Comparing Machine Learning Methods for Gene Expression Data
Author Information
Author(s): Pirooznia Mehdi, Yang Jack Y, Yang Mary Qu, Deng Youping
Primary Institution: University of Southern Mississippi
Hypothesis
Which machine learning methods are most effective for classifying microarray gene expression data?
Conclusion
The study found that the choice of feature selection methods and the number of genes significantly influence the success of classification in gene expression data.
Supporting Evidence
- The study applied various classification methods including SVM and neural networks to analyze gene expression data.
- Results showed that feature selection methods significantly impacted classification accuracy.
- Eight different datasets were used to evaluate the performance of the methods.
Takeaway
This study looked at different ways to sort genes and found that picking the right genes helps scientists better understand diseases like cancer.
Methodology
The study compared various classification, clustering, and feature selection methods using eight publicly available microarray datasets.
Limitations
The performance of classification methods may vary depending on the dataset, and the study did not explore all possible methods.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website