Counts of all walks as atomic and molecular descriptors

Ruecker, Gerta; Ruecker, C.

doi:10.1021/ci00015a005

Cited by 140 publications

(132 citation statements)

References 10 publications

Supporting

Mentioning

132

Contrasting

Order By: Relevance

“…By using DRAGON Web version 3.0, 37 we derived a total of 1497 1D, 2D, and 3D molecular descriptors from the 3D structure of each compound. These descriptors can be divided into 18 classes including 47 constitutional descriptors, 70 geometrical descriptors, 266 topological descriptors, 150 RDF descriptors, 38 21 molecular walk counts, 39 160 3D-MoRSE descriptors, 40 64 BCUT descriptors, 41 99 WHIM descriptors, 42 21 Galvez topological charge indices, 43 197 GETAWAY descriptors, 44 96 2D autocorrelations, 121 functional groups, 14 charge descriptors, 120 atom-centered descriptors, 4 aromaticity indices, 45 3 empirical descriptors, 41 Randic molecular profiles, 46 and 3 molecular properties. Moreover, an additional set of 105 electrotopological state descriptors 47 and 5 linear solvation energy relationship descriptors 48 were computed by using our own developed code.…”

Section: Datasetsmentioning

confidence: 99%

Prediction of Cytochrome P450 3A4, 2D6, and 2C9 Inhibitors and Substrates by Using Support Vector Machines

Yap

Chen

2005

J. Chem. Inf. Model.

152

185

View full text Add to dashboard Cite

Statistical learning methods have been used in developing filters for predicting inhibitors of two P450 isoenzymes, CYP3A4 and CYP2D6. This work explores the use of different statistical learning methods for predicting inhibitors of these enzymes and an additional P450 enzyme, CYP2C9, and the substrates of the three P450 isoenzymes. Two consensus support vector machine (CSVM) methods, "positive majority" (PM-CSVM) and "positive probability" (PP-CSVM), were used in this work. These methods were first tested for the prediction of inhibitors of CYP3A4 and CYP2D6 by using a significantly higher number of inhibitors and noninhibitors than that used in earlier studies. They were then applied to the prediction of inhibitors of CYP2C9 and substrates of the three enzymes. Both methods predict inhibitors of CYP3A4 and CYP2D6 at a similar level of accuracy as those of earlier studies. For classification of inhibitors of CYP2C9, the best CSVM method gives an accuracy of 88.9% for inhibitors and 96.3% for noninhibitors. The accuracies for classification of substrates and nonsubstrates of CYP3A4, CYP2D6, and CYP2C9 are 98.2 and 90.9%, 96.6 and 94.4%, and 85.7 and 98.8%, respectively. Both CSVM methods are potentially useful as filters for predicting inhibitors and substrates of P450 isoenzymes. These methods generally give better accuracies than single SVM classification systems, and the performance of the PP-CSVM method is slightly better than that of the PM-CSVM method.

show abstract

Section: Datasetsmentioning

confidence: 99%

Prediction of Cytochrome P450 3A4, 2D6, and 2C9 Inhibitors and Substrates by Using Support Vector Machines

Yap

Chen

2005

J. Chem. Inf. Model.

152

185

View full text Add to dashboard Cite

show abstract

“…This vertex descriptor has already been studied in chemical graph theory and is known as the atomic length-n walk-count descriptor in the literature. 16 Finally, given the Morgan indices after n iterations, we propose to augment the label of a vertex by its value, before computing the marginalized graph kernel. This results in a family of kernels (K n ) ng0 , indexed by the number of iterations for the Morgan index computation.…”

Section: Label Enrichment With the Morgan Indexmentioning

confidence: 99%

Graph Kernels for Molecular Structure−Activity Relationship Analysis with Support Vector Machines

Mahé

Ueda

Akutsu

et al. 2005

J. Chem. Inf. Model.

161

143

View full text Add to dashboard Cite

The support vector machine algorithm together with graph kernel functions has recently been introduced to model structure-activity relationships (SAR) of molecules from their 2D structure, without the need for explicit molecular descriptor computation. We propose two extensions to this approach with the double goal to reduce the computational burden associated with the model and to enhance its predictive accuracy: description of the molecules by a Morgan index process and definition of a second-order Markov model for random walks on 2D structures. Experiments on two mutagenicity data sets validate the proposed extensions, making this approach a possible complementary alternative to other modeling strategies.

show abstract

“…24 This index is calculated as half the sum of all path lengths (¼ the number of bonds) between two atoms i and j in the molecule. To name but a few other wellknown descriptors of this type, one can quote the Balaban index, 25 the indices introduced by Randic,[26][27][28][29][30] the Zagreb index, 31,32 and the Hosoya index. 33 Field-based descriptors: The previous indices are mostly atom-based, and although they have proven useful to chemists, more and more work has been done and is currently being done on so-called field-based descriptors.…”

Section: Basic Elements Of Molecular Similaritymentioning

confidence: 99%

“…[21] to Eq. [27], a Dirac delta function is also implied. As argued, positive definite values for the MQSM are obtained with positive definite operators only, because the involved density functions are positive definite.…”

Section: Extension To Other Operatorsmentioning

confidence: 99%

“…In fact, such a case has already been introduced in the so-called kinetic MQSM of Eq. [27], where we use the gradient of the electron density. This process is also true for those situations in which extended density functions are used in which several new density functions were derived from extended Hilbert space.…”

Section: Electron Densities For Molecular Quantum Similaritymentioning

confidence: 99%

See 1 more Smart Citation