Evaluation of in silico model predictions for mammalian acute oral toxicity and regulatory application in pesticide hazard and risk assessment.

The United States Environmental Protection Agency (USEPA) uses the lethal dose 50% (LD50) value from in vivo rat acute oral toxicity studies for pesticide product label precautionary statements and environmental risk assessment (RA). The Collaborative Acute Toxicity Modeling Suite (CATMoS) is a quantitative structure-activity relationship (QSAR)-based in silico approach to predict rat acute oral toxicity that has the potential to reduce animal use when registering a new pesticide technical grade active ingredient (TGAI). This analysis compared LD50 values predicted by CATMoS to empirical values from in vivo studies for the TGAIs of 177 conventional pesticides. The accuracy and reliability of the model predictions were assessed relative to the empirical data in terms of USEPA acute oral toxicity categories and discrete LD50 values for each chemical. CATMoS was most reliable at placing pesticide TGAIs in acute toxicity categories III (>500-5000 mg/kg) and IV (>5000 mg/kg), with 88% categorical concordance for 165 chemicals with empirical in vivo LD50 values ≥ 500 mg/kg. When considering an LD50 for RA, CATMoS predictions of 2000 mg/kg and higher were found to agree with empirical values from limit tests (i.e., single, high-dose tests) or definitive results over 2000 mg/kg with few exceptions.

Experimental and Computational Methods to Assess Central Nervous System Penetration of Small Molecules.

In CNS drug discovery, the estimation of brain exposure to lead compounds is critical for their optimization. Compounds need to cross the blood-brain barrier (BBB) to reach the pharmacological targets in the CNS. The BBB is a complex system involving passive and active mechanisms of transport and efflux transporters such as P-glycoproteins (P-gp) and breast cancer resistance protein (BCRP), which play an essential role in CNS penetration of small molecules. Several in vivo, in vitro, and in silico methods are available to estimate human brain penetration. Preclinical species are used as in vivo models to understand unbound brain exposure by deriving the Kp,uu parameter and the brain/plasma ratio of exposure corrected with the plasma and brain free fraction. The MDCK-mdr1 (Madin Darby canine kidney cells transfected with the MDR1 gene encoding for the human P-gp) assay is the commonly used in vitro assay to estimate compound permeability and human efflux. The in silico methods to predict brain exposure, such as CNS MPO, CNS BBB scores, and various machine learning models, help save costs and speed up compound discovery and optimization at all stages. These methods enable the screening of virtual compounds, building of a CNS penetrable compounds library, and optimization of lead molecules for CNS penetration. Therefore, it is crucial to understand the reliability and ability of these methods to predict CNS penetration. We review the in silico, in vitro, and in vivo data and their correlation with each other, as well as assess published experimental and computational approaches to predict the BBB penetrability of compounds.

A novel davunetide (NAPVSIPQQ to NAPVSIPQE) point mutation in activity-dependent neuroprotective protein (ADNP) causes a mild developmental syndrome.

NAP (NAPVSIPQ, drug candidate name, davunetide) is the neuroprotective fragment of activity-dependent neuroprotective protein (ADNP). Recent studies identified NAPVSIP as a Src homology 3 (SH3) domain-ligand association site, responsible for controlling signalling pathways regulating the cytoskeleton. Furthermore, the SIP motif in NAP/ADNP was identified as crucial for direct microtubule end-binding protein interaction facilitating microtubule dynamics and Tau microtubule interaction, at the microtubule end-binding protein site EB1 and EB3. Most de novo ADNP mutations reveal heterozygous STOP or frameshift STOP aberrations, driving the autistic/intellectual disability-related ADNP syndrome. Here, we report for the first time on a de novo missense mutation, resulting in ADNP containing NAPVISPQE instead of NAPVSIPQQ, in a child presenting developmental hypotonia, possibly associated with inflammation affecting food intake in early life coupled with fear of peer interactions and suggestive of a novel case of the ADNP syndrome. In silico modelling showed that the mutation Q (polar side chain) to E (negative side chain) affected the electrostatic characteristics of ADNP (reducing, while scattering the electrostatic positive patch). Comparison with the most prevalent pathogenic ADNP mutation, p.Tyr719*, indicated a further reduction in the electrostatic patch. Previously, exogenous NAP partially ameliorated deficits associated with ADNP p.Tyr719* mutations in transfected cells and in CRISPR/Cas9 genome edited cell and mouse models. These findings stress the importance of the NAP sequence in ADNP and as a future putative therapy for the ADNP syndrome.

An in silico approach to understanding the interaction between cardiovascular and pulmonary lymphatic dysfunction.

The lung is extremely sensitive to interstitial fluid balance, yet the role of pulmonary lymphatics in lung fluid homeostasis and its interaction with cardiovascular pressures is poorly understood. In health, there is a fine balance between fluid extravasated from the pulmonary capillaries into the interstitium and the return of fluid to the circulation via the lymphatic vessels. This balance is maintained by an extremely interdependent system governed by pressures in the fluids (air and blood) and tissue (interstitium), lung motion during breathing, and the permeability of the tissues. Chronic elevation in left atrial pressure (LAP) due to left heart disease increases the capillary blood pressure. The consequent fluid accumulation in the delicate lung tissue increases its weight, decreases its compliance, and impairs gas exchange. This interdependent system is difficult, if not impossible, to study experimentally. Computational modeling provides a unique perspective to analyze fluid movement in the cardiopulmonary vasculature in health and disease. We have developed an initial in silico model of pulmonary lymphatic function using an anatomically structured model to represent ventilation and perfusion and underlying biophysical laws governing fluid transfer at the interstitium. This novel model was tested against increased LAP and noncardiogenic effects (increased permeability). The model returned physiologically reasonable values for all applications, predicting pulmonary edema when LAP reached 25 mmHg and with increased permeability.NEW & NOTEWORTHY This model presents a novel approach to understanding the interaction between cardiac dysfunction and pulmonary lymphatic function, using anatomically structured models and biophysical equations to estimate regional variation in fluid transport from blood to interstitial and lymphatic flux. This fluid transport model brings together advanced models of ventilation, perfusion, and lung mechanics to produce a detailed model of fluid transport in health and various altered pathological conditions.

Development of In Silico Models for Predicting Potential Time-Dependent Inhibitors of Cytochrome P450 3A4.

Cytochrome P450 3A4 (CYP3A4) is one of the major drug metabolizing enzymes in the human body and metabolizes ∼30-50% of clinically used drugs. Inhibition of CYP3A4 must always be considered in the development of new drugs. Time-dependent inhibition (TDI) is an important P450 inhibition type that could cause undesired drug-drug interactions. Therefore, identification of CYP3A4 TDI by a rapid convenient way is of great importance to any new drug discovery effort. Here, we report the development of in silico classification models for prediction of potential CYP3A4 time-dependent inhibitors. On the basis of the CYP3A4 TDI data set that we manually collected from literature and databases, both conventional machine learning and deep learning models were constructed. The comparisons of different sampling strategies, molecular representations, and machine-learning algorithms showed the benefits of a balanced data set and the deep-learning model featured by GraphConv. The generalization ability of the best model was tested by screening an external data set, and the prediction results were validated by biological experiments. In addition, several structural alerts that are relevant to CYP3A4 time-dependent inhibitors were identified via information gain and frequency analysis. We anticipate that our effort would be useful for identification of potential CYP3A4 time-dependent inhibitors in drug discovery and design.

The application of acute oral toxicity computational models in dangerous goods classification.

Acute oral toxicity (AOT) data inform the acute toxicity potential of a compound and guides occupational safety and transportation practices. AOT data enable the categorization of a chemical into the appropriate AOT Globally Harmonized System (GHS) category based on the severity of the hazard. AOT data are also utilized to identify compounds that are Dangerous Goods (DGs) and subsequent transportation guidance for shipping of these hazardous materials. Proper identification of DGs is challenging for novel compounds that lack data. It is not feasible to err on the side of caution for all compounds lacking AOT data and to designate them as DGs, as shipping a compound as a DG has cost, resource, and time implications. With the wealth of available historical AOT data, AOT testing approaches are evolving, and in silico AOT models are emerging as tools that can be utilized with confidence to assess the acute toxicity potential of de novo molecules. Such approaches align with the 3R principles, offering a reduction or even replacement of traditional in vivo testing methods and can also be leveraged for product stewardship purposes. Utilizing proprietary historical in vivo AOT data for 210 pharmaceutical compounds (PCs), we evaluated the performance of two established in silico AOT programs: the Leadscope AOT Model Suite and the Collaborative Acute Toxicity Modeling Suite. These models accurately identified 94% and 97% compounds that were not DGs (GHS categories 4, 5, and not classified (NC)) suggesting that the models are fit-for-purpose in identifying PCs with low acute oral toxicity potential (LD50 >300 mg/kg). Utilization of these models to identify compounds that are not DGs can enable them to be de-prioritized for in vivo testing. This manuscript provides a detailed evaluation and assessment of the two models and recommends the most suitable applications of such models.

The VEGA Tool to Check the Applicability Domain Gives Greater Confidence in the Prediction of In Silico Models.

A sound assessment of in silico models and their applicability domain can support the use of new approach methodologies (NAMs) in chemical risk assessment and requires increasing the users' confidence in this approach. Several approaches have been proposed to evaluate the applicability domain of such models, but their prediction power still needs a thorough assessment. In this context, the VEGA tool capable of assessing the applicability domain of in silico models is examined for a range of toxicological endpoints. The VEGA tool evaluates chemical structures and other features related to the predicted endpoints and is efficient in measuring applicability domain, enabling the user to identify less accurate predictions. This is demonstrated with many models addressing different endpoints, towards toxicity of relevance to human health, ecotoxicological endpoints, environmental fate, physicochemical and toxicokinetic properties, for both regression models and classifiers.

The Road to Achieving the European Commission's Chemicals Strategy for Nanomaterial Sustainability-A PATROLS Perspective on New Approach Methodologies.

The European Green Deal outlines ambitions to build a more sustainable, climate neutral, and circular economy by 2050. To achieve this, the European Commission has published the Chemicals Strategy for Sustainability: Towards a Toxic-Free Environment, which provides targets for innovation to better protect human and environmental health, including challenges posed by hazardous chemicals and animal testing. The European project PATROLS (Physiologically Anchored Tools for Realistic nanOmateriaL hazard aSsessment) has addressed multiple aspects of the Chemicals Strategy for Sustainability by establishing a battery of new approach methodologies, including physiologically anchored human and environmental hazard assessment tools to evaluate the safety of engineered nanomaterials. PATROLS has delivered and improved innovative tools to support regulatory decision-making processes. These tools also support the need for reducing regulated vertebrate animal testing; when used at an early stage of the innovation pipeline, the PATROLS tools facilitate the safe and sustainable development of new nano-enabled products before they reach the market.

Using in vitro ADME data for lead compound selection: An emphasis on PAMPA pH 5 permeability and oral bioavailability.

Membrane permeability plays an important role in oral drug absorption. Caco-2 and Madin-Darby Canine Kidney (MDCK) cell culture systems have been widely used for assessing intestinal permeability. Since most drugs are absorbed passively, Parallel Artificial Membrane Permeability Assay (PAMPA) has gained popularity as a low-cost and high-throughput method in early drug discovery when compared to high-cost, labor intensive cell-based assays. At the National Center for Advancing Translational Sciences (NCATS), PAMPA pH 5 is employed as one of the Tier I absorption, distribution, metabolism, and elimination (ADME) assays. In this study, we have developed a quantitative structure activity relationship (QSAR) model using our ∼6500 compound PAMPA pH 5 permeability dataset. Along with ensemble decision tree-based methods such as Random Forest and eXtreme Gradient Boosting, we employed deep neural network and a graph convolutional neural network to model PAMPA pH 5 permeability. The classification models trained on a balanced training set provided accuracies ranging from 71% to 78% on the external set. Of the four classifiers, the graph convolutional neural network that directly operates on molecular graphs offered the best classification performance. Additionally, an ∼85% correlation was obtained between PAMPA pH 5 permeability and in vivo oral bioavailability in mice and rats. These results suggest that data from this assay (experimental or predicted) can be used to rank-order compounds for preclinical in vivo testing with a high degree of confidence, reducing cost and attrition as well as accelerating the drug discovery process. Additionally, experimental data for 486 compounds (PubChem AID: 1645871) and the best models have been made publicly available (https://opendata.ncats.nih.gov/adme/).

Using inverse finite element analysis to identify spinal tissue behaviour in situ.

In computational modelling of musculoskeletal applications, one of the critical aspects is ensuring that a model can capture intrinsic population variability and not only representative of a "mean" individual. Developing and calibrating models with this aspect in mind is key for the credibility of a modelling methodology. This often requires calibration of complex models with respect to 3D experiments and measurements on a range of specimens or patients. Most Finite Element (FE) software's do not have such a capacity embedded in their core tools. This paper presents a versatile interface between Finite Element (FE) software and optimisation tools, enabling calibration of a group of FE models on a range of experimental data. It is provided as a Python toolbox which has been fully tested and verified on Windows platforms. The toolbox is tested in three case studies involving in vitro testing of spinal tissues.

Framework for risk assessment of PFAS utilizing experimental studies and in-silico models.

Perfluoroalkyl substances (PFAS), especially PFOS and PFOA, are two widely used synthetic chemicals that can impact human health based on evidence from animal and epidemiologic studies. In this paper, we have reviewed and summarized the influence of PFAS exposure on health, pointing the quality of evidence, and applied translational techniques to integrate evidence for PFAS policy making. This is the first review where highly referred articles on PFAS used for policymaking by several regulatory agencies were collected and evaluated based on the review guidelines developed by the US National Toxicology Program's Office of Health Assessment and Translation (OHAT) review guidelines. Several limitations were observed, including co-exposure to multiple chemicals and limited measurement of primary and secondary outcomes related to specific toxicity. However, data from all the studies provided a moderate to strong level of confidence for link between PFAS exposure and different adverse outcomes. Secondly, for translating the risk to humans, an in-silico model and scaling approach was utilized. Physiologically based pharmacokinetic model (PBPK) was used to calculate the human equivalent dose (HED) from two widely accepted studies and compared with tolerable daily intakes (TDIs) established by various regulatory agencies. Inter-species dose extrapolation was done to compare with human the relevance of dosing scenarios used in animals. Overall, a framework for translation of risk was proposed based on the conclusions of this review with the goal of improving policymaking. The current paper can improve the methodological protocols for PFAS experimental studies and encourage the utilization of in-silico models for translating risk.

Determination of "fitness-for-purpose" of quantitative structure-activity relationship (QSAR) models to predict (eco-)toxicological endpoints for regulatory use.

In silico models are used to predict toxicity and molecular properties in chemical safety assessment, gaining widespread regulatory use under a number of legislations globally. This study has rationalised previously published criteria to evaluate quantitative structure-activity relationships (QSARs) in terms of their uncertainty, variability and potential areas of bias, into ten assessment components, or higher level groupings. The components have been mapped onto specific regulatory uses (i.e. data gap filling for risk assessment, classification and labelling, and screening and prioritisation) identifying different levels of uncertainty that may be acceptable for each. Twelve published QSARs were evaluated using the components, such that their potential use could be identified. High uncertainty was commonly observed with the presentation of data, mechanistic interpretability, incorporation of toxicokinetics and the relevance of the data for regulatory purposes. The assessment components help to guide strategies that can be implemented to improve acceptability of QSARs through the reduction of uncertainties. It is anticipated that model developers could apply the assessment components from the model design phase (e.g. through problem formulation) through to their documentation and use. The application of the components provides the possibility to assess QSARs in a meaningful manner and demonstrate their fitness-for-purpose against pre-defined criteria.

In silico prediction of polyethylene-aqueous and air partition coefficients of organic contaminants using linear and nonlinear approaches.

Low-density polyethylene (LDPE) passive sampling is very attractive for use in determining chemicals concentrations. Crucial to the measurement is the coefficient (KPE) describing partitioning between LDPE and environmental matrices. 255, 117 and 190 compounds were collected for the development of datasets in three different matrices, i.e., water, air and seawater, respectively. Further, 3 pp-LFER models and 9 QSPR models based on classical multiple linear regression (MLR) coupled with prevalent nonlinear algorithms (artificial neural network, ANN and support vector machine, SVM) were performed to predict LDPE-water (KPE-W), LDPE-air (KPE-A) and LDPE-seawater (KPE-SW) partition coefficients. These developed models have satisfying predictability (R2adj: 0.805-0.966, 0.963-0.991 and 0.817-0.941; RMSEtra: 0.233-0.565, 0.200-0.406 and 0.260-0.459) and robustness (Q2ext: 0.840-0.943, 0.968-0.984 and 0.797-0.842; RMSEext: 0.308-0.514, 0.299-0.426 and 0.407-0.462) in three datasets (water, air and seawater), respectively. In particular, the reasonable mechanism interpretations revealed that the molecular size, hydrophobicity, polarizability, ionization potential, and molecular stability were the most relevant properties, for governing chemicals partitioning between LDPE and environmental matrices. The application domains (ADs) assessed here exhibited the satisfactory applicability. As such, the derived models can act as intelligent tools to predict unknown KPE values and fill the experimental gaps, which was further beneficial for the construction of enormous and reliable database to facilitate a distinct understanding of the distribution for organic contaminants in total environment.

Using mathematics in MRI data management for glioma assesment.

Our aim is to review the mathematical tools usefulness in MR data management for glioma diagnosis and treatment optimization. MRI does not give access to organs variations in hours or days. However a lot of multiparametric data are generated. Mathematics could help to override this paradox, the aim of this article is to show how. We first make a review on mathematical modelling using equations. Afterwards we present statistical analysis. We provide detailed examples in both sections. We finally conclude, giving some clues on in silico models.

Structure-Property Relationships and Machine Learning Models for Addressing CYP3A4-Mediated Victim Drug-Drug Interaction Risk in Drug Discovery.

Among the FDA-approved small molecule drugs (2005-2016) that are primarily metabolized by cytochrome P450 (CYP), 64% are primarily metabolized by CYP3A4. As the proportion of an individual drug's fraction metabolized through CYP3A4 increases, the risk for the drug to be a victim of an interaction with CYP3A4 inhibitors or inducers increases. Therefore, it is important to assess the extent of involvement of individual CYP enzymes in the overall clearance for a scaffold early in discovery and mitigate the CYP3A4-mediated victim-drug-drug interaction (DDI) risk, if warranted by the desired clinical profile of the drug. To mitigate the CYP3A4-mediated victim DDI risk in discovery, we analyzed the physicochemical properties of the CYP3A4 substrates and found that molecular weight was the property that provided the best separation of the CYP3A4 substrates from other CYP substrates. In addition, neutral and basic compounds with MW ≥ 360 g/mol tend to be primarily metabolized by CYP3A4, whereas acidic compounds with MW < 360 g/mol are most likely to be primarily metabolized by other CYP enzymes. We then developed Support Vector Machine based on fingerprints (SVM-FP) and Deep-Learning (DL) models to predict if a molecule will be primarily metabolized by CYP3A4. Our models were trained on 2306 compounds, which is the largest training set among published models for this endpoint. Both models showed positive predictive values (PPV) > 80% in predicting a CYP3A4 substrate on a prospective testing set. Given the high PPV of the models, project teams can confidently deprioritize compounds predicted to be CYP3A4 substrates to avoid the potential liability of CYP3A4 victim DDI. Teams can then focus time and resources on synthesizing compounds that are predicted to have a lower dependency on CYP3A4 metabolism and confirm that experimentally. Through such iterative in silico-in vitro learning circles, drug discovery teams can decide if metabolism through non-CYP3A4 pathways could be achieved in the SAR of a chemical series to mitigate the CYP3A4 victim DDI risk.

ANTISOMA: A Computational Pipeline for the Reduction of the Aggregation Propensity of Monoclonal Antibodies.

Monoclonal antibodies (mAbs) constitute a promising class of therapeutics, since ca. 25% of all biotech drugs in development are mAbs. Even though their therapeutic value is now well established, human- and murine-derived mAbs do have deficiencies, such as short in vivo lifespan and low stability. However, the most difficult obstacle to overcome, toward the exploitation of mAbs for disease treatment, is the prevention of the formation of protein aggregates. ANTISOMA is a pipeline for the reduction of the aggregation tendency of mAbs through the decrease in their intrinsic aggregation propensity, based on an automated amino acid substitution approach. The method takes into consideration the special features of mAbs and aims at proposing specific point mutations that could lead to the redesign of those promising therapeutics, without affecting their epitope-binding ability. The method is available online at http://bioinformatics.biol.uoa.gr/ANTISOMA .

Skin Doctor: Machine Learning Models for Skin Sensitization Prediction that Provide Estimates and Indicators of Prediction Reliability.

The ability to predict the skin sensitization potential of small organic molecules is of high importance to the development and safe application of cosmetics, drugs and pesticides. One of the most widely accepted methods for predicting this hazard is the local lymph node assay (LLNA). The goal of this work was to develop in silico models for the prediction of the skin sensitization potential of small molecules that go beyond the state of the art, with larger LLNA data sets and, most importantly, a robust and intuitive definition of the applicability domain, paired with additional indicators of the reliability of predictions. We explored a large variety of molecular descriptors and fingerprints in combination with random forest and support vector machine classifiers. The most suitable models were tested on holdout data, on which they yielded competitive performance (Matthews correlation coefficients up to 0.52; accuracies up to 0.76; areas under the receiver operating characteristic curves up to 0.83). The most favorable models are available via a public web service that, in addition to predictions, provides assessments of the applicability domain and indicators of the reliability of the individual predictions.

An In Silico Approach for Assessment of the Membrane Transporter Activities of Phenols: A Case Study Based on Computational Models of Transport Activity for the Transporter Bilitranslocase.

Phenols are the most abundant naturally accessible antioxidants present in a human normal diet. Since numerous beneficial applications of phenols as preventive agents in various diseases were revealed, the evaluation of phenols bioavailability is of high interest of researchers, consumers and drug manufacturers. The hydrophilic nature of phenols makes a cell membrane penetration difficult, which imply an alternative way of uptake via membrane transporters. However, the structural and functional data of membrane transporters are limited, thus the in silico modelling is really challenging and urgent tool in elucidation of transporter ligands. Focus of this research was a particular transporter bilitranslocase (BTL). BTL has a broad tissue expression (vascular endothelium, absorptive and excretory epithelia) and can transport wide variety of poly-aromatic compounds. With available BTL data (pKi [mmol/L] for 120 organic compounds) a robust and reliable QSAR models for BTL transport activity were developed and extrapolated on 300 phenolic compounds. For all compounds the transporter profiles were assessed and results show that dietary phenols and some drug candidates are likely to interact with BTL. Moreover, synopsis of predictions from BTL models and hits/predictions of 20 transporters from Metrabase and Chembench platforms were revealed. With such joint transporter analyses a new insights for elucidation of BTL functional role were acquired. Regarding limitation of models for virtual profiling of transporter interactions the computational approach reported in this study could be applied for further development of reliable in silico models for any transporter, if in vitro experimental data are available.

Convergence of models of human ventricular myocyte electrophysiology after global optimization to recapitulate clinical long QT phenotypes.

In-silico models of human cardiac electrophysiology are now being considered for prediction of cardiotoxicity as part of the preclinical assessment phase of all new drugs. We ask the question whether any of the available models are actually fit for this purpose. We tested three models of the human ventricular action potential, the O'hara-Rudy (ORD11), the Grandi-Bers (GB10) and the Ten Tusscher (TT06) models. We extracted clinical QT data for LQTS1 and LQTS2 patients with nonsense mutations that would be predicted to cause 50% loss of function in IKs and IKr respectively. We also obtained clinical QT data for LQTS3 patients. We then used a global optimization approach to improve the existing in silico models so that they reproduced all three clinical data sets more closely. We also examined the effects of adrenergic stimulation in the different LQTS subsets. All models, in their original form, produce markedly different and unrealistic predictions of QT prolongation for LQTS1, 2 and 3. After global optimization of the maximum conductances for membrane channels, all models have similar current densities during the action potential, despite differences in kinetic properties of the channels in the different models, and more closely reproduce the prolongation of repolarization seen in all LQTS subtypes. In-silico models of cardiac electrophysiology have the potential to be tremendously useful in complementing traditional preclinical drug testing studies. However, our results demonstrate they should be carefully validated and optimized to clinical data before they can be used for this purpose.

In silico pharmacology: Drug membrane partitioning and crossing.

Over the past decade, molecular dynamics (MD) simulations have become particularly powerful to rationalize drug insertion and partitioning in lipid bilayers. MD simulations efficiently support experimental evidences, with a comprehensive understanding of molecular interactions driving insertion and crossing. Prediction of drug partitioning is discussed with respect to drug families (anesthetics; ß-blockers; non-steroidal anti-inflammatory drugs; antioxidants; antiviral drugs; antimicrobial peptides). To accurately evaluate passive permeation coefficients turned out to be a complex theoretical challenge; however the recent methodological developments based on biased MD simulations are particularly promising. Particular attention is paid to membrane composition (e.g., presence of cholesterol), which influences drug partitioning and permeation. Recent studies concerning in silico models of membrane proteins involved in drug transport (influx and efflux) are also reported here. These studies have allowed gaining insight in drug efflux by, e.g., ABC transporters at an atomic resolution, explicitly accounting for the mandatory forces induced by the surrounded lipid bilayer. Large-scale conformational changes were thoroughly analyzed.