The Role of AI in Drug Discovery

The article is focused on the use of artificial intelligence in drug discovery and explains how the use of AI helps speed up the process of identifying and developing new therapeutic agents. The use of machine learning helps in data analysis of big data, drug-target interactions, and effective drug planning and design.

AI has brought a dramatic change to the process of drug discovery from drug identification to the development of new drugs. A machine learning method is capable of estimating the molecular characteristics, mimicking the drug interactions, and processing the biological information. The incorporation of the integration of AI explains the time and cost that may be used in conventional ways of drug discovery. However, the issue is on the quality of data, transparency of the algorithm, and regulatory problems.

The employment of AI has also made it possible to identify new target drug targets and prodrug candidates as well as repositioning agents. Some of achievements are AI discovered drugs such as compounds for curing diseases including COVID 19, ALS, among others. It has also enhanced the methods of clinical trial, most specifically, the selection of patients and prediction of trial results. Prolonged developments in this field are likely to put more profound reforms in drug discovery cycle.

Author: Parker Whitman

References: Zhavoronkov A, Aliper A, Artamonov A, et al. Deep learning enables rapid identification of potent DDR1 kinase inhibitors. Nat Biotechnol. 2019 Apr;37(4):358-364. doi:10.1038/s41587-019-0054-x.

Stokes JM, Yang K, Swanson K, et al. A deep learning approach to antibiotic discovery. Cell. 2020 Feb 20;180(4):688-702.e13. doi:10.1016/j.cell.2020.01.021.

Ghasemi F, Mehridehnavi A, Pérez-Garrido A, Pérez-Sánchez H. Neural network and deep-learning algorithms used in QSAR studies: Merits and drawbacks. Drug Discov Today. 2018 Oct;23(10):1784-1790. doi:10.1016/j.drudis.2018.06.013.