Skip to main content
. 2020 Jun 22;16(6):e9389. doi: 10.15252/msb.20199389

Figure 1. scClassify framework and ensemble model construction (see also Fig EV1).

Figure 1

  1. Schematic illustration of the scClassify framework. Gene selections: DE, differentially expressed; DD, differentially distributed; DV, differentially variable; BD, bimodally distributed; DP, differentially expressed proportions. Similarity metrics: P, Pearson's correlation; S, Spearman's correlation; K, Kendall's correlation; J, Jaccard distance; C, cosine distance; W, weighted rank correlation.
  2. Schematic illustration of the joint classification using multiple reference datasets.
  3. Classification accuracy of all pairs of reference and test datasets was calculated using all combinations of six similarity metrics and five gene selection methods.
  4. Improvement in classification accuracy after applying an ensemble learning model over the best single model (i.e. weighted kNN + Pearson + DE).