Adaptive Neuro-Fuzzy Inference System: An Instant and Architecture-Free Predictor for Improved QSAR Studies
- 21 July 2001
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Medicinal Chemistry
- Vol. 44 (17) , 2772-2783
Abstract
The application of an adaptive neuro-fuzzy inference system (ANFIS) has been developed for obtaining sufficient quantitative structure−activity relationships (QSAR) with high accuracy. To this end, a data set of 68 pyrimidines derivatives as DHFR inhibitors, described first in the excellent independent studies of Hansch et al. (J. Med. Chem. 1982, 25, 777−784 and J. Med. Chem. 1991, 34, 46−54) and later by So and Richards (J. Med. Chem. 1992, 35, 3201−3207), was examined. The ANFIS system, first time applied in the literature to QSAR studies, was trained using a hybrid algorithm consisting of back-propagation and least-squares estimation while the optimum number and shape of membership functions were obtained through the subtractive clustering algorithm. Prior to the development and evaluation of the ANFIS system, geometry optimization of the examined compounds was performed, deriving a series of diverse descriptors from which the best subset was selected by using a hybrid genetic algorithm system. The predictive abilities of the resulting models compared to those produced from classical multivariate regression such as linear and nonlinear (quadratic) partial least squares regression (PLS and QPLS, respectively). The ANFIS method outperformed both the PLS models as well as the published results, leading to substantial gain in both the prediction ability and the computation speed (almost instant training).Keywords
This publication has 19 references indexed in Scilit:
- Radial basis function networks in host–guest interactions: instant and accurate formation constant calculationsAnalytica Chimica Acta, 2000
- Calibration in non-linear near infrared reflectance spectroscopy: a comparison of several methodsAnalytica Chimica Acta, 1999
- Optimization of the Inner Relation Function of QPLS Using Genetic AlgorithmJournal of Chemical Information and Computer Sciences, 1997
- Nonlinear CoMFA using QPLS as a Novel 3D-QSAR ApproachQuantitative Structure-Activity Relationships, 1997
- Dynamics of trimethoprim bound to dihydrofolate reductase—a deuterium NMR studySolid State Nuclear Magnetic Resonance, 1996
- Pyrrolo[2,3-d]pyrimidines and pyrido[2,3-d]pyrimidines as conformationally restricted analogues of the antibacterial agent trimethoprimBioorganic & Medicinal Chemistry, 1996
- New benzylpyrimidines: inhibition of DHFR from various species. QSAR, CoMFA and PC analysisEuropean Journal of Medicinal Chemistry, 1995
- Variable Selection in QSAR Studies. II. A Highly Efficient Combination of Systematic Search and EvolutionQuantitative Structure-Activity Relationships, 1994
- Novel pyrrolo[2,3-d]pyrimidine antifolates: synthesis and antitumor activitiesJournal of Medicinal Chemistry, 1991
- Stereoselective reactions. XVII. Absolute structure-cytotoxic activity relationships of steganacin congeners and analogsJournal of Medicinal Chemistry, 1991