Fig. 3: Comparisons of false/true positive rate (FPR/TPR) for identifying nonlinear relationships within an ecosystem.
From: Linear and nonlinear correlation estimators unveil undescribed taxa interactions in microbiome data
Synthetic data were generated from log-normal distributions. The X-axis denotes the simulation settings, which are a combination of sample size n, number of taxa d, and the dispersion parameter α. Results are represented by the average of corresponding measure (FPR/TPR) ± standard errors (shown as error bars) across 100 simulation runs for each n/d/α setting. Data points are added to the bar charts using dots with jittering. Color and the name of the corresponding correlation methods are shown at the bottom of the graph. Results showed that only SECOM controlled the FPR while maintaining high TPR. Other than SECOM, none of the existing methods identify nonlinear relationships.
