A decoupled alignment kernel for peptide membrane permeability predictions
This work addresses the challenge of limited data and uncertainty calibration for peptide permeability predictions, which is crucial for drug discovery, but it appears incremental as it builds on existing kernel and Gaussian Process methods.
The authors tackled the problem of predicting peptide membrane permeability, a key bottleneck for cyclic peptides targeting intracellular sites, by proposing a decoupled alignment kernel (MD-GAK) and its variant (PMD-GAK) with Gaussian Processes, and showed that it outperforms state-of-the-art models across all metrics.
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.