In what ways can federated learning revolutionize collaborative research and development in the biopharmaceutical sector, and what are the potential hurdles to its widespread adoption?
In this InTechnology video, Camille Morhardt and Prashant Shah talk with Abhishek Pandey, Global Lead and Principal Research Scientist II at AbbVie, about the role of federated learning in facilitating collaboration among pharmaceutical companies without compromising sensitive data. They also discuss the role of OpenFL in enabling federated learning and the future of drug discovery in the context of new medical modalities.
Introduction: The Promise and Perils of AI in Healthcare
Camille Morhardt explores the promising yet intricate landscape of AI in healthcare and drug discovery. While recognizing AI’s potential to revolutionize the field, she raises pertinent concerns surrounding patient privacy, intellectual property rights, and the imperative of establishing trust in AI systems that manage sensitive health data.
The Challenges of Traditional Drug Discovery
Machine learning expert Abhishek Pandey describes the challenges inherent in traditional drug discovery, characterized by its slow pace, high costs, and frequent failures. He explains how AI and machine learning can accelerate drug discovery by leveraging the exponential growth of internet speeds and computational resources.
The Data Deluge and the Need for AI-Powered Solutions
Prashant Shah, a leader in federated learning, delves into the proliferation of diverse and complex data types in drug discovery, such as genomics and high-content imaging. He emphasizes the indispensable role of AI and computational methodologies in extracting valuable insights from this expansive and multifaceted data realm.
Federated Learning: A Privacy-Preserving Paradigm for Collaboration
Addressing the ethical dimensions of utilizing sensitive health data for AI model training, Camille underscores the importance of data privacy. Abhishek acknowledges the obstacles to data sharing presented by privacy regulations and intellectual property concerns. Prashant introduces federated learning as a transformative solution, enabling collaborative model training across disparate data sources while preserving data privacy and security.
OpenFL and the Future of Federated Learning in Drug Discovery
Prashant further introduces OpenFL, a Python library designed to facilitate the development and deployment of federated learning models. He underscores the significance of integrating federated learning with confidential computing technologies to ensure the protection of sensitive information. Abhishek highlights the potential of federated learning to foster collaboration and data sharing within the pharmaceutical industry, thereby paving the way for breakthroughs in the development of novel and innovative medicines.
Abhishek Pandey, Global Lead and Principal Research Scientist II at AbbVie
Abhishek Pandey is the Global Lead and Principal Research Scientist II at AbbVie, specializing in Machine Learning for Drug Discovery. In his role, he leads a team of machine learning scientists focused on developing advanced Machine Learning methods for Target identification and prioritization, ADMET, De Novo design of molecule, Tox, and preclinical/clinical precision medicine. His team is responsible for developing state-of-the-art machine learning algorithms for Discovery, Developmental Sciences, and the AbbVie-Calico alliance departments of AbbVie. Prior to joining AbbVie, Abhishek was a founding member of the AI team at Tempus Labs Inc now known as Tempus AI, helping transform the company in the field of precision medicine and market value. Abhishek holds a Ph.D. in Electrical and Computer Engineering from the University of Arizona and has previous experience as an Embedded systems software engineer at Toshiba Semiconductor in the mobile multimedia division.
Prashant Shah, Intel’s CTO for Federated AI products
Prashant Shah is Intel’s CTO for Federated AI products. He founded OpenFL – a federated machine learning library that enables the development of AI models across private data silos. He has spent over two decades in Health and Life Sciences driving scalable AI architectures. Outside of Intel, he is an advisor to the National Institutes of Health’s ‘All of Us‘ precision medicine research program.
Check it out. For more information, previous podcasts, and full versions, visit our homepage.
#FederatedLearning #DrugDiscovery #ConfidentialComputing
The views and opinions expressed are those of the guests and author and do not necessarily reflect the official policy or position of Intel Corporation.
—–
If you are interested in emerging threats, new technologies, or best tips and practices in cybersecurity, please follow the InTechnology podcast on your favorite podcast platforms: Apple Podcast and Spotify.
Follow our host Camille @morhardt.