DT-Web: a web-based application for drug-target interaction and drug combination prediction through domain-tuned network-based inference

Abstract

Background: The identification of drug-target interactions (DTI) is a costly and time-consuming step in drug discovery and design. Computational methods capable of predicting reliable DTI play an important role in the field. Algorithms may aim to design new therapies based on a single approved drug or a combination of them. Recently, recommendation methods relying on network-based inference in connection with knowledge coming from the specific domain have been proposed.

Description: Here we propose a web-based interface to the DT-Hybrid algorithm, which applies a recommendation technique based on bipartite network projection implementing resources transfer within the network. This technique combined with domain-specific knowledge expressing drugs and targets similarity is used to compute recommendations for each drug. Our web interface allows the users: (i) to browse all the predictions inferred by the algorithm; (ii) to upload their custom data on which they wish to obtain a prediction through a DT-Hybrid based pipeline; (iii) to help in the early stages of drug combinations, repositioning, substitution, or resistance studies by finding drugs that can act simultaneously on multiple targets in a multi-pathway environment. Our system is periodically synchronized with DrugBank and updated accordingly. The website is free, open to all users, and available at http://alpha.dmi.unict.it/dtweb/.

Conclusions: Our web interface allows users to search and visualize information on drugs and targets eventually providing their own data to compute a list of predictions. The user can visualize information about the characteristics of each drug, a list of predicted and validated targets, associated enzymes and transporters. A table containing key information and GO classification allows the users to perform their own analysis on our data. A special interface for data submission allows the execution of a pipeline, based on DT-Hybrid, predicting new targets with the corresponding p-values expressing the reliability of each group of predictions. Finally, It is also possible to specify a list of genes tracking down all the drugs that may have an indirect influence on them based on a multi-drug, multi-target, multi-pathway analysis, which aims to discover drugs for future follow-up studies.

Figure 1

DT-Web Search Example. Once the user provides a query (either a part of the name or the accession number of a drug/target), DT-Web finds all the matching records in the internal database and returns them to the user in a page containing all the information requested. If all the records are drugs, the user will also see, if available, their two-dimensional structures, and a list of all targets, enzymes, transporters, carriers, and predicted targets, which have been computed through DT-Hybrid. Here user searched for DB00014

Figure 2

DT-Web DTI Prediction Example. Once the user provides its own DTI network and, if possible, two similarity matrices for each pair of drug and target, DT-Web applies the pipeline described above, after checking the validity of its input. At the end of such an operation, the user will see a page containing a list of all the drugs for which a result was available, along with the corresponding measures of correlation and p-value. By selecting one drug, the user will also see the list of all the predicted targets along with the scores assigned to each prediction by DT-Hybrid.

Figure 3

DT-Web DTI network view. A DTI network after applying our prediction pipeline. Each node represents a drug (blue heptagon) or a target (gray circle), while each edge represents a drug-target interaction (user-provided ones in black, predictions in red).

Figure 4

DT-Web Drug Combination Prediction Example. Once the user submits a list of genes, DT-Web calculates, using the pathways stored in the database, a list of possible drugs that indirectly target such genes, using the pipeline described above. When finished, the user will see a list of such drugs, ordered by direct and indirect targets, which can be filtered by selecting an appropriate combination of parameters (either one or more drugs/targets). By selecting a drug or a target, the user will also view an excerpt of the pathway used by the algorithm to compute the prediction. By clicking on a drug the user obtains a list of predicted targets.