Nestoras Karathanasis

This study develops ML models to predict multiple myeloma staging and MGUS progression using gene expression data, achieving AUC values above 0.8 with ElasticNet and other algorithms.

The paper identifies stage-specific genes and pathways in Multiple Myeloma using monotonic expressed genes (MEGs) and gene pair ratios, showing their potential as biomarkers for disease progression.

The paper introduces a method to rank cell clusters in scRNA-seq using prior knowledge and user input, enhancing biological relevance.

This paper uses machine learning to predict drug sensitivity in AML patients using the BeatAML dataset, finding RNA sequencing data provides better predictive power than whole exome sequencing or clinical data.

The paper introduces a conceptual framework and bioinformatics pipeline for multi-omics data integration, validated on TCGA datasets to enhance feature identification compared to single-omics analysis.

The paper uses machine learning to identify spatial informative genes and reconstruct 3-D embryo structure from single-cell transcriptomics data, achieving top rankings in DREAM challenges.

The paper predicts cellular positions in the Drosophila embryo using scRNA-seq data by benchmarking methods against spatially annotated genes.