Applied Biological Data Science

Firstly, we highlight the importance of mining public datasets using AI-bioinformatics expertise to unveil valuable biological insights that could pave the way for new therapeutics and diagnostics. Significant demand exists for innovative software and modelling techniques to identify and classify complex biological patterns efficiently. Moreover, user-friendly databases facilitating the comparison and retrieval of insights are in demand. 

Secondly, from sequences up to structural data, from nucleic acids to proteins are rich data to explore and model, enabling the understanding of key factors affecting human health, such as infectious diseases and cancer. 

Finally, Generative AI (GenAI – like Large Language Models (LLMs)), promises to be a powerful tool to apply to biological data problems and bring a new dimension to deal with complex biological data. We work on data augmentation with GenAI, where datasets are often limited and just a tiny sample is available. Augmenting the dataset enhances classification tasks in bioinformatics. We aim to deploy novel GenAI solutions across the Franklin, in areas such as chemical to structural biology, to better understand data complexity. Together, these approaches will enhance our understanding of biological systems through ambitious applications of AI and advanced data analysis methods.