Skip to main content


Figure 1 | BMC Bioinformatics

Figure 1

From: Protein function prediction by massive integration of evolutionary analyses and multiple data sources

Figure 1

Performance of Jones-UCL in comparison with the component methods. Comparison of the COGIC score distributions achieved by the individual predictors on the MF (upper panel) and BP (lower panel) benchmark sets. Each box spans from the first to the third quartile of the corresponding distribution; the median value is highlighted as a thick line, while putative outliers are plotted as empty circles. The width of each box is proportional to the number of targets predicted and officially assessed. Some names have been shortened ("Orthologues" for Orthologous Groups, "Prof-Prof Aln" for Profile-Profile Alignment, "AA 3-gram Mining" for amino acid trigram mining and "Text Mining" for Swiss-Prot Text Mining).

Back to article page