Melisa E. Gantner

Development of conformation independent computational models for the early recognition of breast cancer resistance protein substrates.

ABC efflux transporters are polyspecific members of the ABC superfamily that, acting as drug and metabolite carriers, provide a biochemical barrier against drug penetration and contribute to detoxification. Their overexpression is linked to multidrug resistance issues in a diversity of diseases. Breast cancer resistance protein (BCRP) is the most expressed ABC efflux transporter throughout the intestine and the blood-brain barrier, limiting oral absorption and brain bioavailability of its substrates. Early recognition of BCRP substrates is thus essential to optimize oral drug absorption, design of novel therapeutics for central nervous system conditions, and overcome BCRP-mediated cross-resistance issues. We present the development of an ensemble of ligand-based machine learning algorithms for the early recognition of BCRP substrates, from a database of 262 substrates and nonsubstrates compiled from the literature. Such dataset was rationally partitioned into training and test sets by application of a 2-step clustering procedure. The models were developed through application of linear discriminant analysis to random subsamples of Dragon molecular descriptors. Simple data fusion and statistical comparison of partial areas under the curve of ROC curves were applied to obtain the best 2-model combination, which presented 82% and 74.5% of overall accuracy in the training and test set, respectively.

Computer-Aided Recognition of ABC Transporters Substrates and Its Application to the Development of New Drugs for Refractory Epilepsy

Despite the introduction of more than 15 third generation antiepileptic drugs to the market from 1990 to the moment, about one third of the epileptic patients still suffer from refractory to intractable epilepsy. Several hypotheses seek to explain the failure of drug treatments to control epilepsy symptoms in such patients. The most studied one proposes that drug resistance might be related with regional overactivity of efflux transporters from the ATP-Binding Cassette (ABC) superfamily at the blood-brain barrier and/or the epileptic foci in the brain. Different strategies have been conceived to address the transporter hypothesis, among them inhibiting or down-regulating the efflux transporters or bypassing them through a diversity of artifices. Here, we review scientific evidence supporting the transporter hypothesis along with its limitations, as well as computer-assisted early recognition of ABC transporter substrates as an interesting strategy to develop novel antiepileptic drugs capable of treating refractory epilepsy linked to ABC transporters overactivity.

Development and Validation of a Computational Model Ensemble for the Early Detection of BCRP/ABCG2 Substrates during the Drug Design Stage

Breast Cancer Resistance Protein (BCRP) is an ATP-dependent efflux transporter linked to the multidrug resistance phenomenon in many diseases such as epilepsy and cancer and a potential source of drug interactions. For these reasons, the early identification of substrates and nonsubstrates of this transporter during the drug discovery stage is of great interest. We have developed a computational nonlinear model ensemble based on conformational independent molecular descriptors using a combined strategy of genetic algorithms, J48 decision tree classifiers, and data fusion. The best model ensemble consists in averaging the ranking of the 12 decision trees that showed the best performance on the training set, which also demonstrated a good performance for the test set. It was experimentally validated using the ex vivo everted rat intestinal sac model. Five anticonvulsant drugs classified as nonsubstrates for BRCP by the model ensemble were experimentally evaluated, and none of them proved to be a BCRP substrate under the experimental conditions used, thus confirming the predictive ability of the model ensemble. The model ensemble reported here is a potentially valuable tool to be used as an in silico ADME filter in computer-aided drug discovery campaigns intended to overcome BCRP-mediated multidrug resistance issues and to prevent drug-drug interactions.

Recent Advances on Nanotechnology Applications to Cancer Drug Therapy

One of the greatest challenges in cancer drug therapy is to maximize the effectiveness of the active ingredient while reducing its systemic adverse effects. Conventional (non-targeted) systemic drug therapy is characterized by unspecific distribution of the anticancer drugs: both healthy and affected tissues are thus exposed to the chemotherapeutic agent, giving raise to off-target side-effects. Besides, a number of widely-used chemoterapeutic agents present unfavorable physicochemical properties, such as low solubility or low stability issues, limiting their available routes of administration and therapeutic applications. Nano-delivery systems seem as promising solutions to these issues. They can be used for targeted-drug release, diagnostic imaging and therapy monitoring. Nanosystems allow the formulation of drug delivery systems with tailored properties ( e.g. solubility, biodegradability, release kinetics and distribution) that provide means to improve cancer patients’ quality of life by lowering the administered dose and, incidentally, the cost of clinical treatments. This article overviews the main features of different nanovehicles (linear and non-linear polymeric nanosystems, lipid-based systems, inorganic nanoparticles) and presents a selection of reports on applications of such systems to cancer therapy published between 2010 and 2013.

Systematic Comparison of the Performance of Different 2D and 3D Ligand-Based Virtual Screening Methodologies to Discover Anticonvulsant Drugs

Virtual screening encompasses a wide range of computational approaches aimed at the high-throughput, cost-efficient exploration of chemical libraries or databases to discover new bioactive compounds or novel medical indications of known drugs. Here, we have performed a systematic comparison of the performance of a large number of 2D and 3D ligand-based approaches (2D and 3D similarity, QSAR models, pharmacophoric hypothesis) in a simulated virtual campaign on a chemical library containing 50 known anticonvulsant drugs and 950 decoys with no previous reports of anticonvulsant effect. To perform such comparison, we resorted to Receiver Operating Characteristic curves. We also tested the relative performance of consensus methodologies. Our results indicate that the selective combination of the individual approaches (through voting and ranking combination schemes) significantly outperforms the individual algorithms and/or models. Among the best-performing individual approaches, 2D similarity search based on circular fingerprints and 3D similarity approaches should be highlighted. Combining the results from different query molecules also led to enhanced enrichment.