Performance of MassiveQC. The distribution of running time (A) and sample size (B) for 952 runs from GSE60314. (C) The average accuracy of outlier detection with k contaminated samples (k = 5 to 30). The accuracy is calculated by dividing the number of contaminated samples identified as outliers by the total number of contaminated samples. The y-axis represents the average accuracy of 100 simulations with different numbers of contaminated samples. (D) The average accuracy in different numbers of normal samples.