Joshy George

This study combines DNA sequencing and gene-expression profiling with clinical data to improve diagnosis of cancer of unknown primary (CUP), identifying potential tissue origins in over a third of cases.

The paper uses word embeddings from PubMed to predict which protein kinases are relevant for treating specific cancers using machine learning.

The paper identifies sex-biased differential alternative splicing across multiple human tissues and links it to gene function and estrogen response.

The paper develops bioinformatics workflows to analyze genomic data from patient-derived xenografts, addressing challenges like separating mouse and human reads and identifying somatic mutations without paired normal DNA.

The paper develops a tool to guide scRNA-seq experimental design and analysis for cell type identification, showing that Seurat or Simlr work well with high marker gene fold changes.