Drug-target Affinity Prediction by Molecule Secondary Structure Representation Network

INTRODUCTION

Identification of drug-target interactions (DTI) is a crucial step in drug development with high specificity and low toxicity. To accelerate the process, computer-aided DTI prediction algorithms have been used to screen compounds or targets rapidly. Furthermore, DTI prediction can be used to identify potential targets for existing drugs, thus uncovering new indications and repositioning them. Therefore, it is of great importance to develop efficient and accurate DTI prediction algorithms.

METHOD

Current algorithms usually represent drugs as extracted features, which are learned by convolutional neural networks (CNNs) from its linear representation, or utilize graph neural networks (GNNs) to learn its graph representation. However, these methods either lose information or fail to capture the structural information of the drug. To address this issue, a novel molecule secondary structure representation network (MSSRN) is proposed to learn drug characterization more accurately. Firstly, the network performs relational graph convolutional networks (R-GCNs) on the drug's molecular graph and integrates drug sequence convolutions to learn the sequential information. Secondly, inspired by the attention mechanism, spatial importance weights of the drug sequence are calculated to guide R-GCNs to learn the topological information of the drug.

RESULT

A drug-target affinity model, called MSSRN-DTA, was then constructed by using MSSRN to learn drug structure and CNN to learn protein sequence.

CONCLUSION

The effectiveness of the proposed method is verified by comparing it with other alternative methods and baseline models on two benchmark datasets.

Chemical informatics and the drug discovery knowledge pyramid

The magnitude of the challenges in preclinical drug discovery is evident in the large amount of capital invested in such efforts in pursuit of a small static number of eventually successful marketable therapeutics. An explosion in the availability of potentially drug-like compounds and chemical biology data on these molecules can provide us with the means to improve the eventual success rates for compounds being considered at the preclinical level, but only if the community is able to access available information in an efficient and meaningful way. Thus, chemical database resources are critical to any serious drug discovery effort. This paper explores the basic principles underlying the development and implementation of chemical databases, and examines key issues of how molecular information may be encoded within these databases so as to enhance the likelihood that users will be able to extract meaningful information from data queries. In addition to a broad survey of conventional data representation and query strategies, key enabling technologies such as new context-sensitive chemical similarity measures and chemical cartridges are examined, with recommendations on how such resources may be integrated into a practical database environment.