In silico approaches for predicting ADME properties of drugs

QSAR of cytochrome inhibitors

Cytochrome P450 (CYP450) enzymes are predominantly involved in the Phase I metabolism of xenobiotics. Metabolic inhibition and induction can give rise to clinically important drug-drug interactions. Metabolic stability is a prerequisite for sustaining the therapeutically relevant concentrations, and very often drug candidates are sacrificed due to poor metabolic profiles. Computational tools such as quantitative structure-activity relationships are widely used to study different metabolic end points successfully to accelerate the drug discovery process. There are a lot of computational studies on clinically important CYPs already reported in recent years. But other clinically significant families are to yet be explored computationally. Powerfulness of quantitative structure-activity relationship will drive computational chemists to develop new potent and selective inhibitors of different classes of CYPs for the treatment of different diseases with least drug-drug interactions. Furthermore, there is a need to enhance the accuracy, interpretability and confidence in the computational models in accelerating the drug discovery pathways.

Computing with evidence Part II: An evidential approach to predicting metabolic drug-drug interactions

We describe a novel experiment that we conducted with the Drug Interaction Knowledge-base (DIKB) to determine which combinations of evidence enable a rule-based theory of metabolic drug-drug interactions to make the most optimal set of predictions. The focus of the experiment was a group of 16 drugs including six members of the HMG-CoA-reductase inhibitor family (statins). The experiment helped identify evidence-use strategies that enabled the DIKB to predict significantly more interactions present in a validation set than the most rigorous strategy developed by drug experts with no loss of accuracy. The best-performing strategies included evidence types that would normally be of lesser predictive value but that are often more accessible than more rigorous types. Our experimental methods represent a new approach to leveraging the available scientific evidence within a domain where important evidence is often missing or of questionable value for supporting important assertions.

Quantitative structure/activity relationship modelling of pharmacokinetic properties using genetic algorithm-combined partial least squares method

Quantitative structure/activity relationship (QSAR) approaches have widely been applied to gain deeper understandings of the relationships between ADME parameters and molecular structure and properties. QSAR models for predicting ADME properties are required to cover structurally diverse compounds. In the present investigation, we describe application of genetic algorithm-combined partial least squares (GA-PLS) method to QSAR modelling of various ADME properties. By selecting an appropriate set of molecular descriptors automatically by the use of genetic algorithm, many ADME properties could be well-explained by simple molecular descriptors derived from 2-dimensional chemical structure.

Estimation of ADME Properties in Drug Discovery: Predicting Caco-2 Cell Permeability Using Atom-Based Stochastic and Non-stochastic Linear Indices

The in vitro determination of the permeability through cultured Caco-2 cells is the most often-used in vitro model for drug absorption. In this report, we use the largest data set of measured P(Caco-2), consisting of 157 structurally diverse compounds. Linear discriminant analysis (LDA) was used to obtain quantitative models that discriminate higher absorption compounds from those with moderate-poorer absorption. The best LDA model has an accuracy of 90.58% and 84.21% for training and test set. The percentage of good correlation, in the virtual screening of 241 drugs with the reported values of the percentage of human intestinal absorption (HIA), was greater than 81%. In addition, multiple linear regression models were developed to predict Caco-2 permeability with determination coefficients of 0.71 and 0.72. Our method compares favorably with other approaches implemented in the Dragon software, as well as other methods from the international literature. These results suggest that the proposed method is a good tool for studying the oral absorption of drug candidates.

Modeling drug mechanism knowledge using evidence and truth maintenance

To protect the safety of patients, it is vital that researchers find methods for representing drug mechanism knowledge that support making clinically relevant drug-drug interaction (DDI) predictions. Our research aims to identify the challenges of representing and reasoning with drug mechanism knowledge and to evaluate potential informatics solutions to these challenges through the process of developing a knowledge-based system capable of predicting clinically relevant DDIs that occur via metabolic mechanisms. In previous work, we designed a simple, rule-based, model of metabolic inhibition and induction and applied it to a database containing assertions about 267 drugs. This pilot system taught us that drug mechanism knowledge is often dynamic, missing, or uncertain. In this paper, we propose methods to address these properties of mechanism knowledge and describe a new prototype system, the Drug Interaction Knowledge-base (DIKB), that implements our proposed methods so that we can explore their strengths and limitations. A novel feature of the DIKB is its use of a truth maintenance system to link changes in the evidence support for assertions about drug properties to the set of interactions and non-interactions the system predicts.

Caco-2 cell permeability modelling: a neural network coupled genetic algorithm approach

The ability to cross the intestinal cell membrane is a fundamental prerequisite of a drug compound. However, the experimental measurement of such an important property is a costly and highly time consuming step of the drug development process because it is necessary to synthesize the compound first. Therefore, in silico modelling of intestinal absorption, which can be carried out at very early stages of drug design, is an appealing alternative procedure which is based mainly on multivariate statistical analysis such as partial least squares (PLS) and neural networks (NN). Our implementation of neural network models for the prediction of intestinal absorption is based on the correlation of Caco-2 cell apparent permeability (P (app)) values, as a measure of intestinal absorption, to the structures of two different data sets of drug candidates. Several molecular descriptors of the compounds were calculated and the optimal subsets were selected using a genetic algorithm; therefore, the method was indicated as Genetic Algorithm-Neural Network (GA-NN). A methodology combining a genetic algorithm search with neural network analysis applied to the modelling of Caco-2 P (app) has never been presented before, although the two procedures have been already employed separately. Moreover, we provide new Caco-2 cell permeability measurements for more than two hundred compounds. Interestingly, the selected descriptors show to possess physico-chemical connotations which are in excellent accordance with the well known relevant molecular properties involved in the cellular membrane permeation phenomenon: hydrophilicity, hydrogen bonding propensity, hydrophobicity and molecular size. The predictive ability of the models, although rather good for a preliminary study, is somewhat affected by the poor precision of the experimental Caco-2 measurements. Finally, the generalization ability of one model was checked on an external test set not derived from the data sets used to build the models. The result obtained is of interesting practical application and underlines that the successful model construction is strictly dependent on the structural space representation of the data set used for model development.

Quantitative structure-pharmacokinetic/pharmacodynamic relationships

Quantitative structure-activity relationships have long been considered a vital component of drug discovery and development, providing insight into the role of molecular properties in the biological activity of similar and unrelated compounds. Recognition that in vitro bioassay and/or pre-clinical activity are insufficient for anticipating which compounds are suitable leads for further development has shifted the focus toward integrated pharmacokinetic (PK) and pharmacodynamic (PD) processes. Over the last decade, considerable progress has been made in constructing empirical and mechanistic quantitative structure-PK relationships (QSPKR), as well as diverse mechanism-based pharmacodynamic models of drug effects. In this review, traditional and contemporary approaches to developing QSPKR models are discussed, along with selected examples of attempts to couple QSPKR and pharmacodynamic models to anticipate the intensity and time-course of the pharmacological effects of new or related compounds, or quantitative structure-pharmacodynamic relationships modeling. Such models are in accordance with the goals of systems biology and the ideal of designing drugs and delivery systems from first principles.

In Silico Prediction of Pharmacokinetic Properties

In silico methods for predicting pharmacokinetic properties range from data-based approaches such as quantitative structure-activity relationships (QSARs), similarity searches, and 3-dimensional QSAR, to structure-based methods such as ligand-protein docking and pharmacophore modelling. Data-based modelling approaches are effective for many drug absorption, distribution, metabolism, and excretion (ADME) processes such as passive membrane permeation, where their molecular mechanism is barely delineated. Therefore QSAR approaches have been applied to simulate the relationships between ADME parameters and molecular structure and properties. In the present investigation, we describe the application of the genetic algorithm-combined partial least-squares (GA-PLS) method to QSAR modelling of various ADME properties. By selecting an appropriate set of molecular descriptors automatically using the genetic algorithm, many ADME properties could be well explained by simple molecular descriptors derived from the 2-dimensional chemical structure.