Several studies [5], [15] [17], [19] have reported the performance of MHC-II binding peptide prediction methods using datasets of unique peptides.
The performance is analyzed and compared with several existing methods using datasets obtained from the Protein Information Resource center.
We evaluated the methods using datasets simulated to present different scenarios corresponding to a given combination of the following parameters: sample size (5 or 10), proportion of differentially expressed genes (5% or 10%), ratio of up-regulated vs. down-regulated (1 1 or 3 1), lower bound of fold change (1.5 or 1.1), and lower bound of depth (5 or 1).
We evaluated the methods using datasets simulated to represent different scenarios corresponding to a given combination of parameters of number of true hits, the amount of noise, the skewness of the data, the strength of chemotherapeutic drug effect, and the RNAi effect.
Predictive accuracy, the correlation between the predicted and the true breeding values r g, g ^, was estimated by the ratio of predictive ability s g, ^ p to the square root of heritability for each of the indirect methods using datasets with and without outliers.
We tested the five DCEA methods using dataset GSE3068 obtained from GEO (Table 1).
We compared the performance of the three methods using simulated datasets and a real biological dataset, in which an overexpression line CBF2_OX was compared with wild type control.
Secondly, because the true tree is not known for biological supertree datasets, it is difficult to evaluate supertree methods using biological datasets.
To evaluate the Sec-GO method, two existing methods and their used datasets are adopted for performance comparisons.
Hence, there have been numerous works investigating efficient methods using reduced datasets.
