TABLE 3.
SIDA (+covariates) uses RS and includes other covariates (see text) as a third dataset. SIDANet uses prior network information from the gene expression data alone. sLDA (Ens) separately applies sparse LDA on the gene expression and metabolomics data and combines discriminant vectors when estimating classification errors. sLDA (Stack) applies sparse LDA on the stacked data. SIDA and SIDANet have competitive error rate and higher estimated correlations. It seems that including covariates does not make the average classification accuracy and correlation any better
| Error (%) | # Genes | # m/z features | Correlation | |
|---|---|---|---|---|
| SIDA | 22.54 | 166.05 | 123.60 | 0.61 |
| SIDA (+ covariates) | 22.46 | 69.05 | 33.35 | 0.31 |
| SIDANet | 21.83 | 247.30 | 111.90 | 0.67 |
| SIDANet (+ covariates) | 22.75 | 64.05 | 33.80 | 0.31 |
| sCCA | 46.48 | 139.75 | 336.25 | 0.43 |
| JACA | 25.49 | 637.20 | 871.65 | 0.52 |
| sLDA (Ens) | 30.28 | 14.20 | 11.60 | 0.23 |
| sLDA (Stack) | 19.15 | 4.25 | 6.20 | 0.09 |