Linear Separability of Gene Expression Dataset

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

• Dr. Benny Chor (University of Tel-Aviv)
• Wednesday 18 October 2006, 14:00-15:00
• MR5, DAMTP.

If you have a question about this talk, please contact Danielle Stretch.

We examine simple geometric properties of gene expression datasets, where samples are taken from two distinct classes (e.g. two types of cancer). Specifically, the problem of linear separability for pairs of genes is investigated. We developed and implemented novel, highly efficient algorithmic tools for finding all pairs of genes that induce a linear separation of the two sample classes. These tools are based on computational geometric properties, and were applied to ten publicly available cancer datasets. We discovered that seven out of the ten datasets examined are highly separable. Statistically, this phenomenon is highly significant, and is very unlikely to occur at random.

This talk is part of the Computational and Systems Biology series.

This talk is included in these lists:

• All CMS Events
• All Talks (aka the CURE list)
• Biology
• CamBridgeSens
• Cambridge talks
• Computational and Systems Biology
• Graduate-Seminars
• Life Science Interface Seminars
• Life Sciences
• Life Sciences
• ME Seminar
• MR5, DAMTP
• PMRFPS's
• School of Physical Sciences
• Trust & Technology Initiative - interesting events
• custom
• my_list
• other talks
• se393's list

Note that ex-directory lists are not shown.