1,357 results match your criteria Journal of chemical information and computer sciences[Journal]


Application of machine learning to improve the results of high-throughput docking against the HIV-1 protease.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2216-24

Lead Discovery Center, Novartis Institutes for Biomedical Research, 250 Massachusetts Avenue, Cambridge, Massachusetts 02139, USA.

We have previously reported that the application of a Laplacian-modified naive Bayesian (NB) classifier may be used to improve the ranking of known inhibitors from a random database of compounds after High-Throughput Docking (HTD). The method relies upon the frequency of substructural features among the active and inactive compounds from 2D fingerprint information of the compounds. Here we present an investigation of the role of extended connectivity fingerprints in training the NB classifier against HTD studies on the HIV-1 protease using three docking programs: Glide, FlexX, and GOLD. Read More

View Article

Download full-text PDF

Source
http://pubs.acs.org/doi/abs/10.1021/ci0497861
Publisher Site
http://dx.doi.org/10.1021/ci0497861DOI Listing
November 2005
12 Reads

Generalization of a targeted library design protocol: application to 5-HT7 receptor ligands.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2207-15

Computational Chemistry, Department of Structural Chemistry, Biovitrum AB, S-112 76 Stockholm, Sweden.

Herein a general concept for the design of targeted libraries for proteins with binding sites that are divided into subsites is laid out, including several practical aspects and their solutions. The design is based on a chemogenomic classification of the subsites followed by collection of bioactive molecular fragments and virtual library generation. The general process is outlined and applied to the assembly of a library of 500 molecules targeting the serotonin type 7 (5-HT7) receptor, a class A G-Protein Coupled Receptor (GPCR). Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049822wDOI Listing
November 2005
5 Reads

REALISIS: a medicinal chemistry-oriented reagent selection, library design, and profiling platform.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2199-206

Johnson & Johnson Pharmaceutical Research and Development, a division of Janssen Pharmaceutica NV, Turnhoutseweg 30, B-23 40 Beerse, Belgium.

REALISIS is a software system for reagent selection, library design, and profiling, developed to fit the workflow of bench chemists and medicinal chemists. Designed to be portable, the software offers a comprehensive graphical user interface and rapid, integrated functionalities required for reagent retrieval and filtering, product enumeration, and library profiling. REALISIS is component-based, consisting of four main modules: reagent searching; reagent filtering; library enumeration; and library profiling. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049879iDOI Listing
November 2005
14 Reads
4 Citations

SitePrint: three-dimensional pharmacophore descriptors derived from protein binding sites for family based active site analysis, classification, and drug design.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2190-8

Department of Pharmaceutical Chemistry, School of Pharmacy, University of California San Francisco, Box 2240, N474-A Genentech Hall, San Francisco, California 94143-2240, USA.

Integrating biological and chemical information is one key task in drug discovery, and one approach to attaining this goal is via three-dimensional pharmacophore descriptors derived from protein binding sites. The SitePrint program generates, aligns, scores, and classifies three-dimensional pharmacophore descriptors, active site grids, and ligand surfaces. The descriptors are formed from molecular fragments that have been docked, minimized, filtered, and clustered in protein active sites. Read More

View Article

Download full-text PDF

Source
http://pubs.acs.org/doi/abs/10.1021/ci049814f
Publisher Site
http://dx.doi.org/10.1021/ci049814fDOI Listing
November 2005
42 Reads

Development of linear, ensemble, and nonlinear models for the prediction and interpretation of the biological activity of a set of PDGFR inhibitors.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2179-89

Department of Chemistry, Penn State University, University Park, Pennsylvania 16802, USA.

A QSAR modeling study has been done with a set of 79 piperazyinylquinazoline analogues which exhibit PDGFR inhibition. Linear regression and nonlinear computational neural network models were developed. The regression model was developed with a focus on interpretative ability using a PLS technique. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049849fDOI Listing
November 2005
11 Reads

CoMFA 3D-QSAR analysis of HIV-1 RT nonnucleoside inhibitors, TIBO derivatives based on docking conformation and alignment.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2167-78

Department of Chemistry and Biochemistry, Duquesne University, Pittsburgh, Pennsylvania 15282, USA.

HIV-1 RT is one of the key enzymes in the duplication of HIV-1. Inhibitors of HIV-1 RT are classified as nonnucleoside RT inhibitors (NNRTIs) and nucleoside analogues. NNRTIs bind in a region not associated with the active site of the enzyme. Read More

View Article

Download full-text PDF

Source
http://www.csb.pitt.edu/archive/pcbc/publications/zhou.%26.m
Web Search
http://pubs.acs.org/cgi-bin/doilookup/?10.1021/ci049893v
Publisher Site
http://dx.doi.org/10.1021/ci049893vDOI Listing
November 2005
10 Reads

Design and characterization of libraries of molecular fragments for use in NMR screening against protein targets.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2157-66

Vernalis (R&D) Ltd., Granta Park, Abington, Cambridge CB1 6GB, UK.

We have designed four generations of a low molecular weight fragment library for use in NMR-based screening against protein targets. The library initially contained 723 fragments which were selected manually from the Available Chemicals Directory. A series of in silico filters and property calculations were developed to automate the selection process, allowing a larger database of 1. Read More

View Article

Download full-text PDF

Source
http://pubs.acs.org/doi/abs/10.1021/ci049806z
Publisher Site
http://dx.doi.org/10.1021/ci049806zDOI Listing
November 2005
15 Reads

The reduced graph descriptor in virtual screening and data-driven clustering of high-throughput screening data.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2145-56

GlaxoSmithKline, Gunnels Wood Road, Stevenage SG1 2NY, United Kingdom.

Virtual screening and high-throughput screening are two major components of lead discovery within the pharmaceutical industry. In this paper we describe improvements to previously published methods for similarity searching with reduced graphs, with a particular focus on ligand-based virtual screening, and describe a novel use of reduced graphs in the clustering of high-throughput screening data. Literature methods for reduced graph similarity searching encode the reduced graphs as binary fingerprints, which has a number of issues. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049860fDOI Listing
November 2005
15 Reads

Retrieval of crystallographically-derived molecular geometry information.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2133-44

Cambridge Crystallographic Data Centre, 12 Union Road, Cambridge CB2 1EZ, England.

The crystallographically determined bond length, valence angle, and torsion angle information in the Cambridge Structural Database (CSD) has many uses. However, accessing it by means of conventional substructure searching requires nontrivial user intervention. In consequence, these valuable data have been underutilized and have not been directly accessible to client applications. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049780bDOI Listing
November 2005
5 Reads

Binding of fatty acids to beta-cryptogein: quantitative structure-activity relationships and design of selective protein mutants.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2126-32

National Centre for Biomolecular Research and Department of Biochemistry, Faculty of Science, Masaryk University, Kotlarska 2, 611 37 Brno, Czech Republic.

Binding of fatty acids to cryptogein, the proteinaceous elicitor from Phytophthora, was studied by using molecular docking and quantitative structure-activity relationships analysis. Fatty acids bind to the groove located inside the cavity of cryptogein. The structure-activity model was constructed for the set of 27 different saturated and unsaturated fatty acids explaining 87% (81% cross-validated) of the quantitative variance in their binding affinity. Read More

View Article

Download full-text PDF

Source
http://pubs.acs.org/doi/abs/10.1021/ci049832x
Publisher Site
http://dx.doi.org/10.1021/ci049832xDOI Listing
November 2005
51 Reads

An extensive test of 14 scoring functions using the PDBbind refined set of 800 protein-ligand complexes.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2114-25

Department of Internal Medicine and Comprehensive Cancer Center, University of Michigan Medical School, Ann Arbor, Michigan 48109-0934, USA.

Fourteen popular scoring functions, i.e., X-Score, DrugScore, five scoring functions in the Sybyl software (D-Score, PMF-Score, G-Score, ChemScore, and F-Score), four scoring functions in the Cerius2 software (LigScore, PLP, PMF, and LUDI), two scoring functions in the GOLD program (GoldScore and ChemScore), and HINT, were tested on the refined set of the PDBbind database, a set of 800 diverse protein-ligand complexes with high-resolution crystal structures and experimentally determined Ki or Kd values. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049733jDOI Listing
November 2005
10 Reads

New approach by Kriging models to problems in QSAR.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2106-13

Department of Mathematics, Hong Kong Baptist University, Hong Kong, China, College of Mathematics and Statistics, Wuhan University, Wuhan 430072, PR China.

Most models in quantitative structure and activity relationship (QSAR) research, proposed by various techniques such as ordinary least squares regression, principal components regression, partial least squares regression, and multivariate adaptive regression splines, involve a linear parametric part and a random error part. The random errors in those models are assumed to be independently identical distributed. However, the independence assumption is not reasonable in many cases. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049798mDOI Listing
November 2005
7 Reads

Quantitative structure-activity relationship for cyclic imide derivatives of protoporphyrinogen oxidase inhibitors: a study of quantum chemical descriptors from density functional theory.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2099-105

Key Laboratory of Pesticide & Chemical Biology (CCNU), Ministry of Education, College of Chemistry, Central China Normal University, Wuhan 430079, PR China.

This study examined the applicability of various density functional theory (DFT)-based descriptors, such as energy gap (DeltaE) between the highest occupied molecular orbital (HOMO) and the lowest unoccupied molecular orbital (LUMO), weighted nucleophilic atomic frontier electron density (WNAFED, FNi), mean molecular polarizability (alpha), and net atomic charge (Qi), in quantitative structure-activity relationship (QSAR) studies on a class of important protoporphyrinogen oxidase (Protox) inhibitors including a series of cyclic imide derivatives with various heterocyclic rings and substituents. Our QSAR analysis using the quantum chemical descriptors calculated at the B3LYP/6-31G(d,p) level led to a useful explicit correlation relationship, i.e. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049793pDOI Listing
November 2005
10 Reads

Constructing optimum blood brain barrier QSAR models using a combination of 4D-molecular similarity measures and cluster analysis.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2083-98

Laboratory of Molecular Modeling and Design (M/C 781), College of Pharmacy, The University of Illinois at Chicago, 833 South Wood Street, Chicago, Illinois 60612-7231, USA.

A new method, using a combination of 4D-molecular similarity measures and cluster analysis to construct optimum QSAR models, is applied to a data set of 150 chemically diverse compounds to build optimum blood-brain barrier (BBB) penetration models. The complete data set is divided into subsets based on 4D-molecular similarity measures using cluster analysis. The compounds in each cluster subset are further divided into a training set and a test set. Read More

View Article

Download full-text PDF

Source
http://pubs.acs.org/doi/abs/10.1021/ci0498057
Publisher Site
http://dx.doi.org/10.1021/ci0498057DOI Listing
November 2005
10 Reads

How H-bonding affects aromaticity of the ring in variously substituted phenol complexes with bases. 4. Molecular geometry as a source of chemical information.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2077-82

Department of Chemistry, Warsaw University, Pasteura 1, 02-093 Warsaw, Poland.

Aromaticity of the ring of variously substituted phenols in their H-bonded complexes with various bases was a subject of analysis based on 664 geometries retrieved from CSD and by use of the aromaticity index HOMA. GEO and EN, the components of the HOMA index, describing a decrease of aromaticity due to an increase of bond alternation (GEO term) and bond elongation (EN term), were also studied. There is an approximate monotonic dependence of HOMA and GEO on the H-bond strength estimated by the C-O bond length of the hydroxyl group in phenols. Read More

View Article

Download full-text PDF

Source
http://pubs.acs.org/doi/abs/10.1021/ci049817s
Publisher Site
http://dx.doi.org/10.1021/ci049817sDOI Listing
November 2005
16 Reads

QSPR using MOLGEN-QSPR: the example of haloalkane boiling points.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2070-6

Department of Mathematics, Universität Bayreuth, D-95440 Bayreuth, Germany.

MOLGEN-QSPR is a software newly developed for use in quantitative structure property relationships (QSPR) work. It allows to import, to manually edit, or to generate chemical structures, to detect duplicate structures, to import or to manually input property values, to calculate the values of a broad pool of molecular descriptors, to establish QSPR equations (models), and using such models to predict unknown property values. In connection with the molecule generator MOLGEN, MOLGEN-QSPR is able to predict property values for all compounds in a predetermined structure space (inverse QSPR). Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049802uDOI Listing
November 2005
7 Reads

Use of classification regression tree in predicting oral absorption in humans.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2061-9

ZyxBio, LLC, PO Box 2255, Hudson, Ohio 44236, USA.

The purpose of this study is to explore the use of classification regression trees (CART) in predicting, in the dose-independent range, the fraction dose absorbed in humans. Since the results from clinical formulations in humans were used for training the model, a hypothetical state of drug molecules already dissolved in the intestinal fluid was adopted. Therefore, the molecular attributes affecting dissolution were not considered in the model. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci040023nDOI Listing
November 2005
9 Reads

EChem++--an object-oriented problem solving environment for electrochemistry. 2. The kinetic facilities of Ecco--a compiler for (electro-)chemistry.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2051-60

Institut für Organische Chemie, Universität Tübingen, Auf der Morgenstelle 18, D-72076 Tübingen, Germany.

We describe a modeling software component Ecco, implemented in the C++ programming language. It assists in the formulation of physicochemical systems including, in particular, electrochemical processes within general geometries. Ecco's kinetic part then translates any user defined reaction mechanism into an object-oriented representation and generates the according mathematical model equations. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci0497814DOI Listing
November 2005
9 Reads

Semiempirical quantum chemical method and artificial neural networks applied for lambdamax computation of some azo dyes.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2047-50

Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, China 200030.

The maximum absorption wavelengths of 31 azo dyes have been calculated by two comprehensive methods using the semiempirical quantum chemical method, PM3, and the weight decay based artificial neural network (WD-ANN) or the early stopping based artificial neural network (ES-ANN). The average absolute errors of WD-ANN and that of ES-ANN are 10.07 nm and 12. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049941bDOI Listing
November 2005
9 Reads

Diagnosing anorexia based on partial least squares, back propagation neural network, and support vector machines.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2040-6

Department of Chemistry, Lanzhou University, Lanzhou 730000, China.

Support vector machine (SVM), as a novel type of learning machine, for the first time, was used to develop a predictive model for early diagnosis of anorexia. It was based on the concentration of six elements (Zn, Fe, Mg, Cu, Ca, and Mn) and the age extracted from 90 cases. Compared with the results obtained from two other classifiers, partial least squares (PLS) and back-propagation neural network (BPNN), the SVM method exhibited the best whole performance. Read More

View Article

Download full-text PDF

Source
http://pubs.acs.org/doi/abs/10.1021/ci049877y
Publisher Site
http://dx.doi.org/10.1021/ci049877yDOI Listing
November 2005
9 Reads

Similarity search profiling reveals effects of fingerprint scaling in virtual screening.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2032-9

Department of Computer-Aided Drug Discovery, Albany Molecular Research, Inc., AMRI Bothell Research Center, 18804 North Creek Parkway, Bothell, Washington 98011-8012, USA.

Fingerprint scaling is a method to increase the performance of similarity search calculations. It is based on the detection of bit patterns in keyed fingerprints that are signatures of specific compound classes. Application of scaling factors to consensus bits that are mostly set on emphasizes signature bit patterns during similarity searching and has been shown to improve search results for different fingerprints. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci0400819DOI Listing
November 2005
5 Reads

Optimized partition of minimum spanning tree for piecewise modeling by particle swarm algorithm. QSAR studies of antagonism of angiotensin II antagonists.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2027-31

State Key Laboratory of Chemo/Biosensing and Chemometrics, College of Chemistry and Chemical Engineering, Hunan University, Changsha 410082, China.

In quantitative structure-activity relationship (QSAR) modeling, when compounds in a training set exhibit a significant structural distinction between each other, in particular when chemicals of biological interest interacting on the receptor involve a different mechanism, it might be difficult to construct a single linear model for the whole population of compounds of interest with desired residuals. Developing a piecewise linear local model can be effective to circumvent the aforementioned problem. In this paper, piecewise modeling by the particle swarm optimization (PMPSO) approach is applied to QSAR study. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci034292+DOI Listing
November 2005
10 Reads

Linear indices of the "molecular pseudograph's atom adjacency matrix": definition, significance-interpretation, and application to QSAR analysis of flavone derivatives as HIV-1 integrase inhibitors.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):2010-26

Department of Pharmacy, Faculty of Chemical-Pharmacy, and Department of Drug Design, Chemical Bioactive Center, Central University of Las Villas, Santa Clara, 54830, Villa Clara, Cuba.

This report describes a new set of molecular descriptors of relevance to QSAR/QSPR studies and drug design, atom linear indices fk(xi). These atomic level chemical descriptors are based on the calculation of linear maps on Rn[fk(xi): Rn--> Rn] in canonical basis. In this context, the kth power of the molecular pseudograph's atom adjacency matrix [Mk(G)] denotes the matrix of fk(xi) with respect to the canonical basis. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049950kDOI Listing
November 2005
12 Reads

A new statistical approach to predicting aromatic hydroxylation sites. Comparison with model-based approaches.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):1998-2009

Laboratory of Structure-Function Based Drug Design, Institute of Biomedical Chemistry of the Russian Academy of Medical Sciences, 10 Pogodinskaya Str., Moscow 119121, Russia.

A new approach is described that is able to predict the most probable metabolic sites on the basis of a statistical analysis of various metabolic transformations reported in the literature. The approach is applied to the prediction of aromatic hydroxylation sites for diverse sets of substrates. Training is performed using the aromatic hydroxylation reactions from the Metabolism database (Accelrys). Read More

View Article

Download full-text PDF

Source
http://pubs.acs.org/doi/abs/10.1021/ci049834h
Publisher Site
http://dx.doi.org/10.1021/ci049834hDOI Listing
November 2005
12 Reads

Benzo[c]quinolizin-3-ones theoretical investigation: SAR analysis and application to nontested compounds.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):1987-97

Instituto de Física Gleb Wataghin, Universidade Estadual de Campinas, CP 6165, CEP 13083-970, Campinas -SP, Brazil.

We investigate with the use of theoretical methodologies the activity of a set of 41 benzo[c]quinolizin-3-ones (BC3), some of them explored as selective inhibitors of the human 5alpha-reductase steroid. For the structure-activity study we have considered dividing the molecules into groups of tested and nontested compounds. Semiempirical calculations and pattern recognition methods such as Electronic Indices Methodology (EIM), Principal Components Analysis (PCA), Hierarchical Cluster Analysis (HCA), and K-Nearest Neighbors (KNN) have been applied to search for a correlation between experimental activity and theoretical descriptors. Read More

View Article

Download full-text PDF

Source
http://pubs.acs.org/doi/abs/10.1021/ci049837u
Publisher Site
http://dx.doi.org/10.1021/ci049837uDOI Listing
November 2005
8 Reads

Quantitative prediction of logk of peptides in high-performance liquid chromatography based on molecular descriptors by using the heuristic method and support vector machine.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):1979-86

Department of Chemistry, Lanzhou University, Lanzhou 730000, China.

A new method support vector machine (SVM) and the heuristic method (HM) were used to develop the nonlinear and linear models between the capacity factor (logk) and seven molecular descriptors of 75 peptides for the first time. The molecular descriptors representing the structural features of the compounds only included the constitutional and topological descriptors, which can be obtained easily without optimizing the structure of the molecule. The seven molecular descriptors selected by the heuristic method in CODESSA were used as inputs for SVM. Read More

View Article

Download full-text PDF

Source
http://pubs.acs.org/doi/abs/10.1021/ci049891a
Publisher Site
http://dx.doi.org/10.1021/ci049891aDOI Listing
November 2005
11 Reads

Ensemble methods for classification in cheminformatics.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):1971-8

Computational Biology & Applied Algorithmics Group, Max-Planck-Institut für Informatik, Stuhlsatzenhauseg 85, 66123 Saarbrücken, Germany, and Roche Pharma Research, Basel, Switzerland.

We describe the application of ensemble methods to binary classification problems on two pharmaceutical compound data sets. Several variants of single and ensembles models of k-nearest neighbors classifiers, support vector machines (SVMs), and single ridge regression models are compared. All methods exhibit robust classification even when more features are given than observations. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049850eDOI Listing
November 2005
6 Reads

Comparing ligand interactions with multiple receptors via serial docking.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):1961-70

Center for Advanced Research in Biotechnology, U Maryland Biotechnology Institute, 9600 Gudelsky Drive, Rockville, Maryland 20850, USA.

Standard uses of ligand-receptor docking typically focus on the association of candidate ligands with a single targeted receptor, but actual applications increasingly require comparisons across multiple receptors. This study demonstrates that comparative docking to multiple receptors can help to select homology models for virtual compound screening and to discover ligands that bind to one set of receptors but not to another, potentially similar, set. A serial docking algorithm is furthermore described that reduces the computational costs of such calculations by testing compounds against a series of receptor structures and discarding a compound as soon as it fails to satisfy specified bind/no bind criteria for each receptor. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049803mDOI Listing
November 2005
6 Reads

Computational models for the helix tilt angle.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):1952-60

Department of ECECS, University of Cincinnati, Cincinnati, Ohio 45221-0030, USA.

The concept of hydrophobic imbalance and that of hydrophobic and hydrophilic centers are used along with side chain models in the computation of helix orientation and tilt angle in or near a membrane. Rotamer statistics are used to infer typical side chain positions and chain length for each amino acid, and the results are used in fast computation of helix orientation. Sliding windows are used to compute local tilt angles on long alpha-helices that defy idealized modeling and generate tilt angle profiles. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049859gDOI Listing
November 2005
7 Reads

Expanded interaction fingerprint method for analyzing ligand binding modes in docking and structure-based drug design.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):1942-51

Department of Pharmacology, University of Cambridge, Tennis Court Road, Cambridge CB2 1QJ, UK.

An expanded interaction fingerprint method has been developed for analyzing the binding modes of ligands in docking and structure-based design methods. Taking the basic premise of representing a ligand in terms of a binary string that denotes its interactions with a target protein, we have expanded the method to include additional interaction-specific information. By considering the hydrogen-bonding strength and/or accessibility of the hydrogen bonding groups within a binding site as well as their geometric arrangement we aim to provide a better representation of a ligand-protein interaction. Read More

View Article

Download full-text PDF

Source
http://pubs.acs.org/doi/abs/10.1021/ci049870g
Publisher Site
http://dx.doi.org/10.1021/ci049870gDOI Listing
November 2005
13 Reads

Active learning with support vector machine applied to gene expression data for cancer classification.

Authors:
Ying Liu

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):1936-41

Georgia Institute of Technology, College of Computing, Atlanta, Georgia 30322, USA.

There is growing interest in the application of machine learning techniques in bioinformatics. The supervised machine learning approach has been widely applied to bioinformatics and gained a lot of success in this research area. With this learning approach researchers first develop a large training set, which is a time-consuming and costly process. Read More

View Article

Download full-text PDF

Source
http://pubs.acs.org/doi/abs/10.1021/ci049810a
Publisher Site
http://dx.doi.org/10.1021/ci049810aDOI Listing
November 2005
13 Reads

Accelerated K-means clustering in metric spaces.

Authors:
Andrew Smellie

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):1929-35

ArQule Inc., 19 Presidential Way, Woburn, Massachusetts 01801, USA.

The K-means method is a popular technique for clustering data into k-partitions. In the adaptive form of the algorithm, Lloyds method, an iterative procedure alternately assigns cluster membership based on a set of centroids and then redefines the centroids based on the computed cluster membership. The most time-consuming part of this algorithm is the determination of which points being clustered belong to which cluster center. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci0499222DOI Listing
November 2005
5 Reads

Similarity to molecules in the training set is a good discriminator for prediction accuracy in QSAR.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):1912-28

Molecular Systems Department, RY50S-100 Merck Research Laboratories, Rahway, New Jersey 07065, USA.

How well can a QSAR model predict the activity of a molecule not in the training set used to create the model? A set of retrospective cross-validation experiments using 20 diverse in-house activity sets were done to find a good discriminator of prediction accuracy as measured by root-mean-square difference between observed and predicted activity. Among the measures we tested, two seem useful: the similarity of the molecule to be predicted to the nearest molecule in the training set and/or the number of neighbors in the training set, where neighbors are those more similar than a user-chosen cutoff. The molecules with the highest similarity and/or the most neighbors are the best-predicted. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049782wDOI Listing
November 2005
39 Reads

Representation of the molecular topology of cyclical structures by means of cycle graphs. 3. Hierarchical model of screening of chemical databases.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):1903-11

Department of Computing and Numerical Analysis, University of Córdoba, Campus Universitario de Rabanales, Albert Einstein Building, E-14071 Córdoba, Spain.

The increase in the size and complexity of chemical databases necessitates the proposal and development of efficient methods of classification and recovery of information, which supposes proposal of a model of classification of database records and the use of a compatible model of screening for inspection of clusters and recovery of the molecules that satisfy the search criterion. The cycle graphs model based on consideration of all the cycles and chains (and equivalent cycles and chains) present in the molecular structure has been proven appropriate for classification of chemical databases, giving rise to a generation of different classification levels depending on the structural elements (cycles and chains) that are considered. In this paper we propose a screening model, compatible with the cycle graphs model, based on a hierarchy of levels of abstraction. Read More

View Article

Download full-text PDF

Source
http://pubs.acs.org/doi/abs/10.1021/ci049889j
Publisher Site
http://dx.doi.org/10.1021/ci049889jDOI Listing
November 2005
11 Reads

Combining unsupervised and supervised artificial neural networks to predictaquatic toxicity.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):1897-902

DEI, Politecnico di Milano, Piazza Leonardo da Vinci 31, 20131 Milano, Italy.

Most quantitative structure-activity relationship (QSAR) models are linear relationships and significant for only a limited domain of compounds. Here we propose a data-driven approach with a flexible combination of unsupervised and supervised neural networks able to predict the toxicity of a large set of different chemicals while still respecting the QSAR postulates. Since QSAR is applicable only to similar compounds, which have similar biological and physicochemical properties, large numbers of compounds are clustered before building local models, and local models are ensembled to obtain the final result. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci0401219DOI Listing
November 2005
5 Reads

Molecules-in-molecule estimation of the extent of localization of Kekuléan substructures in polycyclic aromatic hydrocarbons.

J Chem Inf Comput Sci 2004 Nov-Dec;44(6):1891-6

Department of Chemistry, Joetsu University of Education, Joetsu 943-8512, Japan.

This article first revises graph-theoretical (local aromaticity and overall molecular) indices, introduced by M. Randić in 1975, for benzenoid hydrocarbons and somewhat improves them for computer enumeration. This goes beyond total Kekulé structure enumeration, yielding an index calculation useful for the quantitative estimation of localization of different Kekuléan substructures (including ethylene-, benzene-, annulene-, and radialene-units). Read More

View Article

Download full-text PDF

Source
http://pubs.acs.org/doi/abs/10.1021/ci049894n
Publisher Site
http://dx.doi.org/10.1021/ci049894nDOI Listing
November 2005
7 Reads

Personal experience with four kinds of chemical structure drawing software: review on ChemDraw, ChemWindow, ISIS/Draw, and ChemSketch.

J Chem Inf Comput Sci 2004 Sep-Oct;44(5):1886-90

College of Life Science and Pharmaceutical Engineering, Nanjing University of Technology, Nanjing 210009, China.

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049794hDOI Listing
November 2005
43 Reads

The Merck index 13.2 CD-ROM edition from CambridgeSoft.

Authors:
William G Town

J Chem Inf Comput Sci 2004 Sep-Oct;44(5):1883-5

Kilmorie Consulting, 24A Elsinore Road, Forest Hill, London SE23 2SL, United Kingdom.

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci0400462DOI Listing
November 2005
4 Reads

Enzyme binding selectivity prediction: alpha-thrombin vs trypsin inhibition.

J Chem Inf Comput Sci 2004 Sep-Oct;44(5):1872-82

Laboratories of Molecular Modeling and NMR Spectroscopy and of Chemometrics, National Institute of Chemistry, Hajdrihova 19, P.O. Box 660, 1001 Ljubljana, Slovenia.

In the present work we explore the possibility of an in-depth computational analysis of available experimental X-ray structures in the specific case of a series of alpha-thrombin and trypsin complexes with their respective inhibitors for the development of a novel scoring function based on molecular electrostatic potential computed at the contact surface in the enzyme-inhibitor molecular complex. We subsequently employ the chemometrical approach to determine which are the interactions in the large volume of data that determine the resulting experimental binding constant between ligand and receptor. The results of the model evaluated with molecules in the independent validation set show that a reasonable average error of 1. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci0401017DOI Listing
November 2005
5 Reads

A ligand-based molecular modeling study on some matrix metalloproteinase-1 inhibitors using several 3D QSAR techniques.

J Chem Inf Comput Sci 2004 Sep-Oct;44(5):1857-71

Institute of Molecular Medicine & Department of Life Science, National Tsing Hua University, Hsinchu 30013, Taiwan.

Some three-dimensional quantitative structure-activity relationship (3D-QSAR) models have been constructed using the comparative molecular field analysis (CoMFA) and comparative molecular similarity indices (CoMSIA) for a series of 84 proline-based plus 12 structurally more diversified nonproline matrix metalloproteinase inhibitors. The structures of these inhibitors were built from a structure template extracted from the crystal structure of stromelysin. The structures built were divided into the training and test sets for both the CoMFA and CoMSIA analyses for each being composed of 60 and 24 inhibitors, respectively. Read More

View Article

Download full-text PDF

Source
http://pubs.acs.org/doi/abs/10.1021/ci049824g
Publisher Site
http://dx.doi.org/10.1021/ci049824gDOI Listing
November 2005
9 Reads

Influenza virus neuraminidase inhibitors: generation and comparison of structure-based and common feature pharmacophore hypotheses and their application in virtual screening.

J Chem Inf Comput Sci 2004 Sep-Oct;44(5):1849-56

Institute of Pharmacy, Computer Aided Molecular Design Group, University of Innsbruck, Innrain 52, A-6020 Innsbruck, Austria.

X-ray crystallographic data of the influenza virus neuraminidase in complex with different inhibitors were used to generate chemical feature-based pharmacophore models of the binding site of this enzyme. The models were built using the software package Catalyst. Pharmacophore hypotheses derived from the 3-D structure of ligands cocrystallized with the enzyme were then compared with automatically generated common feature pharmacophore hypotheses for neuraminidase inhibitors. Read More

View Article

Download full-text PDF

Source
http://pubs.acs.org/doi/abs/10.1021/ci049844i
Publisher Site
http://dx.doi.org/10.1021/ci049844iDOI Listing
November 2005
11 Reads

Enhancing the effectiveness of virtual screening by fusing nearest neighbor lists: a comparison of similarity coefficients.

J Chem Inf Comput Sci 2004 Sep-Oct;44(5):1840-8

Krebs Institute for Biomolecular Research and Department of Information Studies, University of Sheffield, Western Bank, Sheffield S10 2TN, U.K.

This paper evaluates the effectiveness of various similarity coefficients for 2D similarity searching when multiple bioactive target structures are available. Similarity searches using several different activity classes within the MDL Drug Data Report and the Dictionary of Natural Products databases are performed using BCI 2D fingerprints. Using data fusion techniques to combine the resulting nearest neighbor lists we obtain group recall results which, in many cases, are a considerable improvement on standard average recall values obtained for individual structures. Read More

View Article

Download full-text PDF

Source
http://pubs.acs.org/doi/abs/10.1021/ci049867x
Publisher Site
http://dx.doi.org/10.1021/ci049867xDOI Listing
November 2005
28 Reads

Insights into phenylalanine derivatives recognition of VLA-4 integrin: from a pharmacophoric study to 3D-QSAR and molecular docking analyses.

J Chem Inf Comput Sci 2004 Sep-Oct;44(5):1829-39

Dipartimento di Chimica e Tecnologia del Farmaco, Università di Perugia, via del Liceo 1, 06127 Perugia, Italy.

The very late antigen-4 (VLA-4), also known as integrin alpha4beta1, is expressed on monocytes, T- and B-lympohocytes, basophils, and eosinophils and is involved in the massive recruitment of granulocytes in different pathological conditions such as multiple sclerosis and asthma. VLA-4 interacts with its endogenous ligand VCAM-1 during chronic inflammation, and blockade of VLA-4 /VCAM-1 interaction is a potential target for immunosuppression. Two classes of VLA-4 antagonists have so far been reported: beta-amino acid derivatives containing a diaryl urea moiety (BIO-1211) and phenylalanine derivatives (TR-14035). Read More

View Article

Download full-text PDF

Source
http://pubs.acs.org/doi/abs/10.1021/ci049914l
Publisher Site
http://dx.doi.org/10.1021/ci049914lDOI Listing
November 2005
21 Reads

A comparative study on feature selection methods for drug discovery.

Authors:
Ying Liu

J Chem Inf Comput Sci 2004 Sep-Oct;44(5):1823-8

Georgia Institute of Technology, College of Computing, Atlanta, Georgia 30322, USA.

Feature selection is frequently used as a preprocessing step to machine learning. The removal of irrelevant and redundant information often improves the performance of learning algorithms. This paper is a comparative study of feature selection in drug discovery. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049875dDOI Listing
November 2005
10 Reads

Comparison of 2D similarity and 3D superposition. Application to searching a conformational drug database.

J Chem Inf Comput Sci 2004 Sep-Oct;44(5):1816-22

Institut für Informatik, Humboldt-Universität zu Berlin, 10099 Berlin, Germany.

In a database of about 2000 approved drugs, represented by 10(5) structural conformers, we have performed 2D comparisons (Tanimoto coefficients) and 3D superpositions. For one class of drugs the correlation between structural resemblance and similar action was analyzed in detail. In general Tanimoto coefficients and 3D scores give similar results, but we find that 2D similarity measures neglect important structural/funtional features. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049920hDOI Listing
November 2005
8 Reads

Defining privileged reagents using subsimilarity comparison.

J Chem Inf Comput Sci 2004 Sep-Oct;44(5):1810-5

Johnson & Johnson Pharmaceutical Research and Development, L.L.C., P.O. Box 776, Welsh and McKean Roads, Spring House, Pennsylvania 19477-0776, USA.

We have developed a new method for assigning a drug-like score to reagents. This algorithm uses topological torsion (TT) 2D descriptors to compute the subsimilarity of any given reagent to a substructural element of any compound in the CMC. The utility of this approach is demonstrated by scoring a test set of reagents derived from the "Comprehensive Survey of Combinatorial Library Synthesis: 2000" (J. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049854jDOI Listing
November 2005
4 Reads

Application of the PharmPrint methodology to two protein kinases.

J Chem Inf Comput Sci 2004 Sep-Oct;44(5):1803-9

Computational, Analytical, and Structural Sciences, GlaxoSmithKline, Five Moore Drive, Research Triangle Park, North Carolina 27709, USA.

The PharmPrint methodology developed by McGregor and Muskal1,2 was used to construct quantitative structure-activity relationship (QSAR) models for the prediction of cyclin-dependent kinase-2 (CDK2) and vascular endothelial growth factor receptor-2 (VEGFR2) inhibition. The QSAR models were constructed based on a binary description of biological activity--a value of zero for inactive and one for active compounds. Subsets of "active" kinase inhibitors (that is, inhibitors with pIC50 > or = 6. Read More

View Article

Download full-text PDF

Source
http://pubs.acs.org/doi/abs/10.1021/ci0498968
Publisher Site
http://dx.doi.org/10.1021/ci0498968DOI Listing
November 2005
14 Reads

Validated QSAR prediction of OH tropospheric degradation of VOCs: splitting into training-test sets and consensus modeling.

J Chem Inf Comput Sci 2004 Sep-Oct;44(5):1794-802

Department of Structural and Functional Biology, QSAR and Environmental Chemistry Research Unit, University of Insubria, via Dunant 3, 21100 Varese, Italy.

The rate constant for hydroxyl radical tropospheric degradation of 460 heterogeneous organic compounds is predicted by QSAR modeling. The applied Multiple Linear Regression is based on a variety of theoretical molecular descriptors, selected by the Genetic Algorithms-Variable Subset Selection (GA-VSS) procedure. The models were validated for predictivity by both internal and external validation. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049923uDOI Listing
November 2005
15 Reads

Molecular dynamics simulation of the LOV2 domain from Adiantum capillus-veneris.

J Chem Inf Comput Sci 2004 Sep-Oct;44(5):1788-93

Institut für Physikalische und Theoretische Chemie, Universität Regensburg, Universitätsstrasse 31, D-93053 Regensburg, Germany.

The mechanism for signal transduction from the LOV-domains toward the kinase region of phototropin is still not well understood. We have performed molecular dynamics (MD) simulations and CONCOORD calculations on the LOV2 domain of Adiantum capillus-veneris, with the goal to detect possible differences between the two forms of the LOV domain which may not show up in the static crystal structures. Since no such clear differences are found in the MD simulations also, we suggest that the real, biologically active conformation of the LOV domain within the whole phototropin is different from the crystal structure of the isolated LOV domains. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci049883uDOI Listing
November 2005
5 Reads

Novel receptor surface approach for 3D-QSAR: the weighted probe interaction energy method.

J Chem Inf Comput Sci 2004 Sep-Oct;44(5):1774-87

School of Chemistry, Seoul National University, Seoul 151-742, Korea.

A 3D-QSAR technique, called the WeP (weighted probe interaction energy) method, has been developed based on the notion that certain regions of the receptor surface contribute, to varying extents, to the differences in the activities of the ligands, while other regions do not. The probes, placed around the surface of a superimposed set of ligands, were associated with fractional weights, and then an optimal distribution of probe weights that accounts for the activity profile of the training ligands was determined using a genetic algorithm. It has been shown for the three test samples that the pseudoreceptors, which consist of the surviving probes with nonzero weight values, have good predictabilities. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1021/ci0498721DOI Listing
November 2005
5 Reads