Topic Models with Relational Features for Drug Design

  • Tanveer A. Faruquie
  • Ashwin Srinivasan
  • Ross D. King
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7842)


To date, ILP models in drug design have largely focussed on models in first-order logic that relate two- or three-dimensional molecular structure of a potential drug (a ligand) to its activity (for example, inhibition of some protein). In modelling terms: (a) the models have largely been logic-based (although there have been some attempts at probabilistic models); (b) the models have been mostly of a discriminatory nature (they have been mainly used for classification tasks); and (c) data for concepts to be learned are usually provided explicitly: “hidden” or latent concept learning is rare. Each of these aspects imposes certain limitations on the use of such models for drug design. Here, we propose the use of “topic models”—correctly, hierarchical Bayesian models—as a general and powerful modelling technique for drug design. Specifically, we use the feature-construction cabilities of a general-purpose ILP system to incorporate complex relational information into topic models for drug-like molecules. Our main interest in this paper is to describe computational tools to assist the discovery of drugs for malaria. To this end, we describe the construction of topic models using the GlaxoSmithKline Tres Cantos Antimalarial TCAMS dataset. This consists of about 13,000 inhibitors of the 3D7 strain of P. falciparum in human erythrocytes, obtained by screening of approximately 2 million compounds. We investigate the discrimination of molecules into groups (for example, “more active” and “less active”). For this task, we present evidence that suggests that when it is important to maximise the detection of molecules with high activity (“hits”), topic-based classifiers may be better than those that operate directly on the feature-space representation of the molecules. Besides the applicability for modelling anti-malarials, an obvious utility of topic-modelling as a technique of reducing the dimensionality of ILP-constructed feature spaces is also apparent.


Relational Feature Topic Model Latent Dirichlet Allocation Lactone Ring Inductive Logic Programming 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Adams, N.M., Hand, D.J.: Comparing classifiers when misallocation costs are uncertain. Pattern Recognition 32, 1139–1147 (1999)CrossRefGoogle Scholar
  2. 2.
    Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. Journal of Machine Learning Research 3, 993–1022 (2003)zbMATHGoogle Scholar
  3. 3.
    Boyle, N.M., Banck, M., James, C.A., Morley, C., Vandermeersch, T., Hutchison, D.R.: Open Babel: an open chemical toolbox. Chemoinformatics 3, 33 (2011), CrossRefGoogle Scholar
  4. 4.
    Elkan, C.: The foundations of cost-sensitive learning. In: Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence, pp. 973–978 (2001)Google Scholar
  5. 5.
    Gamo, F., Sanz, L.M., Vidal, J., de Cozar, C., Alvarez, E., Lavandera, J., Vanderwall, D.E., Green, D.V.S., Kumar, V., Hasan, S., Brown, J.R., Peishoff, C.E., Cardon, L.R., Garcia-Bustos, J.F.: Thousands of chemical starting points for antimalarial lead identification. Nature 465(7296), 305–310 (2010)CrossRefGoogle Scholar
  6. 6.
    Grun, B., Hornik, K.: topicmodels: An R Package for fitting Topic Models. Journal of Statistical Software 40(13), 1–30 (2011)Google Scholar
  7. 7.
    Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA Data Mining Software: An Update. SIGKDD Explorations 11(1) (2009)Google Scholar
  8. 8.
    King, R.D., Muggleton, S.H., Srinivasan, A., Sternberg, M.J.E.: Structure-activity relationships derived by machine learning: The use of atoms and their bond connectivities to predict mutagenicity by inductive logic programming. Proc. of the National Academy of Sciences 93, 438–442 (1996)CrossRefGoogle Scholar
  9. 9.
    King, R.D., Srinivasan, A.: Prediction of rodent carcinogenicity bioassays from molecular structure using inductive logic programming. Environmental Health Perspectives 104(5), 1031–1040 (1996)Google Scholar
  10. 10.
    O’Neill, P.M., Barton, V.E., Ward, S.A.: The Molecular Mechanism of Action of Artemisinin—The Debate Continues. Molecules 15, 1705–1721 (2010)CrossRefGoogle Scholar
  11. 11.
    Kramer, S., Lavrac, N., Flach, P.: Propositionalization approaches to relational data mining. In: Relational Data Mining, pp. 262–286. Springer, New York (2001)CrossRefGoogle Scholar
  12. 12.
    Srinivasan, A.: The Aleph Manual (1999),
  13. 13.
    Srinivasan, A., King, R.D.: Feature construction with Inductive Logic Programming: a study of quantitative predictions of biological activity aided by structural attributes. In: Muggleton, S. (ed.) ILP 1996. LNCS (LNAI), vol. 1314, pp. 89–104. Springer, Heidelberg (1997)CrossRefGoogle Scholar
  14. 14.
    Taranto, C., Di Mauro, N., Esposito, F.: rsLDA: A Bayesian heirarchical model for relational learning. In: ICDKE, pp. 68–74 (2011)Google Scholar
  15. 15.
    WHO. Global plan for artemisinin resistance containment, GPARC (2011),
  16. 16.
    WHO. World Malaria Report 2011 (2011),

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Tanveer A. Faruquie
    • 1
  • Ashwin Srinivasan
    • 2
  • Ross D. King
    • 3
  1. 1.IBM Research—IndiaNew DelhiIndia
  2. 2.Indraprastha Institute of Information Technology, Delhi (IIIT-D)New DelhiIndia
  3. 3.School of Computer ScienceUniversity of ManchesterUnited Kingdom

Personalised recommendations