Predicting combinative drug pairs via multiple classifier system with positive samples only.

BACKGROUND AND OBJECTIVE: Due to the synergistic effects of drugs, drug combination is one of the effective approaches for treating complex diseases. However, the identification of drug combinations by dose-response methods is still costly. It is promising to develop supervised learning-based approaches to predict potential drug combinations on a large scale. Nevertheless, these approaches have the inadequate utilization of heterogeneous features, which causes the loss of information useful to classification. Moreover, they have an intrinsic bias, because they assume unknown drug pairs as non-combinations, of which some could be real drug combinations in practice. METHODS: To address above issues, this work first designs a two-layer multiple classifier system (TLMCS) to effectively integrate heterogeneous features involving anatomical therapeutic chemical codes of drugs, drug-drug interactions, drug-target interactions, gene ontology of drug targets, and side effects. To avoid the bias caused by labelling unknown samples as negative, it then utilizes the one-class support vector machines, (which requires no negative instance and only labels approved drug combinations as positive instances), as the member classifiers in TLMCS. Last, both a 10-fold cross validation (10-CV) and a novel prediction are performed to validate the performance of TLMCS. RESULTS: The comparison with three state-of-the-art approaches under 10-CV exhibits the superiority of TLMCS, which achieves the area under the receiver operating characteristic curve = 0.824 and the area under the precision-recall curve = 0.372. Moreover, the experiment under the novel prediction demonstrates its ability, where 9 out of the top-20 predicted combinative drug pairs are validated by checking the published literature. Furthermore, for each of the newly-validated drug combinations, this work analyses the combining mode of the member drugs and investigates their relationship in terms of drug targeting pathways. CONCLUSIONS: The proposed TLMCS provides an effective framework to integrate those heterogeneous features and is trained by only positive samples such that the bias of taking unknown drug pairs as negative samples can be avoided. Furthermore, its results in the novel prediction reveal five types of drug combinations and three types of drug relationships in terms of pathways.

Effects of large gradient high magnetic field (LG-HMF) on the long-term culture of aquatic organisms: Planarians example.

Large gradient high magnetic field (LG-HMF) is a powerful tool to study the effects of altered gravity on organisms. In our study, a platform for the long-term culture of aquatic organisms was designed based on a special superconducting magnet with an LG-HMF, which can provide three apparent gravity levels (µ g, 1 g, and 2 g), along with a control condition on the ground. Planarians, Dugesia japonica, were head-amputated and cultured for 5 days in a platform for head reconstruction. After planarian head regeneration, all samples were taken out from the superconducting magnet for a behavioral test under geomagnetic field and normal gravity conditions. To analyze differences among the four groups, four aspects of the planarians were considered, including head regeneration rate, phototaxis response, locomotor velocity, and righting behavior. Data showed that there was no significant difference in the planarian head regeneration rate under simulated altered gravity. According to statistical analysis of the behavioral test, all of the groups had normal functioning of the phototaxis response, while the planarians that underwent head reconstruction under the microgravity environment had significantly slower locomotor velocity and spent more time in righting behavior. Furthermore, histological staining and immunohistochemistry results helped us reveal that the locomotor system of planarians was affected by the simulated microgravity environment. We further demonstrated that the circular muscle of the planarians was weakened (hematoxylin and eosin staining), and the epithelial cilia of the planarians were reduced (anti-acetylated tubulin staining) under the simulated microgravity environment. Bioelectromagnetics. 2018;39:428-440. © 2018 Wiley Periodicals, Inc.