Fragmental Approach in QSPR

Зефиров, Н. С.; Palyulin, V. A.

doi:10.1021/ci020010e

Cited by 73 publications

(53 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Other fragmental methods are unable to treat acyclic and cyclic alkanes simultaneously with the same accuracy. Zefirov and Palyulin have reported [9], that in the model based on 7 fragmental descriptors they have obtained for the training set of 104 acyclic and cyclic alkanes r 0.9878 and s 4.3 K. We are unable to make direct comparison of this model with our results because calculated T boil values for all molecules haven×t been listed in this article. M. Randic and M. Pompe [16] have investigated topological descriptors for T boil estimations of alcohols.…”

Section: Combination Of Fragmental and Topological Descriptors For Qsmentioning

confidence: 72%

See 1 more Smart Citation

Combination of Fragmental and Topological Descriptors for QSPR Estimations of Boiling Temperature

Tsygankova

2004

QSAR Comb. Sci.

View full text Add to dashboard Cite

The novel QSPR equation for estimation of physicochemical properties of organic substances is proposed. This equation includes contributions depending on the counts of bonds and nonadditive contribution. The nonadditive term is represented as an explicit function of topological distances on the line graph of molecules. The original mathematical form for description of nonadditive contribution is suggested. The application of the derived equation to estimation of normal boiling temperatures for the saturated hydrocarbons (total number of compounds n 198; correlation coefficient r 0.9966; mean square deviation s 3.4 K) has proved the effectiveness of the proposed approach. The modification of correlation equation is made for estimations of normal boiling temperatures for substances with OH and NH 2 groups (n 139; r 0.9971; s 3.9 K).

show abstract

Section: Combination Of Fragmental and Topological Descriptors For Qsmentioning

confidence: 72%

“…Methane is a specific molecule, it drops out from our model as well as from many others (for example, see [5,9]). In our model ethane is represented by single fragment À bond CH 3 À CH 3 , which is not found in other hydrocarbons.…”

Section: Resultsmentioning

confidence: 95%

Combination of Fragmental and Topological Descriptors for QSPR Estimations of Boiling Temperature

Tsygankova

2004

QSAR Comb. Sci.

View full text Add to dashboard Cite

show abstract

“…Palyulin and his collaborators [31,38] used certain types of tree fragments for classification and reported good results for QSAR and QSPR prediction problems. Table 7 and Table 8.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Acyclic Subgraph Based Descriptor Spaces for Chemical Compound Retrieval and Classification

Wale

Karypis²

2006

View full text Add to dashboard Cite

In recent years the development of computational techniques that build models to correctly assign chemical compounds to various classes or to retrieve potential drug-like compounds has been an active area of research. These techniques are used extensively at various phases during the drug development process. Many of the best-performing techniques for these tasks, utilize a descriptor-based representation of the compound that captures various aspects of the underlying molecular graph's topology. In this paper we introduce and describe algorithms for efficiently generating a new set of descriptors that are derived from all connected acyclic fragments present in the molecular graphs. In addition, we introduce an extension to existing vector-based kernel functions to take into account the length of the fragments present in the descriptors. We experimentally evaluate the performance of the new descriptors in the context of SVM-based classification and ranked-retrieval on 28 classification and retrieval problems derived from 17 datasets. Our experiments show that for both the classification and retrieval tasks, these new descriptors consistently and statistically outperform previously developed schemes based on the widely used fingerprint-and Maccs keys-based descriptors, as well as recently introduced descriptors obtained by mining and analyzing the structure of the molecular graphs.

show abstract

“…Two-dimensional representations of local atomic environments are better known as fragment descriptors [41]; 2D descriptors are typically computed in sets, and are represented as arrays of binary, integer, or real numbers. In most cases, they encode the presence or absence of specific structural patterns in the target molecule, and are classified by three broad criteria: dimensionality (fixed-length or variablelength), resolution (binary or nonbinary), and uniqueness (hashed or nonhashed).…”

Section: D 1d and 2d Computational Descriptorsmentioning

confidence: 99%

Developing Best Practices for Descriptor‐Based Property Prediction: Appropriate Matching of Datasets, Descriptors, Methods, and Expectations

Krein

Huang

Morkowchuk

et al. 2012

Statistical Modelling of Molecular Descriptors in QSAR/QSPR

View full text Add to dashboard Cite

For well over 100 years, chemists have explored the relationship between the chemical structure and biological activity, and dreamed of predicting them as well as other measurable properties. The first description of a relationship between composition and activity [1] was based on observations of correlation between specific molecular features and observable physiochemical properties [2]. With some data tabulation, it was found that structure-activity relationships could be used to quantify chemical intuition: For a small change in the molecular structure, a corresponding small change in activity could be explained by analyzing regular changes the numerical representations of molecular structure. The power inherent in this type of relationship quickly became obvious, and increased in importance with the quick tabulation abilities of computers. The reductionist qualities of quantitative structureactivity relationships (QSARs) have resulted in both praise and condemnation for the discipline throughout its existence [3][4][5]. Without debating the philosophical validity of reductionist views, a more practical approach is to understand how and when QSARs are applicable to relevant problems. As discussed below, there are many choices to make when matching available data with types of chemical descriptors and machine learning methodologies (Figure 2.1). Inherent in these choices are decisions that affect the level of difficulty and computational effort needed to develop a model and to establish its domain of applicability -a crucial element for managing end-user expectations of model performance. Most models are constructed using methods that project or compress information into a simpler form, consequently representing a compromise between mode interpretability and predictive power. For any nontrivial QSAR the importance of good chemical descriptors cannot be overstated -even the most capable machine learning methodology cannot extract signal from descriptor variance that is not monotonically related to the endpoint of interest. This is the essential Tao of building QSARs, where the ultimate goal is to construct chemically meaningful, validated models. Achievement of this goal relies Statistical Modelling of Molecular Descriptors in QSAR/QSPR. First Edition. Edited

show abstract

Fragmental Approach in QSPR

Cited by 73 publications

References 72 publications

Combination of Fragmental and Topological Descriptors for QSPR Estimations of Boiling Temperature

Combination of Fragmental and Topological Descriptors for QSPR Estimations of Boiling Temperature

Acyclic Subgraph Based Descriptor Spaces for Chemical Compound Retrieval and Classification

Developing Best Practices for Descriptor‐Based Property Prediction: Appropriate Matching of Datasets, Descriptors, Methods, and Expectations

Contact Info

Product

Resources

About