rewirebio.iobenchmarks
Configuration

GenePT-w

GenePT-w represents cells by expression-weighted averages of gene embeddings derived from gene-description text.

SourcesGenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT · Introduction (paragraph 4); Methods/Data Collection and Transformation: (paragraph 2)

1 evaluation · 1 result

How it worksEvaluated procedure (conceptual)
Evaluated procedure (conceptual)1. Gene-description embeddings and single-cell expression values. Then: 2. GenePT-w. Then: 3. Cell embeddings for downstream cell-analysis tasksEvaluated procedure (conceptual)1. Gene-description embeddings and single-cell expression values. Then: 2. GenePT-w. Then: 3. Cell embeddings for downstream cell-analysis tasksEvaluated procedure (conceptual)1. Gene-description embeddings and single-cell expression values. Then: 2. GenePT-w. Then: 3. Cell embeddings for downstream cell-analysis tasks

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

SourcesGenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT · Methods/Data Collection and Transformation: (paragraph 4); Related Work/Using language models for cell biology (paragraph 1)

Overview

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

Model Capabilities & Hardware Requirements

Deployment facts recorded for GenePT-w. Fields the record does not carry are marked not recorded.

ParametersNot recorded
Minimum VRAMNot recorded
Inference LatencyNot recorded
Context WindowNot recorded
AccessOfficial study implementation and usage documentation…
LicenseNot recorded

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: GenePT-wTask: Cell-type structure in frozen embeddings
Dataset: Aorta single-cell dataset
0.54 Adjusted rand index
unitless · unknown

Uncertainty: Not yet extracted

Coverage: Not reported scored / Not reported eligible

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

GenePT-w: Cell-type structure in frozen embeddings

k-means on pretrained cell embeddings; agreement with original cell-type labels.

Aggregation: Not reported

GenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT · Table 2, Aorta / Cell type row, GenePT-w ARI column

Source checking is not independent reproduction. Release 2026-11-21-c8bea25e5abb.

Use this configuration

How it works, versions and access

How it works

How the evaluated method works

Gene descriptions from NCBI are embedded using GPT-3.5. The weighted variant averages gene vectors according to each cell’s expression values; it differs from the sentence-embedding variant.

SourcesGenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT · Methods/Data Collection and Transformation: (paragraph 4); Related Work/Using language models for cell biology (paragraph 1)
What was evaluated

The linked evaluation record identifies GenePT-w: Cell-type structure in frozen embeddings. Its dataset, split, adaptation and evidence origin remain attached to the reported results.

SourcesGenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-lit-b3-011
Strengths, limitations and unresolved questions

Strengths and limitations

Limitations and conditions

  • Depends on coverage and content of gene annotations and a proprietary text-embedding model; it is not a direct measurement of molecular mechanism.
    SourcesGenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT · Appendix/Appendix B Additional results for the gene level functionality and property predictions/B.3 Addressing potential information leakage/B.5 Experiments with tissue-dependent gene emebddings (paragraph 4); Methods/Data Collection and Transformation: (paragraph 1)
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-7c595040de69bc

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 typeStudy-specific predictive method; this record is the paper-specific evaluated configuration.
SourcesGenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT · Methods/Data Collection and Transformation: (paragraph 4); Related Work/Using language models for cell biology (paragraph 1)
Architecture / procedureGene descriptions from NCBI are embedded using GPT-3.5. The weighted variant averages gene vectors according to each cell’s expression values; it differs from the sentence-embedding variant.
SourcesGenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT · Methods/Data Collection and Transformation: (paragraph 4); Related Work/Using language models for cell biology (paragraph 1)
Biological inputsGene-description embeddings and single-cell expression values
SourcesGenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT · Related Work/Deciphering natural language embeddings (paragraph 4); Related Work/Deciphering natural language embeddings (paragraph 5)
OutputsCell embeddings for downstream cell-analysis tasks
SourcesGenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT · Related Work/Deciphering natural language embeddings (paragraph 4); Methods/Downstream gene-level and cell-level applications: (paragraph 1)
ParametersAn aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sources
Sources (2)GenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT; yiqunchen/GenePT README.md · Methods/Data Collection and Transformation:; Methods/Downstream gene-level and cell-level applications:; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision
Known versions / configurationGenePT-w is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sources
SourcesGenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label.
Training data / fittingThe biological representation uses NCBI gene descriptions; the method does not train a new foundation model on a large cell-expression corpus.
SourcesGenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT · Abstract (paragraph 1); Introduction (paragraph 4)
Context limitsA maximum input/context length for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sources
Sources (2)GenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT; yiqunchen/GenePT README.md · Methods/Data Collection and Transformation:; Methods/Downstream gene-level and cell-level applications:; inspected for explicit maximum input length (dataset lengths and family-wide limits are not substituted); README.md at pinned repository revision
AccessOfficial study implementation and usage documentation: https://github.com/yiqunchen/GenePT/blob/3602699e7425a7be577771f8f07e218db6c79b9f/README.md. This pinned documentation revision is not automatically the evaluated weight revision.
Sourcesyiqunchen/GenePT README.md · README.md; installation, model download and usage instructions
Code licenceNo explicit code licence was established from the paper’s availability statement and inspected repository-root documentation. · Not reported in inspected sources
Sourcesyiqunchen/GenePT README.md · README.md and repository-root licence-file search
Weights licenceThe 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
Sourcesyiqunchen/GenePT 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 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview 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
GenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT

Original source ↗

Methods/Data Collection and Transformation: (paragraph 4); Related Work/Using language models for cell biology (paragraph 1)

Version: PMC archival version PMC10614824.2
Retrieved: 2026-09-16T10:44:03.399274+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: 230a2ec55458d9243eaeeebf3244df7409eb02d47f4b809ee56a06dcb6fdd047

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

Inspected artifact

Diagram steps
  • Gene-description embeddings and single-cell expression values
  • GenePT-w
  • Cell embeddings for downstream cell-analysis tasks
Individual claims
GenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT

Original source ↗

Methods/Data Collection and Transformation: (paragraph 4); Related Work/Using language models for cell biology (paragraph 1)

Version: PMC archival version PMC10614824.2
Retrieved: 2026-09-16T10:44:03.399274+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: 230a2ec55458d9243eaeeebf3244df7409eb02d47f4b809ee56a06dcb6fdd047

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

Inspected artifact

Diagram title
Evaluated procedure (conceptual)
Individual claims
GenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT

Original source ↗

Methods/Data Collection and Transformation: (paragraph 4); Related Work/Using language models for cell biology (paragraph 1)

Version: PMC archival version PMC10614824.2
Retrieved: 2026-09-16T10:44:03.399274+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: 230a2ec55458d9243eaeeebf3244df7409eb02d47f4b809ee56a06dcb6fdd047

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
GenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT

Original source ↗

Methods/Data Collection and Transformation: (paragraph 4); Related Work/Using language models for cell biology (paragraph 1)

Version: PMC archival version PMC10614824.2
Retrieved: 2026-09-16T10:44:03.399274+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: 230a2ec55458d9243eaeeebf3244df7409eb02d47f4b809ee56a06dcb6fdd047

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

Inspected artifact

Architecture / procedure
Gene descriptions from NCBI are embedded using GPT-3.5. The weighted variant averages gene vectors according to each cell’s expression values; it differs from the sentence-embedding variant.
Individual claims
GenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT

Original source ↗

Methods/Data Collection and Transformation: (paragraph 4); Related Work/Using language models for cell biology (paragraph 1)

Version: PMC archival version PMC10614824.2
Retrieved: 2026-09-16T10:44:03.399274+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: 230a2ec55458d9243eaeeebf3244df7409eb02d47f4b809ee56a06dcb6fdd047

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
yiqunchen/GenePT README.md

Original source ↗

README.md; checkpoint/access documentation and licence scope

Version: 3602699e7425a7be577771f8f07e218db6c79b9f
Retrieved: 2026-09-16T19:54:16.422790+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: 8740cf98377f964131399de818db5de938db4d9e6abe20fac3cd0354887a99c2

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

Inspected artifact

Biological inputs
Gene-description embeddings and single-cell expression values
Individual claims
GenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT

Original source ↗

Related Work/Deciphering natural language embeddings (paragraph 4); Related Work/Deciphering natural language embeddings (paragraph 5)

Version: PMC archival version PMC10614824.2
Retrieved: 2026-09-16T10:44:03.399274+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: 230a2ec55458d9243eaeeebf3244df7409eb02d47f4b809ee56a06dcb6fdd047

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

Inspected artifact

Outputs
Cell embeddings for downstream cell-analysis tasks
Individual claims
GenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT

Original source ↗

Related Work/Deciphering natural language embeddings (paragraph 4); Methods/Downstream gene-level and cell-level applications: (paragraph 1)

Version: PMC archival version PMC10614824.2
Retrieved: 2026-09-16T10:44:03.399274+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: 230a2ec55458d9243eaeeebf3244df7409eb02d47f4b809ee56a06dcb6fdd047

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
yiqunchen/GenePT README.md

Original source ↗

Methods/Data Collection and Transformation:; Methods/Downstream gene-level and cell-level applications:; 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: 3602699e7425a7be577771f8f07e218db6c79b9f
Retrieved: 2026-09-16T19:54:16.422790+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: 8740cf98377f964131399de818db5de938db4d9e6abe20fac3cd0354887a99c2

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
GenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT

Original source ↗

Methods/Data Collection and Transformation:; Methods/Downstream gene-level and cell-level applications:; 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: PMC archival version PMC10614824.2
Retrieved: 2026-09-16T10:44:03.399274+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: 230a2ec55458d9243eaeeebf3244df7409eb02d47f4b809ee56a06dcb6fdd047

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

Inspected artifact

How to read the evidence

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: needs review

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

Technical metadata for this record is tracked under stable ID reported-model-7c595040de69bc.

Related records

How to cite

GenePT-w. Rewire biological model benchmark database, release 2026-11-21-c8bea25e5abb. https://benchmarks.rewirebio.io/database/configuration/reported-model-7c595040de69bc/

Release 2026-11-21-c8bea25e5abb. 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