A comparative study of different machine learning methods on microarray gene expression data
2008

Comparing Machine Learning Methods for Gene Expression Data

Sample size: 8 publication Evidence: moderate

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)

10.1186/1471-2164-9-S1-S13

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication