Revealing Drug-Target Interactions with Computational Models and Algorithms

• Published in: Molecules (Basel, Switzerland) Switzerland), 2019-05, Vol.24 (9), p.1714
• Main Authors: Zhou, Liqian, Li, Zejun, Yang, Jialiang, Tian, Geng, Liu, Fuxing, Wen, Hong, Peng, Li, Chen, Min, Xiang, Ju, Peng, Lihong
• Format: Article
• Language: English
• Subjects: Algorithms; computational models; Computer applications; Cytochrome; Deep learning; Drug interactions; drug repositioning; drug-target interaction prediction; Experimental methods; FDA approval; High-throughput screening; Learning algorithms; Ligands; Machine learning; machine learning-based methods; Mathematical models; Medical research; network-based methods; Ontology; Open access; Peptides; Pharmaceutical industry; Pharmacology; Proteins; R&D; Research & development; Review; Software packages; Therapeutic targets; Websites
• ISSN: 1420-3049; 1420-3049
• DOI: 10.3390/molecules24091714

Identifying possible drug-target interactions (DTIs) has become an important task in drug research and development. Although high-throughput screening is becoming available, experimental methods narrow down the validation space because of extremely high cost, low success rate, and time consumption. Therefore, various computational models have been exploited to infer DTI candidates. We introduced relevant databases and packages, mainly provided a comprehensive review of computational models for DTI identification, including network-based algorithms and machine learning-based methods. Specially, machine learning-based methods mainly include bipartite local model, matrix factorization, regularized least squares, and deep learning. Although computational methods have obtained significant improvement in the process of DTI prediction, these models have their limitations. We discussed potential avenues for boosting DTI prediction accuracy as well as further directions.