# Benchmarking Peptide-Protein Affinity Prediction Across Peptide and Target Shifts

arXiv: https://arxiv.org/abs/2608.30175 · HTML: https://mlsanity.com/paper/2608.30175/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 44 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 7 of 7)

- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Large-Scale Chemical Language Representations Capture Molecular Structure and Properties](https://mlsanity.com/paper/2106.09553/) (2021)
- [ChemBERTa-2: Towards Chemical Foundation Models](https://mlsanity.com/paper/2209.01712/) (2022)
- [PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion](https://mlsanity.com/paper/2412.17780/) (2024)
- [Calibration and generalizability of probabilistic models on low-data chemical datasets with DIONYSUS](https://mlsanity.com/paper/2212.01574/) (2022)
- [Molecular Fingerprints Are Strong Models for Peptide Function Prediction](https://mlsanity.com/paper/2501.17901/) (2025)
- [HELM-BERT: A Transformer for Medium-sized Peptide Property Prediction](https://mlsanity.com/paper/2512.23175/) (2025)

## Abstract (arXiv)

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.