Table 1 Average and standard deviation of Correlation coefficient (CC) values using different models. The data were obtained from 10 cross-validation. The CC values were obtained from testing dataset when cutoff selected from the training set. * Wilcox rank sum paired test shows significant (p-value < 0.001) better than the corresponding single nucleotide model.
From: Generalizations of Markov model to characterize biological sequences
Samples (size) | Single nucleotide | Di-nucleotide | Tri-nucleotide |
|---|---|---|---|
CpG-poor Promoters (1,466) | 0.24 ± 0.05 | 0.28 ± 0.03* | 0.34 ± 0.04* |
All Promoters (12,333) | 0.54 ± 0.02 | 0.54 ± 0.03 | 0.56 ± 0.02* |
All Exons (219,624) | 0.63 ± 0.00 | 0.64 ± 0.00* | 0.67 ± 0.00* |