Abstract
Virtual screening is an important challenge for bioinformaticians and molecular biologists. Finding the most active ligands that bind to target molecules by intelligent methods reduces the computational efforts in the drug discovery process dramatically. Recently, we proposed a neuro-fuzzy based approach to virtual screening by generating interval rules, each one with a class assignment for enriched regions of active ligands. The underlying input data is based on so called descriptor vector calculations. Descriptors are designed by experts, and they represent properties of the molecules. It is not assumed that all descriptors in a usually high dimensional descriptor vector are needed for classification. We demonstrate the usefulness of a neuro-fuzzy system for rule-based classification and feature selection. On the one hand the classification results can be used for efficient virtual screening, and on the other hand the rules can be used by experts for the ongoing drug design process. By feature analysis of the rules descriptor vectors can be redesigned. In the future more tools are needed that are capable not only of achieving several analysis results but giving also rule-based hints to the experts of how to plan their further research activities.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Agrawal R, Skrikant R (1994) Fast algorithms for mining association rules. In: Bocca J, Jarke M, Zaniolo C (eds) Proceedings of the 20th international conference on very large databases (VLDB), Santiago de Chile. Chile, Morgan Kaufmann, San Mateo, pp 487–499
Ajay (2002) Predicting drug-likeness: why and how?. Curr Top Med Chem 2(12): 1273–1286
Berg JM, Tymoczko JL, Stryer L (2002) Biochemistry. W.H. Freeman, New York
Böhm H-J, Schneider G (2000) Virtual screening for bioactive molecules. Wiley Weinheim, New York
Borgelt C, Berthold MR (2002) Mining molecular fragments: finding relevant substructures of molecules. In: Kumar V, Tsumoto S, Zhong N, Yu PS, Wu X (eds) 2nd IEEE international conference on data mining (ICDM), Maebashi City, Japan. IEEE Computer Society Press, Piscateway, pp 51–58
Bruno-Blanch L, Galvez J, Garcia-Domenech R (2003) Topological virtual screening: a way to find new anticonvulsant drugs from chemical diversity. Bioorg Med Chem Lett 13(16): 2749–2754
Carhart RE, Smith DH, Venkataraghavan R (1985) Atom pairs as molecular features in structure-activity studies: definition and applications. J Chem Inf Comput Sci 25: 64–73
Fechner U, Franke L, Renner S, Schneider P, Schneider G (2003) Comparison of correlation vector-descriptor for similarity searching. J Comput Aided Mol Des 17: 687–698
Gasteiger J, Engel T (2003) Cheminformatics: a textbook, Wiley Weinheim, New York
Godden JW, Furr JR, Bajorath J (2003) Recursive median partitioning for virtual screening of large databases. J Chem Inf Comput Sci 43: 182–188
Huber KP, Berthold MR (1995) Building precise classifiers with automatic rule extraction. In: IEEE international conference on neural networks (ICNN), Perth, Western Australia. Causal Productions, Adelaide, pp 1263–1268
Lipinski CA, Lombardo F, Dominy BW, Feeney PJ (2001) Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings. Adv Drug Deliv Rev 46: 3–26
Lyne PD (2002) Structure-based virtual screening: an overview. Drug Discov Today 7(20): 1047–1055
Moreau G, Broto P (1980) Autocorrelation of a molecular structure: a new molecular descriptor. Nouveau J de Chimie 4: 359–360
Paetz J (2001) Metric rule generation with septic shock patient data. In: Cercone N, Lin TY, Wu X (eds) Proceedings of the 1st international conference on data mining (ICDM), San Jose. IEEE Computer Society Press, Los Alamitos, pp 637–638
Paetz J (2003) Knowledge based approach to septic shock patient data using a neural network with trapezoidal activation functions. Artif Intell Med 28(2): 207–230
Paetz J, Fechner U, Franke L, Renner S, Schneider P, Schneider G (2004) Pharmacophore feature selection with a neuro-fuzzy system, In: Proceedings of the 4th European symposium on intelligent technologies, hybrid systems and their implementation on smart adaptive systems (EUNITE), Aachen, Germany. Verlag Mainz, Aachen, pp 179–184
Raymond JW, Willet P (2002) Effectiveness of graph-based and fingerprint-based similarity measures for virtual screening of 2D chemical structure databases. J Comput-Aided Mol Des 16(1): 59–71
Schneider G, Neidhart W, Giller T, Schmid G (1999) Scaffold hopping by topological pharmacophore search: a contribution to virtual screening. Angew Chemie Int Ed 38(19): 2894–2895
Schneider G, Böhm H-J (2002) Virtual screening and fast automated docking methods. Drug Discov Today 7(1): 64–70
Schneider P, Schneider G (2003) Collection of bioactive reference compounds for focused library design. QSAR Comb Sci 22: 713–718
Shen J, Xu X, Cheng F, Liu H, Luo X, Chen K, Zhao W, Shen X, Jiang H (2003) Virtual screening on natural products for discovering active compounds and target information. Curr Med Chem 10(21): 2327–2342
Skiles JW, Jeng AY, Monovich LG (2000) Matrix metalloproteinase inhibitors for treatment of cancer. Annu Rep Med Chem 35: 167–176
Todeschini R, Consonni V (2000) Handbook of molecular descriptors. Wiley Weinheim, New York
Waszkowycz B, Perkins TDJ, Sykes RA, Li J (2001) Large-scale virtual screening for discovering leads in the postgenomic era. IBM Syst J 40(2): 360–376
Xu H (2002) Retrospect and prospect of virtual screening in drug discovery. Curr Top Med Chem 2(12): 1305–1320
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Paetz, J. Descriptor vector redesign by neuro-fuzzy analysis. Soft Comput 10, 287–294 (2006). https://doi.org/10.1007/s00500-005-0486-8
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-005-0486-8