Configuration

structure-informed pLM

This structure-informed protein language model uses structural prediction objectives during training to improve variant-effect scoring.

Sources

Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot) · Structure-Informed Protein Language Models; Cross-Modal Masked Learning (Denoising) Framework; Table 4

1 evaluation · 1 result

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

Overview

Model type

Study-specific predictive method; this record is the paper-specific evaluated configuration.

Sources

Biological inputs

Protein sequence at inference; sequence/structure pairs supply additional training supervision

Sources

Outputs

Sequence-based variant-effect scores

Sources

Access

Official study implementation and usage documentation: https://github.com/Shen-Lab/Structure-informed_PLM/blob/2307b101f9bf08223729a68f52b8a6fb21f18991/readMe.md. This pinned documentation revision is not automatically the evaluated weight revision.

Sources

Shen-Lab/Structure-informed_PLM readMe.md · readMe.md; installation, model download and usage instructions

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

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: structure-informed pLM	Task: protein variant-effect classification Dataset: variant-effects benchmark	0.803 AUROC fraction · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source structure-informed pLM: protein variant-effect classification combined amino-acid, secondary structure, solvent accessibility and contact-map scoring Aggregation: Not reported Structure-Informed Protein Language Models are Robust Predictors for Variant Effects · PMC12068927 HTML, Table4, AA+SS+RSA+CM row, AUROC column

Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.

Use this model

How it works, versions and access

How it works

How the evaluated method works

Cross-modal masked learning combines amino-acid recovery with secondary-structure, relative-solvent-accessibility and contact-map prediction heads. The linked AA+SS+RSA+CM configuration uses all four objectives.

Sources

What was evaluated

The linked evaluation record identifies structure-informed pLM: protein variant-effect classification. Its dataset, split, adaptation and evidence origin remain attached to the reported results.

Sources

Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot) · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-b2-structure-informed-plm-2025

Strengths, limitations and unresolved questions

Strengths and limitations

Strengths and considerations

Structural context regularises training without requiring a variant structure at inference.
Sources
Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot) · Structure-Informed Protein Language Models; Cross-Modal Masked Learning (Denoising) Framework; Table 4

Limitations and conditions

The training structural information and family-specific adaptation are part of the evaluated method; it is not equivalent to an unadapted sequence-only encoder.
Sources
Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot) · Structure-Informed Protein Language Models; Cross-Modal Masked Learning (Denoising) Framework; Table 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-035a3ab36a3a6a

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	Study-specific predictive method; this record is the paper-specific evaluated configuration. Sources Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot) · Structure-Informed Protein Language Models; Cross-Modal Masked Learning (Denoising) Framework; Table 4
Architecture / procedure	Cross-modal masked learning combines amino-acid recovery with secondary-structure, relative-solvent-accessibility and contact-map prediction heads. The linked AA+SS+RSA+CM configuration uses all four objectives. Sources Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot) · Structure-Informed Protein Language Models; Cross-Modal Masked Learning (Denoising) Framework; Table 4
Biological inputs	Protein sequence at inference; sequence/structure pairs supply additional training supervision Sources Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot) · Structure-Informed Protein Language Models; Cross-Modal Masked Learning (Denoising) Framework; Table 4
Outputs	Sequence-based variant-effect scores Sources Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot) · Structure-Informed Protein Language Models; Cross-Modal Masked Learning (Denoising) Framework; Table 4
Parameters	An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sources Sources (2) Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot); Shen-Lab/Structure-informed_PLM readMe.md · Complete primary text and named comparison table; inspected for aggregate parameter count (component sizes are not added without an exact configuration); readMe.md at pinned repository revision
Known versions / configuration	structure-informed pLM is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sources Sources Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot) · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label.
Training data / fitting	Family datasets combine sequence information with experimental PDB and predicted AlphaFold structures. Sources Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot) · Structure-Informed Protein Language Models; Cross-Modal Masked Learning (Denoising) Framework; Table 4
Context limits	A maximum input/context length for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sources Sources (2) Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot); Shen-Lab/Structure-informed_PLM readMe.md · Complete primary text and named comparison table; inspected for explicit maximum input length (dataset lengths and family-wide limits are not substituted); readMe.md at pinned repository revision
Access	Official study implementation and usage documentation: https://github.com/Shen-Lab/Structure-informed_PLM/blob/2307b101f9bf08223729a68f52b8a6fb21f18991/readMe.md. This pinned documentation revision is not automatically the evaluated weight revision. Sources Shen-Lab/Structure-informed_PLM readMe.md · readMe.md; installation, model download and usage instructions
Code licence	MIT (study repository code at the cited revision; this does not establish every dependency or historical checkpoint licence). Sources Shen-Lab/Structure-informed_PLM 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 Shen-Lab/Structure-informed_PLM readMe.md · readMe.md; checkpoint/access documentation and licence scope

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.

21 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-29-06401fd5b220
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	Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot) Original source ↗ Structure-Informed Protein Language Models; Cross-Modal Masked Learning (Denoising) Framework; Table 4 Version: Human Genetics 2025 journal article (online 2024) Retrieved: 2026-09-16T19:58:11.209175+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: `6686d2646e7b1b1203a7ef6d48bacf966b4cd6b0895fd2855551937c6bb87111` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps Protein sequence at inference structure-informed pLM Sequence-based variant-effect scores Individual claims	Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot) Original source ↗ Structure-Informed Protein Language Models; Cross-Modal Masked Learning (Denoising) Framework; Table 4 Version: Human Genetics 2025 journal article (online 2024) Retrieved: 2026-09-16T19:58:11.209175+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: `6686d2646e7b1b1203a7ef6d48bacf966b4cd6b0895fd2855551937c6bb87111` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Evaluated procedure (conceptual) Individual claims	Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot) Original source ↗ Structure-Informed Protein Language Models; Cross-Modal Masked Learning (Denoising) Framework; Table 4 Version: Human Genetics 2025 journal article (online 2024) Retrieved: 2026-09-16T19:58:11.209175+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: `6686d2646e7b1b1203a7ef6d48bacf966b4cd6b0895fd2855551937c6bb87111` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Model type Study-specific predictive method; this record is the paper-specific evaluated configuration. Individual claims	Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot) Original source ↗ Structure-Informed Protein Language Models; Cross-Modal Masked Learning (Denoising) Framework; Table 4 Version: Human Genetics 2025 journal article (online 2024) Retrieved: 2026-09-16T19:58:11.209175+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: `6686d2646e7b1b1203a7ef6d48bacf966b4cd6b0895fd2855551937c6bb87111` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Architecture / procedure Cross-modal masked learning combines amino-acid recovery with secondary-structure, relative-solvent-accessibility and contact-map prediction heads. The linked AA+SS+RSA+CM configuration uses all four objectives. Individual claims	Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot) Original source ↗ Structure-Informed Protein Language Models; Cross-Modal Masked Learning (Denoising) Framework; Table 4 Version: Human Genetics 2025 journal article (online 2024) Retrieved: 2026-09-16T19:58:11.209175+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: `6686d2646e7b1b1203a7ef6d48bacf966b4cd6b0895fd2855551937c6bb87111` 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	Shen-Lab/Structure-informed_PLM readMe.md Original source ↗ readMe.md; checkpoint/access documentation and licence scope Version: 2307b101f9bf08223729a68f52b8a6fb21f18991 Retrieved: 2026-09-16T20:43:16.171470+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: `06787a14ac0e9a094fe524472bb2b06b5025aa8af122d913f3ed9c352938b161` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Biological inputs Protein sequence at inference; sequence/structure pairs supply additional training supervision Individual claims	Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot) Original source ↗ Structure-Informed Protein Language Models; Cross-Modal Masked Learning (Denoising) Framework; Table 4 Version: Human Genetics 2025 journal article (online 2024) Retrieved: 2026-09-16T19:58:11.209175+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: `6686d2646e7b1b1203a7ef6d48bacf966b4cd6b0895fd2855551937c6bb87111` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Outputs Sequence-based variant-effect scores Individual claims	Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot) Original source ↗ Structure-Informed Protein Language Models; Cross-Modal Masked Learning (Denoising) Framework; Table 4 Version: Human Genetics 2025 journal article (online 2024) Retrieved: 2026-09-16T19:58:11.209175+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: `6686d2646e7b1b1203a7ef6d48bacf966b4cd6b0895fd2855551937c6bb87111` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims	Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot) Original source ↗ Complete primary text and named comparison table; inspected for aggregate parameter count (component sizes are not added without an exact configuration); readMe.md at pinned repository revision Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Human Genetics 2025 journal article (online 2024) Retrieved: 2026-09-16T19:58:11.209175+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.4.value` Source artifact SHA-256: `6686d2646e7b1b1203a7ef6d48bacf966b4cd6b0895fd2855551937c6bb87111` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims	Shen-Lab/Structure-informed_PLM readMe.md Original source ↗ Complete primary text and named comparison table; inspected for aggregate parameter count (component sizes are not added without an exact configuration); readMe.md at pinned repository revision Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 2307b101f9bf08223729a68f52b8a6fb21f18991 Retrieved: 2026-09-16T20:43:16.171470+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.4.value` Source artifact SHA-256: `06787a14ac0e9a094fe524472bb2b06b5025aa8af122d913f3ed9c352938b161` 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

View linked audit checks and correction history

Release 2026-09-29-06401fd5b220 · Record review: needs review

4 source records and release history

Structure-Informed Protein Language Models are Robust Predictors for Variant Effects · Original source · Human Genetics 2025 journal article (online 2024)
Structure-Informed Protein Language Models are Robust Predictors for Variant Effects (reviewed HTML snapshot) · Original source · Human Genetics 2025 journal article (online 2024)
Shen-Lab/Structure-informed_PLM readMe.md · Original source · 2307b101f9bf08223729a68f52b8a6fb21f18991
Shen-Lab/Structure-informed_PLM LICENSE · Original source · 2307b101f9bf08223729a68f52b8a6fb21f18991

Download this release

Technical metadata and extraction receipts

Stable ID: reported-model-035a3ab36a3a6a

areas: proteins-complexes
entity level: method
version: not stated in table
reported name: structure-informed pLM
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 source-scoped entry preserves the method/configuration actually named in an evaluation. It is neither a global family identity nor proof of an immutable checkpoint; the linked evaluation retains adaptation, fitting and scoring details.; source ids: evidence-reported-structure-informed-current-html; source locator: Structure-Informed Protein Language Models; Cross-Modal Masked Learning (Denoising) Framework; Table 4; ambiguities: Configuration means the source-labelled evaluated identity. It does not establish missing checkpoint hashes, default settings or equivalence to same-named records in other papers.

Related records

model: structure-informed pLM: protein variant-effect classification

Suggest a correction