Application of Random Forest and Multiple Linear Regression Techniques to QSPR Prediction of an Aqueous Solubility for Military Compounds

Abstract

The relationship between the aqueous solubility of more than two thousand eight hundred organic compounds and their structures was investigated using a QSPR approach based on Simplex Representation of Molecular Structure (SiRMS). The dataset consists of 2537 diverse organic compounds. Multiple Linear Regression (MLR) and Random Forest (RF) methods were used for statistical modeling at the 2D level of representation of molecular structure. Statistical characteristics of the best models are quite good (MLR method: R(2) =0.85, Q(2) =0.83; RF method: R(2) =0.99, R(2) oob =0.88). The external validation set of 301 compounds (including 47 nitro-, nitroso- and nitrogen-rich compounds of military interest) which were not included in the training set and modeling process, was used for evaluation of the models predictivity. Thus, well-fitted and robust (R(2) test (MLR)=0.76 and R(2) test (RF)=0.82) models were obtained for both statistical techniques using descriptors based on the topological structural information only. The predicted solubility values for military compounds are in good agreement with experimental ones. Developed QSPR models represent powerful and easy-to-use virtual screening tool that can be recommended for prediction of aqueous solubility.

Novel enhanced applications of QSPR models: Temperature dependence of aqueous solubility

“…Recent reviews provide the state‐of‐art analysis of QSPR applicability in terms of aqueous solubility description and prediction. It was highlighted that current tendency in QSPR models development is to create models capable of describing and predicting solubility of large sets of structurally diverse compounds.…”

“…Recently, we have investigated aqueous solubility of military‐relevant compounds using QSPR approach . In addition, QSPR analysis of aqueous solubility of more than 2500 organic compounds which belong to different classes and the influence of salinity on solubility was the subject of other publications . However, all models available in the literature for aqueous solubility prediction at QSPR level suffer from a serious limitation.…”

“…Therefore, in the current work, we have broadened the principles and techniques formulated in Ref. [ ] by adding one additional parameter—the temperature of dissolution inclusion into QSPR consideration.…”

A metabonomics investigation of multiple sclerosis by nuclear magnetic resonance

“…This eminent technique and potent method can diminish the variance and improve the prediction accuracy. RF has been utilized as a classification and regression method in several biological studies . Both the RF classification and RF regression procedures can identify important features useful in either elucidating the variation in the outputs of interest or classifying the results in to different groups.…”

Quantitative Structure-Property Relationship Analysis of Drugs’ Pharmacokinetics Within the Framework of Biopharmaceutics Classification System Using Simplex Representation of Molecular Structure

“…Any compounds whose bioavailability is strongly affected by the dose and formulation was excluded from the dataset. Random forest method [61,62] was used for the development of QSPR classification models. All compounds were divided into three (high, medium and low bioavailability, Table 14.1) or two (high and acceptable, Table 14.2) classes.…”