These days, it seems you can’t look online without seeing an article about how artificial intelligence (AI) is revolutionizing the world at an alarming pace.
One industry that will benefit from the rise of AI and machine learning is drug discovery. However, these techniques are not only applied in the laboratory when designing biochemical properties of drugs. AI can also be used in clinical trials to identify participants and ensure that results are applicable to diverse populations.
you can learn more about technology network talked with Doctor. Wang Yuanis Head of Research and Analytics at UCB and how AI is being applied at every stage of drug development, from drug design to clinical trials, with the goal of making a real difference to patients’ lives. I found
Sarah Whelan (SW): What are the main uses of AI in drug discovery, and how is AI helping innovation in this area?
Wang Yuan (YW): AI refers to the use of cognitive technologies such as algorithms, machine learning, and robotic process automation. At its core, AI enables computers and machines to mimic human cognition and encompass the functions of learning, decision-making, and action execution.
In pharmaceuticals, AI has opened up amazing possibilities, from understanding disease pathology to better designed clinical trials. For example, while an individual can sequence every amino acid in every protein encoded by her DNA, an AI model can also predict the structure of a protein from the sequence. On this basis, the stability and efficacy of antibody sequences against disease-causing proteins can be increased. AI’s ability to interpret the health of individual cells will enable us to better understand the biology and pathology of disease and discover potential drug interventions.
As a scientific community, we now have access to vast amounts of data. By utilizing patient data from electronic medical records, researchers can identify complex patterns associated with specific diseases. By leveraging AI capabilities and machine learning algorithms that analyze vast amounts of data, we can make better use of information from previous clinical trials. This learning can inform future clinical trials and identify promising solutions for the patients we treat.
SW: How is this technology being used in clinical trials, and what changes will this make for patients?
YW: Advanced AI can play a pivotal role in clinical trials by enhancing treatment scheduling, trial recruitment, and data accessibility for physicians.currently only Five% Percentage of eligible patients currently enrolled in clinical studies. AI tools will play a key role in meeting this challenge by speeding up the process of finding eligible participants, analyzing medical records, and alerting healthcare professionals and patients to clinical trial opportunities. can do.
A low proportion of eligible participants in clinical trials can also lead to a lack of diversity and potentially limit the efficacy of developmental medicines to specific subgroups. To ensure that the solutions we develop are effective for real-world people, we ensure that the trials we design reflect the patient communities we serve. need to do it. By leveraging the power of AI to identify eligible participants, optimize trial design, and leverage real-world data, researchers can overcome patient recruitment challenges, increase diversity and inclusion, You can contribute to the improvement of the entire clinical trial. The integration of AI technology in clinical trials has immense potential to advance medical research and provide better medical outcomes for patients around the world.
SW: What are the main challenges facing AI in drug design?
YW: AI offers great opportunities in drug design, but it can also pose challenges. Biological systems are very complex and our understanding of their complexity is still developing. AI models in drug design must take this complexity into account, taking into account the interplay between multiple targets, pathways and physiological responses. Incorporating such complexity into AI algorithms to accurately represent diverse biological processes remains a challenge, and at present, all that these algorithms can leverage to learn representations of these processes remains challenging. I do not have information on 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 a strong, collaborative team of dedicated researchers at the heart of our mission to drive innovation.
SW: What do you consider to be the most promising or exciting aspects?
YW: Harnessing the power of AI has the potential to move toward a more precise approach to drug design and discovery, which could also lead to more personalized drug development.
Understanding the complexity of disease will enable us to design optimal molecules for treatment. However, this process is time consuming due to the sheer volume of data and molecules to analyze. We are working closely with Microsoft to accelerate and enhance our drug discovery and development capabilities.
The partnership will combine the strength of Microsoft’s computing services with UCB’s expertise in developing meaningful patient solutions that automate the creation of extensive knowledge graphs. This ambitious partnership aims to establish a comprehensive, 360-degree, data-enabled view of patient populations to enable faster discovery and development of medicines for individuals with serious illnesses. This collaboration highlights the potential for AI technologies to work synergistically with scientists and data experts to uncover new correlations and patterns that are important for driving innovation.
The use of AI has the potential to bring tangible value to patients as it facilitates efficient analysis of genetic data, disease pathways and gene sequences. This will enable researchers and healthcare providers to pinpoint the unique needs of individual patients, paving the way for highly individualized and targeted treatments. Harnessing the power of AI in drug discovery efforts will accelerate drug discovery and develop more personalized approaches to improve patient outcomes and transform the landscape of treatment for serious diseases. It has great potential.top of form bottom of form
SW: Are there any recent examples 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 in CT scans performed for other purposes.
Vertebral fragility fractures, the most common osteoporotic fracture, often have no noticeable symptoms and can increase the risk of hip fracture. Bonebot’s advanced predictive capabilities can now help identify previously unnoticed fractures. As a result, patients may benefit from more effective clinical interventions, potentially reducing osteoporosis-related comorbidities.
This AI-based technology utilizes images not specifically taken to assess the spine, such as chest x-rays. To maximize the potential of this project, UCB has partnered with ImageBiposy Lab to integrate BoneBot with the existing ImageBiopsy Lab ZOO MSK platform to bring the solution into clinical practice and positively impact the patient and health ecosystem. produce the impact of
SW: AI enables the exploration of vast datasets across large populations. How will this help make medicines more popular and applicable to diverse populations?
YW: AI can help remove ethnic and geographic barriers by enabling access to and understanding of massive datasets. With the help of AI, clinical trials can achieve greater diversity and inclusion.
The data collection landscape has advanced significantly in recent years, providing valuable insights into disease from both clinical and societal perspectives. A comprehensive understanding and synthesis of data and information about disease epidemiology, longitudinal studies, and real-world data can help build a global picture of the disease and identify areas of therapeutic interest.
Historically, certain populations, such as ethnic minorities and the elderly, have been underrepresented in clinical trials. AI can help solve this problem by identifying gaps in representation and suggesting strategies to ensure diverse participation. By including a wider range of people in clinical trials, researchers can gain insight into the efficacy and safety of drugs in different populations.
SW: What do you think the future holds for AI in drug discovery? What advances do you think we’ll see in the future?
YW: The future of AI in drug discovery is uncertain, as the capabilities of AI are evolving at an unprecedented rate. In addition to shortening lab-to-patient time, improving clinical trial diversity and moving healthcare in a more personalized direction, AI will provide predictive information on drug safety and toxicity. I hope that. By leveraging computational models, AI algorithms can help assess potential risks and side effects of drug candidates, helping reduce the likelihood of unintended side effects occurring during clinical trials. This improves patient safety and increases efficiency in the drug development process.
AI also has the potential to Helps optimize combination therapy, where multiple drugs are used together. By analyzing diverse datasets and patient-specific characteristics, AI algorithms can predict the synergistic effects of various drug combinations and identify optimal dosing regimens. This may lead to the development of more effective therapeutic strategies, especially in complex diseases such as cancer.
Dr. Yuan Wang was talking with Dr. Sarah Whelan, science writer at Technology Networks.
