Clustering gene expression data with a penalized graph-based metric
2011

New Metric for Clustering Gene Expression Data

publication Evidence: moderate

Author Information

Author(s): BayĆ” Ariel, Granitto Pablo M

Primary Institution: CIFASIS French Argentine International Center for Information and Systems Sciences

Hypothesis

Can the Penalized k-Nearest-Neighbor-Graph (PKNNG) metric improve clustering results for gene expression data?

Conclusion

The PKNNG metric shows promising clustering results and can enhance the performance of traditional clustering methods.

Supporting Evidence

  • The PKNNG metric can be used with various clustering algorithms.
  • Clustering results on artificial datasets showed improved performance with the PKNNG metric.
  • The method allows researchers to use familiar clustering techniques without needing to learn new methods.

Takeaway

This study introduces a new way to group genes based on their expression data, making it easier for researchers to understand complex biological information.

Methodology

The study uses a two-step method to create a k-Nearest-Neighbor-Graph and applies penalized weights to connect subgraphs.

Limitations

The study does not address the problem of determining the optimal number of clusters.

Digital Object Identifier (DOI)

10.1186/1471-2105-12-2

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication