Bacformer Large (frozen embeddings with a trained linear head)
Bacformer Large embeddings computed with the backbone frozen and a single trained linear layer on top, which turns the stored embeddings into the task prediction.
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 Bacformer Large (frozen embeddings with a trained linear head). Fields the record does not carry are marked not recorded.
Evaluated Checkpoint: As benchmarked in version 3 of the preprint
Evaluations and results
10 evaluations · 10 results. Different protocols are not a single leaderboard.
Sorted by AUPRC (linear head on frozen gene embeddings, genus-level split, median over held-out test genomes) (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 configuration | Protocol and dataset | AUPRC (linear head on frozen gene embeddings, genus-level split, median over held-out test genomes) | AUPRC (linear head on frozen pair embeddings plus their cosine similarity, genus-level split, mean over held-out test genomes) | AUPRC (linear head per drug on frozen genome embeddings, random 70/10/20 split, mean over 37 antibiotics) | AUPRC (linear head per trait on frozen genome embeddings, macro-averaged across classes of each trait, genus-level split, mean over traits and seeds) | AUROC (linear head on frozen gene embeddings, genus-level split, median over held-out test genomes) | AUROC (linear head on frozen pair embeddings plus their cosine similarity, genus-level split, mean over held-out test genomes) | AUROC (linear head per drug on frozen genome embeddings, random 70/10/20 split, mean over 37 antibiotics) | AUROC (linear head per trait on frozen genome embeddings, macro-averaged across classes of each trait, genus-level split, mean over traits and seeds) | Pearson (linear head per drug on frozen genome embeddings predicting log(1+MIC), random 70/10/20 split, mean over 56 antibiotics, printed as a percentage) | R² (linear head per drug on frozen genome embeddings predicting log(1+MIC), random 70/10/20 split, mean over 56 antibiotics, printed as a percentage) |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Bacformer Large (frozen embeddings with a trained linear head)Evaluation | BacBench essential gene prediction, linear probe AUPRC, BacBench essential gene dataset from the Database of Essential Genes | 55.87 ± 21.38 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| Bacformer Large (frozen embeddings with a trained linear head)Evaluation | BacBench antibiotic resistance, binary linear probe AUPRC, Antibiotic resistance binary prediction subset, 37 antibiotics | Not reported | Not reported | 76.14 ± 19.59 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| Bacformer Large (frozen embeddings with a trained linear head)Evaluation | BacBench antibiotic resistance, binary linear probe AUROC, Antibiotic resistance binary prediction subset, 37 antibiotics | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | 92.15 ± 4.20 | Not reported | Not reported | Not reported |
| Bacformer Large (frozen embeddings with a trained linear head)Evaluation | BacBench antibiotic resistance, MIC regression Pearson correlation, Antibiotic resistance MIC regression subset, 56 antibiotics | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | 65.73 ± 12.88 | Not reported |
| Bacformer Large (frozen embeddings with a trained linear head)Evaluation | BacBench antibiotic resistance, MIC regression R squared, Antibiotic resistance MIC regression subset, 56 antibiotics | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | 42.59 ± 19.54 |
| Bacformer Large (frozen embeddings with a trained linear head)Evaluation | BacBench essential gene prediction, linear probe AUROC, BacBench essential gene dataset from the Database of Essential Genes | Not reported | Not reported | Not reported | Not reported | 77.97 ± 11.16 | Not reported | Not reported | Not reported | Not reported | Not reported |
| Bacformer Large (frozen embeddings with a trained linear head)Evaluation | BacBench phenotypic trait prediction, linear probe AUPRC, BacBench phenotypic trait dataset | Not reported | Not reported | Not reported | 48.34 ± 36.39 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| Bacformer Large (frozen embeddings with a trained linear head)Evaluation | BacBench phenotypic trait prediction, linear probe AUROC, BacBench phenotypic trait dataset | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | 73.33 ± 12.13 | Not reported | Not reported |
| Bacformer Large (frozen embeddings with a trained linear head)Evaluation | BacBench protein-protein interaction, linear probe AUPRC, BacBench protein-protein interaction dataset from STRING DB | Not reported | 50.84 ± 10.34 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| Bacformer Large (frozen embeddings with a trained linear head)Evaluation | BacBench protein-protein interaction, linear probe AUROC, BacBench protein-protein interaction dataset from STRING DB | Not reported | Not reported | Not reported | Not reported | Not reported | 78.35 ± 2.40 | Not reported | Not reported | Not reported | Not reported |
All 10 result rows with coverage, uncertainty and sources
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: Bacformer Large (frozen embeddings with a trained linear head) | Protocol: BacBench antibiotic resistance, binary linear probe AUPRC Dataset subset: Antibiotic resistance binary prediction subset, 37 antibiotics | 76.14 ± 19.59 AUPRC (linear head per drug on frozen genome embeddings, random 70/10/20 split, mean over 37 antibiotics) unitless · higher Uncertainty: SD 19.59. The caption says the spread is across antibiotics; the Methods state 37 antibiotics in the binary setting and 56 in the regression setting. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceBacformer Large on BacBench antibiotic resistance, binary linear probe AUPRC One linear model per drug on mean-pooled whole-genome embeddings: a single layer preceded by dropout of 0.1 and layer normalisation, binary cross-entropy for the resistant or susceptible setting and mean squared error for the log(1+MIC) regression, at most 100 epochs, early stopping patience 10 on validation AUROC or validation R squared, a learning-rate sweep per model across seeds and drugs, Adam with weight decay 0.01, and three random splits. Aggregation: Not reported Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 · Table S18, row 'Bacformer Large', column 'Binary AUPRC' |
| Configuration: Bacformer Large (frozen embeddings with a trained linear head) | Protocol: BacBench antibiotic resistance, binary linear probe AUROC Dataset subset: Antibiotic resistance binary prediction subset, 37 antibiotics | 92.15 ± 4.20 AUROC (linear head per drug on frozen genome embeddings, random 70/10/20 split, mean over 37 antibiotics) unitless · higher Uncertainty: SD 4.20. The caption says the spread is across antibiotics; the Methods state 37 antibiotics in the binary setting and 56 in the regression setting. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceBacformer Large on BacBench antibiotic resistance, binary linear probe AUROC One linear model per drug on mean-pooled whole-genome embeddings: a single layer preceded by dropout of 0.1 and layer normalisation, binary cross-entropy for the resistant or susceptible setting and mean squared error for the log(1+MIC) regression, at most 100 epochs, early stopping patience 10 on validation AUROC or validation R squared, a learning-rate sweep per model across seeds and drugs, Adam with weight decay 0.01, and three random splits. Aggregation: Not reported Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 · Table S18, row 'Bacformer Large', column 'Binary AUROC' |
| Configuration: Bacformer Large (frozen embeddings with a trained linear head) | Protocol: BacBench antibiotic resistance, MIC regression Pearson correlation Dataset subset: Antibiotic resistance MIC regression subset, 56 antibiotics | 65.73 ± 12.88 Pearson (linear head per drug on frozen genome embeddings predicting log(1+MIC), random 70/10/20 split, mean over 56 antibiotics, printed as a percentage) unitless · higher Uncertainty: SD 12.88. The caption says the spread is across antibiotics; the Methods state 37 antibiotics in the binary setting and 56 in the regression setting. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceBacformer Large on BacBench antibiotic resistance, MIC regression Pearson correlation One linear model per drug on mean-pooled whole-genome embeddings: a single layer preceded by dropout of 0.1 and layer normalisation, binary cross-entropy for the resistant or susceptible setting and mean squared error for the log(1+MIC) regression, at most 100 epochs, early stopping patience 10 on validation AUROC or validation R squared, a learning-rate sweep per model across seeds and drugs, Adam with weight decay 0.01, and three random splits. Aggregation: Not reported Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 · Table S18, row 'Bacformer Large', column 'Regression Pearson' |
| Configuration: Bacformer Large (frozen embeddings with a trained linear head) | Protocol: BacBench antibiotic resistance, MIC regression R squared Dataset subset: Antibiotic resistance MIC regression subset, 56 antibiotics | 42.59 ± 19.54 R² (linear head per drug on frozen genome embeddings predicting log(1+MIC), random 70/10/20 split, mean over 56 antibiotics, printed as a percentage) unitless · higher Uncertainty: SD 19.54. The caption says the spread is across antibiotics; the Methods state 37 antibiotics in the binary setting and 56 in the regression setting. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceBacformer Large on BacBench antibiotic resistance, MIC regression R squared One linear model per drug on mean-pooled whole-genome embeddings: a single layer preceded by dropout of 0.1 and layer normalisation, binary cross-entropy for the resistant or susceptible setting and mean squared error for the log(1+MIC) regression, at most 100 epochs, early stopping patience 10 on validation AUROC or validation R squared, a learning-rate sweep per model across seeds and drugs, Adam with weight decay 0.01, and three random splits. Aggregation: Not reported Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 · Table S18, row 'Bacformer Large', column 'Regression R2' |
| Configuration: Bacformer Large (frozen embeddings with a trained linear head) | Protocol: BacBench essential gene prediction, linear probe AUPRC Dataset: BacBench essential gene dataset from the Database of Essential Genes | 55.87 ± 21.38 AUPRC (linear head on frozen gene embeddings, genus-level split, median over held-out test genomes) unitless · higher Uncertainty: SD 21.38 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceBacformer Large on BacBench essential gene prediction, linear probe AUPRC The backbone is frozen and a single linear layer, preceded by dropout of 0.2 and layer normalisation, is trained on the gene embeddings with binary cross-entropy loss, at most 100 epochs, early stopping patience 10 on macro AUROC over validation genomes, Adam with weight decay 0.02, and a learning-rate sweep per model. Evo and Evo-2 are reported without layer normalisation, which the authors state worked better for them. Aggregation: Not reported Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 · Table S14, row 'Bacformer Large', column 'AUPRC' |
| Configuration: Bacformer Large (frozen embeddings with a trained linear head) | Protocol: BacBench essential gene prediction, linear probe AUROC Dataset: BacBench essential gene dataset from the Database of Essential Genes | 77.97 ± 11.16 AUROC (linear head on frozen gene embeddings, genus-level split, median over held-out test genomes) unitless · higher Uncertainty: SD 11.16 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceBacformer Large on BacBench essential gene prediction, linear probe AUROC The backbone is frozen and a single linear layer, preceded by dropout of 0.2 and layer normalisation, is trained on the gene embeddings with binary cross-entropy loss, at most 100 epochs, early stopping patience 10 on macro AUROC over validation genomes, Adam with weight decay 0.02, and a learning-rate sweep per model. Evo and Evo-2 are reported without layer normalisation, which the authors state worked better for them. Aggregation: Not reported Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 · Table S14, row 'Bacformer Large', column 'AUROC' |
| Configuration: Bacformer Large (frozen embeddings with a trained linear head) | Protocol: BacBench phenotypic trait prediction, linear probe AUPRC Dataset: BacBench phenotypic trait dataset | 48.34 ± 36.39 AUPRC (linear head per trait on frozen genome embeddings, macro-averaged across classes of each trait, genus-level split, mean over traits and seeds) unitless · higher Uncertainty: SD 36.39 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceBacformer Large on BacBench phenotypic trait prediction, linear probe AUPRC One linear model per trait on mean-pooled whole-genome embeddings: a single layer preceded by dropout of 0.1 and layer normalisation, cross-entropy loss, at most 100 epochs, early stopping patience 10 on validation AUROC, a learning-rate sweep per model across seeds and traits, and no class weighting. Scores are macro-averaged across the classes of each trait. Aggregation: Not reported Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 · Table S16, row 'Bacformer Large', column 'AUPRC' |
| Configuration: Bacformer Large (frozen embeddings with a trained linear head) | Protocol: BacBench phenotypic trait prediction, linear probe AUROC Dataset: BacBench phenotypic trait dataset | 73.33 ± 12.13 AUROC (linear head per trait on frozen genome embeddings, macro-averaged across classes of each trait, genus-level split, mean over traits and seeds) unitless · higher Uncertainty: SD 12.13 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceBacformer Large on BacBench phenotypic trait prediction, linear probe AUROC One linear model per trait on mean-pooled whole-genome embeddings: a single layer preceded by dropout of 0.1 and layer normalisation, cross-entropy loss, at most 100 epochs, early stopping patience 10 on validation AUROC, a learning-rate sweep per model across seeds and traits, and no class weighting. Scores are macro-averaged across the classes of each trait. Aggregation: Not reported Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 · Table S16, row 'Bacformer Large', column 'AUROC' |
| Configuration: Bacformer Large (frozen embeddings with a trained linear head) | Protocol: BacBench protein-protein interaction, linear probe AUPRC Dataset: BacBench protein-protein interaction dataset from STRING DB | 50.84 ± 10.34 AUPRC (linear head on frozen pair embeddings plus their cosine similarity, genus-level split, mean over held-out test genomes) unitless · higher Uncertainty: SD 10.34 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceBacformer Large on BacBench protein-protein interaction, linear probe 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 'Bacformer Large', column 'Finetuned AUPRC' |
| Configuration: Bacformer Large (frozen embeddings with a trained linear head) | Protocol: BacBench protein-protein interaction, linear probe AUROC Dataset: BacBench protein-protein interaction dataset from STRING DB | 78.35 ± 2.40 AUROC (linear head on frozen pair embeddings plus their cosine similarity, genus-level split, mean over held-out test genomes) unitless · higher Uncertainty: SD 2.40 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceBacformer Large on BacBench protein-protein interaction, linear probe 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 'Bacformer Large', column 'Finetuned AUROC' |
Source checking is not independent reproduction. Release 2026-11-21-adc15377fab2.
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
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
Sources and history
Release 2026-11-21-adc15377fab2 · Record review: source checked
1 source record and release history
- Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 · Original source · Version 3, posted 17 August 2026 according to the page banner; the bioRxiv API lists version 3 with date 2026-08-19
Technical metadata and record identifiers
Technical metadata for this record is tracked under stable ID bacformer-20261115-config-bacformer-large-linear-probe.
Source locator: Table S9, row 'Bacformer Large'; Methods 'Benchmarking' and 'General modelling details'
Related records
- configuration of: bacformer-large-masked-complete-genomes
- family: Bacformer Large
- uses model: ESMC
- system: Bacformer Large on BacBench antibiotic resistance, binary linear probe AUPRC
- system: Bacformer Large on BacBench antibiotic resistance, binary linear probe AUROC
- system: Bacformer Large on BacBench antibiotic resistance, MIC regression Pearson correlation
- system: Bacformer Large on BacBench antibiotic resistance, MIC regression R squared
- system: Bacformer Large on BacBench essential gene prediction, linear probe AUPRC
- system: Bacformer Large on BacBench essential gene prediction, linear probe AUROC
- system: Bacformer Large on BacBench phenotypic trait prediction, linear probe AUPRC
- system: Bacformer Large on BacBench phenotypic trait prediction, linear probe AUROC
- system: Bacformer Large on BacBench protein-protein interaction, linear probe AUPRC
- system: Bacformer Large on BacBench protein-protein interaction, linear probe AUROC
How to cite
Bacformer Large (frozen embeddings with a trained linear head). Rewire biological model benchmark database, release 2026-11-21-adc15377fab2. https://benchmarks.rewirebio.io/database/configuration/bacformer-20261115-config-bacformer-large-linear-probe/
Release 2026-11-21-adc15377fab2. 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