Article
Biological Domain Knowledge Based Feature Selection, Applied on Gene Expression Data
Search Medline for
Authors
Published: | February 26, 2021 |
---|
Outline
Text
In biological data analysis, most of the computational feature selection methodologies (that use machine learning) were taken from other fields, without considering the nature of the biological data. In this talk, we review existing feature ranking and feature selection approaches that are based on the biological knowledge. One of the goals of the current talk is to encourage the bioinformatics community to reconsider how feature selection in biological datasets can benefit from the effective use of the biological and biomedical relationships of the features during the selection process.
I will present our related works in this topic as such SVM-RCE, SVM-RNE, and maTE.
The authors declare that they have no competing interests.
The authors declare that an ethics committee vote is not required.