Results 1 
5 of
5
Analysis of the internal representations developed by neural networks for structures applied to quantitative structureactivity relationship studies of benzodiazepines
 J. Chem. Inf. Comput. Sci
, 2001
"... An application of recursive cascade correlation (CC) neural networks to quantitative structureactivity relationship (QSAR) studies is presented, with emphasis on the study of the internal representations developed by the neural networks. Recursive CC is a neural network model recently proposed for ..."
Abstract

Cited by 9 (3 self)
 Add to MetaCart
An application of recursive cascade correlation (CC) neural networks to quantitative structureactivity relationship (QSAR) studies is presented, with emphasis on the study of the internal representations developed by the neural networks. Recursive CC is a neural network model recently proposed for the processing of structured data. It allows the direct handling of chemical compounds as labeled ordered directed graphs, and constitutes a novel approach to QSAR. The adopted representation of molecular structure captures, in a quite general and flexible way, significant topological aspects and chemical functionalities for each specific class of molecules showing a particular chemical reactivity or biological activity. A class of 1,4benzodiazepin2ones is analyzed by the proposed approach. It compares favorably versus the traditional QSAR treatment based on equations. To show the ability of the model in capturing most of the structural features that account for the biological activity, the internal representations developed by the networks are analyzed by principal component analysis. This analysis shows that the networks are able to discover relevant structural features just on the basis of the association between the molecular morphology and the target property (affinity). I.
MOLecular Structure GENeration with MOLGEN, new features and future developments
 Fresenius J. Anal. Chem
, 1997
"... MOLGEN is a computer program system which is designed for generating molecular graphs fast, redundancy free and exhaustively. In the present paper we describe its basic features, new features of the current release MOLGEN 3.5, and future developments which provide considerable improvements and ex ..."
Abstract

Cited by 6 (4 self)
 Add to MetaCart
MOLGEN is a computer program system which is designed for generating molecular graphs fast, redundancy free and exhaustively. In the present paper we describe its basic features, new features of the current release MOLGEN 3.5, and future developments which provide considerable improvements and extensions. 1 Introduction MOLGEN [17] is a generator for molecular graphs (=connectivity isomers or constitutional formulae) allowing to generate all isomers that correspond to a given molecular formula and (optional) further conditions like prescribed and forbidden substructures, ring sizes etc. The input consists of ffl the empirical formula, together with ffl an optional list of macroatoms, which means prescribed substructures that must not overlap, ffl an optional goodlist, that consists of prescribed substructures which may overlap, ffl an optional badlist, containing forbidden substructures, ffl an optional interval for the minimal and maximal size of rings, ffl an optional num...
On a conjecture on wiener indices in combinatorial chemistry
 Proc. of the 9th International Computing and Combinatorics Conference ’03 , 2003
, 2004
"... Drugs and other chemical compounds are often modeled as polygonal shapes, where each vertex represents an atom of the molecule, and covalent bonds between atoms are represented by edges between the corresponding vertices. This polygonal shape derived from a chemical compound is often called its mole ..."
Abstract

Cited by 3 (0 self)
 Add to MetaCart
Drugs and other chemical compounds are often modeled as polygonal shapes, where each vertex represents an atom of the molecule, and covalent bonds between atoms are represented by edges between the corresponding vertices. This polygonal shape derived from a chemical compound is often called its molecular graph, and can be a path, a tree, or in general a graph. An indicator defined over this molecular graph, the Wiener index, has been shown to be strongly correlated to various chemical properties of the compound. The Wiener index conjecture for trees states that for any integerÒ(except for a finite set), one can find a tree with Wiener indexÒ. This conjecture has been open for quite some time, and many authors have presented incremental progress on this problem. In this paper, we present further progress towards proving this conjecture — through the design of efficient algorithms, we show that enumerating all possible trees to verify this conjecture (as done by all the previous approaches) is not necessary, but instead searching in a small special family of trees suffices, thus achieving the first polynomial (inÒ) time algorithm to verify the conjecture up to integerÒ. More precisely, we (�) present an infinite family of trees and prove various properties of these trees, (��) show that a large number of integers, up to at least�(compared with the previous best�) are representable as Wiener indices of trees in this succinct family, (���) provide several efficient algorithms for computing trees with given Wiener indices, (�Ú) implement our algorithms and experimentally show that their performance is asymptotically much better than their theoretical worstcase upper bound.
Wiener Indices of Balanced Binary Trees
"... Molecules and molecular compounds are often modeled by molecular graphs. One of the most widely known topological descriptor [6, 9] is the Wiener index named after chemist Harold Wiener [13]. The Wiener index of a graph G(V, E) is defined as W (G) = � ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
Molecules and molecular compounds are often modeled by molecular graphs. One of the most widely known topological descriptor [6, 9] is the Wiener index named after chemist Harold Wiener [13]. The Wiener index of a graph G(V, E) is defined as W (G) = �
Mathematical Simulations in Combinatorial Chemistry
, 1996
"... A novel technique for chemical synthesis in drug research is combinatorial chemistry, where usually a set of buildingblock molecules is attached to a core structure in all the combinatorially possible ways. The resulting set of compounds (called a library) can then be systematically screened for a ..."
Abstract
 Add to MetaCart
A novel technique for chemical synthesis in drug research is combinatorial chemistry, where usually a set of buildingblock molecules is attached to a core structure in all the combinatorially possible ways. The resulting set of compounds (called a library) can then be systematically screened for a desired biological activity. In this paper we discuss ways and limits of a mathematical simulation of this procedure. At first, two methods for selecting the buildingblocks from a given structure pool are presented with the objective to obtain only dissilimar library entries. Next an algorithm is described for the exhaustive and redundancyfree generation of a combinatorial library, illustrated by a singlestep and a multicomponent reaction. Finally equations for the enumeration of the library sizes are derived and the limits of the virtual combinatorial chemistry, i.e. purely in computer and without experiment, are discussed. 1