Nazar Shevchuk

The paper identifies differential expression and functional roles of TKS4 isoforms in breast cancer, showing their distinct subcellular localization and oncogenic effects.

The paper evaluates ADMET prediction models on TDC leaderboards, finding most top models lack reproducibility and exhibit data leakage, with only three methods passing rigorous checks.

This paper combines geometric pocket detection with large language models to prioritize protein binding pockets for drug discovery, using a curated dataset and automated pipeline.

This paper improves ADMET prediction by augmenting Mol2Vec embeddings with classical descriptors and feature selection, achieving top results on 10 of 16 TDC benchmarks.