"In this paper, we use a quantitative structure-retention relationship (QSRR) method to predict the retention times of polychlorinated biphenyls (PCBs) in comprehensive two-dimensional gas chromatography (GCxGC). We analyse the GCxGC retention data taken from the literature by comparing predictive capability of different regression methods. The various models are generated using 70 out of 209 PCB congeners in the calibration stage, while their predictive performance is evaluated on the remaining 139 compounds. The two-dimensional chromatogram is initially estimated by separately modelling retention times of PCBs in the first and in the second column ((1) t (R) and (2) t (R), respectively). In particular, multilinear regression (MLR) combined with genetic algorithm (GA) variable selection is performed to extract two small subsets of predictors for (1)t(R) and (2)t(R) from a large set of theoretical molecular descriptors provided by the popular software Dragon, which after removal of highly correlated or almost constant variables consists of 237 structure-related quantities. Based on GA-MLR analysis, a four-dimensional and a five-dimensional relationship modelling (1)t(R) and (2)t(R), respectively, are identified. Single-response partial least square (PLS-1) regression is alternatively applied to independently model (1)t(R) and (2)t(R) without the need for preliminary GA variable selection. Further, we explore the possibility of predicting the two-dimensional chromatogram of PCBs in a single calibration procedure by using a two-response PLS (PLS-2) model or a feed-forward artificial neural network (ANN) with two output neurons. In the first case, regression is carried out on the full set of 237 descriptors, while the variables previously selected by GA-MLR are initially considered as ANN inputs and subjected to a sensitivity analysis to remove the redundant ones. Results show PLS-1 regression exhibits a noticeably better descriptive and predictive performance than the other investigated approaches. The observed values of determination coefficients for (1)t(R) and (2)t(R) in calibration (0.9999 and 0.9993, respectively) and prediction (0.9987 and 0.9793, respectively) provided by PLS-1 demonstrate that GCxGC behaviour of PCBs is properly modelled. In particular, the predicted two-dimensional GCxGC chromatogram of 139 PCBs not involved in the calibration stage closely resembles the experimental one. Based on the above lines of evidence, the proposed approach ensures accurate simulation of the whole GCxGC chromatogram of PCBs using experimental determination of only 1/3 retention data of representative congeners."

Retention modelling of polychlorinated biphenyls in comprehensive two-dimensional chromatography

D'ARCHIVIO, ANGELO ANTONIO;RUGGIERI, FABRIZIO
2011-01-01

Abstract

"In this paper, we use a quantitative structure-retention relationship (QSRR) method to predict the retention times of polychlorinated biphenyls (PCBs) in comprehensive two-dimensional gas chromatography (GCxGC). We analyse the GCxGC retention data taken from the literature by comparing predictive capability of different regression methods. The various models are generated using 70 out of 209 PCB congeners in the calibration stage, while their predictive performance is evaluated on the remaining 139 compounds. The two-dimensional chromatogram is initially estimated by separately modelling retention times of PCBs in the first and in the second column ((1) t (R) and (2) t (R), respectively). In particular, multilinear regression (MLR) combined with genetic algorithm (GA) variable selection is performed to extract two small subsets of predictors for (1)t(R) and (2)t(R) from a large set of theoretical molecular descriptors provided by the popular software Dragon, which after removal of highly correlated or almost constant variables consists of 237 structure-related quantities. Based on GA-MLR analysis, a four-dimensional and a five-dimensional relationship modelling (1)t(R) and (2)t(R), respectively, are identified. Single-response partial least square (PLS-1) regression is alternatively applied to independently model (1)t(R) and (2)t(R) without the need for preliminary GA variable selection. Further, we explore the possibility of predicting the two-dimensional chromatogram of PCBs in a single calibration procedure by using a two-response PLS (PLS-2) model or a feed-forward artificial neural network (ANN) with two output neurons. In the first case, regression is carried out on the full set of 237 descriptors, while the variables previously selected by GA-MLR are initially considered as ANN inputs and subjected to a sensitivity analysis to remove the redundant ones. Results show PLS-1 regression exhibits a noticeably better descriptive and predictive performance than the other investigated approaches. The observed values of determination coefficients for (1)t(R) and (2)t(R) in calibration (0.9999 and 0.9993, respectively) and prediction (0.9987 and 0.9793, respectively) provided by PLS-1 demonstrate that GCxGC behaviour of PCBs is properly modelled. In particular, the predicted two-dimensional GCxGC chromatogram of 139 PCBs not involved in the calibration stage closely resembles the experimental one. Based on the above lines of evidence, the proposed approach ensures accurate simulation of the whole GCxGC chromatogram of PCBs using experimental determination of only 1/3 retention data of representative congeners."
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11697/88729
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 21
  • ???jsp.display-item.citation.isi??? 21
social impact