Accelerating Drug Discovery with Hybrid Quantum Computing |  NVIDIA Blog

Accelerating Drug Discovery with Hybrid Quantum Computing | NVIDIA Blog

The promise of quantum computing is to solve unsolvable problems. And companies are already making progress with hybrid approaches — those that combine classical and quantum computing — to tackle challenges like drug discovery for incurable diseases.

By accelerating the simulation and modeling of drug molecules using hybrid quantum computing, startup Qubit Pharmaceuticals is dramatically reducing the time and investment needed to identify promising treatments in oncology, inflammatory diseases and antivirals.

Qubit is building a drug discovery platform using the NVIDIA QODA programming model for hybrid quantum-classical computers and the startup’s Atlas software suite. Atlas creates detailed simulations of physical molecules, speeding up calculations by a factor of 100,000 compared to traditional research methods.

Founded in 2020, the Paris and Boston-based company is a member of NVIDIA Inception, a program that provides support, expertise, and go-to-market technology to cutting-edge startups.

Qubit has one of France’s largest GPU supercomputers for drug discovery, powered by NVIDIA DGX systems. The startup aims for pharmaceutical companies to begin testing their first drug candidates discovered through its GPU-accelerated research next year.

“By combining NVIDIA’s advanced computing power and software with Qubit’s simulation and molecular modeling capabilities, we are confident in our ability to dramatically reduce drug discovery time and reduce its cost by a factor of 10,” said Robert Marino, president of Qubit Pharmaceuticals. . “This unique collaboration should allow us to develop the first quantum physics algorithms applied to drug discovery.”

Harnessing Unprecedented Computing Capabilities

Computational drug discovery involves generating high-resolution simulations of potential drug molecules and predicting how well those molecules might bind to a target protein in the body.

For accurate results, researchers must perform massive sampling, simulating hundreds of different conformations – possible spatial arrangements of atoms in a molecule. They must also correctly model the force fields of molecules, the electrical charges that predict affinity or how one molecule binds to another.

This simulation and modeling requires high-performance computing, so Qubit selected an in-house supercomputer built with NVIDIA DGX systems and other NVIDIA-accelerated servers, totaling 200 NVIDIA Tensor Core GPUs. The supercomputer runs Qubit’s Atlas software, performing calculations in just hours that would take years with conventional methods.

Atlas models quantum physics at the microscopic level to achieve maximum precision. The Qubit team is adopting NVIDIA QODA to explore the hybrid use of GPU-accelerated supercomputers and quantum computers, where QPUs, or quantum processing units, could one day accelerate key software cores for molecular modeling.

Using the NVIDIA cuQuantum SDK, Qubit developers can simulate quantum circuits, allowing the team to design algorithms ready to run on future quantum computers.

AI at every stage of drug discovery

Qubit estimates that while conventional research methods require pharmaceutical developers to first synthesize an average of 5,000 drug compounds before preclinical testing to bring a single drug to market, a simulation-based drug discovery approach could reduce the figure. to about 200, which would save hundreds of millions. dollars and years of development time.

The company’s Atlas software includes AI algorithms for every step of the drug discovery cycle. To support target characterization, where researchers analyze a protein that plays a role in disease, Atlas supports molecular dynamics simulations at microsecond timescales, helping scientists identify new pockets for drug molecules bind to the protein.

When screening and validating drug candidates, researchers can use AI models that help narrow the field of potential molecules and generate new compounds. Qubit also develops additional filters that predict the pharmacogability, safety and cross-reactivity of a candidate molecule.

Learn more about Qubit’s HPC and quantum accelerated molecular dynamics software from company co-founders Jean-Philip Piquemal and Louis Lagardère via NVIDIA On-Demand.

Main image courtesy of Qubit Pharmaceuticals.

#Accelerating #Drug #Discovery #Hybrid #Quantum #Computing #NVIDIA #Blog

Leave a Comment

Your email address will not be published. Required fields are marked *