Computational prediction of drug–target interactions using chemogenomic approaches: an empirical survey

Abstract

Computational prediction of drug-target interactions (DTIs) has become an essential task in the drug discovery process. It narrows down the search space for interactions by suggesting potential interaction candidates for validation via wet-lab experiments that are well known to be expensive and time-consuming. In this article, we aim to provide a comprehensive overview and empirical evaluation on the computational DTI prediction techniques, to act as a guide and reference for our fellow researchers. Specifically, we first describe the data used in such computational DTI prediction efforts. We then categorize and elaborate the state-of-the-art methods for predicting DTIs. Next, an empirical comparison is performed to demonstrate the prediction performance of some representative methods under different scenarios. We also present interesting findings from our evaluation study, discussing the advantages and disadvantages of each method. Finally, we highlight potential avenues for further enhancement of DTI prediction performance as well as related research directions.

Drug-Target Interaction prediction using Multi-Graph Regularized Deep Matrix Factorization

“…X m×n can be expressed as a product of two matrices U m×r and V r×n . The complete matrix factorization problem (1) can be framed as, (2).…”

“…Conventionally, this was done through time-taking and expensive wet-lab experiments. In recent times, the introduction of computational techniques for prediction of interaction probability [1][2][3][4] has paved the way for appropriate and effective alternatives which could help avoid costly candidate failures. These methods take some existing experimentally valid interactions which are publicly available in databases like STITCH [5], ChEMBL [6], KEGG DRUG [7], DrugBank [8] and SuperTarget [9] to predict the interaction probability of unknown drug-target pairs.…”

“…In one of the recent studies [2], it was shown that matrix factorization works best for DTI prediction. This method assumes that there are very few (latent) factors which are actually responsible for drug target interactions.…”

“…In the training set, positive samples are the experimentally known interactions while the negative ones are either non-interactions or unknown interactions. The second category includes Similarity-based methods, which take into account two similarity matrices corresponding to drug and target similarity, respectively, along with the drug-target interaction matrix.Amongst the recent techniques proposed for DTI prediction, matrix factorization based models depict the most promising results [2]. There has been recent work on deep Matrix Factorization [22] too.…”

“…Amongst the recent techniques proposed for DTI prediction, matrix factorization based models depict the most promising results [2]. There has been recent work on deep Matrix Factorization [22] too.…”