Levente Fabry-Asztalos

A genetic algorithm optimized fuzzy neural network analysis of the affinity of inhibitors for HIV-1 protease

A fuzzy neural network (FNN) was trained on a dataset of 177 HIV-1 protease ligands with experimentally measured IC(50) values. A set of descriptors was selected to build nonlinear quantitative structure-activity relationships. A genetic algorithm (GA) was implemented to optimize the architecture of the fuzzy neural network used to predict biological activity of HIV-1 protease inhibitors. Evolutionary methods were used to apply feature selection (FS) to this model. Results obtained on an external test set of 21 molecules, with and without feature selection, were compared. Applying feature selection to the GA-FNN resulted in a more accurate prediction of biological activity. Fuzzy IF/THEN rules were extracted from the optimized FNN. In the future the developed models are expected to be useful in the rational design of novel enzyme inhibitors for HIV-1 protease.

Fuzzy ARTMAP Prediction of Biological Activities for Potential HIV-1 Protease Inhibitors Using a Small Molecular Data Set

Obtaining satisfactory results with neural networks depends on the availability of large data samples. The use of small training sets generally reduces performance. Most classical Quantitative Structure-Activity Relationship (QSAR) studies for a specific enzyme system have been performed on small data sets. We focus on the neuro-fuzzy prediction of biological activities of HIV-1 protease inhibitory compounds when inferring from small training sets. We propose two computational intelligence prediction techniques which are suitable for small training sets, at the expense of some computational overhead. Both techniques are based on the FAMR model. The FAMR is a Fuzzy ARTMAP (FAM) incremental learning system used for classification and probability estimation. During the learning phase, each sample pair is assigned a relevance factor proportional to the importance of that pair. The two proposed algorithms in this paper are: 1) The GA-FAMR algorithm, which is new, consists of two stages: a) During the first stage, we use a genetic algorithm (GA) to optimize the relevances assigned to the training data. This improves the generalization capability of the FAMR. b) In the second stage, we use the optimized relevances to train the FAMR. 2) The Ordered FAMR is derived from a known algorithm. Instead of optimizing relevances, it optimizes the order of data presentation using the algorithm of Dagher et al. In our experiments, we compare these two algorithms with an algorithm not based on the FAM, the FS-GA-FNN introduced in . We conclude that when inferring from small training sets, both techniques are efficient, in terms of generalization capability and execution time. The computational overhead introduced is compensated by better accuracy. Finally, the proposed techniques are used to predict the biological activities of newly designed potential HIV-1 protease inhibitors.

Inhibition of HIV-1 protease by a boron-modified polypeptide

Six boronated tetrapeptides with the carboxy moiety of phenylalanine replaced by dihydroxyboron were synthesized, and their activities against human immunodeficiency virus 1 (HIV-1) protease subsequently investigated. The sequences of these peptides were derived from HIV-1 protease substrates, which included the C-terminal part of the scissile bond (Phe-Pro) within the gag-pol polyprotein. Enzymatic studies showed that these compounds were competitive inhibitors of HIV-1 protease with K(i) values ranging from 5 to 18 microM when experiments were performed at high enzyme concentrations (above 5 x 10(-8) M); however, at low protease concentrations inhibition was due in part to an increase of the association constants of the protease subunits. Ac-Thr-Leu-Asn-PheB inhibited HIV-1 protease with a K(i) of 5 microM, whereas the non-boronated parental compound was inactive at concentrations up to 400 microM, which indicates the significance of boronation in enzyme inhibition. The boronated tetrapeptides were inhibitory to an HIV-1 protease variant that is resistant to several HIV-1 protease inhibitors. Finally, fluorescence analysis showed that the interactions between the boronated peptide Ac-Thr-Leu-Asn-PheB and HIV-1 protease resulted in a rapid decrease of fluorescence emission at 360 nm, which suggests the formation of a compound/enzyme complex. Boronated peptides may provide useful reagents for studying protease biochemistry and yield valuable information toward the development of protease dimerization inhibitors.

Neuro-fuzzy Prediction of Biological Activity and Rule Extraction for HIV-1 Protease Inhibitors

A fuzzy neural network (FNN) and multiple linear regression (MLR) were used to predict biological activities of 26 newly designed HIV-1 protease potential inhibitory compounds. Molecular descriptors of 151 known inhibitors were used to train and test the FNN and to develop MLR models. The predictive ability of these two models was investigated and compared. We found the predictive ability of the FNN to be generally superior to that of MLR. The fuzzy IF/THEN rules were extracted from the trained network. These rules map chemical structure descriptors to predicted inhibitory values. The obtained rules can be used to analyze the influence of descriptors. Our results indicate that FNN and fuzzy IF/THEN rules are powerful modeling tools for QSAR studies.

An Integrated Soft Computing Approach for Predicting Biological Activity of Potential HIV-1 Protease Inhibitors

Using a neural network-fuzzy logic-genetic algorithm approach we generate an optimal predictor for biological activities of HIV-1 protease potential inhibitory compounds. We use genetic algorithms (GAs) in the two optimization stages. In the first stage, we generate an optimal subset of features. In the second stage, we optimize the architecture of the fuzzy neural network. The optimized network is trained and used for the prediction of biological activities of newly designed chemical compounds. Finally, we extract fuzzy IF/THEN rules. These rules map physico-chemical structure descriptors to predicted inhibitory values. The optimal subset of features, combined with the generated rules, can be used to analyze the influence of descriptors.

Molecular distance geometry optimization using geometric build-up and evolutionary techniques on GPU

We present a combination of methods addressing the molecular distance problem, implemented on a graphic processing unit. First, we use geometric build-up and depth-first graph traversal. Next, we refine the solution by simulated annealing. For an exact but sparse distance matrix, the build-up method reconstructs the 3D structures with a root-mean-square error (RMSE) in the order of 0.1 Å. Small and medium structures (up to 10,000 atoms) are computed in less than 10 seconds. For the largest structures (up to 100,000 atoms), the build-up RMSE is 2.2 Å and execution time is about 540 seconds. The performance of our approach depends largely on the graph structure. The SA step improves accuracy of the solution to the expense of a computational overhead.

Fuzzy ARTMAP rule extraction in computational chemistry

We focus on extracting rules from a trained FAMR model. The FAMR is a Fuzzy ARTMAP (FAM) incremental learning system used for classification, probability estimation, and function approximation. The set of rules generated is post-processed in order to improve its generalization capability. Our method is suitable for small training sets. We compare our method with another neuro-fuzzy algorithm, and two standard decision tree algorithms: CART trees and Microsoft Decision Trees. Our goal is to improve efficiency of drug discovery, by providing medicinal chemists with a predictive tool for bioactivity of HIV-1 protease inhibitors.

Solving molecular distance geometry problems in OpenCL

We focus on the following computational chemistry problem: Given a subset of the exact distances between atoms, reconstruct the three-dimensional position of each atom in the given molecule. The distance matrix is generally sparse. This problem is both important and challenging. Our contribution is a novel combination of two known techniques (parallel breadth-first search and geometric buildup) and its OpenCL parallel implementation. The approach has the potential to speed up computation of three-dimensional structures of molecules - a critical process in computational chemistry. From experiments on multi-core CPUs and graphic processing units, we conclude that, for sufficient large problems, our implementation shows a moderate scalability.

Bayesian ARTMAP prediction of biological activities for potential HIV-1 protease inhibitors using a small molecular dataset

Several neural architectures were successfully used to predict properties of chemical compounds. Obtaining satisfactory results with neural networks depends on the availability of large data samples. However, most classical Quantitative Structure-Activity Relationship studies have been performed on small datasets. Neural models do generally infer with difficulty from such datasets. In our study, we analyze the performance of the Bayesian ARTMAP for the prediction of biological activities of HIV-1 protease inhibitors, when inferring from a small and structurally diverse dataset of molecules. The Bayesian ARTMAP is a neural model which uses both competitive learning and Bayesian prediction, and has both the universal approximation and best approximation properties. It is the first time when this model is used in a “real-world” function approximation application. We compare the performance of the Bayesian ARTMAP to several other models, each implementing a different learning mechanism. Experiments are performed within Wekas “Experimenter” standard environment. For our small and structurally diverse dataset of chemical compounds, the Bayesian ARTMAP is a good prediction tool, and the most accurate prediction models are the ones which perform local approximation.

Accelerating Molecular Structure Determination Based on Inter-Atomic Distances Using OpenCL

Fast and accurate determination of the 3D structure of molecules is essential for better understanding their physical, chemical, and biological properties. We focus on an existing method for molecular structure determination: restrained molecular dynamics with simulated annealing. In this method a hybrid function, composed by a physical model and experimental restraints, is minimized by simulated annealing. Our goal is to accelerate computation time using commodity multi-core CPUs and GPUs in a heterogeneous computing model. We present a parallel and portable OpenCL implementation of this method. Experimental results are discussed in terms of accuracy, execution time, and parallel scalability. With respect to the XPLOR-NIH professional software package, compared to the single CPU core implementation, we obtain speedups of three to five times (increasing with problem size) on commodity GPUs. We achieve these performances by writing specialized kernels for different problem sizes and hardware architectures.