Enhanced Analytical Framework for Complex Biological Data: Beyond Principal Component Analysis in Cancer Research
Ding et al1 investigated the role of AVL9 in chemoresistance of pancreatic ductal adenocarcinoma under hypoxic and acidic tumor microenvironment conditions. Their analytical approach employed Principal Component Analysis (PCA) for 3 crucial purposes: feature reduction, clustering analysis, and feature importance assessment. For feature reduction, they screened 2000 genes with the highest variation, subsequently reducing dimensionality through PCA. The transformed PCA space enabled cell clustering, revealing distinct cell populations and their relationships.
