A deep neural network: mechanistic hybrid model to predict pharmacokinetics in rat.

An important aspect in the development of small molecules as drugs or agrochemicals is their systemic availability after intravenous and oral administration. The prediction of the systemic availability from the chemical structure of a potential candidate is highly desirable, as it allows to focus the drug or agrochemical development on compounds with a favorable kinetic profile. However, such predictions are challenging as the availability is the result of the complex interplay between molecular properties, biology and physiology and training data is rare. In this work we improve the hybrid model developed earlier (Schneckener in J Chem Inf Model 59:4893-4905, 2019). We reduce the median fold change error for the total oral exposure from 2.85 to 2.35 and for intravenous administration from 1.95 to 1.62. This is achieved by training on a larger data set, improving the neural network architecture as well as the parametrization of mechanistic model. Further, we extend our approach to predict additional endpoints and to handle different covariates, like sex and dosage form. In contrast to a pure machine learning model, our model is able to predict new end points on which it has not been trained. We demonstrate this feature by predicting the exposure over the first 24 h, while the model has only been trained on the total exposure.

Emodepside targets SLO-1 channels of Onchocerca ochengi and induces broad anthelmintic effects in a bovine model of onchocerciasis.

Onchocerciasis (river blindness), caused by the filarial worm Onchocerca volvulus, is a neglected tropical disease mostly affecting sub-Saharan Africa and is responsible for >1.3 million years lived with disability. Current control relies almost entirely on ivermectin, which suppresses symptoms caused by the first-stage larvae (microfilariae) but does not kill the long-lived adults. Here, we evaluated emodepside, a semi-synthetic cyclooctadepsipeptide registered for deworming applications in companion animals, for activity against adult filariae (i.e., as a macrofilaricide). We demonstrate the equivalence of emodepside activity on SLO-1 potassium channels in Onchocerca volvulus and Onchocerca ochengi, its sister species from cattle. Evaluation of emodepside in cattle as single or 7-day treatments at two doses (0.15 and 0.75 mg/kg) revealed rapid activity against microfilariae, prolonged suppression of female worm fecundity, and macrofilaricidal effects by 18 months post treatment. The drug was well tolerated, causing only transiently increased blood glucose. Female adult worms were mostly paralyzed; however, some retained metabolic activity even in the multiple high-dose group. These data support ongoing clinical development of emodepside to treat river blindness.

A workflow to build PBTK models for novel species.

Physiology-based pharmacokinetic and toxicokinetic (PBPK/TK) models allow us to simulate the concentration of xenobiotica in the plasma and different tissues of an organism. PBPK/TK models are therefore routinely used in many fields of life sciences to simulate the physiological concentration of exogenous compounds in plasma and tissues. The application of PBTK models in ecotoxicology, however, is currently hampered by the limited availability of models for focal species. Here, we present a best practice workflow that describes how to build PBTK models for novel species. To this end, we extrapolated eight previously established rabbit models for several drugs to six additional mammalian species (human, beagle, rat, monkey, mouse, and minipig). We used established PBTK models for these species to account for the species-specific physiology. The parameter sensitivity in the resulting 56 PBTK models was systematically assessed to rank the relevance of the parameters on overall model performance. Interestingly, more than 80% of the 609 considered model parameters showed a negligible sensitivity throughout all models. Only approximately 5% of all parameters had a high sensitivity in at least one of the PBTK models. This approach allowed us to rank the relevance of the various parameters on overall model performance. We used this information to formulate a best practice guideline for the efficient development of PBTK models for novel animal species. We believe that the workflow proposed in this study will significantly support the development of PBTK models for new animal species in the future.

Bayer's in silico ADMET platform: a journey of machine learning over the past two decades.

Over the past two decades, an in silico absorption, distribution, metabolism, and excretion (ADMET) platform has been created at Bayer Pharma with the goal to generate models for a variety of pharmacokinetic and physicochemical endpoints in early drug discovery. These tools are accessible to all scientists within the company and can be a useful in assisting with the selection and design of novel leads, as well as the process of lead optimization. Here. we discuss the development of machine-learning (ML) approaches with special emphasis on data, descriptors, and algorithms. We show that high company internal data quality and tailored descriptors, as well as a thorough understanding of the experimental endpoints, are essential to the utility of our models. We discuss the recent impact of deep neural networks and show selected application examples.

Prediction of Oral Bioavailability in Rats: Transferring Insights from in Vitro Correlations to (Deep) Machine Learning Models Using in Silico Model Outputs and Chemical Structure Parameters.

Oral administration of drug products is a strict requirement in many medical indications. Therefore, bioavailability prediction models are of high importance for prioritization of compound candidates in the drug discovery process. However, oral exposure and bioavailability are difficult to predict, as they are the result of various highly complex factors and/or processes influenced by the physicochemical properties of a compound, such as solubility, lipophilicity, or charge state, as well as by interactions with the organism, for instance, metabolism or membrane permeation. In this study, we assess whether it is possible to predict intravenous (iv) or oral drug exposure and oral bioavailability in rats. As input parameters, we use (i) six experimentally determined in vitro and physicochemical endpoints, namely, membrane permeation, free fraction, metabolic stability, solubility, pKa value, and lipophilicity; (ii) the outputs of six in silico absorption, distribution, metabolism, and excretion models trained on the same endpoints, or (iii) the chemical structure encoded as fingerprints or simplified molecular input line entry system strings. The underlying data set for the models is an unprecedented collection of almost 1900 data points with high-quality in vivo experiments performed in rats. We find that drug exposure after iv administration can be predicted similarly well using hybrid models with in vitro- or in silico-predicted endpoints as inputs, with fold change errors (FCE) of 2.28 and 2.08, respectively. The FCEs for exposure after oral administration are higher, and here, the prediction from in vitro inputs performs significantly better in comparison to in silico-based models with FCEs of 3.49 and 2.40, respectively, most probably reflecting the higher complexity of oral bioavailability. Simplifying the prediction task to a binary alert for low oral bioavailability, based only on chemical structure, we achieve accuracy and precision close to 70%.

Reliable and Performant Identification of Low-Energy Conformers in the Gas Phase and Water.

Prediction of compound properties from structure via quantitative structure-activity relationship and machine-learning approaches is an important computational chemistry task in small-molecule drug research. Though many such properties are dependent on three-dimensional structures or even conformer ensembles, the majority of models are based on descriptors derived from two-dimensional structures. Here we present results from a thorough benchmark study of force field, semiempirical, and density functional methods for the calculation of conformer energies in the gas phase and water solvation as a foundation for the correct identification of relevant low-energy conformers. We find that the tight-binding ansatz GFN-xTB shows the lowest error metrics and highest correlation to the benchmark PBE0-D3(BJ)/def2-TZVP in the gas phase for the computationally fast methods and that in solvent OPLS3 becomes comparable in performance. MMFF94, AM1, and DFTB+ perform worse, whereas the performance-optimized but far more expensive functional PBEh-3c yields energies almost perfectly correlated to the benchmark and should be used whenever affordable. On the basis of our findings, we have implemented a reliable and fast protocol for the identification of low-energy conformers of drug-like molecules in water that can be used for the quantification of strain energy and entropy contributions to target binding as well as for the derivation of conformer-ensemble-dependent molecular descriptors.

Development and validation of a physiology-based model for the prediction of pharmacokinetics/toxicokinetics in rabbits.

The environmental fates of pharmaceuticals and the effects of crop protection products on non-target species are subjects that are undergoing intense review. Since measuring the concentrations and effects of xenobiotics on all affected species under all conceivable scenarios is not feasible, standard laboratory animals such as rabbits are tested, and the observed adverse effects are translated to focal species for environmental risk assessments. In that respect, mathematical modelling is becoming increasingly important for evaluating the consequences of pesticides in untested scenarios. In particular, physiologically based pharmacokinetic/toxicokinetic (PBPK/TK) modelling is a well-established methodology used to predict tissue concentrations based on the absorption, distribution, metabolism and excretion of drugs and toxicants. In the present work, a rabbit PBPK/TK model is developed and evaluated with data available from the literature. The model predictions include scenarios of both intravenous (i.v.) and oral (p.o.) administration of small and large compounds. The presented rabbit PBPK/TK model predicts the pharmacokinetics (Cmax, AUC) of the tested compounds with an average 1.7-fold error. This result indicates a good predictive capacity of the model, which enables its use for risk assessment modelling and simulations.

A systematic evaluation of the use of physiologically based pharmacokinetic modeling for cross-species extrapolation.

Transfer of knowledge along the different phases of drug development is a fundamental process in pharmaceutical research. In particular, cross-species extrapolation between different laboratory animals and further on to first-in-human trials is challenging because of the uncertain comparability of physiological processes. Physiologically based pharmacokinetic (PBPK) modeling allows translation of mechanistic knowledge from one species to another by specifically considering physiological and biochemical differences in between. We here evaluated different knowledge-driven approaches for cross-species extrapolation by systematically incorporating specific model parameter domains of a target species into the PBPK model of a reference species. Altogether, 15 knowledge-driven approaches were applied to murine and human PBPK models of 10 exemplary drugs resulting in 300 different extrapolations. Statistical analysis of the quality of the different extrapolations revealed not only species-specific physiology as the key determinant in cross-species extrapolation but also identified a synergistic effect when considering both kinetic rate constants and gene expression profiles of relevant enzymes and transporters. Moreover, we show that considering species-specific physiology, plasma protein binding, enzyme and transport kinetics, as well as tissue-specific gene expression profiles in PBPK modeling increases accuracy of cross-species extrapolations and thus supports first-in-human trials based on prior preclinical knowledge.

Prediction errors in learning drug response from gene expression data - influence of labeling, sample size, and machine learning algorithm.

Model-based prediction is dependent on many choices ranging from the sample collection and prediction endpoint to the choice of algorithm and its parameters. Here we studied the effects of such choices, exemplified by predicting sensitivity (as IC50) of cancer cell lines towards a variety of compounds. For this, we used three independent sample collections and applied several machine learning algorithms for predicting a variety of endpoints for drug response. We compared all possible models for combinations of sample collections, algorithm, drug, and labeling to an identically generated null model. The predictability of treatment effects varies among compounds, i.e. response could be predicted for some but not for all. The choice of sample collection plays a major role towards lowering the prediction error, as does sample size. However, we found that no algorithm was able to consistently outperform the other and there was no significant difference between regression and two- or three class predictors in this experimental setting. These results indicate that response-modeling projects should direct efforts mainly towards sample collection and data quality, rather than method adjustment.

Using expression data for quantification of active processes in physiologically based pharmacokinetic modeling.

Active processes involved in drug metabolization and distribution mediated by enzymes, transporters, or binding partners mostly occur simultaneously in various organs. However, a quantitative description of active processes is difficult because of limited experimental accessibility of tissue-specific protein activity in vivo. In this work, we present a novel approach to estimate in vivo activity of such enzymes or transporters that have an influence on drug pharmacokinetics. Tissue-specific mRNA expression is used as a surrogate for protein abundance and activity and is integrated into physiologically based pharmacokinetic (PBPK) models that already represent detailed anatomical and physiological information. The new approach was evaluated using three publicly available databases: whole-genome expression microarrays from ArrayExpress, reverse transcription-polymerase chain reaction-derived gene expression estimates collected from the literature, and expressed sequence tags from UniGene. Expression data were preprocessed and stored in a customized database that was then used to build PBPK models for pravastatin in humans. These models represented drug uptake by organic anion-transporting polypeptide 1B1 and organic anion transporter 3, active efflux by multidrug resistance protein 2, and metabolization by sulfotransferases in liver, kidney, and/or intestine. Benchmarking of PBPK models based on gene expression data against alternative models with either a less complex model structure or randomly assigned gene expression values clearly demonstrated the superior model performance of the former. Besides accurate prediction of drug pharmacokinetics, integration of relative gene expression data in PBPK models offers the unique possibility to simultaneously investigate drug-drug interactions in all relevant organs because of the physiological representation of protein-mediated processes.

Quantifying stability in gene list ranking across microarray derived clinical biomarkers.

BACKGROUND: Identifying stable gene lists for diagnosis, prognosis prediction, and treatment guidance of tumors remains a major challenge in cancer research. Microarrays measuring differential gene expression are widely used and should be versatile predictors of disease and other phenotypic data. However, gene expression profile studies and predictive biomarkers are often of low power, requiring numerous samples for a sound statistic, or vary between studies. Given the inconsistency of results across similar studies, methods that identify robust biomarkers from microarray data are needed to relay true biological information. Here we present a method to demonstrate that gene list stability and predictive power depends not only on the size of studies, but also on the clinical phenotype. RESULTS: Our method projects genomic tumor expression data to a lower dimensional space representing the main variation in the data. Some information regarding the phenotype resides in this low dimensional space, while some information resides in the residuum. We then introduce an information ratio (IR) as a metric defined by the partition between projected and residual space. Upon grouping phenotypes such as tumor tissue, histological grades, relapse, or aging, we show that higher IR values correlated with phenotypes that yield less robust biomarkers whereas lower IR values showed higher transferability across studies. Our results indicate that the IR is correlated with predictive accuracy. When tested across different published datasets, the IR can identify information-rich data characterizing clinical phenotypes and stable biomarkers. CONCLUSIONS: The IR presents a quantitative metric to estimate the information content of gene expression data with respect to particular phenotypes.

An elastic network model to identify characteristic stress response genes.

Exposing eukaryotic cells to a toxic compound and subsequent gene expression profiling may allow the prediction of selected toxic effects based on changes in gene expression. This objective is complicated by the observation that compounds with different modes of toxicity cause similar changes in gene expression and that a global stress response affects many genes. We developed an elastic network model of global stress response with nodes representing genes which are connected by edges of graded coexpression. The expression of only few genes have to be known to model the global stress response of all but a few atypical responder genes. Those required genes and the atypical response genes are shown to be good biomarker for tox predictions. In total, 138 experiments and 13 different compounds were used to train models for different toxicity classes. The deduced biomarkers were shown to be biologically plausible. A neural network was trained to predict the toxic effects of compounds from profiling experiments. On a validation data set of 189 experiments with 16 different compounds the accuracy of the predictions was assessed: 14 out of 16 compounds have been classified correctly. Derivation of model based biomarkers through the elastic network approach can naturally be extended to other areas beyond toxicology since subtle signals against a broad response background are common in biological studies.