DATA 522 Mining Gene and Protein Expression Data

Focus on data science methods that can efficiently and effectively deal with high-dimensional genomic and proteomic data. Topics may include: supervised feature selection, proper methods of model building and validation, discriminant analysis, support vector machines, bagging, random forests and ensemble approach to feature selection and classification.

Credits

4

Prerequisite

DATA 521 or permission of department chair.

General Education

Offered

  • Spring
  • On Demand