Figure 7
From: Metrics for GO based protein semantic similarity: a systematic evaluation
Bimodal vs. unimodal fit to the semantic similarity results. A - Semantic similarity (Resnik's measure with the BMA approach) vs. LRBS sequence similarity: black points - averaged results; red line - unimodal modelling function; green line - bimodal modelling function. B - Fit residuals of the bimodal and unimodal modelling functions vs. LRBS sequence similarity: red points - fit residuals of the unimodal modelling function; red line - corresponding linear trendline; green points - fit residuals of the bimodal modelling function; green line - corresponding linear trendline. It is clear that the unimodal modelling function does not describe the behaviour of the results accurately, since the fit residuals are unevenly distributed (as reflected by the negative slope of the trendline); whereas the bimodal modelling function shows evenly distributed residuals (with a nearly horizontal trendline at 0).