rewirebio.iobenchmarks

Use caseProteins and complexesResearch only

Predict missense variant effects in a protein of interest

Which predictor best ranks the functional effects of amino acid substitutions in a given protein, with or without an alignment or structure?

You bring
  • Wild-type protein sequence and the substitutions to score
  • Optionally a multiple sequence alignment, an experimental or predicted structure, and labelled assay data
  • The readout of interest (activity, binding, expression, stability or organismal fitness)
You want
Per-predictor rank correlation with deep mutational scanning readouts across many proteins, with breakdowns by alignment depth, function type and taxon, and pairwise win rates on human proteins. No guarantee for a specific protein.
Evidence in this release
2 comparisons shown · 115 tools · 194 configurations
Kept up to date
Evidence last checked 14 October 2026 · re-checked monthly, next due 14 November 2026
Executive Takeaway

For "Predict missense variant effects in a protein of interest", on ProteinGym zero-shot DMS substitutions (commit 144fe22), All assays (Average_Spearman) and breakdowns (Spearman), AIDO Protein-RAG (16B) and VenusREM share the best value, 0.518, reported by ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22.

Best reported valueAIDO Protein-RAG (16B)ProteinGym zero-shot DMS substitutions Spearman summary at…
Spearman0.518ProteinGym zero-shot DMS substitutions (commit 144fe22), All assays (Average_Spearman) and breakdowns
Baseline on this protocolSite-Independent0.359
Ranked tools970 from independent studies

97 tools have a value on this protocol; 0 of them come from studies whose authors did not develop the tool. The use case's baseline, Site-Independent, scored 0.359 on the same protocol.

Ranking

Ranked on ProteinGym zero-shot DMS substitutions (commit 144fe22), All assays (Average_Spearman) and breakdowns (Spearman, higher is better). Only results on this protocol are ranked; other tools are listed below the table.

44 tools in 97 rows, from 1 source. 0 of 97 results (0%) come from an independent study; 97 are from a source that does not say who ran the tool.

Rank▲ModelSpearman (higher is better)vs Site-IndependentEvidenceCoverageReported byLicense
#10.518+44.3%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#10.518+44.3%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#30.507+41.2%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#40.498+38.7%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#50.496+38.2%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#60.488+35.9%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#70.485+35.1%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#80.479+33.4%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#90.476+32.6%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#100.471+31.2%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#110.470+30.9%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#110.470+30.9%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#130.469+30.6%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#140.466+29.8%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…MIT stated in the inspected…
#150.465+29.5%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#160.458+27.6%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#170.457+27.3%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#180.456+27.0%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#180.456+27.0%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#200.455+26.7%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#200.455+26.7%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#220.452+25.9%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#230.449+25.1%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#240.442+23.1%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#250.440+22.6%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#260.439+22.3%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#260.439+22.3%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#280.438+22.0%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#280.438+22.0%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#280.438+22.0%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#310.437+21.7%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#320.435+21.2%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#330.434+20.9%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#340.433+20.6%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#350.432+20.3%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#350.432+20.3%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#370.430+19.8%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#380.428+19.2%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#390.424+18.1%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#400.422+17.5%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Code: MIT
#400.422+17.5%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#420.419+16.7%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#430.418+16.4%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#440.417+16.2%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#450.414+15.3%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…The official facebook/esm2_…
#460.407+13.4%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#460.407+13.4%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Code: MIT
#460.407+13.4%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#490.406+13.1%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…MIT is declared alongside…
#490.406+13.1%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…The official facebook/esm2_…
#510.405+12.8%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…MIT is declared alongside…
#520.400+11.4%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…The official facebook/esm2_…
#520.400+11.4%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#540.399+11.1%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#550.396+10.3%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#560.395+10.0%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#570.394+9.7%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#580.393+9.5%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#590.392+9.2%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#600.391+8.9%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#610.389+8.4%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#620.387+7.8%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…The official facebook/esm2_…
#630.383+6.7%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#640.380+5.8%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#640.380+5.8%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#660.379+5.6%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#670.378+5.3%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#680.374+4.2%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Code: MIT
#680.374+4.2%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#700.373+3.9%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#700.373+3.9%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#720.369+2.8%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#730.366+1.9%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#740.364+1.4%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#740.364+1.4%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#76
Site-Independent[-] Baseline
0.359Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#770.350-2.5%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#780.349-2.8%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#790.347-3.3%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#790.347-3.3%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#810.343-4.5%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#820.336-6.4%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#830.328-8.6%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#840.321-10.6%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…The official facebook/esm2_…
#850.318-11.4%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#860.317-11.7%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#870.305-15.0%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#880.303-15.6%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#890.282-21.4%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#900.280-22.0%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#910.257-28.4%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Code: MIT
#920.233-35.1%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#930.226-37.0%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…The official facebook/esm2_…
#940.190-47.1%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#950.188-47.6%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#960.106-70.5%Source-checked Source does not say who ran it2/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
#970.102-71.6%Source-checked Source does not say who ran it1/2ProteinGym zero-shot DMS substitutions Spearman…Not recorded
71 tools are evaluated elsewhere in this use case but not on this protocol, so not ranked

Baseline

Site-independent alignment model. An alignment-based model that scores each position separately, without the dependencies between positions that EVmutation adds, and with no neural network. It is the first and simplest model in the ProteinGym substitution baselines table (input modality MSA; Hopf et al. 2017).

Machine-learning methods are compared with the baseline on the same data in one table: ProteinGym zero-shot DMS substitutions (commit 144fe22). Baseline rows are marked in each table.

Tools compared

Comparisons

Unified model comparison for this use case. Compare tools against protocol baselines in a single view.

Rows marked Contested rest on results that other studies disagree with. The results are still shown. See the disagreements that involve this use case for what disagrees and what we are doing about it.

ProteinGym zero-shot DMS substitutions (commit 144fe22)

Direct evidenceSource does not say who ran it: The source prints the value but does not say who ran the tool, so it is not counted as independent.

Average_Spearman: mean over proteins of assay-level Spearman correlation between zero-shot scores and DMS readouts, 217 substitution assays, with breakdowns by MSA depth, function type, taxon and mutational depth

Spearman (higher is better), with the other metrics below each value. Showing the top 10 of 44 rows. The best value in each column is highlighted.

ToolAll assays (Average_Spearman) and breakdowns
AIDO Protein-RAG (16B)foundation model
0.518 (best in column)mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
VenusREMfoundation model
0.518 (best in column)mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
ProSST (K=2048)6 sweepsfoundation model
0.507mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
S3F-MSAfoundation model
0.496mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
S2F-MSAfoundation model
0.488mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
Protrieverfoundation model
0.479mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
0.476mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
PoET (200M)foundation model
0.470mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
S3Ffoundation model
0.470mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
0.466mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
0.465mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
VespaGmachine learning
0.458mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
SaProt (650M)2 sweepsfoundation model
0.457mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
S2Ffoundation model
0.456mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
0.456mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
0.455mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
ProtSSN (ensemble)10 sweepsfoundation model
0.449mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
0.439mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
VESPAmachine learning
0.435mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
Tranception L6 sweepsfoundation model
0.434mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
MSA Transformer (ensemble)2 sweepsfoundation model
0.432mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
0.424mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
ESM-IF1foundation model
0.422mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
0.419mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
ESM2 (650M)6 sweepsfoundation model
0.414mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
ESM-1v (ensemble)2 sweepsfoundation model
0.407mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
ESM-C (300M)2 sweepsfoundation model
0.406mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
MIF-STfoundation model
0.400mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
xTrimoPGLM-3B-MLM7 sweepsfoundation model
0.399mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
0.395mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
ESM-1bfoundation model
0.394mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
VESPAlmachine learning
0.393mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
Progen3 3B6 sweepsfoundation model
0.392mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
Progen2 XL5 sweepsfoundation model
0.391mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
MIFfoundation model
0.383mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
RITA XL4 sweepsfoundation model
0.373mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
0.373mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
CARP (640M)4 sweepsfoundation model
0.369mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
0.359mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
Unirep evotunedfoundation model
0.347mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
MULANfoundation model
0.317mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
ProteinMPNNfoundation model
0.257mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
Unirepfoundation model
0.190mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
ProtGPT2foundation model
0.188mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)
Show all 44 rowsShow the top 10 rows only
Caveats and method
  • Averages over proteins do not predict performance on a single protein of interest.
  • Leaderboard rows were computed by the ProteinGym maintainers with their scoring scripts (origin unreported); no Rewire run on the full track.
  • Assays include multiple substitutions; Depth_1 is the singles-only column.
  • Bootstrap standard errors are relative to the top model (the top row prints 0.0).
  • Some leaderboard models were developed by ProteinGym's authors (for example EVE, Tranception and TranceptEVE).
  • Assays come from proteins of many organisms; results for human proteins alone are not given in this summary.
  • Transcribed from the source; no reproduction by Rewire and no human scientific review.

Protocol: ProteinGym v1.3 zero-shot DMS substitutions

Primary benchmark evaluation shown (ProteinGym zero-shot DMS substitutions (commit 144fe22)). 1 additional study protocols (Livesey and Marsh 2025 VEP rankings) are cited in individual tool drawer rows and under Question, sources and review.

Not covered yet

  • Benchmarks report averages over proteins; performance on a single protein varies and is not predicted by the averages.
  • ProteinGym supervised DMS results are stored as tasks from the 2023 paper, not as protocols, so they cannot be linked here; the supervised summaries at commit 144fe22 were not extracted.
  • ProteinGym zero-shot DMS AUC, MCC, NDCG and top-recall summaries at commit 144fe22 were not extracted.
  • Livesey and Marsh rank scores are relative to the 97 compared predictors; per-protein Spearman values are in the figshare deposit, not retrieved.
  • No Rewire run of a full DMS track exists; the ProteinGym rows are leaderboard values.
  • Qualified human scientific review is outstanding; automated transcription does not establish replication.

Contribute evidence or propose a correction

How to cite

Predict missense variant effects in a protein of interest. Rewire biological model benchmark database, release 2026-11-21-c8bea25e5abb. https://benchmarks.rewirebio.io/use-cases/protein-variant-effect-prediction/

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

Question, sources and review

Who this is for, setting and exclusions

Choose a predictor, or a short list, to rank substitutions in the target protein before or alongside an assay, given whether a deep alignment, a structure or labelled data are available.

Who this is for
  • Researchers planning or interpreting deep mutational scans
  • Protein scientists choosing variants for functional assays
  • Computational biologists selecting a zero-shot variant effect predictor
Biological setting
Zero-shot scoring of amino acid substitutions benchmarked against DMS assays: ProteinGym at commit 144fe22 (217 substitution assays across many organisms) and Livesey and Marsh 2025 (36 human DMS sets with ClinVar and gnomAD variants removed).
Research setting
Research use. Agreement with DMS readouts does not establish clinical pathogenicity.

Outside this use case

  • Clinical pathogenicity classification (see the PP3/BP4 and rare-disease use cases)
  • Folding stability alone (see the protein stability use case)
  • Supervised models trained on the target assay
  • Insertions and deletions
  • Design of new sequences
Sources, review and downloads

Automated source review · 2026-10-14 · Claude review agent; no human review claimed. Independent Claude (Opus 5.5) review agent, separate from the extraction agent that built this batch. Automated review only. Transcription, not reproduction.

Drafted by the extraction agent; reviewed in docs/reviews/vep-use-cases-2026-10-14-review.md.

Release 2026-11-21-c8bea25e5abb · question use-case-protein-variant-effect-prediction

Use-case input digest bfbb7ab9303becad1e3cb395568c26f41e72ddb67cd1a89a06d9eaa0f76bd95f

Download questions and review metadata (JSON) (gzip) · Verify release checksums (gzip)