Toward the Prediction of FBPase Inhibitory Activity Using Chemoinformatic Methods

Abstract

Currently, Chemoinformatic methods are used to perform the prediction for FBPase inhibitory activity. A genetic algorithm-random forest coupled method (GA-RF) was proposed to predict fructose 1,6-bisphosphatase (FBPase) inhibitors to treat type 2 diabetes mellitus using the Mold2 molecular descriptors. A data set of 126 oxazole and thiazole analogs was used to derive the GA-RF model, yielding the significant non-cross-validated correlation coefficient r2ncv and cross-validated r2cv values of 0.96 and 0.67 for the training set, respectively. The statistically significant model was validated by a test set of 64 compounds, producing the prediction correlation coefficient r2pred of 0.90. More importantly, the building GA-RF model also passed through various criteria suggested by Tropsha and Roy with r2o and r2m values of 0.90 and 0.83, respectively. In order to compare with the GA-RF model, a pure RF model developed based on the full descriptors was performed as well for the same data set. The resulting GA-RF model with significantly internal and external prediction capacities is beneficial to the prediction of potential oxazole and thiazole series of FBPase inhibitors prior to chemical synthesis in drug discovery programs.

Indexing Natural Products for Their Potential Anti-Diabetic Activity: Filtering and Mapping Discriminative Physicochemical Properties

“…In efforts to detect novel bioactive ligands, ligand-based techniques, including properties-based and pharmacophore-based tools, are being used more and more for modeling the bioactivity of molecules and for the virtual screening of large chemical databases [ 35 , 36 , 37 , 38 ]. Ligand-based modeling tools use optimization algorithms such as Monte Carlo simulations (MCs), simulated annealing (SA) [ 39 ], genetic algorithms (Gas) [ 40 ], neural networks (NNs) [ 41 ], support vector machines (SVM) [ 42 ], the k-nearest neighbor algorithm (kNN) [ 43 , 44 ], Bayesian classifiers and some combinations thereof (Monte Carlo/ simulated annealing algorithm, MCSA) [ 45 , 46 , 47 , 48 , 49 ]. Distinguishing between active and inactive ligands that are useful for treating a certain disease may be accomplished by using sets of active and inactive chemicals and certain optimization techniques [ 50 , 51 , 52 ].…”

Sequential Application of Ligand and Structure Based Modeling Approaches to Index Chemicals for Their hH4R Antagonism

“…As an alternative, ligand-based in silico techniques (including, pharmacophore and chemo-informatic tools) are increasingly used to distinguish active from inactive chemicals and search large databases for novel bioactive products [25] , [26] , [27] . Chemo-informatic tools which use optimization methods such as Genetic Algorithms(GA) [28] , [29] , Neural Networks(NN) [30] , [31] , Monte Carlo(MC), Simulated Annealing(SA) [32] , k-nearest neighbor (kNN) [33] , [34] , Support Vector Machines(SVM) [35] , [36] or Bayesian Classifiers and some of their combinations(MCSA) [34] , [37] , [38] , [39] , [40] , are many times considered to be more useful than Molecular Docking, which is limited to targets with known 3D structures [41] . Molecular Docking often gives unacceptable number of false positives and false negatives and is very time consuming for screening large databases [42] .…”