Skip to main content

Deciphering the cis-regulatory code that guides development using interpretable deep learning

Presentation

Organizer: IRB BioMed Seminars

Date: Friday, 7th July at 12:00h

Place: Fèlix Serratosa, PCB

Speaker:   Dr Julia Zeitlinger, Investigator at the Stowers Institute for Medical Research and Associate Professor at the University of Kansas Medical Center.

https://research.stowers.org/zeitlingerlab/people/julia-zeitlinger.html

Title: “Deciphering the cis-regulatory code that guides development using interpretable deep learning”

Host:  Dr Marco Milán - Programme Chair - Group Leader IRB Barcelona - Development and Growth Control LAB - Mechanisms of Disease Programme.

Host:  Dr Gerardo Jiménez, ICREA Research Professor,  Group Leader - Gene Expression and Signaling Research Group | IBMB (csic.es)

 

Abstract:  

The cis-regulatory code that instructs gene regulation during development, also known as the genome’s second code, is a fundamentally unresolved problem. Recent progress has provided proof-of-principle evidence that this complex cis-regulatory code can be learned with neural networks. The new approach is fundamentally different from traditional methods in that the sequence rules are learned inside a black box directly from genomic sequences through their ability to better predict a specific genomics data set. This dramatically improves the predictive performance, but requires rigorous approaches for extracting, understanding and validating the learned sequence rules to make sure that they represent biology. I will describe how we use this approach using mouse or Drosophila development as model systems and uncover unexpected sequence rules that we can validate with experiments. 

 

IRB BioMed Seminars

IMPORTANT: For attendees outside the PCB community you must register at least 24h before the seminar.

 

 

 

Registration