Zoltán Szállási

The paper identifies an ERCC2 mutation-associated mutational signature in targeted panel sequencing data linked to nucleotide excision repair deficiency in bladder cancer and shows its clinical relevance.

This paper uses open-weight large language models to predict synthetic lethal interactions, outperforming random chance and non-LLM methods in reproducing CRISPR screen results.

This study improves cell type classification in lung cancer tissue sections by incorporating microenvironment information through fisheye transformations, achieving human-level accuracy.

This study combines histopathology and proteomics with a multimodal deep learning framework to improve platinum response prediction in HGSOC, outperforming HRD scores.

The paper analyzes the ADP-ribosylome in breast cancer cell lines to identify site-specific ADP-ribosylation patterns and their relation to PARP inhibitor sensitivity.

The paper identifies genes with low mutation frequency but significant functional impact in 17 cancer types using network propagation, finding 8 previously unreported genes.

The paper develops an engineered bacterium-based RNA interference therapy that reduces inflammation in an IBD model by targeting TNF-alpha.

SOBDetector removes FFPE sequencing artifacts by using a Bayesian logistic regression model trained on TCGA whole exomes, achieving high accuracy and AUC.