PRODIGY: protein-based molecular design for next-generation therapy

About the project

Proteins are at the heart of every human disease, and are thus targets of most therapeutics, but the development of therapeutic molecules is a difficult challenge.

With the emergence of new machine learning (ML) or generative artificial intelligence (GenAI) methods, enabled by big data, we are at the cusp of one of the most substantial transformations in biomedicine of the last 50 years. Combined with recent breakthroughs in structural biology, in particular cryo-EM, ML-based computational models will enable the design of novel proteins, peptides and small molecule drugs with potentially transformative therapeutic potential for a wide range of applications.

Indeed, GenAI approaches have begun to impact society in various domains such as image and text generation, and are becoming a transformative toolbox in molecular design and drug discovery. Despite these impressive advances, GenAI is however still in its infancy and facing many obstacles, in particular in domains where data is limited, and the problems are complex, such as the design of novel molecular matter acting within a biological context. Many fundamental challenges in ML and GenAI approaches remain unsolved, such as imposing empirical priors, data representation, sampling performance, data availability or explainability, and systematic research efforts are paramount.

Within the NCCR PRODIGY (Protein-based Molecular Design for Next-Generation Therapy), we will set up a collaborative network that combines: excellence in fundamental research in ML methods, computational design of small-molecules, peptides and proteins, structural biology, chemical biology, high-throughput biology powered by omics approaches, to innovate on GenAI approaches for the design of novel therapeutic modalities

Leadership team

Bruno Correia

Computational protein design, intersecting biochemistry, structural biology, immunology, and computer science.

Paola Picotti

Molecular ‘omics, with a focus on mass spectrometry-based chemical and structural proteomics.

Beat Fierz

Protein chemistry and biophysics, to reveal molecular mechanisms in the fields of epigenetics genome regulation and cytoskeleton control.

Nicolas Thomä

Chemical and structural biology of gene regulation and the ubiquitin system, development of molecular glues.

Sereina Riniker

Development of methods and software for classical molecular dynamics simulations and cheminformatics, and their application to gain insights into challenging biological and chemical questions.

Matteo Dal Peraro

Multiscale models and dynamic integrative modeling to investigate the assembly and function of molecular assemblies mimicking conditions of the cellular environment.
 

Our Partners

 

What's new with PRODIGY?

Concevoir la vie avec l'intelligence artificielle

Le projet MAKE "Designing Life with AI" veut encourager la communauté étudiante de l’EPFL à expérimenter la recherche via le domaine du design de protéines. Il réunit huit laboratoires.

Link to the article: https://actu.epfl.ch/news/conc...

Link to the project: https://www.designinglifewitha...

New paper from the lab of B. Correia (EPFL)

EPFL scientists from the laboratory of B. Correia have used deep learning to design new proteins that bind to complexes involving other small molecules like hormones or drugs, opening up a world of possibilities in the computational design of molecular interactions for biomedicine. This study is published in the journal Nature.

https://www.nature.com/article...

New paper from the lab of E. Levy (Univ. Geneva)

Proteins, the pillars of cellular function, often assemble into “complexes” to fulfill their functions. A study by the University of Geneva (UNIGE) and the Weizmann Institute, in collaboration with the Technion, reveals why this assembly often begins during the very process of protein synthesis or ‘‘birth.’’ These early interactions involve proteins whose stability depends on their association. They can be compared to a couple in which each partner supports the other. This model paves the way for new strategies to understand and correct assembly errors, which are often associated with pathologies, including neurodegenerative disorders and certain cancers. These findings are published in the journal Cell.

https://www.cell.com/cell/full...

Starting grants for two NCCR PRODIGY members from EPFL


The Swiss National Science Foundation (SNSF) awarded "SNSF Starting Grants" to two EPFL researchers who are involved in our NCCR PRODIGY, as part of the 2024 call. Congratulations to Maria Brbic, Philippe Schwaller! With an SNSF Starting Grant, grantees will lead an independent research project and direct a team of researchers in Switzerland. Maria will work on "Learning the Language of Cells with a Generative Multi-modal Foundation Model” while Philippe will study "Open Large Language Model-Centered Agent Systems for Chemical Research”. Both topics will directly feed into our NCCR PRODIGY.

PRODIGY is online!

The NCCR PRODIGY website is now up and running! Stay tuned for more details and news about our proposal.

Show more posts

Selected recent publications

1.
MARBLE: interpretable representations of neural population dynamics using geometric deep learning.
Nature Methods 1–9 (2025). doi: 10.1038/s41592-024-02582-2
2.
Aerolysin Nanopore Structures Revealed at High Resolution in a Lipid Environment.
Journal of the American Chemical Society 147, 4984–4992 (2025). doi: 10.1021/jacs.4c14288
3.
A Holistic Data-Driven Approach to Synthesis Predictions of Colloidal Nanocrystal Shapes.
Journal of the American Chemical Society jacs.4c17283 (2025). doi: 10.1021/jacs.4c17283
4.
Rapid and sensitive protein complex alignment with Foldseek-Multimer.
Nature Methods (2025). doi: 10.1038/s41592-025-02593-7
5.
Structural basis of SIRT7 nucleosome engagement and substrate specificity.
Nature Communications 16, 1328 (2025). doi: 10.1038/s41467-025-56529-y
6.
Novel strategies to manage CAR-T cell toxicity.
Nature Reviews Drug Discovery (2025). doi: 10.1038/s41573-024-01100-5
7.
Phase separation of a microtubule plus-end tracking protein into a fluid fractal network.
Nature Communications 16, 1165 (2025). doi: 10.1038/s41467-025-56468-8
8.
Computational design of highly signalling-active membrane receptors through solvent-mediated allosteric networks.
Nature Chemistry (2025). doi: 10.1038/s41557-024-01719-2
9.
Targeting protein–ligand neosurfaces with a generalizable deep learning tool.
Nature (2025). doi: 10.1038/s41586-024-08435-4
10.
Phosphorylation of a nuclear condensate regulates cohesion and mRNA retention.
Nature Communications 16, 390 (2025). doi: 10.1038/s41467-024-55469-3
11.
Structural determinants of co-translational protein complex assembly.
Cell 188, 764–777.e22 (2025). doi: 10.1016/j.cell.2024.11.013
 

Keep in touch with PRODIGY

Processing...

© 2024 PRODIGY — Privacy Policy