Abstract
Drug discovery and development have been sped up because of the advances in computational science. In both industry and academics, artificial intelligence (AI) has been widely used. Machine learning (ML), an important component of AI, has been used in a variety of domains, including data production and analytics. One area that stands to gain significantly from this achievement of machine learning is drug discovery. The process of bringing a new drug to market is complicated and time-consuming. Traditional drug research takes a long time, costs a lot of money, and has a high failure rate. Scientists test millions of compounds, but only a small number make it to preclinical or clinical testing. It is crucial to embrace innovation, especially automated technologies, to lessen the complexity involved in drug research and avoid the high cost and lengthy process of bringing a medicine to the market. A rapidly developing field, a branch of artificial intelligence called machine learning (ML), is being used by numerous pharmaceutical businesses. Automating repetitive data processing and analysis processes can be achieved by incorporating ML methods into the drug development process. ML techniques can be used at numerous stages of the drug discovery process. In this study, we will discuss the steps of drug discovery and methods of machine learning that can be applied in these steps, as well as give an overview of each of the research works in this field.
Graphical Abstract
[http://dx.doi.org/10.3390/molecules25225277] [PMID: 33198233]
[http://dx.doi.org/10.1002/0471250953.bi1401s18]
[http://dx.doi.org/10.1177/1087057113497095] [PMID: 23896689]
[http://dx.doi.org/10.1007/978-3-030-22141-6_5]
[http://dx.doi.org/10.1186/s13321-020-00460-5] [PMID: 33431035]
[http://dx.doi.org/10.1186/s13321-020-00445-4] [PMID: 33431010]
[http://dx.doi.org/10.1021/acs.jmedchem.9b02130] [PMID: 32101427]
[http://dx.doi.org/10.1016/j.ijpharm.2020.119837] [PMID: 32961295]
[http://dx.doi.org/10.1038/d41573-019-00007-6] [PMID: 30867601]
[http://dx.doi.org/10.1016/j.drudis.2018.12.039] [PMID: 25448759]
[http://dx.doi.org/10.1021/acs.jcim.8b00768]
[http://dx.doi.org/10.1039/d0sc02203e]
[http://dx.doi.org/10.31838/ijpr/2019.11.01.062]
[http://dx.doi.org/10.1002/int.22389]
[http://dx.doi.org/10.1038/s41598-021-83679-y] [PMID: 33627791]
[http://dx.doi.org/10.1186/s12859-019-3263-x]
[http://dx.doi.org/10.1016/j.compbiolchem.2019.03.016] [PMID: 30939415]
[http://dx.doi.org/10.1093/bioinformatics/btaa880] [PMID: 33070179]
[http://dx.doi.org/10.1038/s41573-019-0024-5] [PMID: 30976107]
[http://dx.doi.org/10.1093/bioinformatics/btac112] [PMID: 35179547]
[http://dx.doi.org/10.3390/ijms22041676] [PMID: 33562347]
[http://dx.doi.org/10.1080/07391102.2021.1898474] [PMID: 33703998]
[http://dx.doi.org/10.1126/sciadv.aap7885] [PMID: 30050984]