Artificial neural network prediction of quantitative structure - retention relationships of polycyclic aromatic hydocarbons in gas chromatography
Abstract
A feed-forward artificial neural network (ANN) model was used to link molecular structures (boiling points, connectivity indices and molecular weights) and retention indices of polycyclic aromatic hydrocarbons (PAHs) in linear temperature-programmed gas chromatography. A randomly taken subset of PAH retention data reported by Lee et al, [Anal. Chem. 51 (1979) 768], containing retention index data for 30 PAHs, was used to make the ANN model. The prediction ability of the trained ANN was tested on unseen data for 18 PAHs from the same article, as well as on the retention data for 7 PAHs experimentally obtained in this work. In addition, two different data sets with known retention indices taken from the literature were analyzed by the same ANN model. It has been shown that the relative accuracy as the degree of agreement between the measured and the predicted retention indices in all testing sets, for most of the studied PAHs, were within the experimental error margins (3 %).
Keywords:
retention index / GC / ANN / PAHs / QSRR / molecular descriptorsSource:
Journal of the Serbian Chemical Society, 2005, 70, 11, 1291-1300
DOI: 10.2298/JSC0511291S
ISSN: 0352-5139
WoS: 000234277000007
Scopus: 2-s2.0-31544473772
Collections
Institution/Community
VinčaTY - JOUR AU - Sremac, Snežana AU - Skrbic, B AU - Onjia, Antonije E. PY - 2005 UR - https://vinar.vin.bg.ac.rs/handle/123456789/2960 AB - A feed-forward artificial neural network (ANN) model was used to link molecular structures (boiling points, connectivity indices and molecular weights) and retention indices of polycyclic aromatic hydrocarbons (PAHs) in linear temperature-programmed gas chromatography. A randomly taken subset of PAH retention data reported by Lee et al, [Anal. Chem. 51 (1979) 768], containing retention index data for 30 PAHs, was used to make the ANN model. The prediction ability of the trained ANN was tested on unseen data for 18 PAHs from the same article, as well as on the retention data for 7 PAHs experimentally obtained in this work. In addition, two different data sets with known retention indices taken from the literature were analyzed by the same ANN model. It has been shown that the relative accuracy as the degree of agreement between the measured and the predicted retention indices in all testing sets, for most of the studied PAHs, were within the experimental error margins (3 %). T2 - Journal of the Serbian Chemical Society T1 - Artificial neural network prediction of quantitative structure - retention relationships of polycyclic aromatic hydocarbons in gas chromatography VL - 70 IS - 11 SP - 1291 EP - 1300 DO - 10.2298/JSC0511291S ER -
@article{ author = "Sremac, Snežana and Skrbic, B and Onjia, Antonije E.", year = "2005", abstract = "A feed-forward artificial neural network (ANN) model was used to link molecular structures (boiling points, connectivity indices and molecular weights) and retention indices of polycyclic aromatic hydrocarbons (PAHs) in linear temperature-programmed gas chromatography. A randomly taken subset of PAH retention data reported by Lee et al, [Anal. Chem. 51 (1979) 768], containing retention index data for 30 PAHs, was used to make the ANN model. The prediction ability of the trained ANN was tested on unseen data for 18 PAHs from the same article, as well as on the retention data for 7 PAHs experimentally obtained in this work. In addition, two different data sets with known retention indices taken from the literature were analyzed by the same ANN model. It has been shown that the relative accuracy as the degree of agreement between the measured and the predicted retention indices in all testing sets, for most of the studied PAHs, were within the experimental error margins (3 %).", journal = "Journal of the Serbian Chemical Society", title = "Artificial neural network prediction of quantitative structure - retention relationships of polycyclic aromatic hydocarbons in gas chromatography", volume = "70", number = "11", pages = "1291-1300", doi = "10.2298/JSC0511291S" }
Sremac, S., Skrbic, B.,& Onjia, A. E.. (2005). Artificial neural network prediction of quantitative structure - retention relationships of polycyclic aromatic hydocarbons in gas chromatography. in Journal of the Serbian Chemical Society, 70(11), 1291-1300. https://doi.org/10.2298/JSC0511291S
Sremac S, Skrbic B, Onjia AE. Artificial neural network prediction of quantitative structure - retention relationships of polycyclic aromatic hydocarbons in gas chromatography. in Journal of the Serbian Chemical Society. 2005;70(11):1291-1300. doi:10.2298/JSC0511291S .
Sremac, Snežana, Skrbic, B, Onjia, Antonije E., "Artificial neural network prediction of quantitative structure - retention relationships of polycyclic aromatic hydocarbons in gas chromatography" in Journal of the Serbian Chemical Society, 70, no. 11 (2005):1291-1300, https://doi.org/10.2298/JSC0511291S . .