Adaptive neuro-fuzzy inference system (ANFIS): A new approach to predictive modeling in QSAR applications: A study of neuro-fuzzy modeling of PCP-based NMDA receptor antagonists

• Published in: Bioorganic & medicinal chemistry 2007-06, Vol.15 (12), p.4265-4282
• Main Authors: Buyukbingol, Erdem, Sisman, Arzu, Akyildiz, Murat, Alparslan, Ferda Nur, Adejare, Adeboye
• Format: Article
• Language: English
• Subjects: ANFIS; Biological and medical sciences; Excitatory Amino Acid Antagonists - chemistry; Excitatory Amino Acid Antagonists - pharmacology; Fuzzy Logic; Fuzzy neural network; Glutamatergic system (aspartate and other excitatory aminoacids); Linear Models; Medical sciences; Models, Molecular; Molecular descriptors; Neuropharmacology; Neurotransmitters. Neurotransmission. Receptors; NMDA antagonists; Pharmacology. Drug treatments; Quantitative Structure-Activity Relationship; Receptors, N-Methyl-D-Aspartate - antagonists & inhibitors
• ISSN: 0968-0896; 1464-3391
• DOI: 10.1016/j.bmc.2007.03.065

This paper proposes a new method, Adaptive Neuro-Fuzzy Inference System (ANFIS) to evaluate physicochemical descriptors of certain chemical compounds for their appropriate biological activities in terms of QSAR models with the aid of artificial neural network (ANN) approach combined with the principle of fuzzy logic. The ANFIS was utilized to predict NMDA ( N-methyl- d-Aspartate) receptor binding activities of phencyclidine (PCP) derivatives. A data set of 38 drug-like compounds was coded with 1244 calculated molecular structure descriptors (clustered in 20 data sets) which were obtained from several sources, mainly from Dragon software. Prior to the progress to the ANFIS system, descriptors from the best subsets were selected using unsupervised forward selection (UFS) to eliminate redundancy and multicollinearity followed by fuzzy linear regression algorithm (FLR) which was used for variable selection. ANFIS was applied to train the final descriptors (Mor22m, E3s, R3v+, and R1e+) using a hybrid algorithm consisting of back-propagation and least-square estimation while the optimum number and shape of related functions were obtained through the subtractive clustering algorithm. Comparison of the proposed method with traditional methods, that is, multiple linear regression (MLR) and partial least-square (PLS) was also studied and the results indicated that the ANFIS model obtained from data sets achieved satisfactory accuracy.