Kliment Olechnovič

Voronota-LT efficiently computes atom-atom contacts within solvent-accessible surfaces using tessellation-based methods, offering speed and flexibility for molecular interaction analysis.

TemStaPro predicts protein thermostability using sequence embeddings from protein language models, showing good agreement with experimental data.

This paper develops a protocol to predict protein complex structures using diversified AlphaFold models and a new scoring method, achieving top results in CASP15.

VoroIF-GNN assesses protein-protein interface accuracy using a graph neural network based on Voronoi tessellation, showing strong performance in CASP15.

The paper introduces VoroCNN, a deep convolutional neural network for predicting local qualities of 3D protein folds using Voronoi tessellation, achieving competitive results compared to existing methods.