Linear Dimension Reduction (PCA)
PCA (Principal Components Analysis) reduces the number of variables (here, genes) while preserving as much information as possible. The first principal component accounts for the largest possible variance in the dataset.
PCA is performed on the scaled data. By default, only the previously determined variable features are used as input (top 2000). The input can be defined using the features argument if you wish to choose a different subset.
pbmc <- RunPCA(pbmc, features = VariableFeatures(object = pbmc))
Running PCA gives you PCs (PC scores) and loadings (the weight/importance of each gene for each PC).