Excitation–emission matrix (EEM) fluorescence spectroscopy has been applied to many fields. In this study, a simple method was proposed to obtain the new constructed three-dimensional (3D) EEM spectra based on the original EEM spectra. Then, the application of the N-PLS method to the new constructed 3D EEM spectra was proposed to quantify target compounds in two complex data sets. The quantitative models were established on external sample sets and validated using statistical parameters. For validation purposes, the obtained results were compared with those obtained by applying the N-PLS method to the original EEM spectra and applying the PLS method to the extracted maximum spectra in the concatenated mode. The comparison of the results demonstrated that, given the advantages of less useless information and a high calculating speed of the new constructed 3D EEM spectra, N-PLS on the new constructed 3D EEM spectra obtained better quantitative analysis results with a correlation coefficient of prediction above 0.9906 and recovery values in the range of 85.6–95.6%. Therefore, one can conclude that the N-PLS method combined with the new constructed 3D EEM spectra is expected to be broadened as an alternative strategy for the simultaneous determination of multiple target compounds.

In recent years, machine learning methods have been applied successfully in many fields. In this paper, three machine learning algorithms, including partial least squares-discriminant analysis (PLS-DA), adaptive boosting (AdaBoost), and light gradient boosting machine (LGBM), were applied to establish models for predicting the Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET for short) properties, namely Caco-2, CYP3A4, hERG, HOB, MN of anti-breast cancer compounds. To the best of our knowledge, the LGBM algorithm was applied to classify the ADMET property of anti-breast cancer compounds for the first time. We evaluated the established models in the prediction set using accuracy, precision, recall, and F1-score. Compared with the performance of the models established using the three algorithms, the LGBM yielded most satisfactory results (accuracy > 0.87, precision > 0.72, recall > 0.73, and F1-score > 0.73). According to the obtained results, it can be inferred that LGBM can establish reliable models to predict the molecular ADMET properties and provide a useful tool for virtual screening and drug design researchers.