Machine Learning approach to identify Adverse Events in Scientific Biomedical Literature

Monitoring the occurrence of adverse events in the scientific literature is a mandatory process in drug marketing surveillance. This is a very time‐consuming and complex task to fulfill the compliance and, most importantly, to ensure patient safety. Therefore, a machine learning (ML) algorithm has been trained to support this manual intellectual review process, by automatically providing a classification of the literature articles into two types. An algorithm has been designed to automatically classify “relevant articles” which are reporting any kind of drug safety relevant information, and those which are not reporting an adverse drug reaction as “not relevant.” The review process is consisted of many rules and aspects which needed to be taken into consideration. Therefore, for the training of the algorithm, thousands of documents from previous screenings have been used. After several iterations of adjustments and fine tuning, the ML approach is definitively a great achievement in pre‐sorting the articles into “relevant” and “non‐relevant” and supporting the intellectual review process.

Distribution and absence of generalized lesions in mice following single dose intramuscular inoculation of the vaccine candidate MVA-MERS-S

Modified Vaccinia Virus Ankara (MVA) is a highly attenuated and replication-deficient virus serving as vaccine against infectious diseases. Here, we assessed the in vivo distribution of a recombinant MVA candidate vaccine against the Middle Eastern Respiratory Syndrome (MVA-MERS-S) in mice. Intramuscularly inoculated mice were necropsied at different time points and examined by histology, immunohistochemistry and real-time PCR. We detected inflammation and myonecrosis at the parenteral site and hyperplasia of the draining lymph nodes. MVA-MERS-S did not result in detectable lesions in tissues peripheral to the parenteral site and draining lymph nodes. Real-time PCR analysis of >240 tissue samples detected MVA-DNA predominantly at the injection site and in the draining lymph nodes, and suggested continuous clearance of the candidate vaccine during the observation period. Levels of parenteral site inflammation and hyperplasia of draining lymph nodes were considered in line with immunological responses to vaccine inoculation.

Tracking Modified Vaccinia Virus Ankara in the Chicken Embryo: In Vivo Tropism and Pathogenesis of Egg Infections

The Modified Vaccinia virus Ankara (MVA) is a highly attenuated vaccinia virus serving as a promising vector vaccine platform to develop vaccines against infectious diseases. In contrast to the well-established replication deficiency and safety of MVA in mammals, much less is known about MVA infection in avian hosts. Here, we used a recombinant MVA expressing fluorescent reporter proteins under transcriptional control of specific viral early and late promoters to study in vivo tropism, distribution, and pathogenesis of MVA infections in embryonated chicken eggs. The chorioallantoic membrane (CAM) of embryonated chicken eggs was inoculated with recombinant MVA, MVA or phosphate-buffered saline. The infection was analyzed by fluorescence microscopy, histology, immunohistochemistry, and virus titration of embryonic tissues. After infection of the CAM, MVA spread to internal and external embryonic tissues with the liver as a major target organ. Macrophages and hematopoietic cells were identified as primary target cells of MVA infection and may be involved in virus spread. Increasing doses of MVA did not result in increased lesion severity or embryonic death. Despite MVA generalization to embryonic tissues, the CAM seems to be the major site of MVA replication. The absence of considerable organ lesions and MVA-associated mortality highlights an excellent safety profile of MVA in chicken hosts.