EVENFLOW participated in the ISCB Student Council Symposium which was held on July 20th, 2025 in Liverpool, UK.

Guillermo Prol Castelo from the Barcelona Supercomputing Center (BSC), project partner, presented a Systematic Literature review, highlighting that the use of generative AI and synthetic data in cancer research remains uncharted, especially when it comes to under-represented groups, such as rare groups in rare diseases like Medulloblastoma. The review also pointed out a lack of longitudinal data in public high-throughput biological datasets.

To address these challenges, a Variational Autoencoder-based method was developed for generating synthetic biomedical data. Its application was showcased in two case studies:

• In Medulloblastoma, the model helped identify a rare subgroup that had been historically misclassified due to the scarcity of samples.
• In kidney cancer, synthetic “intermediate” patients were generated to better understand the disease’s progression from early to late stages and its changes as it becomes more invasive.

These findings underscore the potential of generative models to enhance data-driven cancer research and improve representation in biomedical datasets.

Find the poster presented here.

About the event: The Student Council Symposium is a forum for students and young researchers in the fields of Computational Biology and Bioinformatics. Participants had the opportunity to present their work to an international audience, build a network within the computational biology community and develop important soft skills in an environment that fosters the exchange of ideas and knowledge.