> head(expr_mat)

             Tarca_025_P1C01 Tarca_027_P1C03 Tarca_028_P1C04 Tarca_029_P1C05
100033426_at        7.969054        5.717904        5.533932        9.563440
100033427_at       10.798265        8.210226        8.346338       11.853010
100033428_at        2.107169        2.159903        2.183112        2.356944
100033430_at        2.465297        1.996229        2.188106        2.126542
100033431_at        5.629301        4.196539        4.016405        7.648581
100033432_at        3.245348        2.628399        2.272071        4.652379
100033433_at        2.338819        2.025551        2.253913        3.830992

> head(pheno)
                       SampleID   GA Batch     Set Train Platform
Tarca_001_P1A01 Tarca_001_P1A01 11.0     1 PRB_HTA     1    HTA20
Tarca_013_P1B01 Tarca_013_P1B01 15.3     1 PRB_HTA     1    HTA20
Tarca_025_P1C01 Tarca_025_P1C01 21.7     1 PRB_HTA     1    HTA20
Tarca_037_P1D01 Tarca_037_P1D01 26.7     1 PRB_HTA     1    HTA20
Tarca_049_P1E01 Tarca_049_P1E01 31.3     1 PRB_HTA     1    HTA20
Tarca_061_P1F01 Tarca_061_P1F01 32.1     1 PRB_HTA     1    HTA20



corr_mat <- cor(eset_HTA20, pheno$GA, method = "pearson")

#  filter genes based on correlation value
ncor <- base::ncol(corr_mat)
cmat <- base::col(corr_mat)
ind <- base::order(-cmat, corr_mat, decreasing = TRUE) - (ncor*cmat-ncor)
dim(ind) <- dim(corr_mat)
base::colnames(ind) <- base::colnames(corr_mat)
out <- base::cbind(ID=c(col(ind)), ID2=c(ind))
base::as.data.frame(cbind(out, cor=corr_mat[out]))
final_df <- base::as.data.frame(cbind(out, cor=corr_mat[out]))