Fast feature matching based on r-nearest k-means searching

Feature matching has been frequently applied in computer vision and pattern recognition.In this paper,the authors propose a fast feature matching algorithm for vector-based feature.Their algorithm searches r-nearest neighborhood clusters for the query point after a k-means clustering,which shows higher efficiency in three aspects.First,it does not reformat the data into a complex tree,so it shortens the construction time twice.Second,their algorithm adopts the r-nearest searching strategy to increase the probability to contain the exact nearest neighbor(NN)and take this NN as the global one,which can accelerate the searching speed by 170 times.Third,they set up a matching rule with a variant distance threshold to eliminate wrong matches.Their algorithm has been tested on large SIFT databases with different scales and compared with two widely applied algorithms,priority search km-tree and random kd-tree.The results show that their algorithm outperforms both algorithms in terms of speed up over linear search,and consumes less time than km-tree.Finally,they carry out the CFI test based on ISKLRS database using their algorithm.The test results show that their algorithm can greatly improve the recognition speed without affecting the recognition rate.

Identification of anti-Gram-negative bacteria agents targeting the interaction between ribosomal proteins L12 and L10

Gram-negative bacteria have become the main pathogens and cause serious clinical problems with increased morbidity and mortality. However, the slow discovery of new antimicrobial agents is unable to meet the need for the treatment of bacterial infections caused by drug-resistant strains. The interaction of L12 and L10 is essential for ribosomal function and protein synthesis. In this study, a yeast two-hybrid system was established to successfully detect the interaction between L12 and L10 proteins from gram-negative bacteria Escherichia coli, which allows us to screen compounds that specifically disrupt this interaction. With this system, we identified two compounds IMB-84 and IMB-87 that block L12-L10 interaction and show bactericidal activity against E. coli. We used glutathione-S-transferase(GST) pull-down and surface plasmon resonance(SPR) assays to demonstrate that these compounds disrupt L12-L10 interaction in vitro and the target of compounds was further confirmed by the overexpression of target proteins. Moreover, protein synthesis and elongation factor G-dependent GTPase activities are inhibited by two compounds. Therefore, we have identified two antibacterial agents that disrupt L12-L10 interaction by using yeast two-hybrid system.