TL;DR
A consortium co-led by the Buck Institute and Georgetown University received an ARPA-H award of up to $51.7 million for a four-year effort to predict harmful changes in intrinsically disordered proteins. The project will combine computational models with experiments, initially studying proteins linked to Alzheimer’s disease and Ewing sarcoma. The work is intended to support future diagnostics and treatments, but it has not yet produced a clinical test or therapy.
A research consortium co-led by the Buck Institute for Research on Aging and Georgetown University has received an award of up to $51.7 million from ARPA-H to predict how certain flexible proteins change toward disease-associated states. The four-year project will pair artificial-intelligence models with laboratory experiments, beginning with proteins relevant to Alzheimer’s disease and Ewing sarcoma, with the longer-term aim of informing diagnostics and treatments.
The effort, called SEEDS (Sequence-to-disease: Environment-aware Ensembles of Disordered proteins at Scale), focuses on intrinsically disordered proteins, or IDPs. Unlike proteins that settle into a relatively stable three-dimensional shape, IDPs can take on many forms. Their behavior can shift in response to conditions inside cells, including acidity, molecular crowding, metals, metabolites and chemical modifications.
The consortium plans to use protein sequence and cellular surroundings together to predict how these proteins behave. Researchers will test computational predictions against experimental measurements under different conditions, rather than relying on AI models alone. The team includes researchers from nine academic institutions and seven industry partners, combining expertise in protein science, AI, computational modeling, cancer and neuroscience.
The project addresses a limitation in current protein research: scientists can capture snapshots of some proteins, often after they have aggregated, but cannot reliably forecast how their behavior changes as cellular conditions vary or when those changes become harmful. The source report says the team aims to map protein behavior at scale and develop ways to detect, and eventually intervene in, disease-associated shifts. Those are research goals, not established clinical capabilities.
Aiming to Spot Protein Shifts Earlier
Protein misfolding and aggregation are associated with Alzheimer’s disease, ALS, some cancers and other chronic or degenerative conditions. If researchers can identify changes that precede harmful aggregation, that knowledge could eventually help identify biological signals earlier or suggest points for intervention. The project’s emphasis on prediction before lasting cellular damage reflects a shift toward studying early processes, rather than focusing only on protein clumps after they form.
Many IDPs have been regarded as difficult to target with conventional drugs because they do not maintain the stable structures and binding pockets that many drug-design methods rely on. A better understanding of how their sequence and surroundings shape their behavior could provide new information for future drug development. However, the award does not establish that the consortium will produce an effective medicine or diagnostic within the four-year period.
The work also seeks to address a data gap in AI-driven protein science. The source report notes that tools such as AlphaFold benefited from extensive accumulated structural data, while researchers have less comparable information for disordered proteins. SEEDS plans to generate data and test models for this class of proteins, which could help establish whether useful predictive rules can be learned.
protein analysis kits for research
As an affiliate, we earn on qualifying purchases.
As an affiliate, we earn on qualifying purchases.
The Focus on Disordered Proteins
Proteins perform many functions in cells, and their shapes help determine how they interact. For IDPs, there is no single stable shape to describe: they form ensembles of different conformations. This flexibility can support normal cellular functions, but it also makes it harder to predict how a protein will respond when its environment changes.
SEEDS is part of ARPA-H’s BIOmolecular Grammar for protein Aggregation Modulation and Intervention program, known as BIOGAMI. The program focuses on early stages of protein dysfunction, before misfolding or aggregation leads to lasting cellular damage. Its “molecular grammar” concept refers to seeking rules that connect a protein’s sequence and environment to its behavior.
The SEEDS consortium brings together two research efforts, Georgetown’s INTREPID and the Buck Institute’s SHIFT, according to the source report. Georgetown’s Priyanka Joshi, PhD, and the Buck Institute’s Chuankai (Kai) Zhou, PhD, co-lead the project. ARPA-H Program Manager Shannon Greene, PhD, leads the broader BIOGAMI program.
“We aim to uncover the principles that determine when these proteins remain in healthy functional ensembles and when they begin to shift toward disease-associated states.”
— Chuankai (Kai) Zhou, assistant professor at the Buck Institute
As an affiliate, we earn on qualifying purchases.
Predictions Still Need Testing
The project is at the research stage. It is not yet clear whether the planned models will reliably predict harmful changes across different IDPs, cellular conditions or diseases. The consortium intends to compare predictions with experiments, but the source report provides no results showing that the approach can already identify a protein’s path toward disease.
The report does not specify how much of the award will be distributed at each stage, which individual proteins will be studied first, or when any candidate diagnostic or treatment might be ready for clinical testing. It also gives no evidence that the work will prevent disease or reverse existing damage. Any such benefits remain potential outcomes that would require further research and validation.
As an affiliate, we earn on qualifying purchases.
Four Years of Model Testing
Over the four-year award period, SEEDS is expected to build and test methods for studying IDPs at scale, using computational predictions alongside measurements in experiments. The initial focus is on Alzheimer’s disease and Ewing sarcoma, while the stated research aims address broader questions about protein behavior and disease.
The next meaningful updates will be evidence about whether the models can predict protein behavior under changing cellular conditions and whether those predictions identify changes relevant to disease. Any diagnostic or treatment concepts would need additional development and testing before their performance or availability could be assessed. ARPA-H and the participating research teams have not, in the source report, announced a clinical timetable.
As an affiliate, we earn on qualifying purchases.
Key Questions
What is the SEEDS project?
SEEDS is a four-year consortium effort co-led by the Buck Institute and Georgetown University to study and predict the behavior of intrinsically disordered proteins using computational models and experiments.
How much funding did the team receive?
ARPA-H awarded the project up to $51.7 million. The source report does not provide a detailed breakdown of the award or payments.
Which diseases are the researchers focusing on first?
The project’s initial focus is on proteins relevant to Alzheimer’s disease and Ewing sarcoma. The broader research concerns protein misfolding, which is associated with several diseases.
Does the award mean a new diagnostic or treatment is available?
No. The award funds research intended to inform future diagnostics and treatments. No clinical test or therapy resulting from the project is reported as available.
Why are intrinsically disordered proteins hard to study?
These proteins can take on many shapes, and their behavior can change with their cellular environment. That flexibility makes them harder to model and can leave them without the stable structures that many conventional drug-design methods target.
Source: rss
