Skip to main content
Figure 2 | BMC Bioinformatics

Figure 2

From: A comparison of machine learning algorithms for chemical toxicity classification using a simulated multi-scale data model

Figure 2

Model S1. The "M" nodes represent assays that measure direct molecular interactions with a chemical. These interactions can activate pathways ("P" nodes) which can in turn activate cellular processes ("C" nodes). Finally, the activation of cellular processes can lead to the presence of an organ or organism-level endpoint. For Model S1, an additional 300 random or "R" nodes were included in the input set of features, so that a total of 308 features are examined. Numerical values shown along edges are values of w ik used in Equation 1.

Back to article page