Quantum-enabled feature selection for metabolomic and biometric data analysis

Metabolomics is the study of the complete set of small molecules in the human body. Analyzing metabolomic and biometric data is critical in order to detect, predict, and simulate changes in the health conditions of a patient, providing the opportunity for preventive and personalized medicine. This is generally done using machine learning, but it is a computationally intensive process due to the large number of features, or aspects of the data, that may affect the outcomes. Quantum computing is an emerging technology that will one day enable us to solve some of the world’s hardest problems. The aim of this project is to explore how quantum machine learning can be applied to metabolomic and biometric data analysis through proof-of-concept implementations and benchmarking. A successful outcome of the project will make BioTwin well-positioned to leverage the advantages offered by quantum computing and improve their data analysis pipelines

Faculty Supervisor:

Roman Krems

Student:

Partner:

AI-Genetika inc

Discipline:

Computer science

Sector:

Manufacturing; Professional, scientific and technical services

University:

The University of British Columbia

Program: