![]() ![]() The ability to predict logP and pKa and utilize these parameters to predict logD can therefore be of value for a number of applications, including drug design. Ionization characteristics of a chemical across this pH range therefore influence absorption in different locations in the body. For example, pH varies widely through the body from about 1.5 in the lower portion of the stomach to about 8.5 in the duodenum. This pH-dependent prediction is important to consider when attempting to predict absorption. Together, pKa and logP can be used to predict logD values. ![]() This constant is therefore used to estimate the different relative concentrations of the ionized and non-ionized forms of a chemical at a given pH. ![]() logD is the distribution coefficient that takes into account the pH. These, in turn, will provide context for both biomonitoring data and high-throughput toxicity screening studies.ĭistribution of a chemical in an octanol/water mixture (described by the constants logKow or logP) is affected by the ionizable groups present in the chemical and is pH-dependent. These data sets provide input for high-throughput methods for calculating the apparent volume of distribution at steady state and tissue-specific PK distribution coefficients that will allow for the rapid construction of PK models. are producing data sets that characterize metabolism and excretion for hundreds of chemicals. Approaches such as those described by Wetmore et al. PKa is also an important parameter for physiologically based pharmacokinetic (PK) modeling and in vitro to in vivo extrapolation. Thus, pKa affects absorption, distribution, metabolism, excretion, and toxicity properties and is considered one of the five most important parameters in drug discovery. Chemicals with no charge at a physiological pH will cross the plasma membrane more easily than charged molecules and will therefore have greater potential for pharmacological or toxicological activity. The contributions of physicochemical parameters, including pKa, to environmental fate, transport, and distribution are well-recognized. pKa reflects the ionization state of a chemical, which in turn affects lipophilicity, solubility, protein binding, and ability to cross the plasma membrane and the blood–brain barrier. The pKa of a chemical strongly influences its pharmacokinetic and biochemical properties. Ka is usually represented as pKa = − log10 Ka. The acid dissociation constant (also called the protonation or ionization constant) Ka is an equilibrium constant defined as the ratio of the protonated and the deprotonated form of a compound. This work provides multiple QSAR models to predict the strongest acidic and strongest basic pKas of chemicals, built using publicly available data, and provided as free and open-source software on GitHub. Two commercial pKa predictors from ACD/Labs and ChemAxon were used to benchmark the three best models developed in this work, and performance of our models compared favorably to the commercial products. ![]() The three methods delivered comparable performances on the training and test sets with a root-mean-squared error (RMSE) around 1.5 and a coefficient of determination (R 2) around 0.80. Continuous molecular descriptors, binary fingerprints, and fragment counts were generated using PaDEL, and pKa prediction models were created using three machine learning methods, (1) support vector machines (SVM) combined with k-nearest neighbors (kNN), (2) extreme gradient boosting (XGB) and (3) deep neural networks (DNN). To evaluate different approaches to modeling, several datasets were constructed based on different processing of chemical structures with acidic and/or basic pKas. Chemical structures were curated and standardized for quantitative structure–activity relationship (QSAR) modeling using KNIME, and a subset comprising 79% of the initial set was used for modeling. The experimental strongest acidic and strongest basic pKa values in water for 7912 chemicals were obtained from DataWarrior, a freely available software package. Using a freely available data set and three machine learning approaches, we developed open-source models for pKa prediction. Multiple proprietary software packages exist for the prediction of pKa, but to the best of our knowledge no free and open-source programs exist for this purpose. Thus, pKa affects chemical absorption, distribution, metabolism, excretion, and toxicity properties. The logarithmic acid dissociation constant pKa reflects the ionization of a chemical, which affects lipophilicity, solubility, protein binding, and ability to pass through the plasma membrane. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |