MVDINET: A Novel Multi-Level Enzyme Function Predictor With Multi-View Deep Interactive Learning.

As a class of extremely significant of biocatalysts, enzymes play an important role in the process of biological reproduction and metabolism. Therefore, the prediction of enzyme function is of great significance in biomedicine fields. Recently, computational methods for predicting enzyme function have been proposed, and they effectively reduce the cost of enzyme function prediction. However, there are still deficiencies for effectively mining the discriminant information for enzyme function recognition in existing methods. In this study, we present MVDINET, a novel method for multi-level enzyme function prediction. First, the initial multi-view feature data is extracted by the enzyme sequence. Then, the above initial views are fed into various deep specific network modules to learn the depth-specificity information. Further, a deep view interaction network is designed to extract the interaction information. Finally, the specificity information and interaction information are fed into a multi-view adaptively weighted classification. We compressively evaluate MVDINET on benchmark datasets and demonstrate that MVDINET is superior to existing methods.

Bimetallic nanoparticles against multi-drug resistant bacteria.

We discovered two antibacterial bimetallic nanoparticles (AuRh and AuRu NPs), that possess antibacterial activities against multi-drug resistant (MDR) Gram-negative bacteria and can cure wound infections. None of the nanoparticles comprising just one of these metals elements shows any antibiotic activities.

Antimicrobial resistance and molecular epidemiological characteristics of clinical isolates of Staphylococcus aureus in Changsha area.

BACKGROUND: Increasing prevalence of Staphylococcus aureus (S. aureus), particularly methicillin-resistant S. aureus (MRSA) has been reported in China. In this study, we investigated the drug resistance characteristic, genetic background, and molecular epidemiological characteristic of S. aureus in Changsha. METHODS: Between January 2006 and December 2008, 293 clinical isolates of S. aureus were collected from 11 hospitals in Changsha and identified by the Vitek-2 system. All the isolates were verified as MRSA by PCR amplification of both femA and mecA genes. K-B disk method was used to test drug sensitivity of S. aureus to antibiotics. Pulsed-field gel electrophoresis (PFGE) was performed for genotypic and homologous analysis of 115 isolates randomly selected from the original 293 clinical S. aureus isolates. RESULTS: S. aureus was highly resistant to penicillin, ampicillin, erythromycin, and clindamycin with resistant rates of 96.6%, 96.6%, 77.1%, and 67.2% respectively. All the isolates were susceptible to tecoplanin, vancomycin, and linezolid. MRSA accounted for 64.8% (190/293) of all the S. aureus strains. The 115 S. aureus isolates were clustered into 39 PFGE types by PFGE typing, with 13 predominant patterns (designated types A to M) accounting for 89 isolates. The most prevalent PFGE type was type A (n = 56, 48.7%) and 100.0% of type A strains were MRSA. PFGE type A included 13 subtypes, and the most prevalent subtype was subtype A1 (46.4%, 26/56). Strains with PFGE type A were isolated from eight hospitals (8/11), and both subtypes A1 and A4 strains were isolated in a university hospital. CONCLUSIONS: Clinical isolates of S. aureus in Changsha were resistant to multiple traditional antibiotics. There was an outbreak of PFGE type A MRSA in this area and the A1 subtype was the predominant epidemic clone. Dissemination of the same clone was an important reason for the wide spread of MRSA.