AI and Synthetic Biology: Part 2

The third episode of the Genomics Futures podcast focuses on AI and synthetic genomics!In part two of this two-part episode, we explore how AI will play a key role in shaping the future of genomics. But progress depends on shared data, sustainable models, and local infrastructure, moving from one-size-fits-all medicine to population-level precision, with equity built in.Topics covered in part two include: Precision global health: Instead of a "one-size-fits-all" approach, the future involves "population-level precision".Democratising infrastructure: True equity requires investing in local data centres and infrastructure in low-resource settings so that data is not just collected locally but also processed and controlled by local researchers.The AI-automation feedback loop: Lab automation is critical for accelerating the "learning rate" of biology; robots generate the massive datasets needed to train AI, which in turn helps design better experiments, creating a positive feedback loop.Overcoming the data bottleneck: Biology must focus on creating large, standardised, and quantitative datasets to train reliable predictive models.Pre-competitive data sharing: To speed up drug discovery for thousands of rare diseases, the industry must move toward publicly sharing data on how small molecules interact with proteins, as "data hoarding" is a primary barrier to progress.This episode includes interviews with:Professor Kondwani Jambo, Professor of Immunology and Infection at the Liverpool School of Tropical Medicine, who explores the concept of personalised medicine and democratisation of genomics technologies.Dr Patrick Boyle, an automation and digital data expert, discusses automation in the lab and the possibilities it may offer in twenty-five years. Professor Ben Lehner, Head of the Generative Genomics Programme at the Wellcome Sanger Institute, speaks about the possibilities of engineering biology in the future.Mentioned in the episode:Vision 2063 – a vision aiming to transform Malawi into a wealthy and self-reliant industrialized ‘upper middle-income country’ by the year 2063.AlphaFold – an artificial intelligence programme, which performs predictions of protein structure.Protein Data Bank – a data bank that collects, organises and disseminates data on biological macromolecular structures.25 years on from the release of the first draft of the human genome, the Genomics Futures podcast series explores what the future of genomics will be like in 2050.Across 6 episodes, we explore the themes and topics that arose from discussions that took place during the Genomics Futures workshops, hosted by the Wellcome Sanger Institute and Wellcome in 2025.The aim of these podcasts is not to showcase definitive thoughts, but to explore the possibilities of genomics in twenty five years’ time, hence why some speakers may contradict each other. The views expressed in these podcasts are of the speakers alone.Further information about the workshops including further outputs can be found here: https://www.sanger.ac.uk/innovation/sanger-genomics-futures-series/This podcast is produced by the Wellcome Sanger Institute.