Henning Redestig

This paper introduces a probabilistic preferential learning model for variant effect prediction, showing that uncertainty-aware strategies improve acquisition performance on single-mutation datasets.

This study evaluates whether electrostatic representations improve variant effect prediction models using DMS data, but finds no advantage over evolutionary models.

The paper introduces a protein engineering competition to benchmark computational models for protein design and characterization, with results from a pilot tournament involving seven teams.

The paper shows that structural features of enzymes influence the predictability of variant effects, with consistent dependencies across multiple models.

The paper introduces two phylogenetic tests to identify gene fragments in the wheat genome and finds 1221 likely gene fragment pairs in a draft assembly.