missing backbone spans.
Sourcesfacebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
OutputsSampled protein sequences or conditional sequence likelihoods.
Sourcesfacebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
ParametersThe official checkpoint identifier contains 142M but the same repository model table states 124M. Both values are retained as a source discrepancy, without choosing a total.
Sourcesfacebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
Known versionsesm_if1_gvp4_t16_142M_UR50.
Sourcesfacebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
Training dataCATH 4.3 and predicted UniRef50 structures; README reports 12M structures predicted by AlphaFold2.
Sourcesfacebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
Training cutoffThe official model table identifies CATH 4.3 and predicted UniRef50 structures, but does not state a common latest-structure or sequence date. · Not reported in inspected sources
Sourcesfacebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
Context limitsThe reviewed inverse-folding usage and model table do not establish a universal maximum backbone length; the structural graph and selected inference configuration determine resource use. · Not reported in inspected sources
Sourcesfacebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
Weights licenceSeparate checkpoint-distribution terms are not stated in the inspected release documentation and licence material. The source-code licence alone is not recorded as an explicit weight grant. · Not reported in inspected sources
Sources (2)facebookresearch/esm: README.md; facebookresearch/esm: LICENSE · README.md: Inverse folding and Pre-trained Models; LICENSE: licence text
AccessOfficial project documentation and implementation: https://github.com/facebookresearch/esm
Sourcesfacebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
Code licenceMIT
Sourcesfacebookresearch/esm: LICENSE · LICENSE: licence text

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.

1 evidence row matching the loaded filters

Claims, original sources and review scope · Release 2026-09-30-e37e3ab1284d
Property and statementOriginal source and locationReview and provenance
Relationship: variant of
discovery-model-esm-if1
Individual claims
ProteinGym AMFR assay-level Spearman comparison

Original source ↗

Pinned ProteinGym Spearman CSV header: ESM-IF1

Version: 144fe22b07dfaeec2b366f2346203a9838a55b4c
Retrieved: 2026-09-30

source checked

automated source review · 2026-09-30T21:40:59.576893+00:00

Audit details

Field: links:variant_of:discovery-model-esm-if1

Claim: uc20260930-config-family-706d10073972021e

Source artifact SHA-256: f432423b87f79ac9778dfac86e3d95be041d246bc618dc0a406b35b0b7466437

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

Inspected artifact

Sources and history

View linked audit checks and correction history

Release 2026-09-30-e37e3ab1284d · Record review: source checked

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

Stable ID: uc20260930-proteingym-amfr-config-esm-if1

areas
proteins-complexes
source locator
See linked evaluation and result locators
missing metadata
checkpoint hash: unextracted
review
method: automated_source_review; reviewer: Codex experimental-use-case curation; date: 2026-09-30; reviewed at: 2026-09-30T21:40:59.576893+00:00; scope: Primary-source transcription and catalogue applicability audit; not human scientific review or independent experimental reproduction.
reported name
ESM-IF1
version
144fe22b07dfaeec2b366f2346203a9838a55b4c
Related records

Suggest a correction