AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Flexible Kernels for Protein Property Prediction

Martin Jankowiak, Yerdos Ordabayev, Rudraksh Tuwani, Henry Neil Ward, Hunter Nisonoff, James M McFarland, Gevorg Grigoryan

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Generative protein structure design · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use BLOSUM-based non-linear kernel instead of plain RBF kernel (ablation)LOCK-GP · 21 local landscapespredictive performanceImproved
add regularizing priors on kernel exponents (ablation)LOCK-GP · 21 local landscapespredictive performanceImproved
use local residue-wise exponents instead of global ones (ablation)LOCK-GP · 21 local landscapesfitImproved
assume local linearity (product with linear kernel) (ablation)LOCK-GP · 21 local landscapesuncertainty qualityImproved
switch between different BLOSUM substitution matrices (ablation)LOCK-GP · 21 local landscapespredictive performanceNo clear effect
add structure-conditioned correlation matrices (CLOCK) over BLOSUM LOCKGP kernel · Thermostability multi-landscapeSpearman R (N=50): 0.498 -> 0.755Improved
learn a global correlation matrix instead of BLOSUM50LOCK-GP · Thermostability multi-landscapeSpearman RImproved
add CNN zero-shot RBF kernel to CLOCK-GPCLOCK-GP · Thermostability multi-landscapeSpearman RImproved
train CLOCK-GP on only 10 landscapes instead of Global CLOCK-GP on 280CLOCK-GP · Thermostability multi-landscapeSpearman RImproved
use LOCK-GP instead of Kermut-GP (two foundation models)LOCK-GP · Extrapolation (128 training points)Pearson R: 16/21 datasetsImproved
use LOCK-GP instead of Tanimoto-GPLOCK-GP · Extrapolation (512 training points)MAE: 22% lowerImproved
use ESM-2 ridge regression instead of Tanimoto-GPRidge-ESM2 · Unseen mutations (96 training points)Pearson R: 0.560 -> 0.490Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy