In the ever-evolving field of medical science, artificial intelligence (AI) has emerged as a revolutionary tool, particularly in drug discovery. As a newer alternative to the time-consuming nature of traditional candidate screening and drug discovery, AI-designed drugs have started to make their mark, promising quick and efficient results. This is evident in the estimated market value for AI in drug discovery, which was US$0.6 billion in 2022 and is expected to grow to US$4.0 billion by 2027, at a compound annual growth rate (CAGR) of 45.7% between these years. Although this staggering growth rate is related to the rise in adoption of cloud-based digital technology, as well as the need for more efficient drug discovery approaches, traditional methods continue to hold significant value in the pharmaceutical world. In this article from Vial CRO (Contract Research Organization, we take a deeper look into comparing AI-based drug design with the traditional approach to drug discovery, as well as the pros and cons of each.
Understanding AI-Designed Drugs in Early Drug Discovery
AI-designed drugs are the products of advanced machine learning (ML) algorithms, which have the sophisticated capability of predicting the effectiveness of a compound in treating a specific medical condition. When leveraged for large libraries of potential drug compounds, these algorithms have the potential to drastically reduce the lengthy and costly process of manual drug candidate testing. Therefore, this application provides a revolutionary approach to reshaping the current gaps in the field of drug discovery, offering several major advantages.
Advantages
The first and foremost advantage of AI in drug discovery is its ability to significantly speed up the screening process for researchers. AI can scan and analyze vast amounts of data much faster than manual assessment by humans, making it possible to identify potential drug candidates in a fraction of the time taken by traditional methods. This acceleration of the drug discovery process could potentially save countless lives by bringing effective treatments to market more quickly.
As an example, Exscientia’s AI-designed drug for obsessive compulsive disorder, created in collaboration with the Japanese firm Sumitomo Dainippon Pharma, reached clinical trial testing in just 12 months, as opposed to the average period of 4 to 5 years with traditional methods. As a result of this shorter timeline, AI-designed drugs also offer the potential to reduce the cost of drug discovery because the traditional process of drug discovery typically involves expensive and time-consuming clinical trials to evaluate promising compounds. In contrast, AI has the potential to eliminate the need for some of these early trials by predicting the behavior of a drug based on existing data.
Disadvantages
However, as promising as AI-designed drugs may seem, they come with their own set of drawbacks, particularly the following three:
- Lack of transparency: AI algorithms, particularly those using advanced techniques like deep learning, often suffer from the “black box” problem – it’s difficult to understand why they make the decisions they make. This lack of transparency can be a barrier to acceptance in the medical community, where understanding the rationale behind a drug choice is crucial.
- Over-reliance on data: AI systems are only as good as the data they’re trained on; therefore, if the data is flawed or biased, the AI could make incorrect predictions. Additionally, AI may overlook potentially successful drug candidates simply because they may not fit the patterns in the data it has been trained on.
- Ethical and regulatory concerns: The use of AI in drug discovery raises new ethical and regulatory concerns, such as standardizing the AI discovery process or considering how these predictions can be validated for safety and efficacy. Furthermore, with the large amount of data needed to train these algorithms, sufficient measures would be required to protect patient data privacy.
Understanding Traditional Drug Discovery
Traditional drug discovery, on the other hand, relies on a time-tested, systematic approach that involves a series of in-vitro and in-vivo experiments. These methods, though laborious and time-consuming, have a long track record of being successful in the discovery of countless life-saving drugs over the years. The main goal of this process is to identify potential drug candidates that can effectively treat diseases and improve health outcomes. The process begins with the identification of a biological target, such as a protein or a gene, that is implicated in a disease. Drug candidates that interact with this target in a beneficial way are then identified and optimized, followed by a series of preclinical tests. Promising candidates are then moved on to clinical trials involving human subjects, which ensures that drugs are safe and effective before they reach the market.
Advantages
The most significant advantage of the traditional drug discovery process lies in its rigorousness and reliability. The process is grounded in empirical evidence and thorough testing, ensuring a high degree of confidence in the results, and has yielded countless effective treatments over the years. Furthermore, the traditional drug discovery process values human expertise and intuition. That is, researchers with years of experience and in-depth knowledge of biology and chemistry play an integral role in identifying and testing potential drug candidates. Therefore, this human involvement often leads to insights that would not be possible with the purely computational approach of AI-based discovery.
Disadvantages
However, traditional drug discovery is not without its challenges.
- Lengthy process: One of the primary disadvantages of the traditional drug discovery process is the length of time it takes to bring a new drug to market. Although this process is necessary to ensure the safety and efficacy of new drugs, it is also time-consuming, often taking up to a decade or more before potentially life-saving treatments can reach patients.
- High costs: The extensive testing and trials required to ensure a drug’s safety and effectiveness can cost hundreds of millions of dollars, even at the early discovery and lead optimization stages. These high costs can pose a significant barrier to the development of new drugs, particularly for rare diseases that may not promise a high return on investment.
- Human capacity limitations: The traditional discovery process is labor-intensive and requires a high level of expertise. Human researchers, despite their in-depth knowledge of biology and chemistry, can only analyze a limited amount of data at a given time, creating bottlenecks and slowing the pace of discovery of new treatments.
Comparing AI-Designed Drugs and Traditional Drug Discovery
When comparing AI-designed drugs and traditional drug discovery, it becomes evident that each approach has its strengths and weaknesses. AI-designed drugs offer unprecedented speed and efficiency, while traditional methods provide the reliability and thoroughness that comes from empirical evidence and testing. In an ideal world, the best approach may be a hybrid one that combines the strengths of both methods. AI could be used to quickly identify promising drug candidates, which could then be thoroughly assessed using traditional methods. This combination could potentially lead to the most effective and efficient drug discovery process.
Conclusion
While AI-designed drugs represent an exciting new frontier in drug discovery, traditional methods continue to play an essential role. Each approach comes with its own set of pros and cons, and the key to the most effective and efficient drug discovery process may lie in a balanced combination of both. As technology continues to evolve and AI becomes more sophisticated, it will be interesting to see how the landscape of drug discovery will transform in the future.
Vial is a full-service CRO that also recognizes the role of technology in the future of clinical research and recently launched its AI-based drug discovery arm, Battery Bio. Battery Bio stands at the forefront of AI-driven biotech advancements, leveraging Vial CRO’s modern technology platform and advanced AI/ML algorithms. Trusted by leading sponsors, our specialized teams deliver shorter study timelines, quality affordable services, and a clinical trial experience that puts you first. Contact a Vial representative today to discover how we can help!
