MutFormer: description
Description of MutFormer
Transformer language model over reference and mutated human protein sequences, combining self-attention and convolutional layers, pretrained on protein sequences and fine-tuned for deleteriousness prediction.
Replace a category-only description with a sourced functional description (issue #88). Historical releases retain the original value.
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.
7 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Claimed field description Context-only references | Abstract: Deciphering the Language of Nature: A transformer-based language model for deleterious mutations in proteins (MutFormer) qa-descriptions-20261011-e-source-mutformer: summary Version: arXiv:2110.14746 (title and abstract) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of an arXiv API Atom response for this identifier. The response is not guaranteed byte-stable; the title and summary fields are the evidence. |
| Previous value Variant effect predictor for missense variants. Context-only references | Abstract: Deciphering the Language of Nature: A transformer-based language model for deleterious mutations in proteins (MutFormer) qa-descriptions-20261011-e-source-mutformer: summary Version: arXiv:2110.14746 (title and abstract) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of an arXiv API Atom response for this identifier. The response is not guaranteed byte-stable; the title and summary fields are the evidence. |
| Source location qa-descriptions-20261011-e-source-mutformer: summary Context-only references | Abstract: Deciphering the Language of Nature: A transformer-based language model for deleterious mutations in proteins (MutFormer) qa-descriptions-20261011-e-source-mutformer: summary Version: arXiv:2110.14746 (title and abstract) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of an arXiv API Atom response for this identifier. The response is not guaranteed byte-stable; the title and summary fields are the evidence. |
| Claimed value Transformer language model over reference and mutated human protein sequences, combining self-attention and convolutional layers, pretrained on protein sequences and fine-tuned for deleteriousness prediction. Context-only references | Abstract: Deciphering the Language of Nature: A transformer-based language model for deleterious mutations in proteins (MutFormer) qa-descriptions-20261011-e-source-mutformer: summary Version: arXiv:2110.14746 (title and abstract) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of an arXiv API Atom response for this identifier. The response is not guaranteed byte-stable; the title and summary fields are the evidence. |
| Description Replace a category-only description with a sourced functional description (issue #88). Historical releases retain the original value. Context-only references | Abstract: Deciphering the Language of Nature: A transformer-based language model for deleterious mutations in proteins (MutFormer) qa-descriptions-20261011-e-source-mutformer: summary Version: arXiv:2110.14746 (title and abstract) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of an arXiv API Atom response for this identifier. The response is not guaranteed byte-stable; the title and summary fields are the evidence. |
| Relationship: subject somatic-oncogenicity-20261009-method-mutformer Context-only references | Abstract: Deciphering the Language of Nature: A transformer-based language model for deleterious mutations in proteins (MutFormer) qa-descriptions-20261011-e-source-mutformer: summary Version: arXiv:2110.14746 (title and abstract) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of an arXiv API Atom response for this identifier. The response is not guaranteed byte-stable; the title and summary fields are the evidence. |
| Name MutFormer: description Context-only references | Abstract: Deciphering the Language of Nature: A transformer-based language model for deleterious mutations in proteins (MutFormer) qa-descriptions-20261011-e-source-mutformer: summary Version: arXiv:2110.14746 (title and abstract) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of an arXiv API Atom response for this identifier. The response is not guaranteed byte-stable; the title and summary fields are the evidence. |
Sources and history
Release 2026-10-22-1b7cf027e4f6 · Record review: source checked
1 source record and release history
- Abstract: Deciphering the Language of Nature: A transformer-based language model for deleterious mutations in proteins (MutFormer) · Original source · arXiv:2110.14746 (title and abstract)
Technical metadata and extraction receipts
Stable ID: metadata-correction-7d2251999aae9396c21e
- areas
- dna-genomes
- contexts
- clinical_research
- method types
- supervised_machine_learning
- field
- description
- previous value
- Variant effect predictor for missense variants.
- value
- Transformer language model over reference and mutated human protein sequences, combining self-attention and convolutional layers, pretrained on protein sequences and fine-tuned for deleteriousness prediction.
- source locator
- qa-descriptions-20261011-e-source-mutformer: summary
- review
- method: automated-source-review; ai-assisted-source-review; reviewer: claude; reviewer note: Extractor: Claude integrator agent for issue #88. Reviewer: a separate Claude review agent, independent of the extractor; no human review claimed.; date: 2026-10-11; method note: Compared the store diff with origin/main, read each new description against its cited source passage and checked the licence of each new source record.; note: Approved with two corrections, both applied: the MutFormer source licence is CC BY 4.0 per the arXiv abstract page, and the MetaRNN source locator now names the Background passage. Checked the 27 Chen 2020 descriptions row by row against Table 1 (PMC7033911) and spot-checked AlphaMissense, MisFit, popEVE, VARITY, MetaRNN, MutFormer and gMVP against their abstracts; accurate. Licences on the other new sources match Europe PMC.; receipt: data/omics/qa-descriptions-20261011-e/review.json
Related records
- subject: MutFormer