Tristan Free

speaker

289 appearances 6 recordings 1 series first heard Jun 2026 last heard 23 Jul

Tristan Free’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months

Recordings per month over the last 12 months — 6 in all, peaking in Jun 2026 with 4.

Appearances

newest first · ▶ plays the moment

Talking Techniques · AI & Antibodies mini-series | Reducing antibody viscosity to improve subcutaneous delivery · 15 Jun 2026 podcast

With those um those those practical parameters that you'd need to set, is there somewhere that peop people can is that in the methods section of your paper or where's that available?

Fantastic.

Um and then your your latest paper presents a more zoomed-in look at a panel of clinical stage IgG one and IgG four antibodies um using charge-stabilized self-interaction nanoparticle spectroscopy to measure antibody self-association under varying conditions and then uses this information to train.

uh more machine learning models to predict this property.

Um and and sorry, that that property of self-association.

So firstly, did the models you trained here, did they build on that previous model or were they kind of like a totally new thing that you had developed?

Um and if so, well either way, how did they kind of improve on that first model?

Wow.

So um yeah, r a really uh a a really useful level of um of accuracy for these these models in terms of what they can predict for you.

In terms of the actual sort of the the physical characteristics of the antibodies or the kind of um molecular characteristics of the antibody, um what what did you identify as being most important um in predicting self association?

And and were there any surprises there?

Uh and then th there's also the kind of external factors to consider.

So, you know, what solution are you putting it in and and all of that kind of thing.

So what um

In that side of thing, what what kind of factors external to the antibody itself did you identify as being most important?

Uh and again, yeah, any surprises there.

Fantastic.

Yeah, it's it's good to see the kind of the predictions and investigations you're you're making turn up with something that that already exists 'cause it's been um sort of tried down the ages to to find the perfect formulation.

Yeah, fantastic.

Showing 141–160 of 289 · page 8 of 15