Sorbonne University and Qubit Pharmaceuticals
unveil the world's most powerful Quantum AI
model to discover new medicines

• Sorbonne and Qubit have built the most accurate synthetic database ever for molecular chemistry, leveraging powerful computing resources from GENCI, EuroHPC, and Argonne
  National Laboratory.
• This groundbreaking database powers FeNNix-Bio1, an AI foundation model uniquely combining precision and speed to drastically shorten chemical synthesis timelines in drug discovery and unlock novel molecular mechanisms.
• Potential applications span far beyond pharmaceuticals, extending to enzyme optimization, cosmetics, and beyond.

The team used unprecedented computing power from GENCI, EuroHPC and Argonne to create FeNNix- Bio1, a foundational model built on millions of meticulous molecular simulations. It was trained on the world's most accurate molecular chemistry database, simulated to the highest possible chemical precision. By training on these elementary bricks, the foundation model learns the laws of chemistry and physics, and can reconstruct biomolecules in Lego-like fashion. It learns how molecules interact with each other.

High-resolution molecular modeling thanks to AI

FeNNix-Bio1 has proved its effectiveness in one of the most difficult tasks in molecular modeling: simulating the physical behavior of water in its various phases. Indeed, the foundation model can accurately predict various physical properties, and reproduce the behavior of ions and small organic molecules in solution with remarkable fidelity, where other reference models are unable to do so. This is essential because water is the solvent present in the human body, and its interaction with drugs plays a key role in their activity.

One of the special features of the model is its ability to model the reactivity of molecules, i.e. to create or break chemical bonds, which traditional simulation software cannot do. In this way, FeNNix-Bio1 makes it possible to design covalent drugs (i.e. those which bind directly to the target through the creation of a chemical bond) such as Paxlovid or Ibrutinib.

Extending Google DeepMind's AlphaFold revolution from chemistry to biology using synthetic data

FeNNix-Bio1 represents not just a marginal gain, but a new approach to molecular science. Where traditional simulations are limited in accuracy, speed and areas of applicability, and quantum chemical models are accurate but slow and too computationally expensive for large-scale implementation, FeNNix-Bio1 offers quantum-level accuracy while remaining scalable and cost-effective. The foundation model doesn't just predict structure, it understands how molecules behave and interact.

Predicting a drug's ability to bind to a protein (or to RNA or DNA) is one of the most complex tasks in drug discovery. Chemical space is virtually limitless. An infinite number of drug molecules can be designed, and introduced into an infinite number of targets (around 100,000). There are thus trillions of possible combinations, and it's impossible to fit them all into a database.

One of the most exciting features is its potential to reduce laboratory experimentation and enable the exploration of more innovative drug candidates to tackle targets that are complex or even considered impossible to modulate until now.

To achieve this, the FeNNix-Bio1 researchers developed neural network approaches adapted to applications in chemistry and physics, rather than using LLMs (Large Language Model) architectures, generally optimized for recognizing and generating text. More accurate and less expensive, FeNNix-Bio1 can be trained in a few hours using a standard GPU, whereas other AI models require weeks of supercomputing time.

The launch of this new foundation model opens up new prospects. Its versatility, speed and precision position Qubit Pharmaceuticals beyond the pharmaceutical sector. Potential applications in the chemical sector include the design of industrial enzymes, the optimization of membranes for desalination, the development of new-generation batteries, and the acceleration of green chemistry. Rooted in the laws of physics, the model is adaptable: by changing the molecular building blocks, it is possible to simulate any system.

FeNNix-Bio1 also paves the way for quantum AI - the convergence of quantum computing and machine learning, which promises to revolutionize data generation for molecular simulations. Qubit Pharmaceuticals is already using quantum data to enrich its models – something long thought impossible until 2035, shares Jean-Philip Piquemal.

FeNNix-Bio1 is a paradigm shift in molecule design, testing and validation. With FeNNix-Bio1, we're not just going faster, we're more innovative, more efficient, and we can scale up in several industrial sectors. With the convergence of AI and high-performance computing enabling large-scale simulation of biology and chemistry, and the development of quantum computing shattering the boundaries of physics, the long-awaited vision of automated molecule discovery is becoming a reality at an accelerating pace.