Applying AI Across All Stages of Drug Development
Complete the form below to unlock access to ALL audio articles.
You seemingly can’t look anywhere online recently without seeing stories about how artificial intelligence (AI) is revolutionizing the world as we know it at an alarming pace.
One industry that stands to benefit from the rise of AI and machine learning is drug discovery. However, these techniques are not applied only in the lab when designing a drug’s biochemical properties – AI can also be harnessed in clinical trials to identify participants and ensure that results can be applied to a diverse range of populations.
To learn more, Technology Networks spoke with Dr. Yuan Wang, head of research analytics at UCB, to discover how AI is being applied through all stages of drug development, from drug design to clinical trials, with the goal of making a real difference to patients’ lives.
Sarah Whelan (SW): What are the main applications of AI in drug discovery, and how is it aiding innovation in this space?
Yuan Wang (YW): AI refers to the utilization of cognitive technologies such as algorithms, machine learning and robotic process automation. At its core, AI enables computers and machines to mimic human cognition, encompassing learning, decision-making and action-taking capabilities.
In the pharmaceutical field, AI has opened remarkable possibilities from understanding disease pathology to better-designed clinical trials. For instance, we can sequence every single amino acid within every protein that is coded by an individual’s DNA, while predicting protein structures from sequences is also enabled with AI models. Informed by this, we can enhance the stability and effectiveness of antibody sequences against disease-causing proteins. AI's ability to interpret the health of individual cells empowers us to deepen our understanding of disease biology and pathology, as well as discover potential drug interventions.
As a scientific community, we now have access to huge amounts of data. By harnessing patient data from electronic health records, researchers can identify intricate patterns linked to specific diseases. Utilizing AI capabilities for analyzing huge volumes of data and machine learning algorithms, we can better utilize the information that we have from previous clinical trials. This learning can inform future trials and identify promising solutions for the patients we serve.
SW: How is this technology being utilized for clinical trials, and how does this translate into making a difference for patients?
YW: Advanced AI can play a pivotal role in clinical trials by enhancing treatment schedules, trial recruitment and data accessibility for physicians. Currently, only 5% of eligible patients currently participate in clinical research. AI tools can help play a significant role in addressing this challenge by speeding up the process of finding eligible participants, analyzing medical records and alerting healthcare professionals and patients about clinical trial opportunities.
The low percentage of eligible participants in clinical trials can also lead to a lack of diversity and potential limitations in the effectiveness of developed medications for specific subgroups. To ensure that the solution we develop will be effective in real-world populations, we must ensure that the trials we design reflect the communities of patients that we serve. By leveraging AI's capabilities that can identify eligible participants, optimize trial design and utilize real-world data, researchers can overcome challenges associated with patient recruitment, enhance diversity and inclusivity and overall help improve a clinical trial. The integration of AI technology in clinical trials holds immense potential for advancing medical research and delivering better healthcare outcomes for patients worldwide.
SW: What are the main challenges facing AI in drug design?
YW: While AI offers significant opportunities in drug design, it can also bring challenges. Biological systems are highly complex, and our understanding of their intricacies is still evolving. AI models in drug design need to account for this complexity, considering the interactions between multiple targets, pathways and physiological responses. Incorporating such complexity into AI algorithms and accurately representing the diverse biological processes remains challenging and we do not currently have all the information these algorithms can leverage to learn the representations of these processes. For this reason, AI should be used to inform researchers during the drug discovery process rather than replace them. At UCB, we remain committed to putting strong, collaborative teams of dedicated researchers at the center of our mission to drive forward innovation.
SW: What do you think are the most promising or exciting aspects?
YW: By harnessing the power of AI we have the potential to shift to a more precise approach to drug design and discovery which can also lead to more personalized medicines.
Understanding the intricacies of diseases enables us to design the most suitable molecules for treatment. However, this process is time-intensive due to the vast amount of data and molecules to analyze. To expedite and enhance our drug discovery and development capabilities, we have partnered closely with Microsoft.
This collaboration will combine the strength of Microsoft's computational services, with UCB’s expertise in the field of developing meaningful patient solutions to automate the creation of extensive knowledge graphs. This ambitious partnership seeks to establish a comprehensive 360° data-enabled view of patient populations, enabling us to discover and develop medicines faster for individuals with severe diseases. This collaboration highlights the potential for AI technology to work synergistically with scientists and data specialists, uncovering new correlations and patterns that are crucial for driving innovation.
The utilization of AI can bring undeniable value to patients as it facilitates efficient analysis of genetic data, disease pathways and gene sequences. This empowers researchers and healthcare providers to identify precisely the unique needs of individual patients, paving the way for highly personalized and targeted treatments. Harnessing the power of AI in our drug discovery efforts has exciting potential for improving patient outcomes and transforming the landscape of severe disease treatment by speeding drug discovery and developing a more personalized approach.Top of FormBottom of Form
SW: Do you have any recent case studies or success stories that you would like to highlight?
YW: At the forefront of our approach to improving patient outcomes, we developed Bonebot, an AI-based fracture identification technology that opportunistically screens for vertebral fractures on CT scans being performed for other purposes.
Vertebral fragility fractures, the most prevalent osteoporotic fractures, often lack noticeable symptoms and can elevate the risk of hip fractures. With Bonebot's advanced predictive capabilities, we can now help identify fractures that may have otherwise gone unnoticed. As a result, patients may benefit from more effective clinical intervention, potentially reducing the associated co-morbidities linked to osteoporosis.
This AI-based technology utilizes images that were not specifically taken to assess the spine, such as chest X-rays. To maximize this project’s potential, UCB has partnered with ImageBiposy Lab, which will integrate BoneBot with its existing ImageBiopsy Lab ZOO MSK platform to bring the solution to clinical practice and create a positive impact for patients and the health ecosystem.
SW: AI allows for the interrogation of vast datasets across large populations. How can this help us to make drugs more generalizable and applicable to diverse populations?
YW: AI can help to eliminate barriers imposed by ethnicity or geography by granting access to and understanding vast datasets. By leveraging AI, clinical trials can achieve greater diversity and inclusivity.
The landscape of data collection has undergone significant advancements in recent years, offering valuable insights into diseases from both clinical and social perspectives. By comprehensively understanding and integrating data and information regarding disease epidemiology, long-term studies and real-world data, we can construct a holistic view of the disease and identify targeted areas for treatment.
Historically, certain populations, such as ethnic minorities or elderly individuals, have been underrepresented in clinical trials. AI can help address this issue by identifying gaps in representation and suggesting strategies to ensure diverse participation. By including a broader range of individuals in clinical trials, researchers can gain insights into the drug’s effectiveness and safety in different populations.
SW: What do you think the future holds for AI in the drug discovery space? What advances do you think will be made going forward?
YW: With AI’s capabilities evolving at an unprecedented rate there is no telling where the future of AI in the drug discovery space could lead. As well as shortening the time from the lab to the patient, improving clinical trial diversity and moving medicine in a more personalized direction, we hope to see AI informing drug safety and toxicity predictions. By leveraging computational models, AI algorithms can help assess the potential risks and side effects of drug candidates, helping to reduce the likelihood of unexpected adverse reactions during clinical trials. This can enhance patient safety and increase the efficiency of the drug development process.
AI also has the potential to assist in optimizing combination therapies, which involve using multiple drugs together. By analyzing diverse datasets and patient-specific characteristics, AI algorithms can predict the synergistic effects of different drug combinations and identify optimal dosage regimens. This can lead to the development of more effective treatment strategies, particularly in complex diseases like cancer.
Dr. Yuan Wang was speaking to Dr. Sarah Whelan, Science Writer for Technology Networks.