Novel visualization methods for protein data

Shahzad Mumtaz; Ian Nabney; Darren Flower

Novel visualization methods for protein data

Shahzad Mumtaz
, Ian Nabney
, Darren Flower

Aston University

Research output: Chapter in Book/Published conference output › Conference publication

2 Citations (Scopus)

191 Downloads (Pure)

Abstract

Visualization of high-dimensional data has always been a challenging task. Here we discuss and propose variants of non-linear data projection methods (Generative Topographic Mapping (GTM) and GTM with simultaneous feature saliency (GTM-FS)) that are adapted to be effective on very high-dimensional data. The adaptations use log space values at certain steps of the Expectation Maximization (EM) algorithm and during the visualization process. We have tested the proposed algorithms by visualizing electrostatic potential data for Major Histocompatibility Complex (MHC) class-I proteins. The experiments show that the variation in the original version of GTM and GTM-FS worked successfully with data of more than 2000 dimensions and we compare the results with other linear/nonlinear projection methods: Principal Component Analysis (PCA), Neuroscale (NSC) and Gaussian Process Latent Variable Model (GPLVM).

Original language	English
Title of host publication	2012 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)
Publisher	IEEE
Pages	198-205
Number of pages	8
Publication status	Published - 2012
Event	2012 IEEE symposium on computational intelligence in bioinformatics and computational biology - San Diego, California, United States Duration: 9 May 2012 → 12 May 2012

Conference

Conference	2012 IEEE symposium on computational intelligence in bioinformatics and computational biology
Country/Territory	United States
City	San Diego, California
Period	9/05/12 → 12/05/12
Other	This symposium will bring together top researchers, practitioners, and students from around the world to discuss the latest advances in the field of Computational Intelligence and its application to real world problems in biology, bioinformatics, computational biology, chemical informatics, bioengineering and related fields. Computational Intelligence (CI) approaches include artificial neural networks and machine learning techniques, fuzzy logic, evolutionary algorithms and meta-heuristics, hybrid approaches and other emerging techniques.

Bibliographical note

© 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Access to Document

Novel visualization methods for protein data
© 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 1.01 MB

Cite this

@inproceedings{962b00bcdb684f7c9006c9e06d02f7db,

title = "Novel visualization methods for protein data",

abstract = "Visualization of high-dimensional data has always been a challenging task. Here we discuss and propose variants of non-linear data projection methods (Generative Topographic Mapping (GTM) and GTM with simultaneous feature saliency (GTM-FS)) that are adapted to be effective on very high-dimensional data. The adaptations use log space values at certain steps of the Expectation Maximization (EM) algorithm and during the visualization process. We have tested the proposed algorithms by visualizing electrostatic potential data for Major Histocompatibility Complex (MHC) class-I proteins. The experiments show that the variation in the original version of GTM and GTM-FS worked successfully with data of more than 2000 dimensions and we compare the results with other linear/nonlinear projection methods: Principal Component Analysis (PCA), Neuroscale (NSC) and Gaussian Process Latent Variable Model (GPLVM).",

author = "Shahzad Mumtaz and Ian Nabney and Darren Flower",

note = "{\textcopyright} 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.; 2012 IEEE symposium on computational intelligence in bioinformatics and computational biology ; Conference date: 09-05-2012 Through 12-05-2012",

year = "2012",

language = "English",

pages = "198--205",

booktitle = "2012 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Novel visualization methods for protein data

AU - Mumtaz, Shahzad

AU - Nabney, Ian

AU - Flower, Darren

N1 - © 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2012

Y1 - 2012

N2 - Visualization of high-dimensional data has always been a challenging task. Here we discuss and propose variants of non-linear data projection methods (Generative Topographic Mapping (GTM) and GTM with simultaneous feature saliency (GTM-FS)) that are adapted to be effective on very high-dimensional data. The adaptations use log space values at certain steps of the Expectation Maximization (EM) algorithm and during the visualization process. We have tested the proposed algorithms by visualizing electrostatic potential data for Major Histocompatibility Complex (MHC) class-I proteins. The experiments show that the variation in the original version of GTM and GTM-FS worked successfully with data of more than 2000 dimensions and we compare the results with other linear/nonlinear projection methods: Principal Component Analysis (PCA), Neuroscale (NSC) and Gaussian Process Latent Variable Model (GPLVM).

AB - Visualization of high-dimensional data has always been a challenging task. Here we discuss and propose variants of non-linear data projection methods (Generative Topographic Mapping (GTM) and GTM with simultaneous feature saliency (GTM-FS)) that are adapted to be effective on very high-dimensional data. The adaptations use log space values at certain steps of the Expectation Maximization (EM) algorithm and during the visualization process. We have tested the proposed algorithms by visualizing electrostatic potential data for Major Histocompatibility Complex (MHC) class-I proteins. The experiments show that the variation in the original version of GTM and GTM-FS worked successfully with data of more than 2000 dimensions and we compare the results with other linear/nonlinear projection methods: Principal Component Analysis (PCA), Neuroscale (NSC) and Gaussian Process Latent Variable Model (GPLVM).

UR - https://www.scopus.com/pages/publications/84864071478

M3 - Conference publication

SP - 198

EP - 205

BT - 2012 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)

PB - IEEE

T2 - 2012 IEEE symposium on computational intelligence in bioinformatics and computational biology

Y2 - 9 May 2012 through 12 May 2012

ER -

Novel visualization methods for protein data

Abstract

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this