Special Issue Paper

Browsing large-scale cheminformatics data with dimension reduction

  1. Jong Youl Choi1,*,
  2. Seung-Hee Bae1,
  3. Judy Qiu1,
  4. Bin Chen2,
  5. David Wild2

Article first published online: 14 JUN 2011

DOI: 10.1002/cpe.1781

Issue

Concurrency and Computation: Practice and Experience

Concurrency and Computation: Practice and Experience

Volume 23, Issue 17, pages 2315–2325, 10 December 2011

Additional Information

How to Cite

Choi, J. Y., Bae, S.-H., Qiu, J., Chen, B. and Wild, D. (2011), Browsing large-scale cheminformatics data with dimension reduction. Concurrency Computat.: Pract. Exper., 23: 2315–2325. doi: 10.1002/cpe.1781

Author Information

  1. 1

    School of Informatics and Computing, Pervasive Technology Institute, Indiana University, Bloomington, IN, USA

  2. 2

    School of Informatics and Computing, Indiana University, Bloomington, IN, USA

* Jong Youl Choi, School of Informatics and Computing, Pervasive Technology Institute, Indiana University, Bloomington, IN 47408, USA.
E-mail: jychoi@indiana.edu

Publication History

  1. Issue published online: 20 OCT 2011
  2. Article first published online: 14 JUN 2011
  3. Manuscript Accepted: 17 APR 2011
  4. Manuscript Revised: 26 MAR 2011
  5. Manuscript Received: 6 OCT 2010

Funded by

  • Microsoft “CRMC”
  • NIH. Grant Number: RC2HG005806-02
  • National Science Foundation (NSF). Grant Number: 0910812

SEARCH

SEARCH BY CITATION

ARTICLE TOOLS

View Full Article (HTML) Get PDF (1255K)

Keywords:

  • visualization;
  • MDS;
  • GTM;
  • interpolation;
  • semantic web

SUMMARY

Visualization of large-scale high dimensional data is highly valuable for data analysis facilitating scientific discovery in many fields. We present PubChemBrowse, a customized visualization tool for cheminformatics research. It provides a novel 3D data point browser that displays complex properties of massive data on commodity clients. As in Geographic Information System browsers for Earth and Environment data, chemical compounds with similar properties are nearby in the browser. PubChemBrowse is built around in-house high performance parallel Multi-dimensional scaling and Generative topographic mapping services and supports fast interaction with an external property database. These properties can be overlaid on 3D mapped compound space or queried for individual points. We prototype the integration with Chem2Bio2RDF system using SPARQL endpoint to access over 20 publicly accessible bioinformatics databases. We describe our design and implementation of the integrated PubChemBrowse application and outline its use in drug discovery. The same core technologies are generally applicable to develop high performance scientific data browsing systems for other applications. Copyright © 2011 John Wiley & Sons, Ltd.

View Full Article (HTML) Get PDF (1255K)