Artwork

Content provided by AIRR-Community. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by AIRR-Community or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ppacc.player.fm/legal.
Player FM - Podcast App
Go offline with the Player FM app!

On AIRR 17: Data over algorithms: key lessons from the Immune Epitope Database with Bjoern Peters

43:46
 
Share
 

Manage episode 473099533 series 3328144
Content provided by AIRR-Community. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by AIRR-Community or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ppacc.player.fm/legal.

In this episode of On AIRR, Dr. Bjoern Peters, Professor at the La Jolla Institute for Immunology (LJI), explores how high-quality data serves as the foundation for advancing AI-based immunological predictions and diagnostics.

Originally from Germany, Dr. Peters began his academic journey in theoretical physics at Hamburg, focusing on quantum optics, before pivoting to biophysics during his PhD at Humboldt University. This shift was inspired by the challenge of understanding epitope presentation pathways and the limitations of epitope-prediction algorithms, which led him to work with Dr. Alessandro Sette at LJI to develop the Immune Epitope Database (IEDB) — the world’s largest resource for immune epitope data.

Throughout the conversation, Dr. Peters traces the evolution of epitope research, starting with his work on MHC-peptide binding predictions and expanding into broader immunological data collection. He emphasizes that high-quality datasets often outcompete algorithmic improvements and shares the story of how the IEDB was established to consolidate immune epitope data. The conversation explores the status of data standardization and use of ontologies in structuring biomedical data, particularly in immunology. Dr. Peters highlights how work done by the IEDB and the Adaptive Immune Receptor Repertoire Community (AIRR-C) in these areas is critical for advancing immunology and enabling prediction and diagnostics. Finally, the discussion covers challenges of predicting epitopes from immune repertoires, the growing interest in using AIRR sequencing for diagnostics, and the importance of rigorous, unbiased validation of prediction models for clinical applications.

Comments are welcome to the inbox of [email protected] or on social media under the tag #onAIRR. Further information can be found here: https://www.antibodysociety.org/the-airr-community/airr-c-podcast.

The episode is hosted by Dr. Ulrik Stervbo and Dr. Zhaoqing Ding.

Announcements and links

  continue reading

17 episodes

Artwork
iconShare
 
Manage episode 473099533 series 3328144
Content provided by AIRR-Community. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by AIRR-Community or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ppacc.player.fm/legal.

In this episode of On AIRR, Dr. Bjoern Peters, Professor at the La Jolla Institute for Immunology (LJI), explores how high-quality data serves as the foundation for advancing AI-based immunological predictions and diagnostics.

Originally from Germany, Dr. Peters began his academic journey in theoretical physics at Hamburg, focusing on quantum optics, before pivoting to biophysics during his PhD at Humboldt University. This shift was inspired by the challenge of understanding epitope presentation pathways and the limitations of epitope-prediction algorithms, which led him to work with Dr. Alessandro Sette at LJI to develop the Immune Epitope Database (IEDB) — the world’s largest resource for immune epitope data.

Throughout the conversation, Dr. Peters traces the evolution of epitope research, starting with his work on MHC-peptide binding predictions and expanding into broader immunological data collection. He emphasizes that high-quality datasets often outcompete algorithmic improvements and shares the story of how the IEDB was established to consolidate immune epitope data. The conversation explores the status of data standardization and use of ontologies in structuring biomedical data, particularly in immunology. Dr. Peters highlights how work done by the IEDB and the Adaptive Immune Receptor Repertoire Community (AIRR-C) in these areas is critical for advancing immunology and enabling prediction and diagnostics. Finally, the discussion covers challenges of predicting epitopes from immune repertoires, the growing interest in using AIRR sequencing for diagnostics, and the importance of rigorous, unbiased validation of prediction models for clinical applications.

Comments are welcome to the inbox of [email protected] or on social media under the tag #onAIRR. Further information can be found here: https://www.antibodysociety.org/the-airr-community/airr-c-podcast.

The episode is hosted by Dr. Ulrik Stervbo and Dr. Zhaoqing Ding.

Announcements and links

  continue reading

17 episodes

All episodes

×
 
Loading …

Welcome to Player FM!

Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.

 

Quick Reference Guide

Listen to this show while you explore
Play