Search

Artificial neural networks (ANNs) are nowadays applied as the most efficient methods in the majority of machine learning approaches, including data-driven modeling for assessment of the toxicity of chemicals. We developed a combined neural network methodology that can be used in the scope of new approach methodologies (NAMs) assessing chemical or drug toxicity. Here, we present QSAR models for predicting the physical and biochemical properties of molecules of three different datasets: aqueous solubility, acute fish toxicity toward fat head minnow, and bio-concentration factors. A novel neural network modeling method is developed by combining two neural network algorithms, namely, the counter-propagation modeling strategy (CP-ANN) with the back-propagation-of-errors algorithm (BPE-ANN). The advantage is a short training time, robustness, and good interpretability through the initial CP-ANN part, while the extension with BPE-ANN improves the precision of predictions in the range between minimal and maximal property values of the training data, regardless of the number of neurons in both neural networks, either CP-ANN or BPE-ANN. [ABSTRACT FROM AUTHOR]

The development of QSPR models to predict aqueous solubility (logS) is presented. A structurally diverse set of over 1600 compounds with experimentally determined solubility values (AqSolDB database) is used for building the data-driven models based on multiple linear regression (MLR) and artificial neural network (ANN) methods to predict aqueous solubility. Molecular structures are encoded by numerous structural descriptors, including the connectivity index developed by Randić in 1975, and many later derived variations. To evaluate the potency of Randić-like descriptors in the structure-property relationship, we developed models based on two sets of descriptors, first using only Randićlike descriptors calculated with Dragon, and second using 17 commonly applied descriptors available in the AqSolDB database. All models were validated with external prediction sets, with the RMSE ranging from 0.8 to 1.1. Interestingly, the RMSE of predicted LogS values of models based only on the Randić-like descriptors were in average just 0.1 larger than the models with 17 descriptors preselected as suitable for modelling logS. [ABSTRACT FROM AUTHOR]

Nanostructures like fullerene derivatives (FDs) belong to a new family of nano-sized organic compounds. Fullerenes have found a widespread application in material science, pharmaceutical, biomedical, and medical fields. This fact caused the importance of the study of pharmacological as well as toxicological properties of this relatively new family of chemicals. In this work, a large set of 169 FDs and their binding activity to 1117 disease-related proteins was investigated. The structure-based descriptors widely used in drug design (so-called drug-like descriptors) were applied to understand cheminformatics characteristics related to the binding activity of fullerene nanostructures. Investigation of applied descriptors demonstrated that polarizability, topological diameter, and rotatable bonds play the most significant role in the binding activity of FDs. Various cheminformatics methods, including the counter propagation artificial neural network (CPANN) and Kohonen network as visualization tool, were applied. The results of this study can be applied to compose the priority list for testing in risk assessment related to the toxicological properties of FDs. The pharmacologist can filter the data from the heat map to view all possible side effects for selected FDs. [ABSTRACT FROM AUTHOR]