Led by neurologist Xiaobo Mao, Ph.D., the Johns Hopkins Medicine team, supported by an award from the Advanced Research Projects Agency for Health, will build an artificial intelligence model to identify how shape-shifting proteins misfold and use this knowledge to support earlier disease detection and treatment 

A Johns Hopkins Medicine-led research team has received an award of up to $52.1 million over four years from the Advanced Research Projects Agency for Health (ARPA-H), part of the Department of Health and Human Services, to better understand the rules that decide what shape a protein takes — and how those rules could support the identification of earlier diagnostics and therapeutic targets when proteins fold the wrong way. The team will start this work, which will be publicly shared through open-access resources, by studying Parkinson’s disease and Ewing sarcoma, a rare cancer of bone and soft tissue in children and young adults.

Xiaobo Mao, Ph.D., a professor of neurology at the Johns Hopkins University School of Medicine, created the scientific vision for the project, serves as its principal investigator and assembled a team of 21 investigators across 12 institutions in the United States and Europe to conduct this research. The team, which is called Dynamic Ensemble-to-Rescue: Decoding and Controlling the IDR Molecular Grammar at Scale (DETR), is one of several in ARPA-H’s new BIOmolecular Grammar for protein Aggregation Modulation and Intervention (BIOGAMI) program — which is designed to help researchers detect protein misfolding and intervene at earlier stages of disease, especially for neurodegenerative conditions, such as Alzheimer’s disease and Parkinson’s disease. BIOGAMI is led by ARPA-H Program Manager Shannon Greene, Ph.D.

The goal of the DETR research is to generate three novel tools and resources for clinicians and researchers: a cerebrospinal fluid test to read the shape of alpha-synuclein (which forms the deposits that define Parkinson’s disease) and potentially identify disease years before symptoms occur; a class of molecules that binds the harmful form of a disordered protein while sparing the healthy form; and an open foundation model that lets any laboratory ask the same question of any of the thousands of disease proteins that don’t have proven drug therapies. 

This is where the research comes in for understanding how proteins, like alpha-synuclein, fold. 

“We can read a protein’s sequence in seconds, but for this class of proteins, the sequence still does not tell us which shape it will take and whether that shape will harm the patient,” says Mao. “If we can predict the shape, we can design a drug that recognizes the harmful form and leaves the healthy one alone.” 

To support these endpoints — the computational model, diagnostic test and targeted therapies — the program is organized into two technical areas over two 24-month phases. 

The first is to establish the molecular grammar of these regions: to determine the primary sequence, structural features and environmental conditions that govern how they behave and to build a foundational model of that behavior. It integrates computational and experimental work — with high-throughput laboratory platforms generating the measurements the model is trained and tested on. 

The second is to modulate these proteins to detect and control folding. 

For early detection, the goal is to identify protein misfolding, which could serve as a biomarker in diagnostic tests. For future therapies, the vision is to restore a protein’s function, or prevent the aggregation and misfolding from starting, while leaving the working form untouched.

While DETR’s focus is to study these mechanisms in Parkinson’s disease and Ewing sarcoma (a rare type of cancerous tumor), the foundational knowledge from the models is designed to support their use in studying other conditions. This could include those that BIOGAMI has focused on, including neurodegenerative conditions like Alzheimer’s disease and chronic conditions, including cancer, heart disease and type 2 diabetes, as well as infections that may be dormant but that can appear years later.

The Xiaobo Mao Laboratory in the Institute for Cell Engineering studies protein aggregation from end to end: why misfolded proteins form, how they move from one neuron to the next, how they injure cells — and how that biology can be converted into a biomarker, a drug target and a therapy. Its central question is how misfolded alpha-synuclein spreads and clumps into toxic forms. The lab also recently identified molecular underpinnings that may help explain associations between air pollution and increased risks for Lewy body dementia. 

Eight other laboratories from Johns Hopkins Medicine, which serves as the prime institution guiding this research, are also part of DETR. Additional institutions include Columbia University; the Gladstone Institutes; the Massachusetts Institute of Technology; the University of Michigan, Ann Arbor; Emory University; the University of Copenhagen; the Institute for Research in Biomedicine in Barcelona; the University of Texas at Austin; Arizona State University; the University of Texas at Dallas and the University of Washington with the Seattle Institute for Biomedical and Clinical Research.