ANN-QSAR model for selection of anticancer leads from structurally heterogeneous series of compounds.

Developing a model for predicting anticancer activity of any classes of organic compounds based on molecular structure is very important goal for medicinal chemist. Different molecular descriptors can be used to solve this problem. Stochastic molecular descriptors so-called the MARCH-INSIDE approach, shown to be very successful in drug design. Nevertheless, the structural diversity of compounds is so vast that we may need non-linear models such as artificial neural networks (ANN) instead of linear ones. SmartMLP-ANN analysis used to model the anticancer activity of organic compounds has shown high average accuracy of 93.79% (train performance) and predictability of 90.88% (validation performance) for the 8:3-MLP topology with different training and predicting series. This ANN model favourably compares with respect to a previous linear discriminant analysis (LDA) model [H. González-Díaz et al., J. Mol. Model 9 (2003) 395] that showed only 80.49% of accuracy and 79.34% of predictability. The present SmartMLP approach employed shorter training times of only 10h while previous models give accuracies of 70-89% only after 25-46 h of training. In order to illustrate the practical use of the model in bioorganic medicinal chemistry, we report the in silico prediction, and in vitro evaluation of six new synthetic tegafur analogues having IC(50) values in a broad range between 37.1 and 138 microgmL(-1) for leukemia (L1210/0) and human T-lymphocyte (Molt4/C8, CEM/0) cells. Theoretical predictions coincide very well with experimental results.

[1]  B. Winograd,et al.  Promising new developments in cancer chemotherapy , 1999, Cancer Chemotherapy and Pharmacology.

[2]  Christian Cachin,et al.  Pedagogical pattern selection strategies , 1994, Neural Networks.

[3]  Maykel Pérez González,et al.  A topological sub-structural approach of the mutagenic activity in dental monomers. 1. Aromatic epoxides , 2004 .

[4]  H. Wiener.  Structural determination of paraffin boiling points. , 1947, Journal of the American Chemical Society.

[5]  Miguel A. Cabrera,et al.  Markovian chemicals "in silico" design (MARCH-INSIDE), a promising approach for computer-aided molecular design I: discovery of anticancer compounds , 2003, Journal of molecular modeling.

[6]  Humberto González Díaz,et al.  Simple stochastic fingerprints towards mathematical modelling in biology and medicine. 1. The treatment of coccidiosis , 2004, Bulletin of mathematical biology.

[7]  P. Olinga,et al.  IN VITRO AND EX VIVO TEST SYSTEMS TO RATIONALIZE DRUG DESIGN AND DELIVERY , 1994 .

[8]  Ernesto Estrada,et al.  A novel approach for the virtual screening and rational design of anticancer compounds. , 2000, Journal of medicinal chemistry.

[9]  Eugenio Uriarte,et al.  Stochastic-based descriptors studying peptides biological properties: modeling the bitter tasting threshold of dipeptides. , 2004, Bioorganic & medicinal chemistry.

[10]  Ernesto Estrada,et al.  Characterization of the folding degree of proteins , 2002, Bioinform..

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

[12]  Han van de Waterbeemd,et al.  Chemometric Methods in Molecular Design: van de Waterbeemd/Chemometric , 1995 .

[13]  Humberto González Díaz,et al.  Symmetry considerations in Markovian chemicals 'in silico' design (MARCH-INSIDE) I: central chirality codification, classification of ACE inhibitors and prediction of \sigma-receptor antagonist activities , 2003, Comput. Biol. Chem..

[14]  Maykel Pérez González,et al.  TOPS-MODE approach to predict mutagenicity in dental monomers , 2004 .

[15]  Y. Martin,et al.  Quantitative drug design , 1978 .

[16]  J. Burdett,et al.  Moments method and elemental structures , 1985 .

[17]  Rafael Bello,et al.  Learning Optimization in a MLP Neural Network Applied to OCR , 2002, MICAI.

[18]  Ivan Gutman,et al.  Spectral moments of polymer graphs , 1996 .

[19]  E Uriarte,et al.  Recent advances on the role of topological indices in drug discovery research. , 2001, Current medicinal chemistry.

[20]  M. A. Cabrera Pérez,et al.  A novel approach to determining physicochemical and absorption properties of 6-fluoroquinolone derivatives: experimental assessment. , 2002, European journal of pharmaceutics and biopharmaceutics : official journal of Arbeitsgemeinschaft fur Pharmazeutische Verfahrenstechnik e.V.

[21]  H Kubinyi,et al.  Chance favors the prepared mind--from serendipity to rational drug design. , 1999, Journal of receptor and signal transduction research.

[22]  Carl Robert Noller,et al.  Chemistry of Organic Compounds , 1951 .

[23]  Humberto González Díaz,et al.  What Are the Limits of Applicability for Graph Theoretic Descriptors in QSPR/QSAR? Modeling Dipole Moments of Aromatic Compounds with TOPS-MODE Descriptors , 2003, J. Chem. Inf. Comput. Sci..

[24]  D. J. Triggle,et al.  Comprehensive medicinal chemistry II , 2006 .

[25]  Francisco Torrens,et al.  3D-chiral quadratic indices of the 'molecular pseudograph's atom adjacency matrix' and their application to central chirality codification: classification of ACE inhibitors and prediction of sigma-receptor antagonist activities. , 2004, Bioorganic & medicinal chemistry.

[26]  Maykel Pérez González,et al.  Designing Antibacterial Compounds through a Topological Substructural Approach , 2004, J. Chem. Inf. Model..

[27]  Han van de Waterbeemd,et al.  Chemometric methods in molecular design , 1995 .

[28]  S. Vilar,et al.  Probabilistic neural network model for the in silico evaluation of anti-HIV activity and mechanism of action. , 2006, Journal of medicinal chemistry.

[29]  E Estrada,et al.  In silico studies for the rational discovery of anticonvulsant compounds. , 2000, Bioorganic & medicinal chemistry.

[30]  J. Massagué.  TGF-beta signal transduction. , 1998, Annual review of biochemistry.

[31]  Humberto González-Díaz,et al.  Predicting stability of Arc repressor mutants with protein stochastic moments. , 2005, Bioorganic & medicinal chemistry.

[32]  Humberto González Díaz,et al.  Markovian negentropies in bioinformatics. 1. A picture of footprints after the interaction of the HIV-1 -RNA packaging region with drugs , 2003, Bioinform..

[33]  Humberto González Díaz,et al.  Markovian chemicals "in silico" design (MARCH-INSIDE), a promising approach for computer aided molecular design II: experimental and theoretical assessment of a novel method for virtual screening of fasciolicides , 2002, Journal of molecular modeling.

[34]  W. Denny.  The role of medicinal chemistry in the discovery of DNA-active anticancer drugs: from random searching, through lead development, to de novo design , 1992 .

[35]  Humberto González-Díaz,et al.  Markov entropy backbone electrostatic descriptors for predicting proteins biological activity. , 2004, Bioorganic & medicinal chemistry letters.

[36]  Maykel Pérez González,et al.  TOPS-MODE Based QSARs Derived from Heterogeneous Series of Compounds. Applications to the Design of New Herbicides , 2003, J. Chem. Inf. Comput. Sci..

[37]  L. Santana,et al.  1-Cyclopentyluracils: Synthesis and conformational analysis by X-ray crystallography and AM1 theoretical calculations , 1998 .

[38]  Ronal Ramos de Armas,et al.  Vibrational Markovian modelling of footprints after the interaction of antibiotics with the packaging region of HIV type 1 , 2003, Bulletin of mathematical biology.

[39]  Roberto Todeschini,et al.  Handbook of Molecular Descriptors , 2002 .

[40]  M. Palumbo,et al.  Antineoplastic agents 1998 , 1998 .

[41]  A. Balaban,et al.  Topological Indices and Related Descriptors in QSAR and QSPR , 2003 .

[42]  Ivan Gutman,et al.  Dependence of spectral moments of benzenoid hydrocarbons on molecular structure , 1991 .

[43]  Mark A. Murcko,et al.  Virtual screening : an overview , 1998 .