Probabilistic Inference of Biological Networks via Data Integration

Figure 2

Graphical depiction showing the typical improvement in accuracy we see when using a weighted sum of base kernels via MKL. Here, we compare the average performance of the best-performing composite kernel, (solid grey bars), with the corresponding base kernels (hashed bars) on data sets of three different sizes. By leveraging information from multiple kernels, provides an accuracy increase of 4% to 5% over the best of the base kernels. When we use MKL over all 30 base kernels combined (), we achieve a further 1.2% to 1.4% increase (black bars). Differences between and its base kernels are significant at ; differences between and are significant at .