Biomaterial Database

Three-dimensional quantitative structure-activity relationships from molecular similarity matrices and genetic neural networks. 1. Method and validations. 1997

S S So, and M Karplus

Department of Chemistry and Chemical Biology, Harvard University, Cambridge, Massachusetts 02138, USA.

The utility of genetic neural network (GNN) to obtain quantitative structure-activity relationships (QSAR) from molecular similarity matrices is described. In this application, the corticosteroid-binding globulin (CBG) binding affinity of the well-known steroid data set is examined. Excellent predictivity can be obtained through the use of either electrostatic or shape properties alone. Statistical validation using a standard randomization test indicates that the results are not due to chance correlations. Application of GNN on the combined electrostatic and shape matrix produces a six-descriptor model with a cross-validated r2 value of 0.94. The model is superior to those obtained from partial least-squares and genetic regressions, and it also compares favorably with the results for the same data set from other established 3D QSAR methods. The theoretical basis for the use of molecular similarity in QSAR is discussed.

UI	MeSH Term	Description	Entries
D008956	Models, Chemical	Theoretical representations that simulate the behavior or activity of chemical processes or phenomena; includes the use of mathematical equations, computers, and other electronic equipment.	Chemical Models,Chemical Model,Model, Chemical
D011485	Protein Binding	The process in which substances, either endogenous or exogenous, bind to proteins, peptides, enzymes, protein precursors, or allied compounds. Specific protein-binding measures are often used as assays in diagnostic assessments.	Plasma Protein Binding Capacity,Binding, Protein
D000465	Algorithms	A procedure consisting of a sequence of algebraic formulas and/or logical steps to calculate or determine a given task.	Algorithm
D013256	Steroids	A group of polycyclic compounds closely related biochemically to TERPENES. They include cholesterol, numerous hormones, precursors of certain vitamins, bile acids, alcohols (STEROLS), and certain natural drugs and poisons. Steroids have a common nucleus, a fused, reduced 17-carbon atom ring system, cyclopentanoperhydrophenanthrene. Most steroids also have two methyl groups and an aliphatic side-chain attached to the nucleus. (From Hawley's Condensed Chemical Dictionary, 11th ed)	Steroid,Catatoxic Steroids,Steroids, Catatoxic
D013329	Structure-Activity Relationship	The relationship between the chemical structure of a compound and its biological or pharmacological activity. Compounds are often classed together because they have structural characteristics in common including shape, size, stereochemical arrangement, and distribution of functional groups.	Relationship, Structure-Activity,Relationships, Structure-Activity,Structure Activity Relationship,Structure-Activity Relationships
D014156	Transcortin	A serpin family member that binds to and transports GLUCOCORTICOIDS in the BLOOD.	Corticosteroid-Binding Globulin,Serpin A6,Corticosteroid Binding Globulin
D015394	Molecular Structure	The location of the atoms, groups or ions relative to one another in a molecule, as well as the number, type and location of covalent bonds.	Structure, Molecular,Molecular Structures,Structures, Molecular
D016571	Neural Networks, Computer	A computer architecture, implementable in either hardware or software, modeled after biological neural networks. Like the biological system in which the processing capability is a result of the interconnection strengths between arrays of nonlinear processing nodes, computerized neural networks, often called perceptrons or multilayer connectionist models, consist of neuron-like units. A homogeneous group of units makes up a layer. These networks are good at pattern recognition. They are adaptive, performing tasks by example, and thus are better for decision-making than are linear learning machines or cluster analysis. They do not require explicit programming.	Computational Neural Networks,Connectionist Models,Models, Neural Network,Neural Network Models,Neural Networks (Computer),Perceptrons,Computational Neural Network,Computer Neural Network,Computer Neural Networks,Connectionist Model,Model, Connectionist,Model, Neural Network,Models, Connectionist,Network Model, Neural,Network Models, Neural,Network, Computational Neural,Network, Computer Neural,Network, Neural (Computer),Networks, Computational Neural,Networks, Computer Neural,Networks, Neural (Computer),Neural Network (Computer),Neural Network Model,Neural Network, Computational,Neural Network, Computer,Neural Networks, Computational,Perceptron
D055672	Static Electricity	The accumulation of an electric charge on a object	Electrostatic,Electrostatics,Static Charge,Charge, Static,Charges, Static,Electricity, Static,Static Charges