Skip to main content
Figure 1 | BMC Bioinformatics

Figure 1

From: Improving protein fold recognition by random forest

Figure 1

A random forest to classify if two proteins share the same fold. The random forest is comprised of T decision trees. Each tree predicts the probability of class c conditioned on an input feature vector (v) representing the similarity between two proteins. Class c is either 0 (not in the same fold) or 1 (in the same fold). The average probability of all the trees is calculated as P(c|v). The class c with the higher value is the predicted class for the input feature vector.

Back to article page