Nikoletta Katsaouni

RANKOR ranks candidate drugs from transcriptomic signatures using a machine learning framework, outperforming existing methods in bulk and single-cell data.

The paper identifies 1,580 cell type-specific genes and non-coding RNAs associated with coronary artery disease by integrating genetic and epigenetic data from multiple cell types.

This paper introduces a hierarchical representation learning framework for drug mechanism-of-action prediction from gene expression data, achieving improved F1 performance and interpretable latent space capturing MoA-level separation and compound-level substructure.

This paper proposes an energy-efficient recurrent convolutional neural network for arrhythmia detection, showing that large CNNs are computationally redundant for this task.