Get your free personalized podcast brief

We scan new podcasts and send you the top 5 insights daily.

John Baker says live Biobank blood cells are destroyed once a tube is taken out and run on IMU's platform, and many samples are aged. To maximize each one, IMU extracts hundreds of millions of proteomic immunology measurements plus high-resolution single-cell gene expression, then uses neural networks to map those datasets together.

Related Insights

The company's breakthrough potential comes not from collecting raw DNA, but from linking it at an individual level to a rich set of "phenotype" data, including proteomics, metabolomics, and transcriptomics. This deep, multi-layered dataset from novel populations is what unlocks actionable insights for drug discovery.

Generating millions of data points for AI requires industrializing lab workflows. To avoid data degradation from cell stress during long experiments, the Xaira team introduced chemical fixation to preserve cell states and re-engineered processes for time-shifted operations, ensuring consistent, high-quality training data.

Acknowledging the "garbage in, garbage out" principle, Haya heavily invests in generating high-quality, layered, and paired multi-omic data from the same biological material. This curated input is considered the most critical component for building effective AI models to unlock new biology.

John Baker says the founding team opened a £1 profiling shop on King's College campus in 2021. They used it to build the first high-resolution dataset of 1,000 immune systems, now shown on the office wall as the healthy-immune reference. That scrappy sampling gave IMU a population baseline before UK Biobank.

To study complex processes like inflammation, CZI is developing technologies that go beyond analyzing existing data. This includes implantable sensors that track inflammatory markers in real-time (like a glucose monitor) and "live tissue omic platforms" that can map entire proteomes, creating rich, dynamic datasets to train advanced AI models.

John Baker says IMU has about 35 people in Canary Wharf, the vast majority of its global team. He claims the wet-lab and in-silico platform is efficient enough for that team to handle the full Biobank volume, which runs from a few hundred samples now to tens or hundreds of thousands.

Infinimmune’s platform bypasses traditional discovery methods by reading antibodies directly from human memory B cells. The core insight is that the immune system has already spent a lifetime selecting and validating the most effective antibodies, providing a superior, de-risked starting point for new human therapeutics.

To build truly dynamic "virtual cells," two key technological hurdles must be overcome. First, developing high-throughput methods for measuring proteins, the cell's functional units. Second, inventing a sequencing technology that can measure the state of the *same cell* at multiple time points without destroying it.

Traditional methods like crystallography are slow and analyze purified proteins outside their native environment. A-muto's platform uses proteomics and AI to analyze thousands of protein conformations in living disease models, capturing a more accurate picture of disease biology and identifying novel targets.

John Baker says the immune system shifts with breakfast, exercise and circadian rhythms, yet some anchoring features stay consistent for years or decades. IMU wants to separate those stable anchors from the modifiable parts so it can understand disease progression and treatment effects across a population over time.