13C NMR chemical shift sum prediction for alkanes using neural networks

Ivanciuc, Ovidiu; Rabine, Jean-Pierre; Cabrol‐Bass, Daniel

doi:10.1016/s0097-8485(97)00019-3

Cited by 18 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, for MLR equations, this technique induces a too small modification of the initial data set, and for the present study, we have estimated the stability and predictive ability of the MLR model with the leave-20%-out (L20%O) cross-validation method. [47][48][49] The L20%O cross-validation was applied by establishing a prediction set consisting of 20% of the patterns randomly selected from the entire set of experimental data and retaining the remaining 80% of the patterns in a calibration set. The MLR model is developed with the calibration set, and in a second phase, its coefficients are used to compute the viscosity of the molecules from the prediction set.…”

Section: Methodsmentioning

confidence: 99%

“…Because CODESSA does not offer this model validation option, the L20%O cross-validation was performed by exporting the data from CODESSA and doing the computations with the programs used in other QSPR investigations. [47][48][49] RESULTS AND DISCUSSION Using the HyperChem structural files and AMPAC AM1 output files for 369 compounds, CODESSA generated a set of 579 descriptors. Table 2 presents the notation of the 28 descriptors involved in the correlations reported in this paper.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of the Liquid Viscosity of Organic Compounds with a Quantitative Structure−Property Model

Ivanciuc

Filip

et al. 1999

J. Chem. Inf. Comput. Sci.

View full text Add to dashboard Cite

A QSPR (quantitative structure-property relationship) model for the estimation of the liquid viscosity of a large variety of organic compounds was established using the CODESSA (comprehensive descriptors for structural and statistical analysis) approach. The final model was developed with a calibration set containing 337 compounds. The multilinear regression (MLR) equation that relates ln η to five molecular descriptors has s ) 0.37 and r ) 0.920. The five theoretical parameters used in the QSPR model are molecular weight, Randić connectivity index of order 3, hydrogen-donor charged surface area HDCA-2 (electrostatic), maximum electrophilic reactivity index for a carbon atom, and maximum atomic orbital electronic population. The predictive ability of the MLR model was tested by the leave-20%-out cross-validation method, showing that the QSPR model is stable and can be used to obtain good predictions for compounds that were not used in the model calibration. The cross-validation statistical indices show a small decrease when compared with those obtained in the calibration phase (s cv ) 0.38, r cv ) 0.917). The QSPR models developed with CODESSA allow accurate computation of the liquid viscosity of organic compounds using simple constitutional descriptors and quantum indices which can be computed with standard quantum chemistry packages.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Estimation of the Liquid Viscosity of Organic Compounds with a Quantitative Structure−Property Model

Ivanciuc

Filip

et al. 1999

J. Chem. Inf. Comput. Sci.

View full text Add to dashboard Cite

show abstract

“…Later, it was used to study compounds containing heteroatoms and/or rings. Over the last four decades, much effort has been focused on the development of 13 C NMR simulation, specifically for the following aspects: first, the development of computer science and computational chemistry have made 13 C NMR simulation to be an active field [6][7][8][9][10][11]; secondly, ab initio and density functional calculations for chemical shifts of organic molecules have recently emerged as one of the most promising new approaches for structure elucidation [12][13][14][15][16][17][18][19][20]; moreover, many computer systems have been developed for the prediction of NMR chemical shifts and for the elucidation of molecular structures. The combination of NMR chemical shift prediction systems and structural elucidation systems is becoming a powerful tool for automatic structural determination and identification [21,22]; in addition, both graph theory and topological theory are very powerful tools in NMR spectroscopic studies [23,24].…”

Section: Introductionmentioning

confidence: 99%

Quantitative structure spectroscopy relationships of carbon-13 nuclear magnetic resonance chemical shifts of steroids

Tong

Liu

Zhou

et al. 2007

Journal of Molecular Graphics and Modelling

View full text Add to dashboard Cite

“…And recently, many mathematical, chemometric, statistic methods predicting 13 C NMR chemical shifts (CS) of organic compounds have been developed by means of artificial neural network [6][7][8][9][10][11][12][13][14][15] algorithm and/or multiple linear regression method [16]. Neural networks were also used to predict a group of alkanes [17][18][19]. Thereinto a lot of attention has been paid on employment of more general structural parameters, in particular, those derived from chemical graph theory [20][21][22][23][24][25][26][27].…”

Section: Introductionmentioning

confidence: 99%