Investigation of mumps vaccine failures in Minsk, Belarus, 2001-2003
VACCINE
Authors: Atrasheuskaya, Alena V.; Blatun, Elena M.; Kulak, Michail V.; Atrasheuskaya, Alina; Karpov, Igor A.; Rubin, Steven; Ignatyev, George M.
Abstract
The purpose of this study was to investigate mumps vaccine failures (VF) in a highly vaccinated population of Minsk, Belarus, and to investigate a possible role for virus strain-specific immunity. During our 3-year study period, 22 adults were admitted to the Infectious Diseases Hospital in Minsk with a diagnosis of mumps. A genotype HI mumps virus (MuV) strain was identified in all patients. Of 15 patients from whom the paired sera were collected, 9 were confirmed to have been previously vaccinated. Serological examinations indicated primary VF in seven of these cases and secondary VF in two. Despite almost all vaccinated patients possessing MuV specific IgG, few possessed neutralizing antibody to the vaccine strain and titers were nominal. Importantly, none of the sera were able to neutralize a genotype H MuV strain. Our results demonstrate the importance of assaying for neutralizing antibody and support the assertion that antigenic differences between wild type and vaccine MuV strains may play a role in cases of breakthrough infection in vaccinees. @ 2007 Elsevier Ltd. All rights reserved.
Clustering-Based Weighted Extreme Learning Machine for Classification in Drug Discovery Process
NEURAL INFORMATION PROCESSING, ICONIP 2016, PT I
Authors: Kudisthalert, Wasu; Pasupa, Kitsuchart
Abstract
Extreme Learning Machine (ELM) is a universal approximation method that is extremely fast and easy to implement, but the weights of the model are normally randomly selected so they can lead to poor prediction performance. In this work, we applied Weighted Similarity Extreme Learning Machine in combination with Jaccard/Tanimoto (WELM-JT) and cluster analysis (namely, k-means clustering and Support Vector Clustering) on similarity and distance measures (i.e., Jaccard/Tanimoto and Euclidean) in order to predict which compounds with not-so-different chemical structures have an activity for treating a certain symptom or disease. The proposed method was experimented on one of the most challenging datasets named Maximum Unbiased Validation (MUV) dataset with 4 different types of fingerprints (i.e. ECFP_4, ECFP_6, FCFP_4 and FCFP_6). The experimental results show that WELM-JT in combination with k-means-ED gave the best performance. It retrieved the highest number of active molecules and used the lowest number of nodes. Meanwhile, WELM-JT with k-means-JT and ECFP_6 encoding proved to be a robust contender for most of the activity classes.