Predicting Potential Ligands for Orphan GPCRs Based on the Improved Laplacian Regularized Least Squares Method

摘要

Predicting potential interactions between receptors and ligands can provide important clues to the discovery of ligands for orphan GPCRs (oGPCRs). In this paper, we develop an improved Laplacian Regularized Least Squares method (EstLapRLS) to predict potential receptor-ligand associations. The originality lies in the fact that we can utilize more valuable information for ligand-receptor interaction prediction based on two estimated matrices. Experimental results show that the proposed method can obtain a high specificity and sensitivity on cross-validation tests.