Two trends in the antibody discovery field underscore Iain Rogers’s presentation: the difficulty in securing new funding for biologics discovery and the growing interest in AI-integrated technologies.
For Rogers, although AI is not a panacea for discovery efforts, it can have specific use cases: “I'm a bit of an AI pessimist, I have to admit. But I do think that at this stage in 2024, there are very specific applications for AI, very specific ways that we can use it. And I'm also a mass spectrometry nerd. So, I'm going to talk about using AI and mass spectrometry together”
This presentation begins by taking stock of key challenges for antibody discovery: finding new antibodies, de-risking discovery, and easing downstream production. Then, Rogers shares a COVID-era case study where a large number of PBMCs were reduced to 187 sequences, resulting in 9 ACE2-blocking antibodies.
Although this workflow has proved successful, Rogers pointed out that the majority of funding is spent at the end stage: “and 95% of it is spent on clones that were not ultimately selected.”
Rogers instead suggested starting with a far broader diversity of antibodies and using exciting new technology to narrow down to more successful candidates. He details a high-level method involving immunization, purification, functional testing, and sequencing using mass spectrometry and AI to do so.
In particular, Rogers dives into the protein sequencing process, including digestion, liquid chromatography, and tandem mass spectrometry. Furthermore, he advocates for expanding the search for antibodies by considering natural immune responses and different species.
Finally, the presentation emphasizes the need for high-throughput detailed analyses to inform downstream choices, highlighting a new AI partnership for epitope mapping.
