Skip to main content

Table 2 Results of the analysis

From: Analysis of small-sample clinical genomics studies using multi-parameter shrinkage: application to high-throughput RNA interference screening

Id

Untreated

Treated

β ^ i 2 treat

ShrinkHT NP; BFDR

ShrinkHT G; BFDR

limma FDR

608

-0.63

0.22

-0.14

-1.20

-1.29

-1.37

0.337

0.0136

0.080

0.727

749

0.22

0.28

0.43

-0.51

-0.42

-0.25

0.255

0.0362

0.115

0.413

176

0.38

0.39

0.59

-0.06

-0.31

0.11

0.175

0.0738

0.169

0.727

  1. 1st column: siRNA id; 2nd to 7th column: log2 cell viability data for untreated and treated cell lines, corrected for the differential effect in positive control; 8th column: estimate of treatment sensitization effect ('untreated - treated') in excess of the positive control when ShrinkHT is used with a non-parametric prior; 9th and 10th column: BFDRs when using a non-parametric and Gaussian prior; 11th column: Benjamini-Hochberg corrected FDR for limma results