Recently, Artificial intelligence has gained much concern for its wide variety of applications in the pharmaceutical industry. It mimicked human intelligence in machines to help solve complex problems in the drug discovery and development process. As well, it provided a great benefit in reducing the time of the drug discovery process and had a shape-eye ability in many applications. Some of these applications are medical interpretation, detection of early signs of cancer, prevention of medical errors that are caused by electronic health records, and early warning of disease.

Drug Development process
Drug development starts with the identification of novel chemical compounds that have biological activity. This requires screening of chemical libraries, computer simulation, or screening of naturally isolated materials, such as plants, bacteria, and fungi. The first compound that possesses activity against a specific biological target is called a ‘hit’ [1]. The second step in drug development is the identification of a lead molecule. When a lead compound has been found, its chemical structure is used as a starting point for optimization with the aim of discovering compounds that possess maximal therapeutic effects and minimal side effects. [1,2]. During this process, modification of lead compounds occurs to enhance their activity and selectivity towards specific biological targets according to lock and key or induced fit model [2, 4]. At the same time reducing toxicity and undesired effects [3].

Application of artificial intelligence in drug development:
It worth noting that finding successful new drugs is the most difficult part of drug development. This is due to the vast size of chemical space, which is estimated to be in the order of 1060 molecules [5].
The uses of AI in drug development can be:

Identification and validation of drug targets, designing of new drugs, drug repurposing, improving the R&D efficiency, aggregating and analyzing biomedicine information, and refining the decision-making process to recruit patients for clinical trials [6–7]. This did not only reduce the uncertainties in classical methods, but also a limited human intervention that can lead to bias decisions [8].
Prediction of feasible synthetic routes for drug-like molecules [9].
Analysis of large datasets, laborious screening of compounds, and limitation of standard error [10].

The application of AI comes over all stages of drug development as we will mention the most important and common ones.

AI in understanding the pathway or finding molecular targets:
By utilizing genomics information, biochemical approaches, and target tractability, AI has changed the methods of the pathway or target identification to treat diseases [11]. For instance, an AI platform called IBM Watson for Drug Discovery has recognized five new RNA-binding proteins (RBPs)related to the pathogenesis of a neurodegenerative disease known as amyotrophic lateral sclerosis (ALS) [12].
AI in finding the hit or lead:
The most significant part of the drug development process is the synthesis of selected hit molecules. Thus, AI provides the benefit of prioritizing molecules based on the ease of synthesis or developing new tools that are effective for the optimal synthetic route.
AI in the synthesis of drug-like compounds:
AI would help predict reactions of unpredictable steric and electronic effects and incomplete understanding of its mechanism. Currently, several computer-aided organic compound synthesis (CAOCS) systems are available to assist chemists in selecting the synthesis route.
Predicting the mode-of-action of compounds using AI. AI platforms can predict the on- and off-target effects and in the Vivo safety profile of compounds before they are synthesized. This indeed reduces the drug development time, R&D costs, and attrition rates.
AI in the selection of a population for clinical trials. An ideal AI tool to assist in clinical trials should recognize the disease in patients, identify the gene targets and predict the effect of the molecule designed as well as the on- and off-target effects. A novel AI platform called AiCure was also developed as a mobile application to measure medication adherence in a Phase II trial of subjects suffering from schizophrenia, where it was reported that AiCure increased adherence 25% compared with the traditional ‘modified directly observed therapy [13]. The development of AI approaches to identify and predict human-relevant biomarkers of disease allows the recruitment of a specific patient population in Phase II and III clinical trials. The AI predictive modeling in the selection of a patient population would increase the success rate in clinical trials [14,15].

To conclude, AI will permanently change the pharmaceutical industry and the way drugs are discovered. However, for an individual to be efficient in drug development using AI, the individual should know how to train algorithms, requiring domain expertise. This creates a suitable workspace whereby AI and medicinal chemists can work closely together because the former will be able to help in analyzing huge datasets and the latter can train machines, set algorithms, or optimize the analyzed data for a speedier and accurate drug development process. Despite the benefit of AI in speeding up drug development, real experiments still need to be conducted. Additionally, AI can be used in assisting gene therapy or other therapies that are currently not available to us as tools in healthcare. AI is absolutely changing the way we consider the pharmaceutical industry and drug discovery.

[/font]

Zhu, T. et al. (2013) Hit identification and optimization in virtual screening:
practical recommendations based on a critical literature analysis. J. Med. Chem. 56,
6560–6572
Anderson, A.C. (2012) Structure-based functional design of drugs: from target to
lead compound. Methods Mol. Biol. 823, 359–366
Hall, D.R. et al. (2012) Hot spot analysis for driving the development of hits into
leads in fragment-based drug discovery. J. Chem. Inf. Model. 52, 199–209
Alanine, A. et al. (2003) Lead generation-enhancing the success of drug discovery by
investing in the hit to lead the process. Comb. Chem. High Throughput Screen. 6, 51–66
Segler, M.H.S. et al. (2018) Generating focused molecule libraries for drug discovery
with recurrent neural networks. ACS Cent. Sci. 4, 120–131
Huang, Z. et al. (2017) Data mining for biomedicine and healthcare. J. Healthc. Eng.
2017 http://dx.doi.org/10.1155/2017/7107629 Article ID 7107629, 2 pages
Mamoshina, P. et al. (2016) Applications of deep learning in biomedicine. Mol.
Pharm. 13, 1445–1454
Seddon, G. et al. (2012) Drug design for ever, from hype to hope. J. Comput. Aided
Mol. Des. 26, 137–150
Merk, D. et al. (2018) De novo design of bioactive small molecules by artificial
intelligence. Mol. Inform. 37, 1700153
40 Mohs, R.C. and Greig, N.H. (2017) Drug discovery and development: role of basic
biological research. Alzheimer's Dement. 3, 651–657
Wang, Q. et al. (2017) A novel framework for the identification of drug target
proteins: combining stacked auto-encoders with a biased support vector machine.
PLoS One 12, e0176486
Bakkar, N. et al. (2018) Artificial intelligence in neurodegenerative disease research:
use of IBM Watson to identify additional RNA-binding proteins altered in
amyotrophic lateral sclerosis. Acta Neuropathol. 135, 227–247
Bain, E.E. et al. (2017) Use of a novel artificial intelligence platform on mobile
devices to assess dosing compliance in a Phase 2 clinical trial in subjects with
schizophrenia. JMIR Mhealth Uhealth 5, e18
Perez-Gracia, J.L. et al. (2017) Strategies to design clinical studies to identify
predictive biomarkers in cancer research. Cancer Treat. Rev. 53, 79–97
Deliberato, R.O. et al. (2017) Clinical note creation, binning, and artificial
intelligence. JMIR Med. Inf. 5, e24