Partition Quantitative Assessment (PQA): A Quantitative Methodology to Assess the Embedded Noise in Clustered Omics and Systems Biology Data

Abstract

Identifying groups that share common features among datasets through clustering analysis is a typical problem in many fields of science, particularly in post-omics and systems biology research. In respect of this, quantifying how a measure can cluster or organize intrinsic groups is important since currently there is no statistical evaluation of how ordered is, or how much noise is embedded in the resulting clustered vector. Much of the literature focuses on how well the clustering algorithm orders the data, with several measures regarding external and internal statistical validation; but no score has been developed to quantify statistically the noise in an arranged vector posterior to a clustering algorithm, i.e., how much of the clustering is due to randomness. Here, we present a quantitative methodology, based on autocorrelation, in order to assess this problem.

Keywords

• omics data
• data clustering
• noise quantification