Sayan Biswas

Robust Prediction of Patient-Specific Cancer Hallmarks Using Neural Multi-Task Learning: a model development and validation study

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.

Comprehensive Enumeration of Cancer Stem-like Cell Heterogeneity Using Deep Neural Network

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.