CMA: A Bioconductor Package for Classifying High-Dimensional Data
Author Information
Author(s): Martin Slawski, Alfred-Ludwig Boulesteix, Daumer M
Primary Institution: Sylvia Lawry Centre for Multiple Sclerosis Research, Munich, Germany
Hypothesis
Can a new Bioconductor package improve classification accuracy for high-dimensional data?
Conclusion
CMA is a user-friendly package that simplifies classifier construction and evaluation for high-dimensional data.
Supporting Evidence
- CMA provides an overview of the unbiased accuracy of top-performing classifiers.
- The package includes over twenty different classifiers and various evaluation schemes.
- CMA automates hyperparameter tuning to prevent bias in model selection.
- Users can visualize results easily with built-in functions.
Takeaway
CMA helps scientists easily classify data with many variables, like genes, without needing to be experts in statistics.
Methodology
The CMA package automates variable selection, parameter tuning, classifier construction, and evaluation using various methods.
Potential Biases
Inexperienced users may introduce errors by not understanding the tuning parameters or data formats.
Limitations
The package may not perform well with very small sample sizes or when users do not follow good practices in model selection.
Participant Demographics
The study involved 65 samples from four tumor classes.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website