help them to discover new drug pathways through efficient data and pattern analysis.

Using AI to help synthesise the drugs Once a range of potential candidates has been chosen, the next stage is to try and synthesize the drugs — often by first taking a retrosynthetic approach from the final product back to potential reactants, and then working the reaction forward. The ability for AI to choose potential drug structures based on their most likely drug profiles means that fewer drug molecules need to be synthesized at the later stages and this cuts down on ‘trial and error’ approaches. But AI is also aiding the synthetic processes as well. For the most suitable drug candidates deduced at the initial discovery stages, the AI algorithms can take the method and reaction data from previous studies and offer the best potential synthetic route

and reaction conditions for the drug candidates (based on the groups chosen). Everything from the types and concentration of the reagents to the environmental conditions, reaction time, and the type of catalysts (if required) can be deduced, offering a more streamlined synthetic stage once the potential candidates have been chosen. Obviously, algorithms are not

always 100% correct, but AI offers an excellent starting point at the synthetic stage to work with and any tweaks can then be performed by the scientists. At this stage, AI can save a lot of time in deducing the synthetic pathways and can even aid in the scaling up of the synthetic process once the lab- scale reaction has been shown to produce the correct structures and efficient yields.

Why use AI over current computational methods? While current computational methods have helped scientists

to deduce a lot of molecular structures, you need to have an idea of what the drug structure is going to look like (and where it’s going to be used) if you want to deduce the properties and potential effects of that drug in a clinical setting. AI, on the other hand, can take the data from previous studies, analyze the patterns and the trends of the outcomes versus the molecular input and this can be used to design drug structures that may not have been thought about. It can also be used to take known derivatives and tweak them slightly to fit the current clinical need. Because the process is purely analytical, it also removes the human bias from the drug design process (ie, the tendency to gravitate to certain and known functional groups).

Compared to computational methods, AI offers a way to design drugs from the ground up, even without a

Pharma: Drug Discovery

starting point, and can offer insights from the discovery of functional groups to the reaction parameters, and to how they might behave in a clinical setting. Overall, the use of AI in pharmaceutical design offers much more, and while computational methods are still an important part of the process, the ability for AI to become an additional pharmaceutical scientist in the design process is the reason why there has been a growing interest in using AI to design and synthesize drug candidates.


Liam Critchley Freelance Chemistry and Nanotechnology Writer E: liam_critchley@hotmail. com

in: https://www.linkedin. com/in/liam-critchley- nanowriter/ t: nanowriter

Issue 2 • March/April 2021


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60  |  Page 61  |  Page 62  |  Page 63  |  Page 64