Focused multidimensional scaling: interactive visualization for exploration of high-dimensional data.

Clustering High-dimensional data Personalized medicine Visualization

Journal

BMC bioinformatics
ISSN: 1471-2105
Titre abrégé: BMC Bioinformatics
Pays: England
ID NLM: 100965194

Informations de publication

Date de publication:
02 May 2019
Historique:
received: 11 12 2018
accepted: 27 03 2019
entrez: 4 5 2019
pubmed: 3 5 2019
medline: 14 6 2019
Statut: epublish

Résumé

Visualization is an important tool for generating meaning from scientific data, but the visualization of structures in high-dimensional data (such as from high-throughput assays) presents unique challenges. Dimension reduction methods are key in solving this challenge, but these methods can be misleading- especially when apparent clustering in the dimension-reducing representation is used as the basis for reasoning about relationships within the data. We present two interactive visualization tools, distnet and focusedMDS, that help in assessing the validity of a dimension-reducing plot and in interactively exploring relationships between objects in the data. The distnet tool is used to examine discrepancies between the placement of points in a two dimensional visualization and the points' actual similarities in feature space. The focusedMDS tool is an intuitive, interactive multidimensional scaling tool that is useful for exploring the relationships of one particular data point to the others, that might be useful in a personalized medicine framework. We introduce here two freely available tools for visually exploring and verifying the validity of dimension-reducing visualizations and biological information gained from these. The use of such tools can confirm that conclusions drawn from dimension-reducing visualizations are not simply artifacts of the visualization method, but are real biological insights.

Sections du résumé

BACKGROUND BACKGROUND
Visualization is an important tool for generating meaning from scientific data, but the visualization of structures in high-dimensional data (such as from high-throughput assays) presents unique challenges. Dimension reduction methods are key in solving this challenge, but these methods can be misleading- especially when apparent clustering in the dimension-reducing representation is used as the basis for reasoning about relationships within the data.
RESULTS RESULTS
We present two interactive visualization tools, distnet and focusedMDS, that help in assessing the validity of a dimension-reducing plot and in interactively exploring relationships between objects in the data. The distnet tool is used to examine discrepancies between the placement of points in a two dimensional visualization and the points' actual similarities in feature space. The focusedMDS tool is an intuitive, interactive multidimensional scaling tool that is useful for exploring the relationships of one particular data point to the others, that might be useful in a personalized medicine framework.
CONCLUSIONS CONCLUSIONS
We introduce here two freely available tools for visually exploring and verifying the validity of dimension-reducing visualizations and biological information gained from these. The use of such tools can confirm that conclusions drawn from dimension-reducing visualizations are not simply artifacts of the visualization method, but are real biological insights.

Identifiants

pubmed: 31046657
doi: 10.1186/s12859-019-2780-y
pii: 10.1186/s12859-019-2780-y
pmc: PMC6498510
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

221

Subventions

Organisme : NIGMS NIH HHS
ID : R25 GM086262
Pays : United States
Organisme : Deutsche Forschungsgemeinschaft
ID : SFB 1036

Références

Bioinformatics. 2001 Apr;17(4):309-18
pubmed: 11301299
Proc Natl Acad Sci U S A. 2001 Jul 31;98(16):8961-5
pubmed: 11470909
Funct Integr Genomics. 2000 Nov;1(3):156-73
pubmed: 11793234
Bioinformatics. 2002 Nov;18(11):1462-9
pubmed: 12424117
Bioinformatics. 2005 May 15;21(10):2546-7
pubmed: 15713738
Bioinformatics. 2006 Jun 15;22(12):1540-2
pubmed: 16595560
IEEE Trans Vis Comput Graph. 2011 Dec;17(12):2301-9
pubmed: 22034350
Science. 2015 Mar 6;347(6226):1138-42
pubmed: 25700174
Oncotarget. 2017 May 5;8(34):56338-56350
pubmed: 28915594
Nat Biotechnol. 2018 Jun;36(5):411-420
pubmed: 29608179

Auteurs

Lea M Urpa (LM)

Institute for Molecular Medicine Finland (FIMM), University of Helsinki, Helsinki, Finland.

Simon Anders (S)

Institute for Molecular Medicine Finland (FIMM), University of Helsinki, Helsinki, Finland. s.anders@zmbh.uni-heidelberg.de.
Center for Molecular Biology of the University of Heidelberg (ZMBH), Heidelberg, Germany. s.anders@zmbh.uni-heidelberg.de.

Articles similaires

Robotic Surgical Procedures Animals Humans Telemedicine Models, Animal

Odour generalisation and detection dog training.

Lyn Caldicott, Thomas W Pike, Helen E Zulch et al.
1.00
Animals Odorants Dogs Generalization, Psychological Smell

Selecting optimal software code descriptors-The case of Java.

Yegor Bugayenko, Zamira Kholmatova, Artem Kruglov et al.
1.00
Software Algorithms Programming Languages
Animals TOR Serine-Threonine Kinases Colorectal Neoplasms Colitis Mice

Classifications MeSH