BROADCASTS.com

Published: Aug. 29, 2023, 7:46 p.m.

# Summary

\n

In our bodies, the Immune system is detecting foreign pathogens or cancer cells, called antigens, with the help of antibody proteins that detect and physically attach to the surface of those cells.

\n

Unfortunately our immune system is not perfect and does not detect all antigens, meaning that the immune system does not have all antigens it would need to detect all cancer cells for example.

\n

Modern cancer therapies like CAR T-cells therapy therefor introduces additional antibody proteins into the system. This is still not enough to beat cancer, because cancer is a very diverse decease with a high variation of mutations between patients, and the antibodies used in CAR T-cell therapy are developed to be for a cancer type or patient group, but not for individual patience.

\n

\n

Today on the austrian AI podcast I am talking to Moritz Sch\xe4fer who is working on applying Diffusion Models to predict protein structures that support the development of patient specific, and therefore cancer mutation specific antibodies. This type of precision medicine would enable a higher specificity of cancer Therapie and will hopefully improve Treatment outcome.

\n

\n

Existing DL systems like Alpha Fold and alike fall short in predicting the structure of antibody binding sites, primarily due to lack of training data. So there room for improvement, and Moritz work is focused on applying Diffusion Models (so models like DALL-E or Stable Diffusion), which are most well known for their success in generating images, to problem of protein prediction. Diffusion models are generative models that generate samples from their training distribution based on an iterative process of several hundred steps. Where one starts, in case of image generation from pure noise, and in each step replaces noise with something that is closer to the training data distribution.

\n

\n

In Moritz work, they apply classifier guided Diffusion models to generate 3d antibody protein structures.

\n

This means that in the iterative process of a diffusion model where in each step small adjustments are performed, a classifier nudges the changes towards increasing the affinity of the predicted protein to the specific antigen.

\n

\n

# TOC

\n

00:00:00 Beginning

\n

00:03:23 Guest Introduction

\n

00:06:37 The AI Institute at the UniWien

\n

00:07:57 Protein Structure Prediction

\n

00:10:57 Protein Antibodies in Caner Therapy

\n

00:16:17 How precision medicine is applied in cancer Therapy

\n

00:22:17 Lack of training data for antibody protein design

\n

00:30:44 How Diffusion models can be applied in protein design

\n

00:46:06 Classifier based Diffusion Models

\n

00:51:18 Future in prediction medicine

\n

\n

# Sponsors

\n

Quantics: Supply Chain Planning for the new normal - the never normal - https://quantics.io/

\n

Belichberg GmbH: We do digital transformations as your innovation partner - https://belichberg.com/

\n

\n

# References

\n

Moritz Schaefer - https://www.linkedin.com/in/moritzschaefer/

\n

Unser Institut -\xa0[https://www.meduniwien.ac.at/ai/de/contact.php](https://www.meduniwien.ac.at/ai/de/contact.php)

\n

Lab website -\xa0[https://www.bocklab.org/](https://www.bocklab.org/)

\n

LLM bio paper:\xa0[https://www.biorxiv.org/content/10.1101/2023.06.16.545235v1](https://www.biorxiv.org/content/10.1101/2023.06.16.545235v1)

\n

Diffusion Models - https://arxiv.org/pdf/2105.05233.pdf

\n

Diffusion Models (Computerphile) - https://www.youtube.com/watch?v=1CIpzeNxIhU