The Importance of Language Models in Antibodies

4min Snip

00:00

Play full episode

Summary

Transcript

Episode notes

The models that you're building are certainly not limited to one particular application or one particular modality. So we want to provide the model, for example, with some structural information. This is a departure from, let's say, a traditional language model that's just in the sequence space. We're really thinking about how do we bring in meaningful information about that target protein structure so that we can really focus the model on that. I think this is something that's maybe more unique within the AI space, right? This requires really deep thought about how do you best apply AI to these problems.

Drug development is an extremely expensive endeavor, in large part because of the 96% failure rate of clinical drug trials. However, the new frontier of medicine has arrived, and Sean McClain and Joshua Meier (respectively the Founder/CEO and Chief Artificial Intelligence (AI) Officer of Absci) are leading the charge. Absci is a public company harnessing generative AI to create more effective medicines faster and less expensively. During this episode, Sean and Joshua explain how their pooled approach to antibody production works, why they focus so heavily on data, the metrics they use to evaluate their models, and why they are certain that personalized medicine is going to be a reality in the future. There are countless possible mashups of AI and drug discovery, and Absci attempts to bring an innovative approach to biologics to positively impact human health!

“We’re not just developing AI within biologic drug discovery for the sake of it. We’re really wanting to utilize this to be able to discover new biology.” — @SeanRMcClain Key Points From This Episode:

Sean’s original idea behind the founding of Absci and how it has evolved into what it is today.
How Absci is making the process of drug creation much more efficient.
The career path that led Josh to Absci.
How antibodies are currently produced.
The most important aspects to consider when developing an antibody.
A high-level overview of how Absci generates data.
The number of AI-generated designs that Absci can validate in any given week.
Metrics that Absci uses to evaluate their models.
What humanization is in the context of antibody design.
Understanding Absci’s naturalness model.
A common problem in the AI field.
The potential for collaboration with Big Pharma.
How the models Absci is developing can be applied in different contexts.
Sean and Joshua’s thoughts on what the future of medicine is going to look like.
How AI is likely to change the way we approach scientific and technological developments.