This webinar series explores the revolutionary potential of Large Language Models (LLMs) in bioinformatics and computational biology. Through interconnected sessions, participants will progress from core LLM concepts to specialised biological applications, covering everything from fundamental architectures to practical implementation in research environments. The series emphasises hands-on learning, featuring real-world examples from leading biological databases and research platforms, while addressing the unique challenges and opportunities of applying LLMs to biological data.

The webinars making up this series are listed below. Follow the links to find out more about each webinar. Recordings are openly available of all webinars on their individual pages.

Webinars

Who is this series for?

This webinar series is designed for bioinformaticians, computational biologists, data scientists, and researchers interested in applying AI and language models to biological problems.

Outcomes

After completing the webinar series you will be able to:

• Describe the technical foundations of Large Language Models, including transformer architecture, training methodologies, and practical considerations for their deployment in biological applications
• Implement best practices for dataset preparation and curation specific to biological data, including strategies for data collection, cleaning, preprocessing, and annotation while maintaining scientific accuracy
• Apply LLMs to real-world bioinformatics challenges through practical case studies from leading biological databases (InterPro, RNAcentral)
• Evaluate and mitigate common challenges in LLM applications, including hallucination detection, bias management, and verification strategies in biological contexts
• Navigate the current landscape of LLM tools, frameworks, and deployment options for bioinformatics applications, with special emphasis on open-source solutions
• Recognise how tailored AI approaches can enhance text mining for biomedical research

Speakers

This webinar series took place from 26 February to 16 April 2025. Recordings of all webinars, as listed on the series page, are available to watch, but you will need to visit the individual webinar pages to access the videos.