I am reading a very good (recent) publication in clustering: Kiselev et al., 2017, SC3 - consensus clustering of single-cell RNA-Seq data (if you don't have access, see author PDF).
The algorithm framework works as follows:
- Compute distance matrix (Euclidean, Pearson, Spearman) on samples x features matrix.
- Apply feature transformation (PCA, Laplacian) on the distance matrix (samples x samples).
- Apply K-means algorithms on the transformed distance matrix in step 2.
It seems to me that they did in the "wrong" order. In my mind, I will do feature transformation first, followed by computation of distance matrix and then do clustering. But I think they have an justification but I couldn't find it in their paper. Could anyone explain why it works?