Analyzing Biochemical Pathways Using Neural Networks and Genetic Algorithms

The analysis of biochemical pathways has recently gained much interest as these are the processes that keep us alive. A deeper understanding of biochemical reactions must analyze them at atomic resolution. In order to achieve that we have developed a reaction database with the information on the well known Biochemical Pathways wall chart. Based on that, 3D models of the substrates and intermediates of biochemical reactions can be built. It is shown how this information can be used for searching for inhibitors of enzyme catalyzed reactions by superimposition of 3D structures with a genetic algorithm. Physicochemical properties of the bonds directly involved in the reaction event allow a classification of these enzyme catalyzed reactions by self-organizing neural networks. This classification is compared with the enzyme code (EC) classification.

[1]  K N Houk,et al.  Why enzymes are proficient catalysts: beyond the Pauling paradigm. , 2005, Accounts of chemical research.

[2]  G. Stephanopoulos,et al.  Computer‐aided synthesis of biochemical pathways , 1990, Biotechnology and bioengineering.

[3]  Gerhard Klebe,et al.  Comparison of Automatic Three-Dimensional Model Builders Using 639 X-ray Structures , 1994, J. Chem. Inf. Comput. Sci..

[4]  J. Gasteiger,et al.  Calculation of the Charge Distribution in Conjugated Systems by a Quantification of the Resonance Concept , 1985 .

[5]  H. Holzhütter,et al.  Computational Design of Reduced Metabolic Networks , 2004, Chembiochem : a European journal of chemical biology.

[6]  Jakob Skou Pedersen,et al.  Gene finding with a hidden Markov model of genome structure and evolution , 2003, Bioinform..

[7]  Susumu Goto,et al.  LIGAND: database of chemical compounds and reactions in biological pathways , 2002, Nucleic Acids Res..

[8]  Johann Gasteiger,et al.  Hash codes for the identification and classification of molecular structure elements , 1994, J. Comput. Chem..

[9]  Johann Gasteiger,et al.  Query Generation to Search for Inhibitors of Enzymatic Reactions , 2006, J. Chem. Inf. Model..

[10]  Thomas Pfeiffer,et al.  Exploring the pathway structure of metabolism: decomposition into subnetworks and application to Mycoplasma pneumoniae , 2002, Bioinform..

[11]  L. Pauling,et al.  Nature of Forces between Large Molecules of Biological Interest , 1948, Nature.

[12]  M. G. Hutchings,et al.  Quantification of effective polarisability. Applications to studies of X-ray photoelectron spectroscopy and alkylamine protonation , 1984 .

[13]  Johann Gasteiger,et al.  Superposition of Three-Dimensional Chemical Structures Allowing for Conformational Flexibility by a Hybrid Method , 1998, J. Chem. Inf. Comput. Sci..

[14]  J. Åqvist,et al.  Computer Simulation of the Triosephosphate Isomerase Catalyzed Reaction (*) , 1996, The Journal of Biological Chemistry.

[15]  Erich Bornberg-Bauer,et al.  BioMiner - modeling, analyzing, and visualizing biochemical pathways and networks , 2002, ECCB.

[16]  J. Gasteiger,et al.  ITERATIVE PARTIAL EQUALIZATION OF ORBITAL ELECTRONEGATIVITY – A RAPID ACCESS TO ATOMIC CHARGES , 1980 .

[17]  J. Gasteiger,et al.  Enabling the exploration of biochemical pathways. , 2004, Organic & biomolecular chemistry.