Sparse discriminative latent characteristics for predicting cancer drug sensitivity

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

• David Knowles (Stanford University)
• Friday 10 January 2014, 11:00-12:00
• Engineering Department, CBL Room BE-438.

If you have a question about this talk, please contact Zoubin Ghahramani.

This talk has been canceled/deleted

Various recent experimental studies have involved assaying the sensitivity of a range of cancer cell lines to an array of anti-cancer therapeutics. Alongside these sensitivity measurements high dimensional molecular characterisation of the cell lines is typically available, including gene expression measurements, copy number variation and genetic mutations. We propose a sparse multitask regression model which learns discriminative latent characteristics which are highly predictive of drug sensitivity and predictable from molecular features. We use ideas from Bayesian nonparametrics to automatically infer the appropriate number of these latent characteristics. An extension using a binary MRF allows additional prior knowledge, for example which drugs have shared inhibition targets, to be incorporated.

This talk is part of the Machine Learning @ CUED series.

This talk is included in these lists:

This talk is not included in any other list

Note that ex-directory lists are not shown.