Principal Component Analysis
Principal Component Analysis (PCA) is a dimensionality reduction technique useful for visualizing chemical space. Select a dataset and click Perform PCA to visualize its chemical space. Six RDKit-derived descriptors are used: molecular weight (MolWt), LogP, topological polar surface area (TPSA), and the counts of hydrogen-bond donors, acceptors, and rotatable bonds. Points are colored by activity — binary datasets use red (Active = 1) and blue (Inactive = 0); continuous activity uses a continuous color scale.
Please upload a dataset via Cheminformatics → Upload or Retrieve Dataset to run PCA.