Debayan Gupta

This paper develops OncoMark, a neural multi-task learning framework to predict cancer hallmark activities from transcriptomics data, achieving high accuracy across internal and external datasets.

ACSCeND quantifies cancer stem cell composition from bulk RNA-seq data, showing improved accuracy over existing methods and linking CSC abundance to poorer survival outcomes.

This paper introduces OSCORP, a machine learning method that identifies cancer stem cells with 99% accuracy using bulk RNAseq data, revealing CSC states and their clinical and transcriptomic signatures across 22 cancer types.