On molecular identification numbers

Randić, Milan

doi:10.1021/ci00043a009

Cited by 201 publications

(158 citation statements)

References 10 publications

Supporting

Mentioning

156

Contrasting

Unclassified

Order By: Relevance

“…32 ᎐ 34 For example, there are indices based on the counting of ''self-avoiding paths'' 35 and also the count of chains, cycles, and small ''clusters.'' 36 Although restricted counts can be useful in certain applications, such as structure᎐activity relationships, 37 topological indices are typically based on substructures up to a size of seven atoms.…”

Section: Discussionmentioning

confidence: 99%

Exhaustive enumeration of molecular substructures

Bone

Villar

1997

J. Comput. Chem.

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Exhaustive enumeration of molecular substructures

Bone

Villar

1997

J. Comput. Chem.

View full text Add to dashboard Cite

“…Overall, we have calculated 557 ensemble descriptors including easily interpretable descriptors like atom-count descriptors, 44 others which describe the connectivity of the molecular graph, 45 like constitutional descriptors, 46 the topological descriptors of Randic 47 or Kier and Hall, 48,49 autocorrelations, and aromaticity indices 50 as well as 3D-descriptors 51 that encode the 3D van der Waals surface of the molecule annotated with physical properties like charge, hydrogen bond, or acceptor potential. The 3D-based features were calculated from the 3D coordinates of the compounds generated by Corina.…”

Section: Description Of the Data Setsmentioning

confidence: 99%

Classification of Highly Unbalanced CYP450 Data of Drugs Using Cost Sensitive Machine Learning Techniques.

Eitrich¹,

Kless²,

Druska³

et al. 2007

ChemInform

View full text Add to dashboard Cite

In this paper, we study the classifications of unbalanced data sets of drugs. As an example we chose a data set of 2D6 inhibitors of cytochrome P450. The human cytochrome P450 2D6 isoform plays a key role in the metabolism of many drugs in the preclinical drug discovery process. We have collected a data set from annotated public data and calculated physicochemical properties with chemoinformatics methods. On top of this data, we have built classifiers based on machine learning methods. Data sets with different class distributions lead to the effect that conventional machine learning methods are biased toward the larger class. To overcome this problem and to obtain sensitive but also accurate classifiers we combine machine learning and feature selection methods with techniques addressing the problem of unbalanced classification, such as oversampling and threshold moving. We have used our own implementation of a support vector machine algorithm as well as the maximum entropy method. Our feature selection is based on the unsupervised McCabe method. The classification results from our test set are compared structurally with compounds from the training set. We show that the applied algorithms enable the effective high throughput in silico classification of potential drug candidates.

show abstract

“…In order to improve upon the discriminating power of molecular connectivity indices and to reduce their mean isomer degeneracy (see Table 1), Randid put forward a modified version of his index known as the molecular identification number (54]. The newer index was based on a count of appropriately weighted paths in C, though the weighting factor used was the same as that for the X indices.…”

Section: -6-mentioning

confidence: 99%

The modeling of chemical phenomena using topological indices

Rouvray

1987

J Comput Chem

105

View full text Add to dashboard Cite

A class of graph invariants known today as topological indices are being increasingly realized by chemists and others to be powerful tools in the description of chemical phenomena. Topological indices generally characterize both the size and shape of chemical species; in recent years a number of such indices have been put forward that sensitively reflect the amount of branching present in molecules. Chemists are thus able to model accurately the chemical behavior of an extensive range of chemical substances in all three thermodynamic states. In discussing the manifold applications of topological indices to the description of physicochemical properties, we present a survey of the progress to date in this area and point out some of the advantages and drawbacks of using topological indices.

show abstract

On molecular identification numbers

Cited by 201 publications

References 10 publications

Exhaustive enumeration of molecular substructures

Exhaustive enumeration of molecular substructures

Classification of Highly Unbalanced CYP450 Data of Drugs Using Cost Sensitive Machine Learning Techniques.

The modeling of chemical phenomena using topological indices

Contact Info

Product

Resources

About