查看更多>>摘要：The goal of the present study was to use a quantitative structure-retention relationship (QSRR) for the retention indices of 1179 flavour and fragrance organic compounds using the Monte Carlo algorithm of CORAL software. All the organic compounds were represented by SMILES notation for computation of descriptor of correlation weight (DCW). The dataset of 1179 flavour and fragrance organic compounds was used to make nine splits, each of which was further segmented into four sets: training, invisible training, calibration, and validation. The task of the index of ideality correlation (IIC) was analysed in-depth and it was found that the QSRR models generated by the use of IIC were more robust and significant. Two target functions i.e. TFA (IICweight= 0.0), TFB (IICweight = 0.2) were applied to build 18 QSRR models. The established QSRR model with TFB having R2validation = 0.9015 for split 6 was considered as the prime model. The reliability and robustness of the prime model was also confirmed by the numerical value of Q2validation = 0.9000 and Q2calibration = 0.8919. The common promoters of increase and decrease of endpoint were also extracted from three splits 5, 6 and 9. Moreover, consensus modelling employing the split 6 layout of dataset distribution improves the prediction performance by enhancing the numerical value of R2validation from 0.9015 to 0.9241.
查看更多>>摘要：Predicting the response signal in Atmospheric Pressure Chemical Ionization - Mass Spectrometry (APCI-MS) systems appears to be considerably challenging due to a gap in knowledge of governing factors and nature of their relationship with response. In this regard, signal intensity is optimized for each analyte separately through trialand-error approach which impairs the method development and depletes numerous resources. To tackle the given issue, here we proposed the Quantitative Structure - Property Relationship (QSPR) model that estimated the ion signal based on molecular descriptors of tested compounds. In particular, the QSPR model was developed using APCI-MS data acquired for 8 chemical compounds under 41 different experimental conditions. Antipsychotics, namely, sulpiride, risperidone, aripiprazole, bifeprunox, ziprasidone and its three impurities, were selected as model substances to undergo APCI ionization. Experimental (instrumental and solventrelated) parameters were varied according to the scheme of Box-Behnken Design. Gradient Boosted Trees (GBT) technique was used to model sophisticated inputs - output relationships of the monitored system. The GBT algorithm with optimized hyper-parameters (16 estimators, learning rate set to 0.55 and maximal depth set to 7) built a so-called mixed model that yielded satisfactory predictive performance (Root Mean Square Error of Prediction: 5.98%; coefficient of determination: 97.1%). According to the built-in feature selection method, GBT identified experimental factors impacting nebulization and vaporization efficiency, i.e. descriptors related to hydrophobicity and molecular polarizability as the major determinants of observed APCI behavior. Therefore, the proposed model has shed light on the parameters and factors' interactions that govern the generation of APCI ion signals for the analytes with diverse physical-chemical properties. The established QSPR patterns could be reliably used to predict APCI-MS signal in a variety of experimental environments.
NSTL
Elsevier