Martin Jankowiak ⋅ Yerdos Ordabayev ⋅ Rudraksh Tuwani ⋅ Henry N. Ward ⋅ Hunter Nisonoff ⋅ James M. McFarland ⋅ Gevorg Grigoryan
Despite its importance to applications in protein design, predicting protein properties like binding affinity and thermostability from sparse experimental data remains a significant challenge. Accordingly, we introduce a class of sequence kernels that exploit evolutionary substitution matrices as well as local linearity and demonstrate that the resulting Gaussian processes provide data-efficient models of protein property landscapes, frequently outperforming alternatives that rely on foundation model embeddings. Furthermore—by learning what are in effect structure-aware substitution matrices—we show that our kernels can readily incorporate structural information from foundation models. We demonstrate that these structure-conditioned kernels are well suited to multi-task learning across multiple protein property landscapes and can decisively outperform local supervised learning methods.
This repo contains a GPyTorch implementation of the LOCK GP kernel as well as a demo on CR6261-H1 antibody fitness data.
Python 3.10 or later is required. We recommend uv for easy and reproducible installation.
git clone git@github.com:generatebio/lock_gp.git
cd lock_gp
uv python install
uv syncThis repo was tested with PyTorch 2.6.
If you use LOCK GP please consider citing our paper:
@InProceedings{pmlr-v306-jankowiak26a,
title = {Flexible Kernels for Protein Property Prediction},
author = {Jankowiak, Martin and Ordabayev, Yerdos and Tuwani, Rudraksh and Ward, Henry Neil and Nisonoff, Hunter and McFarland, James M and Grigoryan, Gevorg},
booktitle = {Proceedings of the 43rd International Conference on Machine Learning},
pages = {50779--50829},
year = {2026},
volume = {306},
series = {Proceedings of Machine Learning Research},
publisher = {PMLR},
pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/jankowiak26a/jankowiak26a.pdf},
url = {https://proceedings.mlr.press/v306/jankowiak26a.html}
}