Kermut: Composite kernel regression for protein variant effects

Peter Mørch Groth, Mads Herbert Kerrn, Lars Olsen, Jesper Salomon, Wouter Boomsma

Keywords: Gaussian process, uncertainty quantification, proteins, protein, enzyme, variant effects, kernel, protein structure, uncertainty calibration, few-shot learning, transfer learning

TL;DR: Gaussian process regression model with a novel composite kernel, Kermut, achieves state-of-the-art variant effect prediction while providing meaningful uncertainties

Abstract: Reliable prediction of protein variant effects is crucial for both protein optimization and for advancing biological understanding. For practical use in protein engineering, it is important that we can also provide reliable uncertainty estimates for our predictions, and while prediction accuracy has seen much progress in recent years, uncertainty metrics are rarely reported. We here provide a Gaussian process regression model, Kermut, with a novel composite kernel for modeling mutation similarity, which obtains state-of-the-art performance for supervised protein variant effect prediction while also offering estimates of uncertainty through its posterior. An analysis of the quality of the uncertainty estimates demonstrates that our model provides meaningful levels of overall calibration, but that instance-specific uncertainty calibration remains more challenging.

Primary Area: Probabilistic methods (for example: variational inference, Gaussian processes)

Submission Number: 17246