• Corpus ID: 16634739

QSPR and QSAR Models Derived with CODESSA Multipurpose Statistical Analysis Software

@inproceedings{Karelson1999QSPRAQ,
  title={QSPR and QSAR Models Derived with CODESSA Multipurpose Statistical Analysis Software},
  author={Mati Karelson and Uko Maran and Yilin Wang and Alan R. Katritzky},
  year={1999}
}
An overview on the development of QSPR/QSAR equations using various descriptor mining techniques and multilinear regression analysis in the framework of program CODESSA (Comprehensive Descriptors for Structural and Statistical Analysis) is given. The description of the methodologies applied in CODESSA is followed by the presentation of the QSAR and QSPR models derived for eighteen molecular activities and properties. The properties cover single molecular species, interactions between different… 
A New Efficient Approach for Variable Selection Based on Multiregression: Prediction of Gas Chromatographic Retention Times and Response Factors
TLDR
A novel procedure for variable selection based on multiregression (MR) analysis is developed and applied to the quantitative structure−property relationship (QSPR) modeling of gas chromatographic retention times tR and Dietz response factors RF on 152 diverse chemical compounds.
Predictive Carcinogenicity: A Model for Aromatic Compounds, with Nitrogen-Containing Substituents, Based on Molecular Descriptors Using an Artificial Neural Network
TLDR
A back-propagation neural network to predict the carcinogenicity of aromatic nitrogen compounds was developed, and from the tens of descriptors calculated, principal component analysis enabled us to restrict the number of parameters to be used for the artificial neural network (ANN).
Topological models for the prediction of antimycobacterial activity of 4-(5-substituted-1,3,4-oxadiazol-2-yl)pyridines
TLDR
The validation of QSAR models using an external test set revealed that these models can be used for the prediction of antimycobacterial activity of newer 1,3,4-oxadiazole derivatives.
Lazy Learning for Predictive Toxicology based on a Chemical Ontology
  • Eva Armengol, E. Plaza
  • Computer Science, Biology
    Artificial Intelligence Methods And Tools For Systems Biology
  • 2004
TLDR
A new approach based on the chemical nomenclature to represent chemical compounds is introduced and it is shown that both models, SAR and ontology-based, have comparable results for the predictive toxicology task.

References

SHOWING 1-10 OF 65 REFERENCES
QSPR Treatment of Solvent Scales
TLDR
The results of the quantitative structure−property relationship (QSPR) analysis of 45 different solvent scales and 350 solvents using the CODESSA program are presented and the descriptors involved are shown to be in good agreement with the physical concepts invoked by the original authors of the scales.
A model based QSPR analysis of the unified non-specific solvent polarity scale
A Model Based QSPR approach, MQSPR, has been employed to estimate the S′ parameters of the Unified Solvent Polarity Scale. MQSPR selects descriptors, a priori to the correlation analysis, that have
Relationships of Critical Temperatures to Calculated Molecular Properties
TLDR
Quantitative structure−property relationships (QSPR) of critical temperatures with small numbers of physically significant molecular descriptors are developed using the CODESSA technique, which reveals fundamental structural influences on liquid-state properties.
QSPR Prediction of Densities of Organic Liquids
Prediction of Melting Points for the Substituted Benzenes: A QSPR Approach
TLDR
The importance of the hydrogen bonding descriptor (HDSA2) is demonstrated, and quantum chemical descriptors are successfully applied to obtain predictive models.
QSPR Treatment of the Unified Nonspecific Solvent Polarity Scale
TLDR
A three-parameter QSPR equation with R2 = 0.936 was developed for the unified nonspecific solvent polarity scale (S‘) on the basis of theoretical molecular descriptors and predictions are used to extend available S‘ values to a total of 67 solvents.
Multivariate characterization of molecules for QSAR analysis
TLDR
A force field and method for characterizing molecules are described and a set of three‐dimensional matrices each defining the interactions of one chemical group with one target molecule in a condensed phase such as water can be used as the X‐matrix for the computation of quantitative structure‐activity relationships.
A QSPR Study of the Solubility of Gases and Vapors in Water
TLDR
All the parameters involved in these equations can be derived solely from the chemical structure of the compounds which makes them very useful for the prediction of the solubilities of unknown or unavailable compounds.
Quantitative Structure-Property Relationship (QSPR) Correlation of Glass Transition Temperatures of High Molecular Weight Polymers
A new quantitative structure−property relationship (QSPR) five-parameter correlation (R2 = 0.946) of molar glass transition temperatures (Tg/M) for a diverse set of 88 polymers is developed with the
Prediction of Gas Chromatographic Retention Times and Response Factors Using a General Quantitative Structure-Property Relationship Treatment
A general yet effective QSPR treatment on 152 individual structures incorporating a wide cross section of classes of organic compounds has given good six-parameter correlations for gas
...
...