Generative AI for Life Science
Description
Generative AI has become both highly prevalent and highly divisive. While public opinion varies, rapid advancement in GenAI is transforming the life sciences, enabling new approaches to understand biological systems, predict molecular structures and advance clinical diagnostics.
In this workshop, we will demonstrate how GenAI is applied across key life science domains through four interactive sessions. Participants will train models, explore biological datasets and generate real outputs such as synthetic cell images, protein structure predictions, and mRNA sequences for vaccines. By the end of the workshop, you will have hands-on experience in developing GenAI techniques and applying them to solve real-world life science problems.
Content Providers
Learning Outcomes
Understand what generative AI is and how generative models (autoencoders, transformers and multimodal systems) are applied to biological data.
Hands-on experience training and using models for:
- Image analysis and reconstruction (autoencoders).
- Protein feature extraction and structure prediction (protein language models).
- Drug discovery (codon prediction).
Understand key concepts such as latent space representations, intermediate embeddings and attention mechanisms.
Experience with real biomedical datasets including X-ray images and protein sequences.
Methods for evaluating models with practical metrics, visualisations and interpretability tools (e.g. saliency maps).
Prerequisites & Technical Requirements
Prerequisites
Basic familiarity with Python is expected.
Experience with machine learning is preferable but no prior experience with generative AI is required.
Participants should:
Have a laptop with Windows, macOS or Linux.
Be able to access a web browser and use Google Colab.
Topics & Tags
Affiliations & Networks
Activity log
