scRNA-seq: Dimensionality Reduction and Clustering
Pipeline Overview
HVG matrix (cells × ~2000 genes)
→ Scale (z-score, clip ±10)
→ PCA (top 10–50 PCs)
→ k-NN graph (n_neighbors=15–20)
→ UMAP (visualization only)
→ Leiden clustering (on the graph)
PCA
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
X = adata.X if not hasattr(adata.X, 'toarray') else adata.X.toarray()
X_scaled = StandardScaler().fit_transform(X)
X_sca
[Description truncada. Veja o README completo no GitHub.]
