Format

Send to

Choose Destination
BMC Bioinformatics. 2011 Aug 31;12:358. doi: 10.1186/1471-2105-12-358.

Clustering with position-specific constraints on variance: applying redescending M-estimators to label-free LC-MS data analysis.

Author information

1
Institute of High Energy Physics, Austrian Academy of Sciences, Vienna, Austria.

Abstract

BACKGROUND:

Clustering is a widely applicable pattern recognition method for discovering groups of similar observations in data. While there are a large variety of clustering algorithms, very few of these can enforce constraints on the variation of attributes for data points included in a given cluster. In particular, a clustering algorithm that can limit variation within a cluster according to that cluster's position (centroid location) can produce effective and optimal results in many important applications ranging from clustering of silicon pixels or calorimeter cells in high-energy physics to label-free liquid chromatography based mass spectrometry (LC-MS) data analysis in proteomics and metabolomics.

RESULTS:

We present MEDEA (M-Estimator with DEterministic Annealing), an M-estimator based, new unsupervised algorithm that is designed to enforce position-specific constraints on variance during the clustering process. The utility of MEDEA is demonstrated by applying it to the problem of "peak matching"--identifying the common LC-MS peaks across multiple samples--in proteomic biomarker discovery. Using real-life datasets, we show that MEDEA not only outperforms current state-of-the-art model-based clustering methods, but also results in an implementation that is significantly more efficient, and hence applicable to much larger LC-MS data sets.

CONCLUSIONS:

MEDEA is an effective and efficient solution to the problem of peak matching in label-free LC-MS data. The program implementing the MEDEA algorithm, including datasets, clustering results, and supplementary information is available from the author website at http://www.hephy.at/user/fru/medea/.

PMID:
21884583
PMCID:
PMC3178548
DOI:
10.1186/1471-2105-12-358
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for BioMed Central Icon for PubMed Central
Loading ...
Support Center