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.

O papel terapêutico do Programa Farmácia Viva e das plantas medicinais / The therapeutic role of the Program Farmacia Viva and the medicinal plants in the center-south of Piauí

RESUMOEste trabalho realizou um levantamento sobre o uso de plantas medicinais na cidade de Picos-PI, identificou as plantas cultivadas no horto pertencente ao Laboratório Fitoterápico de Picos (LAFIPI), e analisou o uso de fitoterápicos dispensados pelo Programa Farmácia Viva no triênio 2008-2010. Do total dos 750 entrevistados, 37,6% foram homens e 62,4 % mulheres, dentre os quais a maioria não concluiu o segundo grau (69,2%) e 77,2% possuíam renda mensal de até dois salários mínimos. Com relação ao consumo de plantas medicinais, 76,3% afirmaram utilizá-las para tratar doenças, principalmente por considerá-las mais saudáveis (84,8%). A indicação do uso foi orientada, sobretudo, por familiares (82,2%), embora a maioria adquira as plantas em feiras livres (32,8%). Das 127 plantas relatadas, as mais citadas foram erva-cidreira, boldo e hortelã, sendo as folhas a parte mais utilizada (42,3%), predominantemente por infusão (39,4%). As aplicações mais lembradas foram para tratar dores em geral (17%), distúrbios respiratórios (16,5%) e digestivos (16%). As espécies mais cultivadas no horto são chambá (Justicia pectoralis), alecrim pimenta (Lippia sidoides), malva santa (Plectranthus barbatus) e erva cidreira (Lippia alba). O lambedor de chambá foi o fitoterápico mais procurado pela população entre 2008 e 2010. Esse estudo descreveu, pela primeira vez, o uso tradicional de plantas medicinais no município de Picos e demonstrou, também de forma inédita, a relevância de investimentos do Programa Farmácia Viva no município de Picos e sua inclusão no Programa Saúde da Família como forma de disponibilizar à população de baixa renda fitoterápicos produzidos localmente a custos reduzidos.

ABSTRACTThis study performed a research about the use of medicinal plants in Picos city, identifying the plants grown in the garden belonging to the Laboratory of Phytotherapics in Picos (LAFIPI) and analying the use of phytotherapics distributed by the Farmácia Viva Project between 2008-2010. From the total of 750 interviewed participants, 37.6% were men and 62.4 % women. Most of them do not have secondary education (69.2%) and 77.2% had an income of up until two minimum wages. Regarding consumption of medicinal plants, 76.3 % used them to treat diseases, mainly because they considered them to be healthier (84.8%). The indication of use of the plants was mainly suggested by relatives (82.2%), even though the majority of the participants acquires plants in open markets (32.8%). From the 127 plants mentioned, the most cited ones were balm, boldo and mint, and leaves were the most utilized parts (42.3%), predominantly by infusion (39.4%). The most common reasons for the usewere to treat pain in general (17%), and respiratory (16.5%) and digestive disorders (16%). The most cultivated species in the garden were chambá (Justicia pectoralis), alecrim pimenta (Lippia sidoides), malva santa (Plectranthus barbatus) and erva cidreira (Lippia alba). The "chambá licker" was the most herbal medicine searched by the population between 2008 and 2010. This investigation described, for the first time, the traditional use of medicinal plants in Picos and demonstrated,alsounprecedentedly, the relevance of investments in the Farmácia Viva Project in Picos city and its inclusion in the Family Health Program as a strategyin order to provide locally producedphytotherapics for low-income population at low costs.

From Tonic-cups to Bitter-cups: Kwasi bita beker from Suriname Determination, past and present use of an ancient galenic artefact.

In the main markets of Paramaribo (Suriname), many stands offer what is locally called "Bitter-cups", or "Kwasi bita beker", small footed-cups, roughly carved from a whitish wood. The use of these cups is strictly medicinal and it seems to be restricted to Suriname, as they are not found in neighbouring countries (Guyana, French Guiana). The aim of this study was to identify the botanical origin of Bitter-cups still in use in the Saramaka traditional medicine (as information from field people was controversial), and document the ethnopharmacology of this original galenical artefact. Microscopic and high performance liquid chromatography (HPLC) analyses were carried out on Bitter-cup, and anatomical criteria (marginal parenchyma band, size of intervessel and vessel-ray pits, rays width and rays composition, vessels clustering, frequency and size of parenchyma pits) together with HPLC profiles of the macerates showed that the wood cup was similar to Quassia amara L. (Simaroubaceae) wood. Ethnopharmacological investigation indicates that the use of these cups is simply due to the pharmacological properties attributed to "bitters", and is strongly linked to tradition and cultural attitudes. This study also emphasizes the long lasting use of these cups, now restricted to Suriname only, with almost no variation over one century.