Oliver Wardhana

In a 63-tool benchmark, dataset identity explained ≈84% of Cohen's κ variance on synthetic data versus ≈4% for tool identity, and k-nearest-neighbor (kNN) purity predicted accuracy near-linearly (R² = 0.85–0.99).

This study compares 3D culture scaffolds for prostate cancer cells, finding scaffold-dependent differences in spheroid formation and gene expression, particularly in neuroendocrine markers.