Kleanthi Lakiotaki

The paper constructs low-dimensional latent feature spaces of the human transcriptome using dimensionality reduction techniques and evaluates their ability to reconstruct data and improve phenotypic predictions.

The paper introduces JADBIO, an AutoML system for omics data that produces predictive models and biosignatures, showing it can overcome overfitting in high-dimensional, low-sample data.

This study compares three feature selection algorithms for gene expression data, finding that gOMP outperforms LASSO and matches FBED in performance while being more computationally efficient.