ChatGPT Meets Drug Discovery: Unlocking New Frontiers

Gen AI has the potential to transform the drug discovery field. However, these  models need to be trained with quality datasets before they can be productionized. Using an inadequately trained model in this context can result in inaccurate predictions, unviable outcomes, and significant project expenses. In this session, Dr. Jha discusses the importance of data quality in training Gen AI models and its role in enhancing the robustness and reliability of target prediction in the pharmaceutical industry.

In this keynote session, Dr Ma'ayan delves into the transformative impact of generative AI and LLMs in the analysis of gene sets. He discusses how these innovations are enhancing gene annotation prediction, ultimately leading to the discovery of novel therapeutic targets across a broad spectrum of biomedical research applications.

Our keynote speaker, John Wilbanks is a distinguished authority in the field of data governance, backed by a wealth of experience and a forward-thinking vision regarding the future of data and AI. In his session, he sheds light on the hurdles and prospects of effectively implementing data governance strategies that unlock the potential of generative AI.

GenAI is as promising as it is challenging. To stay on top, scientists will have to combine data, infrastructure, models, and subject-matter expertise into a formidable base. While Gen AI is incredibly exciting, what does it really take to get these models into production? How can we keep trusting the results? How does one select the right problem? In this session, Swetabh gives us a breakdown of the tools needed to set your GenAI initiatives up for success.

The panel elucidates on the rise of generative models in drug discovery.Topics covered:

• The applications of these models in different drug discovery domains - genomics, structural biology, and protein design.
• The central role 'data quality' plays in the successful use of these models.
• How the panelists are incorporating (or are planning to incorporate) generative models into their R&D data strategy.
• And the challenges they've faced while applying these models in production.
  

The fireside chat focuses on data management strategy in early stage R&D. Effective data management plays a pivotal role in the pharmaceutical industry. In this conversation, our panelists will cover:

• Effectively managing multi-modal, multi-source data, including CROs, patient data, and in-house data.
• The costs incurred without the right data infrastructure.
• And addressing data downtime, curation costs, and cloud solutions.