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.

[1]  Bernhard Pfahringer,et al.  Locally Weighted Naive Bayes , 2002, UAI.

[2]  Spyros Makridakis,et al.  Accuracy measures: theoretical and practical concerns☆ , 1993 .

[3]  Razvan Andonie,et al.  Function Approximation with ARTMAP Architectures , 2014, Int. J. Comput. Commun. Control.

[4]  Douglas M. Hawkins,et al.  The Problem of Overfitting , 2004, J. Chem. Inf. Model..

[5]  Zheng Rong Yang,et al.  Bio-basis function neural network for prediction of protease cleavage sites in proteins , 2005, IEEE Transactions on Neural Networks.

[6]  J. Doyne Farmer,et al.  Exploiting Chaos to Predict the Future and Reduce Noise , 1989 .

[7]  Jen-Lun Yuan,et al.  Bootstrapping nonparametric feature selection algorithms for mining small data sets , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[8]  E. Lunney,et al.  Synthesis of 5,6-dihydro-4-hydroxy-2-pyrones as HIV-1 protease inhibitors: the profound effect of polarity on antiviral activity. , 1997, Journal of medicinal chemistry.

[9]  D. Fairlie,et al.  Beta-strand mimicking macrocyclic amino acids: templates for protease inhibitors with antiviral activity. , 2002, Journal of medicinal chemistry.

[10]  Michael Georgiopoulos,et al.  Ordered fuzzy ARTMAP: a fuzzy ARTMAP algorithm with a fixed order of pattern presentation , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[11]  T. Niwa.  Prediction of biological targets using probabilistic neural networks and atom-type descriptors. , 2004, Journal of medicinal chemistry.

[12]  Gabriela Espinosa,et al.  A Fuzzy ARTMAP-Based Quantitative Structure-Property Relationship (QSPR) for Predicting Physical Properties of Organic Compounds , 2001 .

[13]  R. Sabourin,et al.  Factors of overtraining with fuzzy ARTMAP neural networks , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[14]  A. Micheli,et al.  A Novel Approach to QSPR/QSAR Based on Neural Networks for Structures , 2003 .

[15]  Rob J Hyndman,et al.  Another look at measures of forecast accuracy , 2006 .

[16]  Razvan Andonie,et al.  A New Fuzzy ARTMAP Approach for Predicting Biological Activity of Potential HIV-1 Protease Inhibitors , 2007, 2007 IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2007).

[17]  James Devillers,et al.  Designing Molecules with Specific Properties from Intercommunicating Hybrid Systems , 1996, J. Chem. Inf. Comput. Sci..

[18]  G. Zeikus,et al.  5,6-Dihydropyran-2-ones possessing various sulfonyl functionalities: potent nonpeptidic inhibitors of HIV protease. , 2000, Journal of medicinal chemistry.

[19]  Haifeng Chen,et al.  Comparative Study of QSAR/QSPR Correlations Using Support Vector Machines, Radial Basis Function Neural Networks, and Multiple Linear Regression , 2004, J. Chem. Inf. Model..

[20]  T. Poggio,et al.  Networks and the best approximation property , 1990, Biological Cybernetics.

[21]  Stephen Grossberg,et al.  A fuzzy ARTMAP nonparametric probability estimator for nonstationary pattern recognition problems , 1995, IEEE Trans. Neural Networks.

[22]  Alexandre Arenas,et al.  An Integrated SOM-Fuzzy ARTMAP Neural System for the Evaluation of Toxicity , 2002, J. Chem. Inf. Comput. Sci..

[23]  S. Sathiya Keerthi,et al.  Improvements to the SMO algorithm for SVM regression , 2000, IEEE Trans. Neural Networks Learn. Syst..

[24]  Alessio Micheli,et al.  Application of Cascade Correlation Networks for Structures to Chemistry , 2004, Applied Intelligence.

[25]  Chun-Wu Yeh,et al.  Acquiring knowledge with limited experience , 2007, Expert Syst. J. Knowl. Eng..

[26]  Nicolas Le Roux,et al.  The Curse of Highly Variable Functions for Local Kernel Machines , 2005, NIPS.

[27]  Stanislav Miertus,et al.  Computational studies on tetrahydropyrimidine-2-one HIV-1 protease inhibitors: improving three-dimensional quantitative structure-activity relationship comparative molecular field analysis models by inclusion of calculated inhibitor- and receptor-based properties. , 2002, Journal of medicinal chemistry.

[28]  D. Hecht,et al.  High-Throughput Ligand Screening via Preclustering and Evolved Neural Networks , 2007, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[29]  Chee Peng Lim,et al.  A hybrid neural network classifier combining ordered fuzzy ARTMAP and the dynamic decay adjustment algorithm , 2008, Soft Comput..

[30]  Igor Grabec,et al.  Hybrid modeling of kinetics for methanol synthesis , 2003 .

[31]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[32]  C. Humblet,et al.  4-hydroxy-5,6-dihydropyrones. 2. Potent non-peptide inhibitors of HIV protease. , 1997, Journal of medicinal chemistry.

[33]  Georgios C. Anagnostopoulos,et al.  Cross-validation in Fuzzy ARTMAP for large databases , 2001, Neural Networks.

[34]  Der-Chiang Li,et al.  Using mega-trend-diffusion and artificial samples in small data set learning for early flexible manufacturing system scheduling knowledge , 2007, Comput. Oper. Res..

[35]  Gary B. Fogel,et al.  Quantitative structure-property relationships for drug solubility prediction using evolved neural networks , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[36]  S. Lawrence,et al.  Function Approximation with Neural Networks and Local Methods: Bias, Variance and Smoothness , 1996 .

[37]  I V Tetko,et al.  Applications of neural networks in structure-activity relationships of a small number of molecules. , 1993, Journal of medicinal chemistry.

[38]  Vladyslav Kholodovych,et al.  3D-QSAR comparative molecular field analysis on opioid receptor antagonists: pooling data from different studies. , 2005, Journal of medicinal chemistry.

[39]  David McLean,et al.  On Global–Local Artificial Neural Networks for Function Approximation , 2006, IEEE Transactions on Neural Networks.

[40]  Razvan Andonie,et al.  Fuzzy ARTMAP with input relevances , 2006, IEEE Transactions on Neural Networks.

[41]  Issam Dagher,et al.  An ordering algorithm for pattern presentation in fuzzy ARTMAP that tends to improve generalization performance , 1999, IEEE Trans. Neural Networks.

[42]  Razvan Andonie,et al.  A genetic algorithm optimized fuzzy neural network analysis of the affinity of inhibitors for HIV-1 protease. , 2008, Bioorganic & medicinal chemistry.

[43]  Andrew W. Moore,et al.  Locally Weighted Learning , 1997, Artificial Intelligence Review.

[44]  Mansooreh Mollaghasemi,et al.  GFAM: A Genetic Algorithm Optimization of Fuzzy ARTMAP , 2006, 2006 IEEE International Conference on Fuzzy Systems.

[45]  Razvan Andonie,et al.  Fuzzy ARTMAP rule extraction in computational chemistry , 2009, 2009 International Joint Conference on Neural Networks.

[46]  Terrence L. Fine,et al.  Neural-network design for small training sets of high dimension , 1998, IEEE Trans. Neural Networks.

[47]  Egon L. Willighagen,et al.  The Blue Obelisk—Interoperability in Chemical Informatics , 2006, J. Chem. Inf. Model..

[48]  Michael Georgiopoulos,et al.  Boosted ARTMAP , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[49]  Tomoko Niwa,et al.  Using General Regression and Probabilistic Neural Networks To Predict Human Intestinal Absorption with Topological Descriptors Derived from Two-Dimensional Chemical Structures , 2003, J. Chem. Inf. Comput. Sci..

[50]  Razvan Andonie,et al.  An Integrated Soft Computing Approach for Predicting Biological Activity of Potential HIV-1 Protease Inhibitors , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[51]  Asim Kumar Debnath,et al.  Comparative Molecular Field Analysis (CoMFA) of a Series of Symmetrical Bis-Benzamide Cyclic Urea Derivatives as HIV-1 Protease Inhibitors , 1998, J. Chem. Inf. Comput. Sci..

[52]  Chee Peng Lim,et al.  Art-Based Autonomous Learning Systems: Part I — Architectures and Algorithms , 2000 .

[53]  James R. Williamson,et al.  Gaussian ARTMAP: A Neural Network for Fast Incremental Learning of Noisy Multidimensional Maps , 1996, Neural Networks.

[54]  Razvan Andonie,et al.  Neuro-fuzzy Prediction of Biological Activity and Rule Extraction for HIV-1 Protease Inhibitors , 2005, 2005 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology.

[55]  Alexandre Arenas,et al.  Fuzzy ARTMAP and Back-Propagation Neural Networks Based Quantitative Structure-Property Relationships (QSPRs) for Octanol-Water Partition Coefficient of Organic Compounds , 2002, J. Chem. Inf. Comput. Sci..

[56]  Hugo Guterman,et al.  Advanced Developments and Applications of the Fuzzy ARTMAP Neural Network in Pattern Classification , 2008, Computational Intelligence Paradigms.

[57]  E. Schreiner,et al.  Inhibitors of HIV-1 proteinase containing 2-heterosubstituted 4-amino-3-hydroxy-5-phenylpentanoic acid: synthesis, enzyme inhibition, and antiviral activity. , 1994, Journal of medicinal chemistry.

[58]  Min Han,et al.  Semi-supervised Bayesian ARTMAP , 2010, Applied Intelligence.

[59]  Nikola Pavesic,et al.  A Fast Simplified Fuzzy ARTMAP Network , 2003, Neural Processing Letters.

[60]  Thomas G. Dietterich.  Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms , 1998, Neural Computation.

[61]  Sorin Draghici,et al.  Predicting HIV drug resistance with neural networks , 2003, Bioinform..

[62]  D. Fairlie,et al.  Protease inhibitors: current status and future prospects. , 2000, Journal of medicinal chemistry.

[63]  A. Wlodawer,et al.  Structure-based inhibitors of HIV-1 protease. , 1993, Annual review of biochemistry.

[64]  A Wlodawer,et al.  Inhibitors of HIV-1 protease: a major success of structure-assisted drug design. , 1998, Annual review of biophysics and biomolecular structure.

[65]  Patricia A. Evans,et al.  A Haplotyping Algorithm for Non-recombinant Pedigree Data Containing Missing Members , 2007, 2007 IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2007).

[66]  Haichao Zhu,et al.  A New Method to Assist Small Data Set Neural Network Learning , 2006, Sixth International Conference on Intelligent Systems Design and Applications.

[67]  D. Signorini,et al.  Neural networks , 1995, The Lancet.

[68]  S E Hagen,et al.  4-Hydroxy-5,6-dihydropyrones as inhibitors of HIV protease: the effect of heterocyclic substituents at C-6 on antiviral potency and pharmacokinetic parameters. , 2001, Journal of medicinal chemistry.

[69]  J. Paetz,et al.  Evolutionary optimization of interval rules for drug design , 2004, 2004 Symposium on Computational Intelligence in Bioinformatics and Computational Biology.

[70]  Aalt Bast,et al.  Comprehensive medicinal chemistry , 1991 .

[71]  Dana Weekes,et al.  Evolutionary optimization, backpropagation, and data preparation issues in QSAR modeling of HIV inhibition by HEPT derivatives. , 2003, Bio Systems.

[72]  Julius T. Tou,et al.  Pattern Recognition Principles , 1974 .

[73]  Léon Bottou,et al.  Local Learning Algorithms , 1992, Neural Computation.

[74]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[75]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[76]  Igor V. Tetko,et al.  Application of Associative Neural Networks for Prediction of Lipophilicity in ALOGPS 2.1 Program , 2002, J. Chem. Inf. Comput. Sci..

[77]  Luiz Eduardo Soares de Oliveira,et al.  Particle Swarm Optimization of Fuzzy ARTMAP Parameters , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[78]  Igor V. Tetko,et al.  Evaluation of potential HIV-1 reverse transcriptase inhibitors by artificial neural networks , 1994, Proceedings of IEEE Symposium on Computer-Based Medical Systems (CBMS).

[79]  Boaz Lerner,et al.  The Bayesian ARTMAP , 2007, IEEE Transactions on Neural Networks.

[80]  Alessio Micheli,et al.  A preliminary empirical comparison of recursive neural networks and tree kernel methods on regression tasks for tree structured domains , 2005, Neurocomputing.

[81]  Yoshua Bengio,et al.  Scaling learning algorithms towards AI , 2007 .