Predicting the cytotoxicity of chemicals using ensemble learning methods and molecular fingerprints.

The prediction of compound cytotoxicity is an important part of the drug discovery process. However, it usually appears as poor predictive performance because the datasets are high-throughput and have a class-imbalance problem. In this study, several strategies of performing a structure-activity relationship study for a cytotoxic endpoint in the AID364 dataset were explored to solve the class-imbalance problem. Random forest adaboost was used as the base learners for 10 types of molecular fingerprints and an ensemble method and six data-balancing methods were applied to balance the classes. As a result, the ensemble model using MACCS fingerprint was found to be the best, giving area under the curve of 85.2% ± 0.35%, sensitivity of 81.8% ± 0.65%, and specificity of 76.0% ± 0.12% in fivefold cross-validation and area under the curve of 78.8%, sensitivity of 55.5% and specificity of 78.5% in external validation. Good performance also appeared on other datasets with different sizes/degrees of imbalance. To explore the structural commonality of cytotoxic compounds, several substructures were identified as an important reference for substructure alerts. The convincing results indicate that the proposed models are helpful in predicting the cytotoxicity of chemicals.

New Horizons in Mycoplasma genitalium Treatment.

Mycoplasmagenitalium is an important sexually transmitted pathogen responsible for both male and female genital tract disease. Appreciation of its significance in human disease has been hampered by its slow growth in culture, difficulty in isolating it, and lack of commercial molecular-based tests for rapid detection. Comparatively few in vitro data on antimicrobial susceptibility are available due to the scarcity of clinical isolates and difficulty in performing susceptibility tests to determine minimum inhibitory concentrations for M. genitalium. Antimicrobial agents that inhibit protein synthesis such as macrolides, along with fluoroquinolones that inhibit DNA replication, have been the treatments of choice for M. genitalium infections. Even though international guidelines recommend azithromycin as first-line treatment, rapid spread of macrolide resistance as well as emergence of quinolone resistance has occurred. Increasing rates of treatment failure have resulted in an urgent need for new therapies and renewed interest in other classes such as aminocyclitols, phenicols, and streptogramins as treatment alternatives. Limited data for new investigational antimicrobials such as the ketolide solithromycin suggest that this drug may eventually prove useful in management of some resistant M. genitalium infections, although it is not likely to achieve cure rates >80% in macrolide-resistant strains, in a similar range as recently reported for pristinamycin. However, agents with completely new targets and/or mechanisms that would be less likely to show cross-resistance with currently available drugs may hold the greatest promise. Lefamulin, a pleuromutilin, and new nonquinolone topoisomerase inhibitors are attractive possibilities that require further investigation.

The role of BCS (biopharmaceutics classification system) and BDDCS (biopharmaceutics drug disposition classification system) in drug development.

Biopharmaceutics Classification System and Biopharmaceutics Drug Distribution Classification System are complimentary, not competing, classification systems that aim to improve, simplify, and speed drug development. Although both systems are based on classifying drugs and new molecular entities into four categories using the same solubility criteria, they differ in the criterion for permeability and have different purposes. Here, the details and applications of both systems are reviewed with particular emphasis of their role in drug development.

Ligand-target prediction using Winnow and naive Bayesian algorithms and the implications of overall performance statistics.

We compared two algorithms for ligand-target prediction, namely, the Laplacian-modified Bayesian classifier and the Winnow algorithm. A dataset derived from the WOMBAT database, spanning 20 pharmaceutically relevant activity classes with 13 000 compounds, was used for performance assessment in 24 different experiments, each of which was assessed using a 15-fold Monte Carlo cross-validation. Compounds were described by different circular fingerprints, ECFP_4 and MOLPRINT 2D. A detailed analysis of the resulting approximately 2.4 million predictions led to very similar measures for overall accuracy for both classifiers, whereas we observed significant differences for individual activity classes. Moreover, we analyzed our data with respect to the numbers of compounds which are exclusively retrieved by either of the algorithmsbut never by the otheror by neither of them. This provided detailed information that can never be obtained by considering the overall performance statistics alone.