Note that the proposed Meta-EC generates a more comprehensive community patterns with respect to meta-data since our result is an agreement by consensus of multiple base clustering approaches.
PE read data along with optimized parameters and suitable multiple assembling and clustering approaches were used to find out non-inflated number of assembled transcript sequences with high coverage and average length.
In vitro approaches may be categorized according to the extent to which they inform networks or simple clustering approaches to categorize information from multiple sources.
For such analyses, some advanced clustering approaches have been suggested, for example the utility of transcriptional consensus clusters derived from multiple cluster algorithms [8], or incorporation of prior knowledge of gene function [9].
Furthermore, hierarchical clustering approaches have emerged.
Multiple clustering algorithms (including agglomerative nesting clustering (agnes), divisive analysis clustering (diana), k-means, partitioning around medoids (pam), and hierarchical clustering (hclust)) were applied with a bootstrapping approach.
Exact clustering approaches were recommended.
In addition, Gavin et al. (2006) utilized iterative hierarchical clustering approach multiple times, each time with a different set of parameters, on the SA scored network, which is best classified as the second category.
Recently, Ward et al. have described methods using a soft clustering approach employing multiple Gaussian fits to elemental correlation plots, and assignment of pixel-probability to groups (each represented by a Gaussian) to effectively relax group membership criteria.
As a solution, in [50] an incremental fuzzy clustering approach called incremental multiple medoids-based fuzzy clustering (IMMFC) was proposed, which is based on the idea of OFCM and HOFCMD and includes a mechanism to select multiple medoids instead of a single one to represent each of the clusters in each chunk.
