Identification of drug-target interactions is an important process in drug discovery. Although high-throughput screening and other biological assays are becoming available, experimental methods for drug-target interaction identification remain to be extremely costly, time-consuming and challenging even nowadays. Therefore, various computational models have been developed to predict potential drug-target associations on a large scale.
Identifies potential target candidates for the given probe small molecules using pharmacophore mapping approach. PharmMapper is a freely accessed web-server designed to profil the potential secondary or side effects for a drug molecule in a different viewpoint from the regular chemogenetic method. It can also be used FOR mapping the regulation genomic network for an existing drug or a drug candidate.
Reveals both expected and unexpected similarities that may be tested by examining the ‘off-target’ activities of the ligands themselves. SEA is a web application that reports proteins based on the set-wise chemical similarity among ligands. This method can be used to rapidly search large compound databases and to build cross-target similarity maps.
Predicts the drug-target interactions. DT_all is able to enhance the predictive accuracies in two scenarios, and the elaborate fusion strategy of multiple classifiers has better predictive power than the naïve combination of multiple similarity metrics. Compared with other two state-of-the-art approaches on the four popular benchmark datasets of binary drug-target interactions, the tool achieves the best results in terms of AUC and AUPR for predicting available targets for new drugs, and predicting approved drugs for new protein targets.
Discovers new uses for existing drugs. DTI prediction uses complex network theory to predict drug-target interactions (DTI) from a drug-target network. It tends to yield high performance when additional information about attributes of drugs, targets, and their interactions is available. The tool provides real, reliable predictions (in contrast to pseudo evaluation) that will benefit the research community and pharmaceutical industry.
Integrates heterogenous drug similarities with protein interation network data to accurately predict drug-target relations. drugCIPHER proposes three linear regression models respectively using drug therapeutic similarity, chemical similarity and their combination as responses and network distance as predictors.
Identifies drug targets. TarFisDock is a web server that allows to identify potential binding proteins for small molecules such as drugs, lead compounds and natural products. The software docks a given small molecule into the possible binding sites of proteins in the target list, calculates and records interaction energies between the small molecule and the proteins and analyzes the reverse docking result. The targets information produced are significant for functional genomic study with the chemical biology paradigm.
Allows integration of genetics, omics and chemical data to aid systematic drug target identification and prioritization. Open Targets is a data integration and visualization platform that integrates evidence from genetics, genomics, transcriptomics, drugs, animal models and scientific literature to score and rank target-disease associations for drug target identification. It also includes causal genetic variants from non genome-wide targeted arrays.