Pipeline

SPIN + ESM2-35M

SPIN uses frozen ESM-2 35M representations to classify proteins into family-specific functional classes.

Sources

Scaling the profile of life by function with SPIN · 3 Results/3.4 Analysis of the SH3 protein family and representational augmentation across clades (paragraph 4); 3 Results/3.3 SPIN on thioredoxin, a widespread protein family (paragraph 1)

1 evaluation · 1 metric row

How it worksEvaluated procedure (conceptual)

Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings.

Sources

Scaling the profile of life by function with SPIN · 2 Materials and methods/2.1 SPIN architecture (paragraph 1); 2 Materials and methods/2.1 SPIN architecture (paragraph 7)

At a glance

Model type

Protein sequence transformer; this record is the paper-specific evaluated configuration.

Sources

facebookresearch/esm README.md · README.md model description

Biological inputs

Protein sequences, optionally with domain annotations

Sources

Scaling the profile of life by function with SPIN · 2 Materials and methods/2.1 SPIN architecture (paragraph 1); 2 Materials and methods/2.9 Datasets (paragraph 1)

Outputs

Family-specific functional classes and optional domain spans

Sources

Scaling the profile of life by function with SPIN · 3 Results/3.3 SPIN on thioredoxin, a widespread protein family (paragraph 1); 3 Results/3.4 Analysis of the SH3 protein family and representational augmentation across clades (paragraph 4)

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

Evaluations and results

Release 2026-09-17-d277315f7d76 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.

Evaluation setupMetricEvidence origin

Results grouped by the exact reported evaluation
Metric and finding	Coverage and uncertainty	Evidence
SPIN + ESM2-35M: protein function annotation Pipeline: SPIN + ESM2-35MTask: protein function annotationDataset: TRX frozen ESM2-35M backbone in SPIN Author-reported evaluation · Evaluation metadata: needs review
0.796 F1 macro-weighted Unit: fraction · Direction: unknown	Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported	source checkedScaling the profile of life by function with SPIN · Table 1, ESM2-35M Test row, F1_m-w column Source checking is not independent reproduction.

How it works

How the evaluated method works

The method adapts a question-answering-style architecture to optionally predict a domain span and classify the selected region; it can also operate without domain annotations.

Sources

Scaling the profile of life by function with SPIN · 2 Materials and methods/2.1 SPIN architecture (paragraph 1); 2 Materials and methods/2.1 SPIN architecture (paragraph 7)

Underlying method and version boundaries

ESM-2 is a transformer protein language-model family. The official repository exposes residue embeddings, sequence-level pooling and models at several sizes; the study configuration determines which of these is evaluated.

Sources

facebookresearch/esm README.md · README.md; introduction, model description, pretrained-model and usage sections at pinned revision

What was evaluated

The linked evaluation record identifies SPIN + ESM2-35M: protein function annotation. Its dataset, split, adaptation and evidence origin remain attached to the reported results.

Sources

Scaling the profile of life by function with SPIN · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-b2-spin-protein-function-2026

Strengths and limitations

Strengths and considerations

Restricting classification to relevant domains provides an explicit route to family-specific functional distinctions.
Sources
Scaling the profile of life by function with SPIN · 3 Results/3.3 SPIN on thioredoxin, a widespread protein family (paragraph 1); 3 Results (paragraph 1)

Limitations and conditions

The defined functional classes and domain assumptions limit the claim; this is not an unrestricted protein-function annotator.
Sources
Scaling the profile of life by function with SPIN · 2 Materials and methods/2.1 SPIN architecture (paragraph 2); 5 Discussion and conclusions (paragraph 4)

Profile review details

Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction.

Stable record: reported-model-f8f0257b98749a

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
Property	Description and evidence
Model type	Protein sequence transformer; this record is the paper-specific evaluated configuration. Sources facebookresearch/esm README.md · README.md model description
Architecture / procedure	The method adapts a question-answering-style architecture to optionally predict a domain span and classify the selected region; it can also operate without domain annotations. Sources Scaling the profile of life by function with SPIN · 2 Materials and methods/2.1 SPIN architecture (paragraph 1); 2 Materials and methods/2.1 SPIN architecture (paragraph 7)
Biological inputs	Protein sequences, optionally with domain annotations Sources Scaling the profile of life by function with SPIN · 2 Materials and methods/2.1 SPIN architecture (paragraph 1); 2 Materials and methods/2.9 Datasets (paragraph 1)
Outputs	Family-specific functional classes and optional domain spans Sources Scaling the profile of life by function with SPIN · 3 Results/3.3 SPIN on thioredoxin, a widespread protein family (paragraph 1); 3 Results/3.4 Analysis of the SH3 protein family and representational augmentation across clades (paragraph 4)
Parameters	35-million-parameter frozen ESM-2 feature extractor; total classifier size is separate. Sources Scaling the profile of life by function with SPIN · Table vbag064-T1 (paragraph 1); 2 Materials and methods/2.5 An experimental setup for comparative analysis (paragraph 4)
Known versions / configuration	ESM2-35M frozen Sources Scaling the profile of life by function with SPIN · Table vbag064-T1 (paragraph 1); 2 Materials and methods/2.5 An experimental setup for comparative analysis (paragraph 4)
Training data / fitting	An independent predictor is fitted per protein family with three random seeds. Functional labels may come from computational annotation; domain boundaries contribute to the domain-span loss when supplied. Sources Scaling the profile of life by function with SPIN · 2 Materials and methods/2.3 Family-specific model tuning (paragraph 1); 2 Materials and methods/2.4 Bootstrap analysis of domain span predictions (paragraph 1)
Context limits	Sequences longer than 1,024 amino acids are excluded in this study. Sources Scaling the profile of life by function with SPIN · 2 Materials and methods/2.1 SPIN architecture (paragraph 5); 3 Results/3.4 Analysis of the SH3 protein family and representational augmentation across clades (paragraph 2)
Access	Official upstream implementation and usage documentation: https://github.com/facebookresearch/esm/blob/2b369911bb5b4b0dda914521b9475cad1656b2ac/README.md. This pinned documentation revision is not automatically the evaluated weight revision. Sources facebookresearch/esm README.md · README.md; installation, model download and usage instructions
Code licence	MIT (upstream repository code at the cited revision; this does not establish every dependency or historical checkpoint licence). Sources facebookresearch/esm LICENSE · LICENSE; complete licence text
Weights licence	The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. · Not reported in inspected sources Sources facebookresearch/esm README.md · README.md; checkpoint/access documentation and licence scope

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.

20 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-17-d277315f7d76
Property and statement	Original source and location	Review and provenance
Diagram caption Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings. Individual claims	Scaling the profile of life by function with SPIN Original source ↗ 2 Materials and methods/2.1 SPIN architecture (paragraph 1); 2 Materials and methods/2.1 SPIN architecture (paragraph 7) Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558225+00:00	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `9701843e93bf7fa3ead71e19693fb07d483f1022379871adfb04486783722a9d` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps ["Protein sequences, optionally with domain annotations","SPIN + ESM2-35M","Family-specific functional classes and optional domain spans"] Individual claims	Scaling the profile of life by function with SPIN Original source ↗ 2 Materials and methods/2.1 SPIN architecture (paragraph 1); 2 Materials and methods/2.1 SPIN architecture (paragraph 7) Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558225+00:00	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `9701843e93bf7fa3ead71e19693fb07d483f1022379871adfb04486783722a9d` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Evaluated procedure (conceptual) Individual claims	Scaling the profile of life by function with SPIN Original source ↗ 2 Materials and methods/2.1 SPIN architecture (paragraph 1); 2 Materials and methods/2.1 SPIN architecture (paragraph 7) Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558225+00:00	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `9701843e93bf7fa3ead71e19693fb07d483f1022379871adfb04486783722a9d` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Model type Protein sequence transformer; this record is the paper-specific evaluated configuration. Individual claims	facebookresearch/esm README.md Original source ↗ README.md model description Version: 2b369911bb5b4b0dda914521b9475cad1656b2ac Retrieved: 2026-09-16T20:00:00.816433+00:00	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `8b273c21a322fc9473d1b68d0dd40c8166ab2f89e4a190aa26ca87251b97cba9` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Architecture / procedure The method adapts a question-answering-style architecture to optionally predict a domain span and classify the selected region; it can also operate without domain annotations. Individual claims	Scaling the profile of life by function with SPIN Original source ↗ 2 Materials and methods/2.1 SPIN architecture (paragraph 1); 2 Materials and methods/2.1 SPIN architecture (paragraph 7) Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558225+00:00	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `9701843e93bf7fa3ead71e19693fb07d483f1022379871adfb04486783722a9d` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Weights licence The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. Individual claims	facebookresearch/esm README.md Original source ↗ README.md; checkpoint/access documentation and licence scope Version: 2b369911bb5b4b0dda914521b9475cad1656b2ac Retrieved: 2026-09-16T20:00:00.816433+00:00	unreported automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `8b273c21a322fc9473d1b68d0dd40c8166ab2f89e4a190aa26ca87251b97cba9` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Biological inputs Protein sequences, optionally with domain annotations Individual claims	Scaling the profile of life by function with SPIN Original source ↗ 2 Materials and methods/2.1 SPIN architecture (paragraph 1); 2 Materials and methods/2.9 Datasets (paragraph 1) Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558225+00:00	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.2.value` Source artifact SHA-256: `9701843e93bf7fa3ead71e19693fb07d483f1022379871adfb04486783722a9d` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Outputs Family-specific functional classes and optional domain spans Individual claims	Scaling the profile of life by function with SPIN Original source ↗ 3 Results/3.3 SPIN on thioredoxin, a widespread protein family (paragraph 1); 3 Results/3.4 Analysis of the SH3 protein family and representational augmentation across clades (paragraph 4) Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558225+00:00	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.3.value` Source artifact SHA-256: `9701843e93bf7fa3ead71e19693fb07d483f1022379871adfb04486783722a9d` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Parameters 35-million-parameter frozen ESM-2 feature extractor; total classifier size is separate. Individual claims	Scaling the profile of life by function with SPIN Original source ↗ Table vbag064-T1 (paragraph 1); 2 Materials and methods/2.5 An experimental setup for comparative analysis (paragraph 4) Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558225+00:00	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.4.value` Source artifact SHA-256: `9701843e93bf7fa3ead71e19693fb07d483f1022379871adfb04486783722a9d` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Known versions / configuration ESM2-35M frozen Individual claims	Scaling the profile of life by function with SPIN Original source ↗ Table vbag064-T1 (paragraph 1); 2 Materials and methods/2.5 An experimental setup for comparative analysis (paragraph 4) Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558225+00:00	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.5.value` Source artifact SHA-256: `9701843e93bf7fa3ead71e19693fb07d483f1022379871adfb04486783722a9d` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

All evidence (CSV)All evidence (JSONL)How to read the evidence

Sources and history

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

3 source records and release history

Scaling the profile of life by function with SPIN · Original source · journal full text in PMC
facebookresearch/esm README.md · Original source · 2b369911bb5b4b0dda914521b9475cad1656b2ac
facebookresearch/esm LICENSE · Original source · 2b369911bb5b4b0dda914521b9475cad1656b2ac

Download this release

Technical metadata and extraction receipts

Stable ID: reported-model-f8f0257b98749a

areas: proteins-complexes
entity level: method
version: ESM2-35M frozen
reported name: SPIN + ESM2-35M
historical missing metadata: checkpoint revision: not_reported_in_legacy_extract; training data: not_reported_in_legacy_extract; licence: not_reported_in_legacy_extract
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: model
entity classification: review date: 2026-09-17; rationale: This record identifies a composed analysis workflow with separately identifiable upstream models, representations or tools and a downstream prediction/scoring procedure. Results belong to that complete composition rather than to an upstream model alone.; source ids: spin-protein-function-2026; evidence-reported-base-esm-readme-md; source locator: 2 Materials and methods/2.1 SPIN architecture (paragraph 1); 2 Materials and methods/2.1 SPIN architecture (paragraph 7) | README.md model description | 3 Results/3.4 Analysis of the SH3 protein family and representational augmentation across clades (paragraph 4); 3 Results/3.3 SPIN on thioredoxin, a widespread protein family (paragraph 1); ambiguities: This is the paper-specific pipeline identity; unspecified component checkpoints or implementation versions are not inferred from its name.

Related records

model: SPIN + ESM2-35M: protein function annotation

Suggest a correction