Skip to main content

Table 3 Cross validation results on discovering new phenotypes

From: Using iterative cluster merging with improved gap statistics to perform online phenotype discovery in the context of high-throughput RNAi screens

Phenotype to be identified

# of cells to be identified

Average accuracy with standard deviation %

Typical Mistakes

Normal

1000

95.2 (3.5)

Left alone

LPA

1000

90.3 (3.1)

Merged into Normal, left alone

CCA

600

89.6 (2.7)

Merged into Rho1

Rho1

600

87.4 (4.2)

Left alone