Using Supervised Learning and Comparing General and ANTI-HIV Drug Databases Using Chemoinformatics

  • Taneja Shweta
  • Raheja Shipra
  • Kaur Savneet
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5909)


Earlier People used to discover new drugs either by chance that is serendipity or by screening the natural products. This process was time consuming, costly as well as required a lot of investment in terms of man-hours. The process of discovering a new drug was very complex and had no rational. Prior to Data Mining , researchers were trying computer methods such as potential drug molecules interactions with the targets and that was also time consuming, costly and required high expertise. Data mining is often described as a discipline to find hidden information in a database. It involves different techniques and algorithms to discover useful knowledge lying hidden in the data. Data mining and the term Knowledge Discovery in Databases (KDD) are often used interchangeably . In this paper, we are implementing the classification technique using WEKA tool for the analysis of similarity between GENERAL DRUGS and ANTI-HIV DRUGS.


Classification Chemoinformatics Data mining HIV drugs 


  1. 1.
    Data Mining Promises To Dig Up New Drugs,Science Daily (February 3, 2009)Google Scholar
  2. 2.
    Zimmermann, A., Bringmann, B.: CTC - correlating tree patterns for classification. In: Fifth IEEE International Conference on Data Mining, Novemmber 27-30, p. 4 (2005), doi:10.1109/ICDM.2005.49Google Scholar
  3. 3.
    Bjorn, B., Albrecht, Z.: Tree Decision Trees for Tree Structured Data. Institute of Computer Science, Machine Learning Lab, Albert-Ludwig-University Freiburg, Georges-Kohler-Allee 79, 79110 Freiburg, GermanyGoogle Scholar
  4. 4.
    Ósk, J.S., Steen, J.F., Brunak, S.: Prediction methods and databases within chemoinformatics: emphasis on drugs and drug candidates 21(10), 2145–2160 (2005), doi:10.1093/bioinformatics/bti314Google Scholar
  5. 5.
    Lumini, A., Nanni, L.: Machine Learning for HIV-1 Protease Cleavage Site Prediction. Elsevier Science Inc., New York (2005)Google Scholar
  6. 6.
    Niko, B., et al.: Diversity and complexity of HIV-1 drug resistance: A bioinformatics approach to predicting phenotype from genotype. IEEE Intelligent Systems 16(6), 35–41 (2001)CrossRefGoogle Scholar
  7. 7.
    Hiroto, S.: Mining complex genotypic features for predicting HIV-1 drug resistance. National Institute of Informatics (2007)Google Scholar
  8. 8.
    Lin Ray, S.: A combined data mining approach for infrequent events: analyzing HIV mutation changes based on treatment history. Stanford University Stanford, CA 94305, United StatesGoogle Scholar
  9. 9.
    Wasim, A.M., Sidhu, M.: Chemoinformatics: Principles and Applications. Pesticide Residue Laboratory, Department of Agricultural Chemicals, Department of Agricultural Chemistry and Soil Science, Bidhan Chandra Krishi Viswavidyalaya, Mohanpur-741252,Nadia, West Bengal, IndiaGoogle Scholar
  10. 10.
    Beerenwinkel, N., Schmidt, B., Walter, H., Kaiser, R., Lengauer, T., Hoffmann, D., Korn, K., Selbig, J.: Identifying drug resistance-associated patterns in HIV genotypesGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Taneja Shweta
    • 1
  • Raheja Shipra
    • 1
  • Kaur Savneet
    • 1
  1. 1.Guru Teg Bahadur Institute of TechnologyNew Delhi

Personalised recommendations