Targeted projection pursuit is a type of statistical technique used for exploratory data analysis, information visualization, and feature selection. It allows the user to interactively explore very complex data (typically having tens to hundreds of attributes) to find features or patterns of potential interest.
In this example targeted projection pursuit is being used to explore projections of a gene expression data set. Each of the 122 points corresponds to a sample taken from a cancer tumor of four diagnostic classes (represented by color). For each sample, the expression level of 100 genes was recorded (represented by the axes). The animation shows that TPP is able to separate two of the classes clearly (red and purple), but two others could not be distinguished (blue and green). The position of the axes then indicates the activation of which genes are most associated with each class.
Conventional, or 'blind', projection pursuit, finds the most "interesting" possible projections in multidimensional data, using a search algorithm that optimizes some fixed criterion of "interestingness" – such as deviation from a normal distribution. In contrast, targeted projection pursuit allows the user to explore the space of projections by manipulating data points directly in an interactive scatter plot.
^Faith, Joseph; Robert Mintram; Maia Angelova (2006). "Targeted Projection Pursuit for Visualising Gene Expression Data Classifications" (PDF). Bioinformatics. 22 (21): 2667–267. doi:10.1093/bioinformatics/btl463. PMID 16954139.
^Haddow, Chris; Marcus Durrant; Justin Perry; Joe Faith (2011). "Predicting Functional Residues of Protein Sequence Alignments as a Feature Selection Task". International Journal of Data Mining and Bioinformatics. 5 (6): 691–705. doi:10.1504/IJDMB.2011.045417. PMID 22295751.
^Gibson, Helen; Joe Faith (2011). "Node-Attribute Graph Layout for Small-World Networks". Proceedings of 15th International Conference on Information Visualisation.
^Sujan, Rajbhandari; Joe Faith (2010). "The Use of Linear Projections in the Visual Analysis of Signals in an Indoor Optical Wireless Link". 2010 7th International Symposium on Communication Systems, Networks & Digital Signal Processing (CSNDSP 2010). IEEE. pp. 576–581. doi:10.1109/CSNDSP16145.2010.5580367. ISBN978-1-4244-8858-2.
Further reading
Joe Faith (2007) "Targeted Projection Pursuit for Interactive Exploration of High-Dimensional Data Sets", Proceedings of 11th International Conference on Information Visualisation
External links
imDEV free Excel add-in for targeted projection pursuits using feature selection coupled with PLS and PLS-DA
Targeted Projection Pursuit project page
This statistics-related article is a stub. You can help Wikipedia by expanding it.
targeted, projection, pursuit, type, statistical, technique, used, exploratory, data, analysis, information, visualization, feature, selection, allows, user, interactively, explore, very, complex, data, typically, having, tens, hundreds, attributes, find, feat. Targeted projection pursuit is a type of statistical technique used for exploratory data analysis information visualization and feature selection It allows the user to interactively explore very complex data typically having tens to hundreds of attributes to find features or patterns of potential interest In this example targeted projection pursuit is being used to explore projections of a gene expression data set Each of the 122 points corresponds to a sample taken from a cancer tumor of four diagnostic classes represented by color For each sample the expression level of 100 genes was recorded represented by the axes The animation shows that TPP is able to separate two of the classes clearly red and purple but two others could not be distinguished blue and green The position of the axes then indicates the activation of which genes are most associated with each class Conventional or blind projection pursuit finds the most interesting possible projections in multidimensional data using a search algorithm that optimizes some fixed criterion of interestingness such as deviation from a normal distribution In contrast targeted projection pursuit allows the user to explore the space of projections by manipulating data points directly in an interactive scatter plot Targeted projection pursuit has found applications in DNA microarray data analysis 1 protein sequence analysis 2 graph layout 3 and digital signal processing 4 It is available as a package for the WEKA machine learning toolkit References Edit Faith Joseph Robert Mintram Maia Angelova 2006 Targeted Projection Pursuit for Visualising Gene Expression Data Classifications PDF Bioinformatics 22 21 2667 267 doi 10 1093 bioinformatics btl463 PMID 16954139 Haddow Chris Marcus Durrant Justin Perry Joe Faith 2011 Predicting Functional Residues of Protein Sequence Alignments as a Feature Selection Task International Journal of Data Mining and Bioinformatics 5 6 691 705 doi 10 1504 IJDMB 2011 045417 PMID 22295751 Gibson Helen Joe Faith 2011 Node Attribute Graph Layout for Small World Networks Proceedings of 15th International Conference on Information Visualisation Sujan Rajbhandari Joe Faith 2010 The Use of Linear Projections in the Visual Analysis of Signals in an Indoor Optical Wireless Link 2010 7th International Symposium on Communication Systems Networks amp Digital Signal Processing CSNDSP 2010 IEEE pp 576 581 doi 10 1109 CSNDSP16145 2010 5580367 ISBN 978 1 4244 8858 2 Further reading EditJoe Faith 2007 Targeted Projection Pursuit for Interactive Exploration of High Dimensional Data Sets Proceedings of 11th International Conference on Information VisualisationExternal links EditimDEV free Excel add in for targeted projection pursuits using feature selection coupled with PLS and PLS DA Targeted Projection Pursuit project page This statistics related article is a stub You can help Wikipedia by expanding it vte Retrieved from https en wikipedia org w index php title Targeted projection pursuit amp oldid 1021682168, wikipedia, wiki, book, books, library,
