EMBARGOED UNTIL 9:00AM EST
Baltimore, Maryland (June 10, 2025) — The Lieber Institute for Brain Development (LIBD) is revolutionizing its drug discovery efforts by expanding its technology capabilities on Amazon Web Services (AWS); migrating its IT infrastructure to fully utilize AWS gen AI and compute services to advance research. The Lieber Institute, home to the world’s largest collection of donated brains used for mental illness research, and a recipient of the 2024 Amazon Web Services (AWS) IMAGINE Grant, plans to develop a new tool called GRAPE that combines generative and predictive AI to find new, more effective treatments for brain disorders such as schizophrenia.
“The Lieber Institute, now powered by AWS, will work faster and more nimbly to bring hope and new treatments to patients and their families,” says Lieber Institute Director and CEO Dr. Daniel Weinberger, M.D. “This is the future of science, and we’re excited to be part of it.”
Building on AWS means the Institute will store its massive collection of genomic and other data in the cloud, and its scientists will benefit from the expansive computing power and artificial intelligence capabilities. AWS offers. Cloud storage will make it easier for Lieber Institute scientists to collaborate and easily share data with scientists anywhere in the world, enhancing their own research and that of their partners.
The human genome contains three billion letters, the human brain contains 170 billion cells, and there are up to 10,000 genes expressed in each cell —a huge amount of data to analyze, requiring leading-edge tools and computing power. Lieber Institute scientists are collaborating with AWS solution architects to create new, custom AI applications to make the power of deep learning available to all the Institute’s scientists, regardless of their fluency in the complex coding languages that make AI possible.
“AWS's AI capabilities give the Institute the speed, security, and scale the organization needs to drive research innovation that will radically change outcomes for people affected by brain health issues by uncovering new treatments that will radically change outcomes for people affected by brain health issues,” said Jeff Kratz, Vice President of Nonprofit and Public Sector Industries at AWS.
At the Lieber Institute, on the Johns Hopkins medical campus in Baltimore, researchers are employing AI to screen chemicals as potential new drugs, create AI agents to act as additional scientists, search for new drug targets to treat brain disorders such as schizophrenia, bipolar disorder, suicide, autism and age-related diseases; and even design new compounds to cure and prevent illness.
“Biomedical research has entered a new era, driven by the explosion of data—especially from single-cell technologies—which now provide the foundation for modern AI applications,” says Dr. Shizhong Han, Ph.D., a Lead Investigator who directs the Institute’s AI efforts. “By harnessing these rich datasets, our researchers are using AI to gain deeper insights into genome function, pinpoint causal genes linked to brain disorders, and design novel therapeutic molecules.”
The Institute’s most precious resource is its data, including the information gathered from more than 5,000 donated human brains, a portion from people who struggled with mental illnesses and neuropsychiatric disorders.
GRAPE Success Story
Last year, the Lieber Institute was named a winner in the AWS IMAGINE Grant Pathfinder – Generative AI category which recognizes highly innovative, mission-critical projects that leverage generation AI. The Lieber Institute will receive up to $200,000 in unrestricted funding, up to $100,000 in AWS Promotional Credits, and implementation support from the AWS Generative AI Innovation Center.
Lieber Institute scientists led by Dr. Han, along with Staff Scientists Michael Nagle, Ph.D., and Jiyun Zhou, Ph.D., are using the funding to develop a new generative AI approach to create new drugs to treat mental illness and evaluate those drugs for effectiveness. Existing drugs for schizophrenia target proteins associated with just a handful of risk genes. Schizophrenia involves hundreds of risk genes, so the effectiveness of current drugs is limited. The Lieber Institute aims to treat the root cause of the disease by mitigating the combined effects of these numerous risk genes.
The new AI tool, called Generative Reinforcement Alignment of Predicted Expression, or GRAPE, will design new molecular structures for potential drugs based on the known gene expression patterns of conditions like schizophrenia. GRAPE is unique in that it will use generative AI to design new drugs—an approach proven in previous research—combined with predictive AI to evaluate the effectiveness of the new drugs.
“AI is making it possible to unravel complex patterns that underly many medical conditions, and to design new tailored treatments based on these patterns. However, it requires incredible amounts of computing power,” says Dr. Nagle. “To make the most of AI, we need powerful supercomputing resources, and we also need new techniques that enable us to stretch these resources as far as possible. GRAPE represents an opportunity for us to maximize our impact for as many patients or as many conditions as possible by applying the latest cutting-edge techniques.”
Cell Painting Success Story
Cell painting is an imaging technique in which scientists use fluorescent dyes to visualize the spatial organization of cells and their components. At the Lieber Institute, Staff Scientist Frank Piscotta, Ph.D., uses the technique to identify new drug targets for schizophrenia.
Cell painting generates very large datasets, and analysis that once took almost a week is now significantly faster.
“With AWS, we can process a dataset in approximately half an hour,” he says.
Scientists also now can run more multiple analyses at once, Dr. Piscotta adds. Researchers can input data once and complete several tests simultaneously, effectively providing the equivalent of extra hands in the lab working at the same time.
LIBD scientists are also collaborating with AWS experts to develop user-friendly applications to enable other researchers at the Institute with less coding experience to incorporate cell painting into their own work. Dr. Piscotta is also working with AWS to facilitate integration of cutting-edge AI tools into the Institute’s existing workflows.
About the Lieber Institute for Brain Development (LIBD)
The mission of the Lieber Institute for Brain Development and the Maltz Research Laboratories is to translate the understanding of basic genetic and molecular mechanisms of schizophrenia and related developmental brain disorders into clinical advances that change the lives of affected individuals. LIBD is an independent, not-for-profit 501(c)(3) organization and a Maryland tax-exempt medical research institute affiliated with the Johns Hopkins University School of Medicine. The Lieber Institute’s brain repository of more than 5,000 human brains is the largest collection of postmortem brains for the study of neuropsychiatric disorders worldwide.
###