Cladribine Tablets (MAVENCLAD ® ) are used to treat relapsing multiple sclerosis (MS). The recommended dose is 3.5 mg/kg, consisting of 2 annual courses, each comprising 2 treatment weeks 1 month apart. We reviewed the clinical pharmacology of Cladribine Tablets in patients with MS, including pharmacokinetic and pharmacometric data. Cladribine Tablets are rapidly absorbed, with a median time to reach maximum concentration (T max ) of 0.5 h (range 0.5-1.5 h) in fasted patients. When administered with food, absorption is delayed (median T max 1.5 h, range 1-3 h), and maximum concentration (C max ) is reduced by 29% (based on geometric mean). Area under the concentration-time curve (AUC) is essentially unchanged. Oral bioavailability of cladribine is approximately 40%, pharmacokinetics are linear and time-independent, and volume of distribution is 480-490 L. Plasma protein binding is 20%, independent of cladribine plasma concentration. Cladribine is rapidly distributed to lymphocytes and retained (either as parent drug or its phosphorylated metabolites), resulting in approximately 30-to 40-fold intracellular accumulation versus extracellular concentrations as early as 1 h after cladribine exposure. Cytochrome P450-mediated biotransformation of cladribine is of minor importance. Cladribine elimination is equally dependent on renal and non-renal routes. In vitro studies indicate that cladribine efflux is minimally P-glycoprotein (P-gp)-related, and clinically relevant interactions with P-gp inhibitors are not expected. Cladribine distribution across membranes is primarily facilitated by equilibrative nucleoside transporter (ENT) 1, concentrative nucleoside transporter (CNT) 3 and breast cancer resistance protein (BCRP), and there is no evidence of any cladribine-related effect on heart rate, atrioventricular conduction or cardiac repolarisation (QTc interval prolongation). Cladribine Tablets are associated with targeted lymphocyte reduction and durable efficacy, with the exposure-effect relationship showing the recommended dose is appropriate in reducing relapse risk. Key PointsThis review discusses the clinical pharmacology of Cladribine Tablets in patients with relapsing multiple sclerosis, presenting pharmacokinetic, pharmacodynamic and pharmacometric data.Cladribine Tablets are associated with a selective reduction in lymphocyte counts and durable efficacy relative to the fast disposition in plasma, and short-term treatment posology in each of the 2 treatment years.The recommended cumulative dose of Cladribine Tablets 3.5 mg/kg over 2 years is shown to be appropriate in reducing relapse risk.

The exponential increase in our ability to harness multi-dimensional biological and clinical data from experimental to real-world settings has transformed pharmaceutical research and development in recent years, with increasing applications of artificial intelligence (AI) and machine learning (ML). Patient-centered iterative forward and reverse translation is at the heart of precision medicine discovery and development across the continuum from target validation to optimization of pharmacotherapy. Integration of advanced analytics into the practice of Translational Medicine is now a fundamental enabler to fully exploit information contained in diverse sources of big data sets such as “omics” data, as illustrated by deep characterizations of the genome, transcriptome, proteome, metabolome, microbiome, and exposome. In this commentary, we provide an overview of ML applications in drug discovery and development, aligned with the three strategic pillars of Translational Medicine (target, patient, dose) and offer perspectives on their potential to transform the science and practice of the discipline. Opportunities for integrating ML approaches into the discipline of Pharmacometrics are discussed and will revolutionize the practice of model-informed drug discovery and development. Finally, we posit that joint efforts of Clinical Pharmacology, Bioinformatics, and Biomarker Technology experts are vital in cross-functional team settings to realize the promise of AI/ML-enabled Translational and Precision Medicine.

One of the objectives of Pharmacometry (PMX) population modeling is the identification of significant and clinically relevant relationships between parameters and covariates. Here, we demonstrate how this complex selection task could benefit from supervised learning algorithms using importance scores. We compare various classical methods with three machine learning (ML) methods applied to NONMEM empirical Bayes estimates: random forest, neural networks (NNs), and support vector regression (SVR). The performance of the ML models is assessed using receiver operating characteristic (ROC) curves. The F1 score, which measures test accuracy, is used to compare ML and PMX approaches. Methods are applied to different scenarios of covariate influence based on simulated pharmacokinetics data. ML achieved similar or better F1 scores than stepwise covariate modeling (SCM) and conditional sampling for stepwise approach based on correlation tests (COSSAC). Correlations between covariates and the number of false covariates does not affect the performance of any method, but effect size has an impact. Methods are not equivalent with respect to computational speed; SCM is 30 and 100-times slower than NN and SVR, respectively. The results are validated in an additional scenario involving 100 covariates. Taken together, the results indicate that ML methods can greatly increase the efficiency of population covariate model building in the case of large datasets or complex models that require long run-times. This can provide fast initial covariate screening, which can be followed by more conventional PMX approaches to assess the clinical relevance of selected covariates and build the final model.

The lack of a common exchange format for mathematical models in pharmacometrics has been a long-standing problem. Such a format has the potential to increase productivity and analysis quality, simplify the handling of complex workflows, ensure reproducibility of research, and facilitate the reuse of existing model resources. Pharmacometrics Markup Language (PharmML), currently under development by the Drug Disease Model Resources (DDMoRe) consortium, is intended to become an exchange standard in pharmacometrics by providing means to encode models, trial designs, and modeling steps.

PurposeIn clinical oncology, combination treatments are widely used and increasingly preferred over single drug administrations. A better characterization of the interaction between drug effects and the selection of synergistic combinations represent an open challenge in drug development process. To this aim, preclinical studies are routinely performed, even if they are only qualitatively analyzed due to the lack of generally applicable mathematical models.MethodsThis paper presents a new pharmacokinetic–pharmacodynamic model that, starting from the well-known single agent Simeoni TGI model, is able to describe tumor growth in xenograft mice after the co-administration of two anticancer agents. Due to the drug action, tumor cells are divided in two groups: damaged and not damaged ones. The damaging rate has two terms proportional to drug concentrations (as in the single drug administration model) and one interaction term proportional to their product. Six of the eight pharmacodynamic parameters assume the same value as in the corresponding single drug models. Only one parameter summarizes the interaction, and it can be used to compute two important indexes that are a clear way to score the synergistic/antagonistic interaction among drug effects.ResultsThe model was successfully applied to four new compounds co-administered with four drugs already available on the market for the treatment of three different tumor cell lines. It also provided reliable predictions of different combination regimens in which the same drugs were administered at different doses/schedules.ConclusionsA good and quantitative measurement of the intensity and nature of interaction between drug effects, as well as the capability to correctly predict new combination arms, suggest the use of this generally applicable model for supporting the experiment optimal design and the prioritization of different therapies.Electronic supplementary materialThe online version of this article (doi:10.1007/s00280-013-2208-8) contains supplementary material, which is available to authorized users.