ASCA or ANOVA-simultaneous component analysis, is a multivariate extension of univariate ANOVA approach. This implementation in MetaboAnalyst currently supports ASCA model for two factors with one interaction effect. The algorithm first partitions the overall data variance (**X**) into individual variances induced by each factor (**A** and **B**), as well as by the interactions (**AB**). The formula is shown below with (**E**) indicates the residuals.

**X = A + B + AB + E**

The SCA part applies PCA to **A**, **B**, **AB** to summarize major variations in each partition. Users need to specify the number of components used for each model. The maximum allowed number of components of each factor must be less than the corresponding levels of the factor. For example, if the phenotype factor contains two levels (control and disease). Only the top component will be extracted. In most cases, users should focus on top one or two components.

Please refer to the original paper for more technical details on ASCA.