Breakfast

Talk Title: “Challenges in Contemporary Drug Discovery”

Abstract: Drug discovery is a complicated semi-empirical process that fails ~90% of the time.  The reasons for this high failure rate are multiple and include the presence of competing targets within a cell or organism; the existence of multiple conformations of any single target protein; significant inconsistencies in binding or kinetic constants in cell-free vs. cellular systems; and failure to consider the effect of a drug on its target(s) within the complex cellular protein-protein interaction network and its consequences for phenotype.  In this presentation, I will discuss the evolving landscape of computational approaches used to identify disease determinants and drug targets, including network- and AI-based approaches and quantum-inspired strategies; experimental approaches to characterizing the dynamic interactions of drugs and their targets in real time in single cells; and efficient single-cell strategies for assessing combinations of drugs.  These principles will be illustrated with examples from specific diseases. The strategies presented will ultimately contribute to and guide the ongoing evolution of precision medicine.

Joseph Loscalzo, MD, PhD, Samuel A. Levine Professor of Medicine, Hersey Distinguished Professor of the Theory and Practice of Medicine, Harvard Medical School, Physician-in-Chief Emeritus, Brigham and Women’s Hospital

Bio:  Joseph Loscalzo is the Samuel A. Levine Professor of Medicine and the Hersey Distinguished Professor of the Theory and Practice of Medicine at Harvard Medical School, and Physician-in-Chief Emeritus at Brigham and Women’s Hospital.  He is a summa cum laude graduate of the University of Pennsylvania, where he also obtained his M.D. and Ph.D. in biochemistry.  He has published over 1,200 scientific articles, written or edited 54 books, and holds 33 patents.  His research focus has been in the areas of vascular and redox biology, systems biology, and network medicine, with continuous funding from the NIH for over 35 years.  He is a member of the American Society of Clinical Investigation, the Association of American Physicians, the National Academy of Medicine, and the American Academy of Arts and Sciences.

Keynote

Talk Title: “Generative AI Applications in Early Drug Discovery”

Abstract: Research in the early phases of drug discovery is fueled by ever-increasing data and data types that are amenable to machine learning (ML). From disease understanding and target identification to assay development and therapeutics design, AI models are making inroads to increasing the efficiency and creativity of research. Generative AI goes beyond classical ML in the ability to synthesize information from large-scale patterns in data. Case studies in genomics, genetics, text, chemistry, protein structure, and imaging are provided to illustrate the transformative impact of generative AI on the future of making medicines.

Jeremy Jenkins, PhD, US Head Discovery Sciences, Novartis

Bio: Jeremy Jenkins is the US Head of Discovery Sciences in Novartis Biomedical Research. He joined Novartis as a postdoc in 2003, following a postdoc at Harvard Medical School and a PhD in Molecular Genetics from The Ohio State University. He received the 2011 Corwin Hansch Award for contributions to the field of QSAR, and the 2017 Novartis Leading Scientist VIVA award for helping to develop the field of in silico chemical biology. His global research teams at Novartis focus on early drug discovery projects and enabling technologies for target ID and lead discovery.

Talk Title: “Protein language models: their power, limitations and future directions”

Abstract: Protein language models are one of the most exciting recent advances in modeling protein sequences. Among other applications, they have proven to be powerful in predicting structures, interactions and functions, and in assessing the impact of amino acid mutations, all central tasks in identifying disease targets. I will discuss how my group has is using protein language models in a variety of settings, and how we are “stress testing” their capabilities in a range of applications. I will conclude by discussing promising avenues for future work.
 

Mona Singh, PhD, Wang Family Professor in Computer Science, Princeton University

Bio: Mona Singh is the Wang Family Professor in Computer Science at Princeton University, where she is jointly appointed in the Computer Science department and the Lewis-Sigler Institute for Integrative Genomics. Mona received the Presidential Early Career Award for Scientists and Engineers (PECASE). She is a Fellow of the International Society for Computational Biology and a Fellow of the Association for Computing Machinery. She was Chair of the NIH Modeling and Analysis of Biological Systems Study Section (2012-2014), and was a council member of the CRA’s Computing Community Consortium (2021-2024). She is currently Editor-In-Chief of the Journal of Computational Biology.

Keynote

Talk Title: “AI@NIH: Drug Discovery, Clinical Healthcare, and Multimodal AI”

Abstract: The National Institutes of Health (NIH), a part of the U.S. Department of Health and Human Services, is the nation’s medical research agency — making important discoveries that improve health and save lives.  Data Science and artificial intelligence (AI) is an NIH-wide priority initiative to take better advantage of the exponential growth of biomedical research datasets, which is an area of critical importance to biomedical research. NIH engages with partners both within NIH and in academia, industry, non-profits, or other government Agencies, to coordinate access to and analysis of many different data types (Big Data) that make up this revolution in biological information. The Office of Data Science Strategy, the Center for Information Technology, the National Library of Medicine, and the other NIH Institutes and Centers regularly collaborate to enable research that leverages AI. In this presentation, existing NIH strategy in research data platforms and AI will be presented along with an overview of ongoing projects in AI and Data Science.

Sean Mooney, PhD, Director, Center for Information Technology, NIH

Bio: Dr. Sean Mooney, Ph.D., serves as the Director of CIT and the NIH Associate Director for Information Technology, Cyberinfrastructure and Cybersecurity (AD ITCC).  As the Director of CIT, he is responsible for providing leadership, vision, and direction for the organization. This includes overseeing an approximately $400 million portfolio that includes a world-renowned supercomputer that allows researchers to conduct large-scale data analyses; a state-of-the-art network that enables research across NIH and around the world; cloud-based services that give researchers a cost-effective way to access datasets and advanced computational tools and services; and the latest collaboration tools to promote flexibility and productivity.  As the Associate Director for ITCC, Dr. Mooney oversees the NIH Office of the Chief Information Officer, which is responsible for NIH enterprise IT strategy, policy, architecture and oversight of a $1.9 billion IT budget.

“Drug discovery bottlenecks and how AI can help”

Panelists:

Etai Jacob, Senior Director, Head of Data Science and AI, Early Oncology, AstraZeneca PLC

Ashwini Ghogare, Head of AI and Automation in Drug Discovery, MilliporeSigma

Juli Klemm, Program Director, Center for Strategic Scientific Initiatives, National Cancer Institute (NCI)

Rob Moccia, Senior Director, Machine Learning Research Lead, Pfizer

Pat Walters, Chief Data Officer, Relay Therapeutics

Networking Lunch

Panel discussion

“New generative AI approaches for drug discovery and need for open innovation”

Panelists: 

Kaitlin McCardle, Senior Editor, Nature Computational Science

Vlad Ivanov, Director, Group Lead, AI/ML Quantitative Data Sciences, Pfizer

Feixiong Cheng, PhD, Inaugural Director, Cleveland Clinic Genome Center

Jim Collins, Termeer Professor of Medical Engineering & Science, Professor, Department of Biological Engineering, Massachusetts Institute of Technology; Wyss Institute, Harvard University; Broad Institute of MIT and Harvard

Breakout sessions

“Prioritization of Open Innovation Tasks”

• Pat Walters, PhD, Chief Data Officer, Relay Therapeutic
• Wendy Cornell, PhD, Manager and Strategy Lead for Drug Discovery Technologies Ecosystem and Partnerships, IBM

Breakout: Multi-Modal Fusion
Room Location: TBD

• Alex Shalek, PhD, Director, Institute for Medical Engineering & Science; Director, Health Innovation Hub; J.W. Kieckhefer Professor, IMES, Chemistry, MIT
• James Kozloski, PhD, Principal Research Scientist; Sr. Manager, Biomedical AI – Healthcare & Life Science Research, IBM
  

Breakout: Model Architecture
Room Location: TBD

• Ching-Huei Tsou, PhD, Senior Research Scientist and Manager, Biomedical Foundation Model / NLP | Accelerated Discovery | HCLS, IBM
  
• Chengxi Zang, Weill Cornell Medicine
  

Breakout: Challenges/Competitions
Room Location: TBD

• Pablo Meyer, PhD, Senior Research Scientist, Manager, Biological Analytics and Modeling, Center for Computational Health, IBM
• Demetri Moustakas, PhD, Treeline Biosciences

Workstream Readout & Next Steps

Coffee break

*To participate in the demo, please bring a laptop.

Location: CDS 1101

Networking Reception