Abstract
An Adaptive Fuzzy Partition (AFP) algorithm, derived from Fuzzy Logic concepts, was used to classify an anticancer data set, including about 1300 compounds subdivided into eight mechanisms of action. AFP classification builds relationships between molecular descriptors and bio-activities by dynamically dividing the descriptor hyperspace into a set of fuzzy subspaces. These subspaces are described by simple linguistic rules, from which scores ranging between 0 and 1 can be derived. The latter values define, for each compound, the degrees of membership of the different mechanisms analyzed. A particular attention was devoted to develop structure–activity relations that have a real utility. Then, well-defined and widely accepted protocols were used to validate the models by defining their robustness and prediction ability. More particularly, after selecting the most relevant descriptors with help of a genetic algorithm, a training set of 640 compounds was isolated by a rational procedure based on Self-Organizing Maps. The related AFP model was then validated with help of a validation set and, above all, of cross-validation and Y-randomization procedures. Good validation scores of about 80% were obtained, underlining the robustness of the model. Moreover, the prediction ability was evaluated with 374 test compounds that had not been used to establish the model and 77% of them were predicted correctly.
Similar content being viewed by others
References
Boyd, M.R., In Teicher B.A. (Ed.), Anticancer Drug Development Guide: Preclinical Screening, Clinical Trials, and Approval. Humana Press, Totowa, NJ, 1997, pp. 23–42.
MDL® Drug Data Report. MDL Information Systems Inc., San Leandro, CA, 2004.
P. Willett (1997) Perspect. Drug Discov. Des. 7/8 1
D.M. Bayada H. Hamersma V.J. van Geerestein (1999) J. Chem. Inf. Comput. Sci., 39 1
E.M. Gordon J.F. Kerwin SuffixJr. (Eds) (1998) Combinatorial Chemistry and Molecular Diversity in Drug Discovery Wiley New York
H. van de Waterbeemd (1995) Chemometric Methods in Molecular Design VCH, Weinheim Germany
H. Kubinyi G. Folkers Y.C. Martin (Eds) (1998) 3D QSAR in Drug Design, Recent Advances Kluwer Escom Dordrecht, The Netherlands
K. Paull R.H. Shoemaker L. Hodes A. Monks D.A. Scudiero L. Rubinstein J. Plowman M.R. Boyd (1989) J. Natl. Cancer Inst., 81 1088
Paull, K., Hamel, E. and Malspeis, L., In Foye, W.O. (Ed.), Cancer Chemotherapeutic Agents. American Chemical Society Books, Washington, DC, 1995, pp. 9–45.
J.N. Weinstein K.W. Kohn M.R. Grever V.N. Viswanadhan L.V. Rubinstein A.P. Monks D.A. Scudiero L. Welch A.D. Koutsoukos A.J. Chiausa K.D. Paull (1992) Science 258 447
W.W. van Osdol T.G. Myers K.D. Paull K.W. Kohn J.N. Weinstein (1994) J. Natl. Cancer Inst. 86 1853
A.D. Koutsoukos L.V. Rubinstein D. Faraggi R.M. Simon S. Kalyandrug J.N. Weinstein K.W. Kohn K.D. Paull (1994) Stat Med. 13 719
J.N. Weinstein T.G. Myers P.M. O’Connor S.H. Friend A.J. Fornace SuffixJr. K.W. Kohn T. Fojo S.E. Bates L.V. Rubinstein N.L. Anderson J.K. Buolamwini W.W. van Osdol A.P. Monks D.A. Scudiero E.A. Sausville D.W. Zaharevitz B. Bunow V.N. Viswanadhan G.S. Johnson R.E. Wittes K.D. Paull (1997) Science 275 343
L.M. Shi Y. Fan J.K. Lee M. Waltham D.T. Andrews U. Scherf K.D. Paull J.N. Weinstein (2000) J. Chem. Inf. Comput. Sci. 40 367 Occurrence Handle10.1021/ci990087b Occurrence Handle1:CAS:528:DyaK1MXnvFKgsb0%3D Occurrence Handle10761142
L.M. Shi T.G. Myers Y. Fan P.M. O’Connor K.D. Paull S.H. Friend J.N. Weinstein (1998) Mol. Pharmacol. 53 241
Y. Fan L.M. Shi K.W. Kohn Y. Pommier J.N. Weinstein (2001) J. Med. Chem. 44 3254
P. Blower M. Fligner J. Verducci J. Bjoraker (2002) J. Chem. Inf. Comput. Sci. 42 393
V.V. Poroikov D.A. Filimonov W.D. Ihlenfeldt T.A. Gloriozova A.A. Lagunin Y.V. Borodina A.V. Stepanchikova M.C. Nicklaus (2003) J. Chem. Inf. Comput. Sci. 43 228
J. Folkman (1995) Nat. Med. 1 27
CIPSLINE ®. Prous Science, Barcelona, Spain, 2003.
F. Ros M. Pintore J.R. Chrétien (2002) Chemometr. Intell. Lab. 63 15
Zadeh, L.A., In Van Ryzin, J. (Ed.), Classification and Clustering. Academic Press, New York Syst., 1977, pp. 251–299.
F. Ros O. Taboureau M. Pintore J.R. Chrétien (2003) Chemometr. Intell. Lab. Sys. 67 29
M. Pintore N. Piclin E. Benfenati G. Gini J.R. Chrétien (2003) Environ. Toxicol. Chem. 22 983
M. Pintore H. van de Waterbeemd N. Piclin J.R. Chrétien (2003) Eur. J. Med. Chem. 38 427
M. Pintore K. Audouze F. Ros J.R. Chretien (2002) Data Sci. J. 1 99
A. Tropsha P. Grammatica V.K. Gombar (2003) QSAR. Comb. Sci., 22 69
MDL® QSAR version 2.2. MDL Information Systems Inc., San Leandro, CA, 2003.
M. Pintore O. Taboureau F. Ros J.R. Chrétien (2001) Eur. J. Med. Chem. 36 349
R.L. Haupt S.E. Haupt (Eds) (1998) Practical Genetic Algorithms Wiley New York
R. Leardi A.L. Gonzales (1998) Chemometr. Intell. Lab. Syst. 41 195
T. Kohonen (Eds) (2001) Self-Organizing Maps Springer-Verlag Berlin, Germany
Y. Lin G.J. Cunninghan (1994) J. Intell. Fuzzy Syst. 2 243
M. Sugeno T.A. Yasakawa (1993) IEEE T. Fuzzy Syst. 1 7
Dubois, D. and Prade, H., In Shafer, G. and Pearl, J. (Eds.), Readings in Uncertain Reasoning. Morgan Kaufmann, San Francisco, CA, 1990, pp. 742–761.
M.M. Gupta J. Qi (1991) Fuzzy Set Syst. 40 431
M. Pintore N. Piclin E. Benfenati G. Gini J.R. Chrétien (2003) QSAR Comb. Sci. 22 210
A. Goldbraikh A. Tropsha (2002) J. Mol. Graph. Model. 20 269
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Piclin, N., Pintore, M., Wechman, C. et al. Classification of a large anticancer data set by Adaptive Fuzzy Partition. J Comput Aided Mol Des 18, 577–586 (2004). https://doi.org/10.1007/s10822-004-4076-0
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/s10822-004-4076-0