rewirebio.iobenchmarks
Configuration

Evo (frozen embeddings, no trained head)

Evo embeddings used without any trained parameters, scored directly by cosine similarity between embeddings or clustered as whole-genome vectors.

4 evaluations · 4 results6 open disagreements between studies involve its model

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Model Capabilities & Hardware Requirements

Deployment facts recorded for Evo (frozen embeddings, no trained head). Fields the record does not carry are marked not recorded.

ParametersNot recorded
Minimum VRAMNot recorded
Inference LatencyNot recorded
Context WindowNot recorded
AccessNot recorded
LicenseNot recorded

Evaluated Checkpoint: As benchmarked in version 3 of the preprint

Evaluations and results

4 evaluations · 4 results. Different protocols are not a single leaderboard.

Sorted by AUPRC (zero-shot operon boundary prediction scored by embedding cosine similarity times a same-strand indicator, mean over the five sequenced strains) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configurationProtocol and datasetAUPRC (zero-shot operon boundary prediction scored by embedding cosine similarity times a same-strand indicator, mean over the five sequenced strains)AUPRC (zero-shot pair scoring by embedding cosine similarity, genus-level split, mean over held-out test genomes)AUROC (zero-shot operon boundary prediction scored by embedding cosine similarity times a same-strand indicator, mean over the five sequenced strains)AUROC (zero-shot pair scoring by embedding cosine similarity, genus-level split, mean over held-out test genomes)
Evo (frozen embeddings, no trained head)EvaluationBacBench operon identification, zero-shot AUPRC, BacBench operon identification dataset from long-read RNA sequencing48.21 ± 28.27Not reportedNot reportedNot reported
Evo (frozen embeddings, no trained head)EvaluationBacBench operon identification, zero-shot AUROC, BacBench operon identification dataset from long-read RNA sequencingNot reportedNot reported74.77 ± 8.33Not reported
Evo (frozen embeddings, no trained head)EvaluationBacBench protein-protein interaction, zero-shot AUPRC, BacBench protein-protein interaction dataset from STRING DBNot reported17.04 ± 7.98Not reportedNot reported
Evo (frozen embeddings, no trained head)EvaluationBacBench protein-protein interaction, zero-shot AUROC, BacBench protein-protein interaction dataset from STRING DBNot reportedNot reportedNot reported51.87 ± 1.85
All 4 result rows with coverage, uncertainty and sources
Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: Evo (frozen embeddings, no trained head)Protocol: BacBench operon identification, zero-shot AUPRC
Dataset: BacBench operon identification dataset from long-read RNA sequencing
48.21 ± 28.27 AUPRC (zero-shot operon boundary prediction scored by embedding cosine similarity times a same-strand indicator, mean over the five sequenced strains)
unitless · higher

Uncertainty: SD 28.27

Coverage: Not reported scored / Not reported eligible

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

Evo on BacBench operon identification, zero-shot AUPRC

Zero-shot. For each pair of contiguous genes the score is the cosine similarity between the two gene embeddings multiplied by an indicator that both genes are on the same strand; the intergenic-distance term of the Bacformer operon model is deliberately left out so that the comparison is about the embeddings. Performance is averaged across all five sequenced strains.

Aggregation: Not reported

Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 · Table S1, row 'Evo', column 'AUPRC'
Configuration: Evo (frozen embeddings, no trained head)Protocol: BacBench operon identification, zero-shot AUROC
Dataset: BacBench operon identification dataset from long-read RNA sequencing
74.77 ± 8.33 AUROC (zero-shot operon boundary prediction scored by embedding cosine similarity times a same-strand indicator, mean over the five sequenced strains)
unitless · higher

Uncertainty: SD 8.33

Coverage: Not reported scored / Not reported eligible

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

Evo on BacBench operon identification, zero-shot AUROC

Zero-shot. For each pair of contiguous genes the score is the cosine similarity between the two gene embeddings multiplied by an indicator that both genes are on the same strand; the intergenic-distance term of the Bacformer operon model is deliberately left out so that the comparison is about the embeddings. Performance is averaged across all five sequenced strains.

Aggregation: Not reported

Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 · Table S1, row 'Evo', column 'AUROC'
Configuration: Evo (frozen embeddings, no trained head)Protocol: BacBench protein-protein interaction, zero-shot AUPRC
Dataset: BacBench protein-protein interaction dataset from STRING DB
17.04 ± 7.98 AUPRC (zero-shot pair scoring by embedding cosine similarity, genus-level split, mean over held-out test genomes)
unitless · higher

Uncertainty: SD 7.98

Coverage: Not reported scored / Not reported eligible

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

Evo on BacBench protein-protein interaction, zero-shot AUPRC

Zero-shot columns score each protein pair by the cosine similarity of the two embeddings. The finetuned columns train a single linear layer, preceded by layer normalisation and dropout of 0.2, on the average of the two frozen protein embeddings together with their cosine similarity, so the input is of dimension D plus one; binary cross-entropy loss, Adam with weight decay 0.01, at most 20 epochs with early stopping patience 5 on AUROC, and a learning-rate sweep per model. Metrics are computed per genome on the test split.

Aggregation: Not reported

Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 · Table S13, row 'Evo', column 'Zero-shot AUPRC'
Configuration: Evo (frozen embeddings, no trained head)Protocol: BacBench protein-protein interaction, zero-shot AUROC
Dataset: BacBench protein-protein interaction dataset from STRING DB
51.87 ± 1.85 AUROC (zero-shot pair scoring by embedding cosine similarity, genus-level split, mean over held-out test genomes)
unitless · higher

Uncertainty: SD 1.85

Coverage: Not reported scored / Not reported eligible

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

Evo on BacBench protein-protein interaction, zero-shot AUROC

Zero-shot columns score each protein pair by the cosine similarity of the two embeddings. The finetuned columns train a single linear layer, preceded by layer normalisation and dropout of 0.2, on the average of the two frozen protein embeddings together with their cosine similarity, so the input is of dimension D plus one; binary cross-entropy loss, Adam with weight decay 0.01, at most 20 epochs with early stopping patience 5 on AUROC, and a learning-rate sweep per model. Metrics are computed per genome on the test split.

Aggregation: Not reported

Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 · Table S13, row 'Evo', column 'Zero-shot AUROC'

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

Use this configuration

How it works, versions and access

Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this configuration. Consult the linked sources and evaluation records below.

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.

0 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

No evidence rows match these filters. Choose another scope or clear the search.

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: source checked

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

Technical metadata for this record is tracked under stable ID bacformer-20261115-config-evo-zero-shot.

Source locator: Table S9, row 'Evo'; Methods 'Benchmarking' and 'General modelling details'

Related records

How to cite

Evo (frozen embeddings, no trained head). Rewire biological model benchmark database, release 2026-11-21-c8bea25e5abb. https://benchmarks.rewirebio.io/database/configuration/bacformer-20261115-config-evo-zero-shot/

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