University of Maryland Grant Targets Quantum and AI Tools for Cancer Research

The University of Maryland has awarded a team grant to researchers exploring the integration of quantum computing and artificial intelligence to accelerate the development of cancer detection and treatment tools. This project, part of the university’s $15 million Grand Challenges Grants Program, focuses on designing single-atom catalysts that can precisely drive chemical reactions within tumor microenvironments. For the quantum computing sector, this initiative represents a significant use case for quantum-enhanced material simulation and its potential to streamline the discovery of life-saving biomedical technologies.

The University of Maryland has launched a research project to integrate quantum computing and artificial intelligence into the search for advanced cancer detection and treatment methods. As one of 11 efforts funded by the university’s $15 million Grand Challenges Grants Program, the three-year initiative involves a multidisciplinary team including Keystone Professor Teng Li, assistant research professor Lianping Wu, and associate professor of computer science Xiaodi Wu. The research focuses on single-atom catalysts, which are precision materials capable of driving chemical reactions at the atomic scale to potentially alter tumor microenvironments and overcome treatment resistance.

The project aims to solve critical challenges in oncology, where traditional therapies like chemotherapy often harm healthy tissue and tumors frequently develop defensive mechanisms. By utilizing quantum computing, the team intends to model the complex behaviors of atoms and electrons that are difficult for classical systems to simulate. These quantum-derived simulations will generate highly accurate databases of electronic structures and catalytic reaction pathways, providing a more reliable foundation for identifying effective materials than conventional trial-and-error discovery methods.

These databases will support machine learning models designed to screen millions of possible catalyst configurations to predict which structures are most suitable for clinical use. While the application of single-atom catalysts remains in the preclinical stage, the Maryland team’s predictive framework is intended to identify the most promising candidates before they move into costly laboratory and animal testing. This approach reflects a broader shift in the quantum computing sector toward computational discovery, offering a systematic and accelerated path for developing materials that could address the global impact of cancer, which causes nearly 10 million deaths annually.