# Peptide function prediction on AutoPeptideML homology clustering split 1.0 (out-of-distribution)

Source: [Peptide function prediction on AutoPeptideML homology clustering split 1.0 (out-of-distribution)](<https://www.sota2.com/research/sota/peptide-function-prediction-on-autopeptideml-homology-clustering-split-1-0-out-of-distribution>)

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

Data updated: 2026-02-26T05:25:45.485Z

Evaluation of model performance on predicting peptide function using the AutoPeptideML homology clustering split 1.0 (out-of-distribution) dataset, measured by AUROC and MCC.

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 | Peptide function prediction |
| Dataset (including any stated split) | AutoPeptideML homology clustering split 1.0 (out-of-distribution) |
| Metric | AUROC |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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

- [AUROC](<https://www.sota2.com/research/sota/peptide-function-prediction-on-autopeptideml-homology-clustering-split-1-0-out-of-distribution.md?metric=AUROC>): Higher is better; unit: PERCENT.

- [MCC](<https://www.sota2.com/research/sota/peptide-function-prediction-on-autopeptideml-homology-clustering-split-1-0-out-of-distribution.md?metric=MCC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | AUROC | Result date | Report paper |
| --- | --- | --- | --- |
| ESM2-650M | 79.7 | Not recorded | 68fa5f851e209131ce9ea943 |
| Prot-T5-XL | 79.7 | Not recorded | 68fa5f851e209131ce9ea943 |
| ESM1b-650M | 78.9 | Not recorded | 68fa5f851e209131ce9ea943 |
| ECFP | 78.1 | Not recorded | 68fa5f851e209131ce9ea943 |
| ESM2-35M | 78 | Not recorded | 68fa5f851e209131ce9ea943 |
| ESM2-150M | 77.7 | Not recorded | 68fa5f851e209131ce9ea943 |
| ESM2-8M | 77.5 | Not recorded | 68fa5f851e209131ce9ea943 |
| Prost-T5 | 77.1 | Not recorded | 68fa5f851e209131ce9ea943 |
| TT | 77.1 | Not recorded | 68fa5f851e209131ce9ea943 |
| RDKit | 76.9 | Not recorded | 68fa5f851e209131ce9ea943 |
| ProtBERT | 75.9 | Not recorded | 68fa5f851e209131ce9ea943 |

### ESM2-650M

AUROC: 79.7. Result ID: 698bcaa47a967eddb77162ff.

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

Recorded evaluation configuration: {"# params":"650M"}. This record does not assert independent reproduction.

### Prot-T5-XL

AUROC: 79.7. Result ID: 698bcaa47a967eddb7716300.

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

Recorded evaluation configuration: {"# params":"3B"}. This record does not assert independent reproduction.

### ESM1b-650M

AUROC: 78.9. Result ID: 698bcaa47a967eddb77162fe.

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

Recorded evaluation configuration: {"# params":"650M"}. This record does not assert independent reproduction.

### ECFP

AUROC: 78.1. Result ID: 698bcaa47a967eddb7716303.

[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: {"# params":"22k"}. This record does not assert independent reproduction.

### ESM2-35M

AUROC: 78. Result ID: 698bcaa47a967eddb77162fd.

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

Recorded evaluation configuration: {"# params":"35M"}. This record does not assert independent reproduction.

### ESM2-150M

AUROC: 77.7. Result ID: 698bcaa47a967eddb77162fa.

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

Recorded evaluation configuration: {"# params":"150M"}. This record does not assert independent reproduction.

### ESM2-8M

AUROC: 77.5. Result ID: 698bcaa47a967eddb77162fc.

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

Recorded evaluation configuration: {"# params":"8M"}. This record does not assert independent reproduction.

### Prost-T5

AUROC: 77.1. Result ID: 698bcaa47a967eddb77162fb.

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

Recorded evaluation configuration: {"# params":"3B"}. This record does not assert independent reproduction.

### TT

AUROC: 77.1. Result ID: 698bcaa47a967eddb7716302.

[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: {"# params":"23k"}. This record does not assert independent reproduction.

### RDKit

AUROC: 76.9. Result ID: 698bcaa47a967eddb7716301.

[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: {"# params":"20k"}. This record does not assert independent reproduction.

### ProtBERT

AUROC: 75.9. Result ID: 698bcaa47a967eddb77162f9.

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

Recorded evaluation configuration: {"# params":"420M"}. This record does not assert independent reproduction.

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