A decoupled alignment kernel for peptide membrane permeability predictions

TL;DR

This paper introduces a simple, chemically meaningful alignment kernel for peptide membrane permeability prediction, leveraging Gaussian Processes to improve uncertainty estimation and outperform state-of-the-art models.

Contribution

The paper proposes a novel decoupled global alignment kernel (MD-GAK) and its variant PMD-GAK, tailored for peptide permeability prediction, emphasizing robustness and uncertainty calibration.

Findings

Outperforms state-of-the-art models across all metrics

Reduces calibration errors with the PMD-GAK variant

Demonstrates effectiveness using Gaussian Processes with the proposed kernels

Abstract

Cyclic peptides are promising modalities for targeting intracellular sites; however, cell-membrane permeability remains a key bottleneck, exacerbated by limited public data and the need for well-calibrated uncertainty. Instead of relying on data-eager complex deep learning architecture, we propose a monomer-aware decoupled global alignment kernel (MD-GAK), which couples chemically meaningful residue-residue similarity with sequence alignment while decoupling local matches from gap penalties. MD-GAK is a relatively simple kernel. To further demonstrate the robustness of our framework, we also introduce a variant, PMD-GAK, which incorporates a triangular positional prior. As we will show in the experimental section, PMD-GAK can offer additional advantages over MD-GAK, particularly in reducing calibration errors. Since our focus is on uncertainty estimation, we use Gaussian Processes as the predictive model, as both MD-GAK and PMD-GAK can be directly applied within this framework. We demonstrate the effectiveness of our methods through an extensive set of experiments, comparing our fully reproducible approach against state-of-the-art models, and show that it outperforms them across all metrics.