Identifying Substructures That Facilitate Compounds to Penetrate the Blood-Brain Barrier via Passive Transport Using Machine Learning Explainer Models.

The local interpretable model-agnostic explanation (LIME) method was used to interpret two machine learning models of compounds penetrating the blood-brain barrier. The classification models, Random Forest, ExtraTrees, and Deep Residual Network, were trained and validated using the blood-brain barrier penetration dataset, which shows the penetrability of compounds in the blood-brain barrier. LIME was able to create explanations for such penetrability, highlighting the most important substructures of molecules that affect drug penetration in the barrier. The simple and intuitive outputs prove the applicability of this explainable model to interpreting the permeability of compounds across the blood-brain barrier in terms of molecular features. LIME explanations were filtered with a weight equal to or greater than 0.1 to obtain only the most relevant explanations. The results showed several structures that are important for blood-brain barrier penetration. In general, it was found that some compounds with nitrogenous substructures are more likely to permeate the blood-brain barrier. The application of these structural explanations may help the pharmaceutical industry and potential drug synthesis research groups to synthesize active molecules more rationally.

Improvement of appropriate pharmacological prophylaxis in hospitalised cancer patients with a multiscreen e-alert system: a single-centre experience.

PURPOSE: Thromboprophylaxis use among medical inpatients, including cancer patients, is suboptimal. We aimed to evaluate the impact of a novel multiscreen version (v2.0) of an e-alert system for VTE prevention in hospitalised cancer medical patients compared to the original software. METHODS: Prospective study including 989 consecutive adult cancer patients with high-risk of VTE. Patients were followed-up 30 days post-discharge. Two periods were defined, according to the operative software. RESULTS: E-alert v2.0 was associated with an increase in the use of LMWH prophylaxis (65.5% vs. 72.0%); risk difference (95% CI) 0.064 (0.0043-0.12). Only 16% of patients in whom LMWH prophylaxis was not prescribed lacked a contraindication. No significant differences in the rates of VTE (2.9% vs. 3.2%) and major bleeding (2.7% vs. 4.0%) were observed. CONCLUSIONS: E-alert v2.0 further increased the use of appropriate thromboprophylaxis in hospitalised cancer patients, although was not associated with a reduction in VTE incidence.

Counterfeit medicines in Peru: a retrospective review (1997-2014).

OBJECTIVE: To consolidate and assess information on counterfeit medicines subject to pharmaceutical alerts issued by the Peruvian Medicines Regulatory Authority over 18 years (1997-2014) of health monitoring and enforcement. DESIGN: A retrospective review of drug alerts. SETTING: A search of the website of the General Directorate of Medicines, Supplies and Drugs (DIGEMID) of the Ministry of Health of Peru for drug alerts issued between 1997 and 2014. ELIGIBILITY CRITERIA: Drug alerts related to counterfeit medicines. RESULTS: A total of 669 DIGEMID alerts were issued during the study period, 354 (52.91%) of which cover 1738 cases of counterfeit medicines (many alerts deal with several cases at a time). 1010 cases (58.11%) involved pharmaceutical establishments and 349 (20.08%) involved non-pharmaceutical commercial outlets. In 126 cases (7.25%), counterfeit medicines were seized in an unauthorised trade (without any marketing authorisation); in 253 cases (14.56%) the type of establishment or business associated with the seized product was not identified. CONCLUSIONS: Counterfeit medicines are a serious public health problem in Peru. A review of the data cannot determine whether counterfeit medicines in Peru increased during the study period, or if monitoring by different government health agencies highlighted the magnitude of the problem by providing more evidence. The problem is clearly structural, since the majority of cases (58.11% of the total) were detected in legitimate supply chains. Most counterfeit medicines involve staple pharmaceutical products and common dosage forms. Considerable work remains to be done to control the serious problem of counterfeit medicines in Peru.