Spearman correlation coefficient between the PLM and ALM frequency profiles.

Spearman correlation coefficient calculated between the PLM and ALM frequency profiles of each instance. Correlation of the frequency profiles of IU Pdiff versus locCons and IU Pdiff versus globCons are indicated as locCons corr and globCons corr respectively. Correlation of 1 would indicate that the PLM and ALM sets cover the same IU Pdiff and locCons/globCons ranges. A correlation of ?1 would imply that those ranges are completely disjoint and diametrically opposed (e.g. high IU Pdiff and low locCons for ALM while low IU Pdiff and high locCons for PLM). Small positive or negative values indicate that the ranges tend to be disjoint but not opposite. Instances in bold have PLM and ALM sets with significantly different IU Pdiff distributions (p-valuesaprotein and module structural classes.

针对每个样本实例，计算其蛋白质语言模型（PLM）与辅助语言模型（ALM）的频率分布谱之间的斯皮尔曼相关系数（Spearman correlation coefficient）。其中，IU Pdiff分别与局部保守性（locCons）、IU Pdiff与全局保守性（globCons）的频率分布谱相关性，分别记为locCons相关系数（locCons corr）与globCons相关系数（globCons corr）。当相关系数为1时，表明PLM与ALM集合覆盖了完全一致的IU Pdiff以及局部/全局保守性取值范围；当相关系数为-1时，则意味着两类取值范围完全不重叠且呈截然相反的对立分布（例如，ALM的IU Pdiff取值偏高而局部保守性偏低，PLM则反之）。较小的正相关或负相关系数，则表明两类取值范围倾向于互不重叠，但并未呈现对立分布。标注为粗体的样本实例，其PLM与ALM集合的IU Pdiff分布存在显著差异（对应蛋白质与模块结构类别的p值）。