University of Birmingham > Talks@bham > CCB seminars > A biased story of diagnosing rare disease and finding the drugs to treat them

A biased story of diagnosing rare disease and finding the drugs to treat them

Add to your list(s) Download to your calendar using vCal

  • UserDr. Robert Hoehndorf, King Abdullah University of Science and Technology (KAUST)
  • ClockWednesday 09 February 2022, 12:00-13:00
  • Houseonline via zoom.

If you have a question about this talk, please contact Jordan McCormick.

Rare diseases, while individually rare, affect around 6% of the population and often have a genetic basis. Diagnosis of rare diseases is challenging and requires a combination of clinical and molecular information together with a large volume of background knowledge about molecular and pathophysiological pathways. Often, once a diagnosis has been made for an individual with a rare disease, only symptomatic or palliative treatments are available. Repurposing approved drugs may offer a solution. I will talk about our work on using machine learning methods that combine background knowledge with molecular data to diagnose rare diseases and find drugs for specific protein targets. I will introduce machine learning methods to find gene-disease associations, variants that cause specific sets of phenotypes, and the state of the art method DTI -Voodoo to identify drugs that target a specific protein. However, I will spend a large part of my talk focusing on biases in data and pitfalls in applying machine learning methods, and some ways to detect and avoid them.

About the speaker: Robert Hoehndorf is an Associate Professor in Computer Science at King Abdullah University of Science and Technology (KAUST) in Thuwal. Prior to joining KAUST , Robert had research positions at Aberystwyth University, the University of Cambridge, the European Bioinformatics Institute, and the Max Planck Institute for Evolutionary Anthropology. His research focuses on the development and application of knowledge-based algorithms in biology and biomedicine.

This talk is part of the CCB seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

Talks@bham, University of Birmingham. Contact Us | Help and Documentation | Privacy and Publicity.
talks@bham is based on talks.cam from the University of Cambridge.