# Antimicrobial peptide prediction on BERT-based models benchmark leave-one-out 1.0

Source: [Antimicrobial peptide prediction on BERT-based models benchmark leave-one-out 1.0](<https://www.sota2.com/research/sota/antimicrobial-peptide-prediction-on-bert-based-models-benchmark-leave-one-out-1-0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:21:39.808Z

Evaluation of model performance for Antimicrobial Peptide prediction using the BERT-based models benchmark, specifically utilizing the leave-one-out 1.0 split.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Antimicrobial peptide prediction |
| Dataset (including any stated split) | BERT-based models benchmark leave-one-out 1.0 |
| Metric | ADAPTABLE |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [ADAPTABLE](<https://www.sota2.com/research/sota/antimicrobial-peptide-prediction-on-bert-based-models-benchmark-leave-one-out-1-0.md?metric=ADAPTABLE>): Higher is better; unit: PERCENT.

- [APD](<https://www.sota2.com/research/sota/antimicrobial-peptide-prediction-on-bert-based-models-benchmark-leave-one-out-1-0.md?metric=APD>): Higher is better; unit: PERCENT.

- [CAMP](<https://www.sota2.com/research/sota/antimicrobial-peptide-prediction-on-bert-based-models-benchmark-leave-one-out-1-0.md?metric=CAMP>): Higher is better; unit: PERCENT.

- [dbAMP](<https://www.sota2.com/research/sota/antimicrobial-peptide-prediction-on-bert-based-models-benchmark-leave-one-out-1-0.md?metric=dbAMP>): Higher is better; unit: PERCENT.

- [DRAMP](<https://www.sota2.com/research/sota/antimicrobial-peptide-prediction-on-bert-based-models-benchmark-leave-one-out-1-0.md?metric=DRAMP>): Higher is better; unit: PERCENT.

- [YADAMP](<https://www.sota2.com/research/sota/antimicrobial-peptide-prediction-on-bert-based-models-benchmark-leave-one-out-1-0.md?metric=YADAMP>): Higher is better; unit: PERCENT.

- [Average F1](<https://www.sota2.com/research/sota/antimicrobial-peptide-prediction-on-bert-based-models-benchmark-leave-one-out-1-0.md?metric=Average%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | ADAPTABLE | Result date | Report paper |
| --- | --- | --- | --- |
| RDKit | 82 | Not recorded | 68fa5f851e209131ce9ea943 |
| AMP-BERT | 81.7 | Not recorded | 68fa5f851e209131ce9ea943 |
| ECFP | 80.8 | Not recorded | 68fa5f851e209131ce9ea943 |
| TT | 80.6 | Not recorded | 68fa5f851e209131ce9ea943 |
| BERT-Protein | 79.4 | Not recorded | 68fa5f851e209131ce9ea943 |
| LM\_pred (BFD) | 73.9 | Not recorded | 68fa5f851e209131ce9ea943 |
| cAMPs pred | 61.3 | Not recorded | 68fa5f851e209131ce9ea943 |
| LM pred | 55.9 | Not recorded | 68fa5f851e209131ce9ea943 |

### RDKit

ADAPTABLE: 82. Result ID: 698bcaa47a967eddb7716344.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f851e209131ce9ea943.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f851e209131ce9ea943.md>)

[Implementation](<https://github.com/scikit-fingerprints/peptides_molecular_fingerprints_classification>)

Recorded evaluation configuration: {"classifier":"LightGBM","fingerprint":"RDKit"}. This record does not assert independent reproduction.

### AMP-BERT

ADAPTABLE: 81.7. Result ID: 698bcaa47a967eddb771633f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f851e209131ce9ea943.md>)

Recorded evaluation configuration: {"fine-tuned":false}. This record does not assert independent reproduction.

### ECFP

ADAPTABLE: 80.8. Result ID: 698bcaa47a967eddb7716346.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f851e209131ce9ea943.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f851e209131ce9ea943.md>)

[Implementation](<https://github.com/scikit-fingerprints/peptides_molecular_fingerprints_classification>)

Recorded evaluation configuration: {"classifier":"LightGBM","fingerprint":"ECFP"}. This record does not assert independent reproduction.

### TT

ADAPTABLE: 80.6. Result ID: 698bcaa47a967eddb7716345.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f851e209131ce9ea943.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f851e209131ce9ea943.md>)

[Implementation](<https://github.com/scikit-fingerprints/peptides_molecular_fingerprints_classification>)

Recorded evaluation configuration: {"classifier":"LightGBM","fingerprint":"Topological Torsion"}. This record does not assert independent reproduction.

### BERT-Protein

ADAPTABLE: 79.4. Result ID: 698bcaa47a967eddb7716340.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f851e209131ce9ea943.md>)

Recorded evaluation configuration: {"fine-tuned":false}. This record does not assert independent reproduction.

### LM\_pred (BFD)

ADAPTABLE: 73.9. Result ID: 698bcaa47a967eddb7716343.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f851e209131ce9ea943.md>)

Recorded evaluation configuration: {"fine-tuned":false}. This record does not assert independent reproduction.

### cAMPs pred

ADAPTABLE: 61.3. Result ID: 698bcaa47a967eddb7716341.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f851e209131ce9ea943.md>)

Recorded evaluation configuration: {"fine-tuned":false}. This record does not assert independent reproduction.

### LM pred

ADAPTABLE: 55.9. Result ID: 698bcaa47a967eddb7716342.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f851e209131ce9ea943.md>)

Recorded evaluation configuration: {"fine-tuned":false}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.