Benchmarking Peptide-Protein Affinity Prediction Across Peptide and Target Shifts
Abstract
Peptide-protein affinity models are often evaluated with a single data split, obscuring whether they interpolate among measurements for observed targets or generalize across peptide or target shifts. We integrated three sources of quantitative peptide-protein binding data to obtain 11,349 deduplicated pairs and benchmarked ten peptide representations, ESM-2 protein embeddings, and six regressors under peptide-similarity, within-target, and leave-target-out partitions. Across 60 matched representation-regressor configurations, mean test Spearman correlations were 0.462, 0.669, and 0.530, respectively. The top configuration shifted from ECFP-16 count fingerprints with random forest in the first two settings to HELM-BERT with Extra Trees when exact target sequences were excluded. Representation-rank correlations ranged from -0.042 to 0.624 across partitions, whereas regressor-rank correlations ranged from 0.771 to 0.943. Learning curves showed that representation differences were largest with limited supervision and narrowed as training data increased. PeptideCLM-2 adaptation and simple element-wise interaction features provided no consistent gain over a frozen encoder and direct concatenation under the tested protocols. These conclusions are specific to a dataset that pools transformed Kd, Ki, and IC50 measurements and to target exclusion at the exact-sequence level. Peptide-protein affinity benchmarks should therefore align data partitions with the intended use and jointly assess the effects of data scale, molecular representation, and downstream learner.
Related
- Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction
- Benchmarking confidence estimation and rescoring for cyclic peptide-protein complex predictions
- Controlled Blood-Brain Barrier Modulation by a High-Affinity Claudin-5 Peptide Binder
- Benchmarking Large Language Models for Assay-Aware Drug-Target Binding Affinity Prediction
- PP-MAPS: Dynamic Pharmacophore Signatures of Protein–Peptide Interfaces from Molecular Dynamics Trajectories
BibTeX
@misc{tian2026benchmarking,
title = {{Benchmarking Peptide-Protein Affinity Prediction Across Peptide and Target Shifts}},
author = {Jiaxin Tian and Darren An and Jun Li},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.30175},
eprint = {2608.30175},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.30175},
}
RIS
TY - UNPB
TI - Benchmarking Peptide-Protein Affinity Prediction Across Peptide and Target Shifts
AU - Jiaxin Tian
AU - Darren An
AU - Jun Li
PY - 2026
DA - 2026/08/31
PB - arXiv
DO - 10.48550/arxiv.2608.30175
UR - https://arxiv.org/abs/2608.30175
AB - Peptide-protein affinity models are often evaluated with a single data split, obscuring whether they interpolate among measurements for observed targets or generalize across peptide or target shifts. We integrated three sources of quantitative peptide-protein binding data to obtain 11,349 deduplicated pairs and benchmarked ten peptide representations, ESM-2 protein embeddings, and six regressors under peptide-similarity, within-target, and leave-target-out partitions. Across 60 matched representation-regressor configurations, mean test Spearman correlations were 0.462, 0.669, and 0.530, respectively. The top configuration shifted from ECFP-16 count fingerprints with random forest in the first two settings to HELM-BERT with Extra Trees when exact target sequences were excluded. Representation-rank correlations ranged from -0.042 to 0.624 across partitions, whereas regressor-rank correlations ranged from 0.771 to 0.943. Learning curves showed that representation differences were largest with limited supervision and narrowed as training data increased. PeptideCLM-2 adaptation and simple element-wise interaction features provided no consistent gain over a frozen encoder and direct concatenation under the tested protocols. These conclusions are specific to a dataset that pools transformed Kd, Ki, and IC50 measurements and to target exclusion at the exact-sequence level. Peptide-protein affinity benchmarks should therefore align data partitions with the intended use and jointly assess the effects of data scale, molecular representation, and downstream learner.
ER -