Machine Learning Meetings and Events
Group Meetings: Group meetings are held Mondays from 11am to Noon (talk starts 11:10am) in D.L. Pratt 290C unless otherwise noted. Meetings are coordinated by Hugo Larochelle.
Tea Talks: Tea talks are held every Wednesday at 4:00pm in D.L. Pratt 290C. Talks should be simple, accessible, and not exceed 15 minutes. Speakers bring snacks, make tea, and provide a copy of the presented paper.
Group Meeting Dec 1, 2008: Inferring RNA Regulatory Codes that Predict Tissue-Dependent Alternative Splicing
- Speaker: Yoseph Barash
- Abstract:
The importance of correct splicing regulation is emphasized by observations that transcripts from most human genes are alternatively spliced in a tissue-dependent manner and that a multitude of disease mutations target splicing signals. However, which of the vast number of possible combinations of RNA sequence features are responsible for regulated splicing outcomes is not understood.
We describe a method for inferring RNA regulatory codes that are predictive of tissue-dependent alternative splicing. Unlike previous methods that identify and analyze one RNA feature at a time, our method automatically extracts multiple biologically informative signals representing diverse types of features that together are maximally predictive of regulated alternative splicing events. Using a dataset from profiling 3700 exons across 27 diverse mouse tissues, we inferred splicing regulatory codes and measured their accuracy for predicting the tissue-dependent patterns of alternative splicing of previously characterized and uncharacterized exons. The inferred codes confirm and extend published observations. Importantly, our analyses reveal that important elements of splicing regulatory code can extend further into introns and involve more varied and complex interactions between sequence features than previously appreciated.
Joint Work with John A. Calarco, Qun Pan, Sidharth Chaudhry, Ofer Shai, Weijun Gao, Benjamin J. Blencowe, Brendan J. Frey