Prediction of gas chromatographic retention indices based on Monte Carlo method

A new method for the prediction of retention indices using Monte Carlo method and based on local graph invariants and SMILES notation of studied compounds has been presented. Very satisfactory results were obtained with the proposed method, since robust model with good statistical quality was develo...

Full description

Saved in:
Bibliographic Details
Published in:Talanta (Oxford) 2017-06, Vol.168, p.257-262
Main Authors: Veselinović, Aleksandar M., Velimorović, Dragan, Kaličanin, Biljana, Toropova, Alla, Toropov, Andrey, Veselinović, Jovana
Format: Article
Language:English
Subjects:
Gas chromatographic retention indices
Molecular graph
Monte Carlo
QSPR
SMILES
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A new method for the prediction of retention indices using Monte Carlo method and based on local graph invariants and SMILES notation of studied compounds has been presented. Very satisfactory results were obtained with the proposed method, since robust model with good statistical quality was developed. The predictive potential of the applied approach was tested and the robustness of the model was proven with different methods. The best calculated QSPR model had following statistical parameters: r2=0.8097 for the training set and r2=0.9372 for the test set. Structural indicators defined responsible for the increases and decreases of gas chromatographic retention indices activity have been calculated. [Display omitted] •A new method for the prediction of retention indices has been presented.•Monte Carlo method and descriptors based on local graph invariants were used.•Very satisfactory results were obtained with the proposed method.
ISSN:0039-9140
1873-3573
DOI:10.1016/j.talanta.2017.03.024