“…MetaAnalyst supports two kinds of analysis: (1) biomarker detection, and (2) phenotype classification. For biomarker detection, the MetaAnalyst packs 28 metagenomic biomarker discovery algorithms, namely, Shotgun-FunctionalizeR [ 19 ], Boruta [ 15 ], edgeR [ 23 ], DESeq2 [ 24 ], ENNB [ 16 ], MetagenomeSeq [ 17 ], MicrobiomeDDA [ 18 ], MetaStats [ 20 ], Raida [ 21 ], LEfSe [ 9 ], RPCA [ 10 ], RegLRSD [ 11 ] , RSPCA [ 46 ], Lasso [ 47 ], Relief [ 48 ], ReliefF [ 49 ], and the following hypothesis tests: Wilcoxon Rank Sum Test [ 50 ], t-Test [ 51 ], log t-Test [ 51 ], square t-Test [ 51 ], Welch’s Test [ 52 ], Chi-square Test [ 53 ], which are implemented using “stats” package R [ 30 ], Kolmogorov Smirnov Test [ 54 ], Levene Absolute Test [ 55 ], Levene Quadratic Test [ 55 ], Brown Forsythe Test [ 56 ], BSS/WSS (Between Sum of Squares over Within Sum of Squares) [ 57 ], and Pearson Correlation [ 58 ], which are implemented using MATLAB. Detailed description of these methods are provided in the User Manual.…”