Episode: 42 - Machine Learning Informatics for Antibody Discovery

The Chain: Protein Engineering Podcast

Innhold levert av Cambridge Healthtech Institute. Alt podcastinnhold, inkludert episoder, grafikk og podcastbeskrivelser, lastes opp og leveres direkte av Cambridge Healthtech Institute eller deres podcastplattformpartner. Hvis du tror at noen bruker det opphavsrettsbeskyttede verket ditt uten din tillatelse, kan du følge prosessen skissert her https://no.player.fm/legal.

1+ y ago 36:04

MP3•Episoder hjem

Charlotte Deane, professor of structural bioinformatics at the University of Oxford and upcoming speaker at the 14th Annual PEGS Europe Conference in Barcelona, joins moderator Brandon DeKosky, assistant professor of chemical engineering at the Massachusetts Institute of Technology, to discuss the use of machine learning in antibody structure prediction.

In this episode, Deane talks about her lab's AI tools for high-throughput prediction pipelines and why collecting general antibody property data will produce better models. She also speaks about the importance of using and building publicly available data sets and her thoughts on what it will take to finally generate a complete antibody design from a computer.
Links from this episode:
University of Oxford Department of Statistics
SAbDAb: The Structural Antibody Database
PEGS Europe
The Critical Assessment of protein Structure Prediction (CASP)

65 episoder

#Science #Biology #Cambridge Healthtech Institute #Proteins #Protein Engineering #Scientists #RD In #Antibodies #Bispecific Antibodies #Solid Tumors