Application of Multivariate Adaptive Regression Splines (MARSplines) for Predicting Antitumor Activity of Anthrapyrazole Derivatives

Predicting Antitumor Activity of Anthrapyrazole Derivatives using Advanced Machine Learning Techniques

BACKGROUND

Anthrapyrazoles are a new class of antitumor agents and successors to anthracyclines possessing a broad range of antitumor activity in various model tumors.

OBJECTIVES

The present study introduces novel QSAR models for the prediction of antitumor activity of anthrapyrazole analogues.

METHODS

The predictive performance of four machine learning algorithms, namely artificial neural networks, boosted trees, multivariate adaptive regression splines, and random forest, was studied in terms of variation of the observed and predicted data, internal validation, predictability, precision, and accuracy.

RESULTS

ANN and boosted trees algorithms met the validation criteria. It means that these procedures may be able to forecast the anticancer effects of the anthrapyrazoles studied. Evaluation of validation metrics, calculated for each approach, indicated the artificial neural network (ANN) procedure as the algorithm of choice, especially with regard to the obtained predictability as well as the lowest value of mean absolute error. The designed multilayer perceptron (MLP)-15-7-1 network displayed a high correlation between the predicted and the experimental pIC50 value for the training, test, and validation set. A conducted sensitivity analysis enabled an indication of the most important structural features of the studied activity.

CONCLUSION

The ANN strategy combines topographical and topological information and can be used for the design and development of novel anthrapyrazole analogues as anticancer molecules.

Construction of a QSAR Model Based on Flavonoids and Screening of Natural Pancreatic Lipase Inhibitors

Pancreatic lipase (PL) is a key hydrolase in lipid metabolism. Inhibition of PL activity can intervene in obesity, a global sub-health disease. The natural product is considered a good alternative to chemically synthesized drugs due to its advantages, such as low side effects. However, traditional experimental screening methods are labor-intensive and cost-consuming, and there is an urgent need to develop high-throughput screening methods for the discovery of anti-PL natural products. In this study, a high-throughput virtual screening process for anti-PL natural products is provided. Firstly, a predictable anti-PL natural product QSAR model (R2train = 0.9444, R2test = 0.8962) were developed using the artificial intelligence drug design software MolAIcal based on genetic algorithms and their conformational relationships. 1068 highly similar (FS > 0.8) natural products were rapidly enriched based on the structure-activity similarity principle, combined with the QSAR model and the ADMET model, for rapid prediction of a total of five potentially efficient anti-PL natural products (IC50pre < 2 μM). Subsequently, molecular docking, molecular dynamics simulation, and MMGBSA free energy calculation were performed to not only reveal the interaction of candidate novel natural products with the amino acid residues of PL but also to validate the stability of these novel natural compounds bound to PL. In conclusion, this study greatly simplifies the screening and discovery of anti-PL natural products and accelerates the development of novel anti-obesity functional foods.

Predicting liquid chromatography-electrospray ionization/mass spectrometry signal from the structure of model compounds and experimental factors; case study of aripiprazole and its impurities

A priori estimation of analyte response is crucial for the efficient development of liquid chromatography-electrospray ionization/mass spectrometry (LC-ESI/MS) methods, but remains a demanding task given the lack of knowledge about the factors affecting the experimental outcome. In this research, we address the challenge of discovering the interactive relationship between signal response and structural properties, method parameters and solvent-related descriptors throughout an approach featuring quantitative structure-property relationship (QSPR) and design of experiments (DoE). To systematically investigate the experimental domain within which QSPR prediction should be undertaken, we varied LC and instrumental factors according to the Box-Behnken DoE scheme. Seven compounds, including aripiprazole and its impurities, were subjected to 57 different experimental conditions, resulting in 399 LC-ESI/MS data endpoints. To obtain a more standard distribution of the measured response, the peak areas were log-transformed before modeling. QSPR predictions were made using features selected by Genetic Algorithm (GA) and providing Gradient Boosted Trees (GBT) with training data. Proposed model showed satisfactory performance on test data with a RMSEP of 1.57 % and a of 96.48 %. This is the first QSPR study in LC-ESI/MS that provided a holistic overview of the analyte's response behavior across the experimental and chemical space. Since intramolecular electronic effects and molecular size were given great importance, the GA-GBT model improved the understanding of signal response generation of model compounds. It also highlighted the need to fine-tune the parameters affecting desolvation and droplet charging efficiency.

Quantitative Structure–Activity Relationship Analysis of Isosteviol-Related Compounds as Activated Coagulation Factor X (FXa) Inhibitors

Stevioside, one of the natural sweeteners extracted from stevia leaves, and its derivatives are considered to have numerous beneficial pharmacological properties, including the inhibition of activated coagulation factor X (FXa). FXa-PAR signaling is a possible therapeutic target to enhance impaired metabolism and insulin resistance in obesity. Thus, the goal of the investigation was a QSAR analysis using multivariate adaptive regression splines (MARSplines) applied to a data set of 20 isosteviol derivatives bearing thiourea fragments with possible FXa inhibitory action. The best MARS submodel described a strong correlation between FXa inhibitory activity and molecular descriptors, such as: B01[C-Cl], E2m, L3v, Mor06i, RDF070i and HATS7s. Five out of six descriptors included in the model are geometrical descriptors quantifying three-dimensional aspects of molecular structure, which indicates that the molecular three-dimensional conformation is of high significance for the MARSplines modeling procedure and obviously for FXa inhibitory activity. High model performance was confirmed through an extensive validation protocol. The results of the study not only confirmed the enhancement in pharmacological activity by the presence of chlorine in a phenyl ring, but also, and primarily, may provide the basis for searching for new active isosteviol analogues, which may serve as drugs or health-beneficial food additives in patients suffering from obesity and comorbidities.