Aleksandra M. Karolak

This paper develops a computational framework combining molecular dynamics and machine learning to predict KRAS mutation-induced drug resistance with over 90% accuracy.

PETIL predicts TIL expansion in bladder cancer using demographic, clinical, and biological features, achieving AUC values of 0.740 and 0.857 in testing and validation cohorts.

This paper introduces TGVAE, a Transformer Graph Variational Autoencoder that generates diverse and chemically valid molecules by using molecular graphs instead of SMILES strings, outperforming existing methods.

This paper introduces a framework for mutational signature analysis using DNA shape parameters to better understand mutagenesis mechanisms and improve mutation rate baselines.

The paper develops microPKPD models to assess patient-specific drug efficacy by simulating drug delivery challenges in tumor microenvironments.