Statistical significance for hierarchical clustering in genetic association and microarray expression studies

Levenstien, Mark A; Yang, Yaning; Ott, Jürg

doi:10.1186/1471-2105-4-62

Cited by 25 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our method differs substantially from the approach of “bootstrap p -values” implemented in the R package pvclust (Suzuki and Shimodaira, 2006 ), that provides a level of significance for each clade of the dendrogram. Similar approaches to detect the significance levels of each individual cluster have been proposed in (Levenstien et al, 2003 ; Park et al, 2009 ). Our approach provides a simple heuristic to decide whether there are clusters, and where to cut the dendrogram to detect these clusters.…”

Section: Discussionmentioning

confidence: 98%

Detection of Significant Groups in Hierarchical Clustering by Resampling

Sebastiani

Perls

2016

Front. Genet.

View full text Add to dashboard Cite

Hierarchical clustering is a simple and reproducible technique to rearrange data of multiple variables and sample units and visualize possible groups in the data. Despite the name, hierarchical clustering does not provide clusters automatically, and “tree-cutting” procedures are often used to identify subgroups in the data by cutting the dendrogram that represents the similarities among groups used in the agglomerative procedure. We introduce a resampling-based technique that can be used to identify cut-points of a dendrogram with a significance level based on a reference distribution for the heights of the branch points. The evaluation on synthetic data shows that the technique is robust in a variety of situations. An example with real biomarker data from the Long Life Family Study shows the usefulness of the method.

show abstract

Section: Discussionmentioning

confidence: 98%

Detection of Significant Groups in Hierarchical Clustering by Resampling

Sebastiani

Perls

2016

Front. Genet.

View full text Add to dashboard Cite

show abstract

“…Complementary, more robust clustering approaches could be used [e.g. ( Gesteira Costa Filho, 2008 ; Levenstien et al , 2003 )] to enhance the robustness of RAmPART. Alternatively, instead of using region-based proposal densities, Hamiltonian Monte–Carlo methods ( Graham and Storkey, 2017 ; Hoffman and Gelman, 2014 ) might be employed for the different temperatures.…”

Section: Discussionmentioning

confidence: 99%

Bayesian parameter estimation for biochemical reaction networks using region-based adaptive parallel tempering

et al. 2018

View full text Add to dashboard Cite

MotivationMathematical models have become standard tools for the investigation of cellular processes and the unraveling of signal processing mechanisms. The parameters of these models are usually derived from the available data using optimization and sampling methods. However, the efficiency of these methods is limited by the properties of the mathematical model, e.g. non-identifiabilities, and the resulting posterior distribution. In particular, multi-modal distributions with long valleys or pronounced tails are difficult to optimize and sample. Thus, the developement or improvement of optimization and sampling methods is subject to ongoing research.ResultsWe suggest a region-based adaptive parallel tempering algorithm which adapts to the problem-specific posterior distributions, i.e. modes and valleys. The algorithm combines several established algorithms to overcome their individual shortcomings and to improve sampling efficiency. We assessed its properties for established benchmark problems and two ordinary differential equation models of biochemical reaction networks. The proposed algorithm outperformed state-of-the-art methods in terms of calculation efficiency and mixing. Since the algorithm does not rely on a specific problem structure, but adapts to the posterior distribution, it is suitable for a variety of model classes.Availability and implementationThe code is available both as Supplementary Material and in a Git repository written in MATLAB.Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

Genetic pathway‐based hierarchical clustering analysis of older adults with cognitive complaints and amnestic mild cognitive impairment using clinical and neuroimaging phenotypes

Sloan

Shen

West

et al. 2010

American J of Med Genetics Pt B

View full text Add to dashboard Cite

Hierarchical clustering is frequently used for grouping results in expression or haplotype analyses. These methods can elucidate patterns between measures that can then be applied to discerning their validity in discriminating between experimental conditions. Here a hierarchical clustering method is used to analyze the results of an imaging genetics study using multiple brain morphology and cognitive testing endpoints for older adults with amnestic mild cognitive impairment (MCI) or cognitive complaints (CC) compared to healthy controls (HC). The single nucleotide polymorphisms (SNPs) are a subset of those included on a larger array that are found in a reported Alzheimer's disease (AD) and neurodegeneration pathway. The results indicate that genetic models within the endpoints cluster together, while there are 4 distinct sets of SNPs that NIH Public Access Author ManuscriptAm J Med Genet B Neuropsychiatr Genet. Author manuscript; available in PMC 2011 July 1. NIH-PA Author ManuscriptNIH-PA Author Manuscript NIH-PA Author Manuscript differentiate between the endpoints, with most significant results associated with morphology endpoints rather than cognitive testing of patients' reported symptoms. The genes found in at least one cluster are ABCB1, APBA1, BACE1, BACE2, BCL2, BCL2L1, CASP7, CHAT, CST3, DRD3, DRD5, IL6, LRP1, NAT1, and PSEN2. The greater associations with morphology endpoints suggests that changes in brain structure can be influenced by an individual's genetic background in the absence of dementia and in some cases (Cognitive Complaints group) even without those effects necessarily being detectable on commonly used clinical tests of cognition. The results are consistent with polygenic influences on early neurodegenerative changes and demonstrate the effectiveness of hierarchical clustering in identifying genetic associations among multiple related phenotypic endpoints.

show abstract

Statistical significance for hierarchical clustering in genetic association and microarray expression studies

Cited by 25 publications

References 20 publications

Detection of Significant Groups in Hierarchical Clustering by Resampling

Detection of Significant Groups in Hierarchical Clustering by Resampling

Bayesian parameter estimation for biochemical reaction networks using region-based adaptive parallel tempering

Genetic pathway‐based hierarchical clustering analysis of older adults with cognitive complaints and amnestic mild cognitive impairment using clinical and neuroimaging phenotypes

Contact Info

Product

Resources

About