Figure 1From: Hon-yaku: a biology-driven Bayesian methodology for identifying translation initiation sites in prokaryotesRelationship between the size of training data set and the accuracy. The x-axis shows the size of the training data set. The leftmost data point corresponds to the leave-one-out analysis based on the full data set of 857 genes in E. coli and 1242 genes in B. subtilis. For the other data points, we created the training data set of the given size by randomly selecting genes from the full data set.Back to article page