Quantum Biomarker Algorithms for Multimodal Cancer Data
Using quantum optimisation to tackle a fundamental and computationally intensive challenge in cancer research, and specifically to develop effective methods for biomarker identification within multimodal cancer data.
OWNER
QUANTUM APPROACH
Optimisation
SDGs
CONTRIBUTORS
Infleqtion
University of Chicago
Massachusetts Institute of Technology
ORIGIN OF CONTRIBUTORS
HOW COULD QUANTUM HELP:
Quantum computing could be used to potentially enhance data processing for multi-modal cancer data, specifically when dealing with complex relationships between genomic, transcriptomic, and pathomic aspects of cancer biology. A hybrid quantum-classical algorithm could be used for feature selection, a key dimensionality reduction technique that helps mitigate overfitting in multi-modal cancer datasets, and where such a structure may reveal novel biological insights by identifying predictive feature sets. This could further be formulated as a combinatorial optimization problem, solvable by a quantum computer using polynomial constrained binary optimization (PCBO), to identify accurate biomarkers across multimodal biological data.
REFERENCES: