A probabilistic theory of clustering

Dougherty, Edward R.; Brun, Marcel

doi:10.1016/j.patcog.2003.10.003

Cited by 54 publications

(44 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We agree with Dougherty and Brun [19,15] that "validation" of clustering results is a heuristic process, even though there are some interesting efforts to objectively incorporate biological knowledge in this process using Gene Ontology, especially when one is clustering gene expression profiles [17,23]. However, to illustrate the usefulness of our software, we collected several examples in which the performance of Simcluster can be considered as qualitatively superior to some traditional approaches imported from the microarray analysis field.…”

Section: Resultssupporting

confidence: 65%

Simcluster: clustering enumeration gene expression data on the simplex space

et al. 2007

View full text Add to dashboard Cite

Transcript enumeration methods such as SAGE, MPSS, and sequencingby-synthesis EST "digital northern", are important high-throughput techniques for digital gene expression measurement. As other counting or voting processes, these measurements constitute compositional data exhibiting properties particular to the simplex space where the summation of the components is constrained. These properties are not present on regular Euclidean spaces, on which hybridization-based microarray data is often modeled. Therefore, pattern recognition methods commonly used for microarray data analysis may be noninformative for the data generated by transcript enumeration techniques since they ignore certain fundamental properties of this space. Here we present a software tool, Simcluster, designed to perform clustering analysis for data on the simplex space. We present Simcluster as a stand-alone command-line C package and as a user-friendly on-line tool. Both versions are available at: http://xerad.systemsbiology.net/simcluster. Simcluster is designed in accordance with a well-established mathematical framework for compositional data analysis, which provides principled procedures for dealing with the simplex space, and is thus

show abstract

Section: Resultssupporting

confidence: 65%

Simcluster: clustering enumeration gene expression data on the simplex space

et al. 2007

View full text Add to dashboard Cite

show abstract

“…Using a model-based approach and a probabilistic theory of clustering as operators on random sets, we assume the points to be clustered belong to a realization of a labeled point process, and define a cluster algorithm, also called a label operator, as a mapping that assigns to every set a label function [54]. K-means, hierarchical, fuzzy C-means, selforganizing maps, and other algorithms, together with their different parameters, are different label operators.…”

Section: Clusteringmentioning

confidence: 99%

“…Historically, cluster operators have not been learned from data, but they can be [54]. Here we consider error estimation.…”

Section: Clusteringmentioning

confidence: 99%

Validation of Computational Methods in Genomics

Doughtery

Jiang²,

Bittner³

2007

View full text Add to dashboard Cite

High-throughput technologies for genomics provide tens of thousands of genetic measurements, for instance, gene-expression measurements on microarrays, and the availability of these measurements has motivated the use of machine learning (inference) methods for classification, clustering, and gene networks. Generally, a design method will yield a model that satisfies some model constraints and fits the data in some manner. On the other hand, a scientific theory consists of two parts: (1) a mathematical model to characterize relations between variables, and (2) a set of relations between model variables and observables that are used to validate the model via predictive experiments. Although machine learning algorithms are constructed to hopefully produce valid scientific models, they do not ipso facto do so. In some cases, such as classifier estimation, there is a well-developed error theory that relates to model validity according to various statistical theorems, but in others such as clustering, there is a lack of understanding of the relationship between the learning algorithms and validation. The issue of validation is especially problematic in situations where the sample size is small in comparison with the dimensionality (number of variables), which is commonplace in genomics, because the convergence theory of learning algorithms is typically asymptotic and the algorithms often perform in counter-intuitive ways when used with samples that are small in relation to the number of variables. For translational genomics, validation is perhaps the most critical issue, because it is imperative that we understand the performance of a diagnostic or therapeutic procedure to be used in the clinic, and this performance relates directly to the validity of the model behind the procedure. This paper treats the validation issue as it appears in two classes of inference algorithms relating to genomics -classification and clustering. It formulates the problem and reviews salient results.

show abstract

“…In existing methods, time series classification is usually carried out using a clustering algorithm because the number of classes is often unknown. However, clustering is typically a subjective process and can be highly problematic [2,6]. There are several differences between supervised classification and clustering procedures:…”

Section: Introductionmentioning

confidence: 99%

“…(2) Clustering involves partitioning all input data samples into different groups, whereas a classifier assigns a class label to each input sample [6]. (3) In clustering, the key parameter, the number of classes, may need to be specified subjectively.…”

Section: Introductionmentioning

confidence: 99%