In this study, we have demonstrated an automated workflow by using KNIME Analytical Platform for modelling and predicting potential HIV-1 protease (HIVP) inhibitors. The workflow has been simplified in three easy steps i.e., 1) retrievethe database of inhibitors for the target disease from ChEMBL website and well-known drug from DrugBank database, 2) generate the descriptors and, 3) select the optimal number of features after machine learning models training. Our results have indicated that the random forest with auto prediction validation method is the most reliable with the best R2 value of 0.9394. Apparently, this workflow can be transformed easily for any other diseases and the quantitative structure-activity relationship (QSAR) model that has been developed can accurately predict in silico how chemical modifications might influence biological behaviour. Overall, the automated workflow which has been presented in this study may significantly reduce the time, cost and efforts needed to design or develop potential HIVP inhibitors.

No abstract

Milk tablets are a popular dairy product in many Asian countries. This research aimed to develop an instant and rapid method for determining sucrose and lactose contents in milk tablets using near-infrared (NIR) spectroscopy. For the quantitative analysis, a training set composed of laboratory-scale milk samples was generated based on a central composite design (CCD) and used to establish partial least squares (PLS) regression for the predictions of sucrose and lactose contents resulting in R2 values of 0.9749 and 0.9987 with the corresponding root mean square error of calibration (RMSEC) values of 1.69 and 0.35. However, the physical difference between the laboratory-scale powder and the final product milk tablet samples resulted in spectral deviations that dramatically affected the predictive performance of the PLS models. Therefore, calibration transfer methods called direct standardization (DS) and piecewise direct standardization (PDS) were used to adjust the NIR spectra from the real milk tablet samples before the quantitative prediction. Using high-performance liquid chromatography (HPLC) as a reference method, the developed NIR-chemometric model could be used to instantly predict the sugar contents in real milk tablets by producing root mean square error of prediction (RMSEP) values for sucrose and lactose of 5.04 and 4.22 with Q2 values of 0.7973 and 0.9411, respectively, after the PDS transformation.