CORAL: Predictions of Quality of Rice Based on Retention Index Using a Combination of Correlation Intensity Index and Consensus Modelling

Abstract

The purpose of this study is to utilize the Monte Carlo technique of CORAL softwareCORAL software for establishing a quantitative structure-retention relationship (QSRR) for the retention indices of 136 primary flavour volatile organic molecules. SMILES notations of volatile organic compounds were used to compute the descriptor of correlation weightCorrelation weights (CW) (DCW). Eight splits have been constructed from the datasetDataset of 136 volatile organic chemicals, each of which was further divided into four sets: training, invisible training, calibration and validation. Two target functionsTarget function i.e. TF1 ( $${\text{CII}}_{{{\text{weight}}}} = 0.0$$ ), TF2 ( $${\text{CII}}_{{{\text{weight}}}} = 0.3$$ ) were applied to build 16 QSRR models. All QSRR models were statistically good. The coefficient of determination derived by TF2 for the validation set of split 4 has the maximum statistical result ( $$R_{{{\text{validation}}}}^{2} = 0.9532$$ ), hence it was accepted as the best model. The assignment of correlation intensity indexCorrelation intensity index (CII) (CII) on QSPR models was thoroughly examined and found to be more consistent and relevant. The common promoters of increase and decrease of endpoint were also extracted from four splits 1, 2, 3 and 4. Furthermore, consensus modellingConsensus modelling using the split 4 architecture of datasetDataset distribution enhances prediction accuracy by increasing the numerical value of $$R_{{{\text{validation}}}}^{2}$$ from 0.9532 to 0.9864.