Zapata, Foxconn, Insilico Medicine, and University of Toronto Study Shows Promise of Hybrid Quantum Generative AI for Drug Discovery

Not only could the quantum-enhanced GANs generate small molecules, but these molecules had more desirable properties than those generated by purely classical GANs.

Metadata
Provider: 
Business Wire, Inc.Business Wire, Inc.
Retrieved on: 
Tuesday, June 6, 2023
Information
Tags: 
Technology, Biotechnology, Nanotechnology, Health, Pharmaceutical, Artificial Intelligence, Other Technology, Research, Software, Networks, Health Technology, Hardware, Science, Semiconductor, Pharmacy, University, Deep learning, Intelligence, Solubility, Doctor of Philosophy, Foxconn, Quantum technology, GAN, QED, BMW, Patient, Machine learning, Insilico Medicine, Drug discovery, Artificial intelligence, SA, Quantum, Pharmaceutical industry, Microscope
Geotags: 
MASSACHUSETTS, UNITED STATES, NORTH AMERICA, EMILIANO ZAPATA
⚠ partially generated by AI ↴
Organisation: 
ZAPATA COMPUTING, ZAPATA COMPUTING, INC.
Summary
Key Points: 
  • Not only could the quantum-enhanced GANs generate small molecules, but these molecules had more desirable properties than those generated by purely classical GANs.
  • As detailed in the research paper, the teams leveraged artificial intelligence and quantum computing techniques to replace each element of GAN with a variational quantum circuit (VQC).
  • In 2021, Zapata researchers were the first to generate high-resolution images using quantum generative models.
  • For more information about Zapata’s research with Insilico Medicine, Foxconn, and the University of Toronto, please visit www.pubs.acs.org/doi/full/10.1021/acs.jcim.3c00562 .


Zapata Computing, the software company building solutions to enterprises’ most computationally complex problems, today announced that it has published research with Insilico Medicine, Foxconn, and the University of Toronto which explores the use of hybrid quantum-classical generative adversarial networks (GAN) for small molecule discovery. Not only could the quantum-enhanced GANs generate small molecules, but these molecules had more desirable properties than those generated by purely classical GANs.

As detailed in the research paper, the teams leveraged artificial intelligence and quantum computing techniques to replace each element of GAN with a variational quantum circuit (VQC). The molecules generated by the quantum-enhanced GANs were then compared with those generated by a purely classical GAN according to three qualitative metrics (validity, uniqueness, and novelty) and three quantitative properties (drug-likeness (QED), solubility, and synthesizability (SA)). Researchers found that the small molecules created through the use of a VQC frequently had better physicochemical properties and performance in the goal-directed benchmark than the classical counterpart.

“At Insilico Medicine, we’re always seeking new ways to transform drug design and development through artificial intelligence to help bring life-saving medications to patients,” said Alex Zhavoronkov, PhD, founder and CEO of Insilico Medicine. “The drug discovery pipeline is traditionally a long and costly process, but recent advances in machine learning and deep learning technologies have proven to help reduce time and costs for pharmaceutical research and development. By working with Zapata and Foxconn, we were able to uncover molecule designs with viable structures that were comparable to those from classical methods.”

“We are pleased to achieve this milestone in the collaboration with Insilico Medicine. Quantum computing can be used to solve complex computational problems. The application of quantum computing in drug discovery will potentially help reduce the time and lower the cost of research and development,” said Min-Hsiu Hsieh, PhD, Director of the Quantum Computing Research Center of Hon Hai Technology Group (Foxconn®).

“This work with Insilico Medicine and Foxconn is a great example of how quantum-enhanced generative AI can be used to solve real-word problems more effectively,” said Yudong Cao, CTO and co-founder at Zapata Computing. “We’ve seen encouraging evidence that demonstrates the potential of quantum and quantum-inspired generative models, and we’re excited to see how these quantum-inspired techniques could help further advance the pharmaceutical industry, as well as other industries looking to overcome complex design challenges.”

Zapata has a track record of breakthrough research in quantum generative AI. In 2021, Zapata researchers were the first to generate high-resolution images using quantum generative models. In more recent work with BMW, Zapata researchers demonstrated how quantum-inspired generative models could improve upon best-in-class traditional optimization solutions for a vehicle manufacturing scheduling problem.

For more information about Zapata’s research with Insilico Medicine, Foxconn, and the University of Toronto, please visit www.pubs.acs.org/doi/full/10.1021/acs.jcim.3c00562.

About Zapata Computing

Zapata Computing, Inc. builds solutions to enterprises’ most computationally complex problems. It has pioneered proprietary methods in generative AI, machine learning, and quantum techniques that run on classical hardware (CPUs, GPUs). Zapata’s Orquestra® platform supports the development and deployment of better, faster, more cost-effective models—for example, Large Language Models, Monte Carlo simulations, and other computationally intense solutions. Zapata was founded in 2017 and is headquartered in Boston, Massachusetts. For more information, visit www.zapatacomputing.com.

Copyright: 
Copyright Business Wire 2023