Federated quantum machine learning for genomics data

Sector: Healthcare (Healthcare Data Privacy and Sharing)

Lead organisation: Zaiku Group Ltd

Consortia: Zaiku Group Ltd, North East Yorkshire Genomics Lab Hub, National Quantum Computing Centre (NQCC)

Biomedical data is an essential resource for developing machine learning (ML) models, with these models being able to aid in diagnosis, treatment, and prevention of diseases. However, the collection, storage, and sharing of biomedical data presents significant challenges due to their sensitive nature, and the ethical considerations. Healthcare data is also subject to strict regulations and privacy laws, making it challenging for researchers to access and share data. This project, led by Zaiku Group Ltd, focused on utilizing quantum computing for federated learning (FL) in genomics data. FL allows multiple organizations to collaboratively train machine learning models without directly sharing data, which is particularly important for sensitive biomedical data. Under this project, the team has investigated the power of quantum computing to enable such privacy-preserving data sharing, with the benefits of classical FL, namely, hybrid classical-quantum FL to benefit the biomedical sector. The project has led to the creation of a cloud-based proof-of-concept platform that enables the training of hybrid quantum machine learning models on genomics datasets without sharing raw data. This project has potential far-reaching implications in accelerating innovation while ensuring data privacy and security.