search.noResults

search.searching

saml.title
dataCollection.invalidEmail
note.createNoteMessage

search.noResults

search.searching

orderForm.title

orderForm.productCode
orderForm.description
orderForm.quantity
orderForm.itemPrice
orderForm.price
orderForm.totalPrice
orderForm.deliveryDetails.billingAddress
orderForm.deliveryDetails.deliveryAddress
orderForm.noItems
Pharma: Drug Discovery


www.chemicalsknowledgehub.com The growing interest in using AI for drug design By Liam Critchley


Artificial Intelligence (AI) is growing in many sectors. While a lot of AI use has been documented around Industry 4.0 and big data, there is an increasing interest in using AI in the chemical sciences. One of the key areas where this is manifesting is in the design and synthesis of new drugs in the pharmaceutical industry.


M


any people talk about artificial intelligence (AI) these days. A lot of these discussions


centre around advanced computing technologies, smart technology, industry 4.0 and the Internet of Things (IoT). While some other discussions focus on the use of AI in manufacturing lines, the scope of AI goes well beyond this into many of the hard and applied sciences. Across the chemical and pharmaceutical sciences is the potential to not only revolutionize the manufacturing side of drugs (and other chemicals) but also the design of drugs.


The past couple of decades has seen a big rise in computational and theoretical methods to predict chemical reactions, how complex materials may look structurally at the molecular level, and how different chemical structures/materials will behave (both normally and in specific scenarios). This has been the rise of computational chemistry and biology, and it has been revolutionary and time-saving in many scientific areas as it reduces the need for a ‘trial and error’ approach in lieu of a more targeted approach using the best theoretically deduced options. The growth in computational methods has been particularly useful for the pharmaceutical sector, as it has enabled some of the more suitable drug candidates to be screened and chosen (using known knowledge of different chemical groups and what they will target/do therapeutically). It has also enabled researchers to gain insights into how those drugs may behave within some of the scenarios they are likely to be used in (before the physical


28


One of the key areas where the growing interest in applying AI in the chemical sciences is in the design and synthesis of new drugs in the pharmaceutical industry.


experiments/trials are performed). There is now the drive to go further and make these computational approaches more accurate and efficient.


Discovering the best chemical groups for drugs A drug’s functionality and ability to deliver a therapeutic load are dependent on the functional groups within the chemical. While pharmaceutical scientists know a lot about which types of functional groups are likely to behave in a certain way, there are so many potential options that it can take a long time to choose the best functional group for the drug. AI has become a tool for speeding up this process. The initial stages of drug discovery — where the targets of interest have been chosen and functional groups are being analyzed to be compatible with site of interest — is being bolstered by AI. In these drug design stages, functional groups are chosen as a possible option for the drug based around


The past couple of decades has seen a big rise in computational and theoretical methods to predict chemical reactions, how complex materials may look structurally at the molecular level, and how different chemical structures/materials will behave


groups could bring to the drug, as well as the absorption, distribution, metabolism, and excretion (ADME) profiles of the end drug. There are a lot of different parameter sets that need to be balanced and there is a lot of literature out there that provides this kind of information for the different functional groups. However, getting a human to collate and analyze all the information that is available is an almost impossible task, so potential solutions can sometimes be missed.


their potential potency, selectivity and ability to bind to the target of interest.


Other considerations that need to be taken into account are the potential toxicity that the functional


This is where AI really offers an advantage over other computational methods, as the data from various trials and studies can be inputted, and the AI algorithms (often artificial neural networks) can spot trends and synergistic properties that a human or a conventional computational approach could not. So, while trained scientists have a good knowledge of a lot of ways to create drugs to function in a certain way, AI can become a tool for scientists to utilize that could


March/April 2021 • Issue 2


(Photo © iStock / LeoWolfert)


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