Skip to main content

Table 1 SVMR 4-level search strategy and results

From: Seeking gene relationships in gene expression data using support vector machine regression

  Search level
  1 2 3 4
Theme Genes that contained highly correlated genes From the same biological family Across biological families Random Walk (all genes)
Sample size 1000 55 RPa 49 ZFPb 49 3554
Sample selection criteria A total of 1000 genes that contained 100 highly correlated genes all in RP family, all in ZFP family RP, ZFP, and DEADc The full data set of all 3554 genes
Training size 2 genes per training, 3 trainings 2 to 10 genes 3 genes per training 3 to 20 genes
Training selection criteria Corr > 0.85, p < 0.001 Randomly from 55 RP genes or from 49 ZFP genes Only from RP family Randomly from entire sample
Best training size 2 genes 4–5 genes 3 genes 3–7 genes
Example of training genes 1. 200088_x_at and 200809_x_at (both are different problems for RPL12) (Pearson corr > 0.92 and Spearman corr > 0.90, p < 0.0001)
2. RPL32 and RPS18 (Pearson corr > 0.94, p < 0.0001)
3. DDX3Y and EIF1AY (Pearson corr > 0.9875, p < 0.0001)d
RPS11
RPS10
RPS3A (201257_x_at)
RPS16
RPS4X
RPS4Y1
RPS5
C1D
ALOX5
ENO2
RERE
Example of captured genes 1. 200088_x_at and 200809_x_at
2. RPL32, RPS15, RPS18, RPS3A, and RPS28
3. DDX3Y and EIF1AY
1. RPL27, RPS3A(2000099_s_at), RPS3A(201257_x_at), RPS29, RPS28
2. RPS15A, RPS18, RPS12, RPS19
3. Similar results were seen among genes with ZFP family
DDX39
DDX3Y
DDX58
DDX26
SCAP1
SGPP1
TGFBR3
CD9
VAMP8
  1. aRP, ribosomal proteins family
  2. bZFP, zinc finger proteins family
  3. cDEAD, DEAD box proteins, which are characterized by the conserved motif (Asp-Glu-Ala-Asp) (DEAD).
  4. dThree pairs of highly correlated gene expressions as three separate training sets, and search separately back in the sample, and found itself and the others.