Prediction of drug solubility from molecular structure using a drug-like training set

Using a training set of 191 drug-like compounds extracted from the AQUASOL database a quantitative structure-property relationship (QSPR) study was conducted employing a set of simple structural and physicochemical properties to predict aqueous solubility. The resultant regression model comprised five parameters (ClogP, molecular weight, indicator variable for aliphatic amine groups, number of rotatable bonds and number of aromatic rings) and demonstrated acceptable statistics (r2 = 0.87, s = 0.51, F = 243.6, n = 191). The model was applied to two test sets consisting of a drug-like set of compounds (r2 = 0.80, s = 0.68, n = 174) and a set of agrochemicals (r2 = 0.88, s = 0.65, n = 200). Using the established general solubility equation (GSE) on the training and drug-like test set gave poorer results than the current study. The agrochemical test set was predicted with equal accuracy using the GSE and the QSPR equation. The results of this study suggest that increasing molecular size, rigidity and lipophilicity decrease solubility whereas increasing conformational flexibility and the presence of a non-conjugated amine group increase the solubility of drug-like compounds. Indeed, the proposed structural parameters make physical sense and provide simple guidelines for modifying solubility during lead optimisation.     

QSPR Modeling of Gibbs Free Energy of Organic Compounds by Weighting of Nearest Neighboring Codes

We examine the encoding of chemical structure of organic compounds by Labeled Hydrogen-Filled Graphs (LHFGs). Quantitative Structure-Property Relationships (QSPR) for a representative set of 150 organic molecules have been derived by means of the optimization of correlation weights of local invariants of the LHFGs. We have tested as local invariants Morgan extended connectivity of zero- and first order, numbers of path of length 2 (P2) and valence shells of distance of 2 (S2) associated with each atom in the molecular structure, and the Nearest Neighboring Codes (NNC). The best statistical characteristics for the Gibbs free energy has been obtained for the NNC weighting. Statistical parameters corresponding to this model are the following n = 100, r² = 0.9974, s = 5.136 kJ/mol, F = 38319 (training set); n = 50, r² = 0.9990, s = 3.405 kJ/mol, F = 48717 (test set). Some possible further developments are pointed out.     

QSPR Modeling of Complex Stability by Optimization of Correlation Weights of the Hydrogen Bond Index and the Local Graph Invariants

The hydrogen bond index (HBI) is the global invariant of a molecular graph and equals the number of vertices representing hydrogen and nitrogen atoms. This index was considered a measure of the capability of a complex to form hydrogen bonds. Optimization of the correlation weights of the HBI and local graph invariants was used for the QSPR modeling of the stability of 110 biometal M²⁺ complexes with -amino acids and phosphate derivatives of adenosine. The statistical parameters of the best model are n = 55, r = 0.9921, s = 0.279, and F = 3328 (learning sample) and n = 55, r = 99.35, s = 0.248, and F = 4027 (control sample).     

QSAR analysis of 1,4-dihydro-4-oxo-1-(2-thiazolyl)-1,8-naphthyridines exhibiting anticancer activity by optimal SMILES-based descriptors

A predictive model of the anticarcinogenic activity of a 1,4-dihydro-4-oxo-1-(2-thiazolyl)-1,8-naphthyridines series has been built, with statistical quality: n = 75, r ² = 0.7688, s = 0.48, F = 243 (training set); n = 25, r ² = 0.8025, s = 0,49, F = 93 (test set). The robustness of this model has been tested in three random splits into training set and test set. Correlation weights (the analogue of the contributions of substituents) of molecular attributes expressed by symbols in the simplified molecular input line entry system (SMILES) notation are able to serve as informative indicators in the search for new anticancer agents.     

Using the QSPR Approach for Estimating the Density of Azole‐based Energetic Compounds

The relationship between density of energetic azole‐based compounds and their molecular structure is investigated through quantitative structure‐property relationship (QSPR) approach. The methodology of this work introduces a new model, which related density of azole‐based energetic compounds to the optimum elemental composition, the degree of unsaturation (DoU) of the compounds, presence of nitroimino group in the structural formula, as well as several non‐additive structural parameters. The presence of nitroimino functional group and also increasing the value of n_O/n_N in the formula of these compounds can enhance their density. The correlation is derived on the basis of experimental density values of 100 azole‐based energetic compounds with different molecular structure as training set. The determination coefficient of the new correlation is 0.923. Also, it has the root mean square deviation (RMSD) and the average absolute deviation (AAD) of 0.038 and 0.030 g · cm^–3, respectively. In addition, the correlation gives good predictions for further 25 azole‐based energetic compounds as test set (Q²_EXT = 0.901). The predictive ability of the correlation is checked using a cross validation method (Q²_LMO = 0.918). The proposed method can also apply for designing novel azole‐based energetic compounds.     

QSPR modelling of the soil sorption coefficient from training sets of different sizes

Quantitative structure–property relationship (QSPR) modelling has been used in many scientific fields. This approach has been extensively applied in environmental research to predict physicochemical properties of compounds with potential environmental impact. The soil sorption coefficient is an important parameter for the evaluation of environmental risks, and it helps to determine the final fate of substances in the environment. In the last few years, different QSPR models have been developed for the determination of the sorption coefficient. In this study, several QSPR models were generated and evaluated for the prediction of log K_oc from the relationship with log P. These models were obtained from an extensive and diverse training set (n = 639) and from subsets of this initial set (i.e. halves, fourths and eighths). The aim of this study was to investigate whether the size of the training set affects the statistical quality of the obtained models. Furthermore, statistical equivalence was verified between the models obtained from smaller sets and the model obtained from the total training set. The results confirmed the equivalence between the models, thus indicating the possibility of using smaller training sets without compromising the statistical quality and predictive capability, as long as most chemical classes in the test set are represented in the training set.