mlsanityData to 7 Oct 2026

Kermut: Composite kernel regression for protein variant effects

arXiv 2407.00002 ↗First posted 9 Apr 2024q-bio.BM cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 20 of its 81 references that are in the map. First posted on arXiv 9 Apr 2024.

Builds on

20 of 81 references.

References · 20

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  2. 2018GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Accelerationcited by 603
  3. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  4. 2019Evaluating Protein Transfer Learning with TAPEcited by 229
  5. 2019Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Visioncited by 182
  6. 2019Exact Gaussian Processes on a Million Data Pointscited by 118
  7. 2020Kernel methods through the roof: handling billions of points efficientlycited by 88
  8. 2019Evaluating and Calibrating Uncertainty Prediction in Regression Taskscited by 85
  9. 2022PiFold: Toward effective and efficient protein inverse foldingcited by 82
  10. 2022Tranception: protein fitness prediction with autoregressive transformers and inference-time retrievalcited by 78
  11. 2022PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understandingcited by 77
  12. 2020ATOM3D: Tasks On Molecules in Three Dimensionscited by 73
8 more
  1. 2020Uncertainty Quantification Using Neural Networks for Molecular Property Predictioncited by 66
  2. 2020BOSS: Bayesian Optimization over String Spacescited by 54
  3. 2020What is a meaningful representation of protein sequences?cited by 22
  4. 2023MUBen: Benchmarking the Uncertainty of Molecular Representation Modelscited by 11
  5. 2023On the role of Model Uncertainties in Bayesian Optimizationcited by 7
  6. 2023Biological Sequence Kernels with Guaranteed Flexibilitycited by 6
  7. 2023Linear-scaling kernels for protein sequences and small molecules outperform deep learning while providing uncertainty quantitation and improved interpretabilitycited by 2
  8. 2018mGPfusion: Predicting protein stability changes with Gaussian process kernel learning and data fusioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 5.

11 papers.

  1. 2025Return of the Latent Space COWBOYS: Re-thinking the use of VAEs for Bayesian Optimisation of Structured Spacescited by 13
  2. 2026AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentationcited by 7
  3. 2026Can Tabular In-Context Learners Generalize to Biomolecular Property Prediction?cited by 2
  4. 2025AlphaFold Database Debiasing for Robust Inverse Foldingcited by 0
  5. 2025Is Sequence Information All You Need for Bayesian Optimization of Antibodies?cited by 0
  6. 2025Spectral Analysis of Molecular Features: When Richer Features Do Not Guarantee Better Generalizationcited by 0
  7. 2025Low-N Protein Activity Optimization with FolDEcited by 0
  8. 2025Few-shot Protein Fitness Prediction via In-context Learning and Test-time Trainingcited by 0
  9. 2026Pareto-Optimal Offline Reinforcement Learning via Smooth Tchebycheff Scalarizationcited by 0
  10. 2026BOAT: Navigating the Sea of In Silico Predictors for Antibody Design via Multi-Objective Bayesian Optimizationcited by 0
  11. 2026StabilityArc: Decoding Protein Sequence Embeddings into Generalizable Stability Landscapescited by 0