PMC:4331677 / 17517-19857 JSONTXT

{"project":"2_test","denotations":[{"id":"25707321-21506615-14839523","span":{"begin":219,"end":221},"obj":"21506615"},{"id":"25707321-19605421-14839524","span":{"begin":307,"end":309},"obj":"19605421"}],"text":"Representative methods for comparison\nIn order to evaluate the proposed method in this paper, we chosen three representative methods for comparison: chemical substructures and protein domains correlation model (CS-PD) [23], bipartite local model with neighbor-based interaction-profile inferring (BLM-NII) [11] and random forest (RF) [15].\n• CS-PD: Proteins were described by domains and ligands were represented by substructures in CS-PD model. Sparse canonical correspondence analysis (SCCA) algorithm was applied to recognize the physical-chemical factors between the domains and substructures. In prediction phase, the domain and substructure physical-chemical factors in a given target-ligand pair were added to generate a discriminant value. If the value was higher than a threshold, the target and ligand were predicted to interact with each other.\n• BLM-NII: On one hand, excluding target ti, make a list of all other known targets of ligand lj, as well as a separate list of the targets not known to be targeted ligand lj. The known targets were given a label +1 and the others a label −1. Then, look for a classification rule that tried to discriminate the +1-labeled data from the −1-labeled data using the available genomic sequence data for the targets. This rule was applied to predict the label of target ti and ligand lj. On the other hand, fixing the same target ti and excluding ligand lj, make a list of all other known ligands targeting ti, as well as a list of ligands not known to target ti. Similar with before, ligands known to target ti were given the label +1 and the others were given the label −1. We looked for a classification rule that tried to discriminate the +1-labeled data from the −1-labeled data, using the available chemical structure data for the ligands. This rule was also used to predict the label of target ti and ligand lj. At last, the two results were combined to generate a final label. For new targets or ligands, a neighbor-based interaction-profile inferring was applied to get an interaction profile.\n• RF: The targets were described as CTD (Composition-Transition-Distribution, [15]) features. The ligands were represented as fingerprints. Then, the two kinds of features were combined into a vector to generate data set. Finally, random forest (RF) was employed to predict interactions."}