Zahra S. Ghoreyshi

This paper develops a biophysical computational framework to identify antigen escape variants and compensatory TCR sequences by integrating mutagenesis data and structural modeling.

The paper develops a biophysical model to predict T cell receptor specificity for viral and tumor antigens using structural data and sequence-based clustering.

This paper develops a memory-driven model to predict enzalutamide resistance in prostate cancer by integrating reinforcement learning and clinical data, outperforming traditional models in capturing treatment dynamics and patient responses.

This paper introduces a stochastic model to study cancer immune escape dynamics, showing how immunomodulation in the tumor microenvironment affects disease recurrence timing in bladder and breast cancer.

This study shows that feature selection improves peptide binding predictions for TCRs by optimizing model complexity and performance using physicochemical properties and machine learning.

This study improves T cell-antigen specificity prediction by integrating kinetic data into affinity-driven models, enhancing predictions for low-affinity TCR-pMHC interactions.