Identifying drug targets is a critical step in pharmacology. Drug phenotypic and chemical indexes are two important indicators in this field. However, in previous studies, the indexes were always isolated and the candidate proteins were often limited to a small subset of the human genome.
Based on the correlations observed in pharmacological and genomic spaces, we develop a computational framework, drugCIPHER, to infer drug-target interactions in a genome-wide scale. Three linear regression models are proposed, which respectively relate drug therapeutic similarity, chemical similarity and their combination to the relevance of the targets on the basis of a protein-protein interaction network. Typically, the model integrating both drug therapeutic similarity and chemical similarity, drugCIPHER-MS, achieved an area under the Receiver Operating Characteristic (ROC) curve of 0.988 in the training set and 0.935 in the test set. Based on drugCIPHER-MS, a genome-wide map of drug biological fingerprints for 726 drugs is constructed, within which unexpected drug-drug relations emerged in 501 cases, implying possible novel applications or side effects.
Our findings demonstrate that the integration of phenotypic and chemical indexes in pharmacological space and protein-protein interactions in genomic space can not only speed the genome-wide identification of drug targets but also find new applications for the existing drugs.