There is very little that is efficient in drug discovery and development. Approximately 90% of medications that reach commercialisation fail. Each one costs more than $1 billion and takes ten years to develop.
However, technical developments in data collection are advancing artificial intelligence in drug discovery, which might open the door to discovering treatments for disorders that have eluded medical researchers for millennia.
Drug discovery procedures are often drawn-out and laborious. Academic or industrial scientists create molecules. They search for ‘targets’ (such as proteins), where the molecule can go in the body to deliver treatment.
Researchers must ensure that the molecule doesn’t mistake a healthy protein for a target. Otherwise, a drug floating about in the body may bind to and destroy a healthy cell, causing a poisonous effect. Once a target is obtained, it is removed from the body and tested against molecules in the laboratory to see what sticks.
However, when clinical trials move forward, many of these medications fail due to unanticipated toxicity in the body or the drug itself not performing as well in people as it did in the lab. This is why most investments fail.
Fortunately, artificial intelligence (AI) can improve the efficiency of drug discovery.
Platforms for drug discovery can more accurately forecast the effects of drugs early on by utilising data. AI links molecules with targets and models how they will behave within the body, increasing the likelihood that they will survive clinical trials and reduce patient toxicity rates.
Although the impact of AI on conventional drug discovery is still in its infancy, when AI-enabled capabilities are added to a traditional process, they can significantly speed up or otherwise improve individual steps and lower the costs of conducting expensive experiments. AI algorithms can alter the majority of discovery jobs (such as the design and testing of molecules) so that physical trials are only necessary to confirm findings.
Pharma companies are partnering with AI drug discovery platforms, with Amgen and Generate Biomedicines announcing a deal worth up to £1.9 billion in 2022.
Pharma businesses need to prepare for a future in which AI is frequently utilised in drug research, given the revolutionary potential of AI. The applications are many, and pharma businesses must decide where and how AI can best contribute.
New players are ramping up quickly and providing considerable value. In practice, this entails taking the time necessary to comprehend the full impact that AI is having on R&D. This includes separating hype from real accomplishment and realising the distinction between standalone software solutions and end-to-end AI-enabled drug discovery.
There are five elements to an AI-first approach in drug discovery.
Companies must create an AI roadmap that outlines specific, high-value use cases compatible with certain discovery initiatives. Focus and prioritisation are crucial.
Businesses should choose a limited number of use cases that are dispersed throughout the various research stages. Otherwise, AI will be viewed as a sideline and not directly related to the company’s R&D strategy or financial objectives.
Prior to creating a complete tool or platform, concentrate on developing a proof-of-concept algorithm: the bare minimum analysis that verifies your capacity to draw insightful conclusions from your data in a particular scientific environment. If the insights prove worthwhile, you can spend money industrialising the tool and improve the user interface.
To be the preferred partner for big AI players, pharma companies must adopt new behaviours and ways of working. Partnerships are a powerful strategy for accelerating AI discovery and building a true value proposition.
Companies should consider how they share data, what their culture looks like in the context of AI, and how quickly they can adapt their business model to new technology. Although those things may not seem critical to the business, they will be for potential AI partners.
Data scientists and engineers are a unique breed. They do not always fit into companies and cultures that are primarily focused on medicine.
But pharmaceutical businesses need more than just expertise in data science and software. Senior decision-makers will probably need to be trained on how AI-generated recommendations are made if only to stop suggestions from being revalidated using conventional methods. To interpret and adequately test the results of the algorithms, medical scientists must be knowledgeable about the analytical methodologies required but not necessarily fluent in them.
Data is pivotal for successful AI and machine learning deployments. Large-scale datasets help to build models for machine learning that can evaluate whether molecules have investable potential.
Researchers can quantify the strength of molecules in binding to a protein. Specific drug interactions and combinations do not react favourably and must be avoided by patients. Vast data volumes help to identify the positive and negative combinations quickly.
AI represents a new era in drug discovery. Companies will need to couple a clear vision with a healthy amount of ambition to be successful.
Choose an area to apply AI and be specific about the improvements you want to see. Decide whether to alter the discovery program using an AI-first model or to utilise AI for optimising the present discovery process.
Further, it can be challenging to scale AI. Teams frequently adhere to well-established procedures and feel at ease using instruments with a long history of success. Businesses need to demonstrate their commitment to AI by focusing on complete processes and thoroughly reevaluating current operating methods.
It’s best to include the entire organisation in the AI journey. In order to overcome hesitancy, management should emphasise the transformational vision, share value proofs and lessons from inside teams, and gradually develop a wave of enthusiasm.
AI is here for good, and it is for us to harness its power. What can be better than using AI to cure previously unsolvable diseases?
Disclaimer: The information provided in this article is solely the author’s opinion and not investment advice – it is provided for educational purposes only. By using this, you agree that the information does not constitute any investment or financial instructions. Do conduct your own research and reach out to financial advisors before making any investment decisions.
The author of this text, Jean Chalopin, is a global business leader with a background encompassing banking, biotech, and entertainment. Mr. Chalopin is Chairman of Deltec International Group, www.deltec.io.
The co-author of this text, Robin Trehan, has a bachelor’s degree in economics, a master’s in international business and finance, and an MBA in electronic business. Mr. Trehan is a Senior VP at Deltec International Group, www.deltec.io.
The views, thoughts, and opinions expressed in this text are solely the views of the authors, and do not necessarily reflect those of Deltec International Group, its subsidiaries, and/or its employees.
Thank you for your interest in the Deltec Initiatives Foundation. You can contact us using the form below.
Before sending a message to us, kindly note that we do not accept requests for funding. Thank you for your understanding.