Figure 1
From: Homology-based prediction of interactions between proteins using Averaged One-Dependence Estimators
Three homology-based features used for training AODEs. (a) A feature set of sequence similarities to known interacting proteins (F Seq = {e-value A , mincov A , e-value B , mincov B }). For a target pair (S A , S B ), the interacting pair (T A , T B ) with the smallest value of √(e-value A 2 + e-value B 2), where e-value x is a BLAST e-value between S x and T x and x is either A or B, is selected, and then the minimum coverage (mincov) for S x and T x is calculated as (the number of positive matches)/(the length of the longer sequence). If no known homologous interacting pair is found, an e-value of 102 and a mincov of 0 are assigned to FSeq. (b) Statistical propensities of domain pairs observed in interacting proteins (FDom). A sum of the interaction propensities for all possible Pfam domain pairs (d A , d B ) appeared in S x and T x is calculated (see more details in the text). If not Pfam domain is found, an FDom value of 0 is given to the target pair. (c) A sum of edge weights along the shortest path between homologous proteins (P A , P B ) in the PPI network (FNet). In this study, we set the default edge weight to be 1.0. If no path is found, an FNet of -1 is given to the target pair.