Marián Novotný

The paper analyzes AlphaFold's predicted binding pockets to determine their similarity to apo or holo states, finding most are holo-like and showing how state affects docking success.

Seq2Pocket improves binding site prediction by combining pLM fine-tuning, data enhancement, and structure-aware post-processing, achieving state-of-the-art performance on benchmark datasets.

This study uses explainable AI to analyze the energy landscape of protein kinases, revealing that allosteric sites are in neutrally frustrated regions, explaining their detection challenges.

This paper compares sequence-based and structure-based methods for predicting allosteric binding sites in protein kinases, finding that sequence-based models perform poorly on allosteric sites despite good performance on orthosteric ones.

This study examines protein-coenzyme interactions in the Protein Data Bank to assess the plausibility of early peptide-cofactor collaborations before the Central Dogma.

This study evaluates a hybrid model combining protein language models and graph neural networks for predicting protein-ligand binding sites, showing that structural information improves performance but complex pLMs can achieve good results without it.

CryptoBench introduces a dataset and benchmark for cryptic protein-ligand binding sites, showing sequence-based methods outperform structure-based ones in prediction accuracy.

AHoJ retrieves apo and holo protein structures for user-defined ligands by aligning and classifying structures based on binding site similarity.

PrankWeb provides a web interface for ligand binding site prediction using P2Rank, allowing visualization and export of results.