Seminars for 2016/17
18 May 2012: Classification in High Throughput Screening (BCS meeting 18 May 2012)
Dr Nick Fieller from Department of Probability & Statistics, University of Sheffield
At 16:50 in 1N1.4.1 .
This paper considers an issue at the earliest stage of drug development in the pharmaceutical industries. Having decided on a disease area and a biochemical pathway to target a search begins for compounds to develop into candidate drugs. Typically high throughput screening experiments are used for the identification and evaluation of compounds. Using a high throughput screen with an automated imaging platform allows a large number of compounds to be tested for relevant biological activity.
Supervised classification methods have important applications in high content screening experiments where they are used to predict which compounds have the potential to be developed into new drugs. The use of supervised classification for high content screening data is investigated and a classification method is proposed for batches of compounds where the rule is updated sequentially using information from the classification of previous batches. This methodology accounts for the possibility that the training data are not a representative sample of the test data and that the underlying group distributions may change as new compounds are analysed.
This event is open to the general public.
<< Back to seminar listing