No abstract

Web-scale search systems typically tackle the scalability challenge with a two-step paradigm: retrieval and ranking. The retrieval step, also known as candidate selection, often involves extracting standardized entities, creating an inverted index, and performing term matching for retrieval. Such traditional methods require manual and time-consuming development of query models. In this paper, we discuss applying learning-to-retrieve technology to enhance LinkedIn's job search and recommendation systems. In the realm of promoted jobs, the key objective is to improve the quality of applicants, thereby delivering value to recruiter customers. To achieve this, we leverage confirmed hire data to construct a graph that evaluates a seeker's qualification for a job, and utilize learned links for retrieval. Our learned model is easy to explain, debug and adjust. On the other hand, the focus for organic jobs is to optimize seeker engagement. We accomplished this by training embeddings for personalized retrieval, fortified by a set of rules derived from the categorization of member feedbacks. In addition to a solution based on a conventional inverted index, we developed an on-GPU solution capable of supporting both KNN and term matching efficiently.

BackgroundDenatonium, a widely used bitter agonist, activates bitter taste receptors on many cell types and plays important roles in chemical release, ciliary beating and smooth muscle relaxation through intracellular Ca2+-dependent pathways. However, the effects of denatonium on the proliferation of airway epithelial cells and on the integrity of cellular components such as mitochondria have not been studied. In this study, we hypothesize that denatonium might induce airway epithelial cell injury by damaging mitochondria.MethodsBright-field microscopy, cell counting kit-8 (CCK-8) assay and flow cytometry analysis were used to examine cellular morphology, proliferation and cell cycle, respectively. Transmission electron microscopy (TEM) was used to examine mitochondrial integrity. JC-1 dye and western blotting techniques were used to measure mitochondrial membrane potential and protein expression, respectively.ResultsFor airway epithelial cells, we observed that denatonium significantly effects cellular morphology, decreases cell proliferation and reduces the number of cells in S phase in a dose-dependent manner. TEM analysis demonstrated that denatonium causes large amplitude swelling of mitochondria, which was confirmed by the loss of mitochondrial membrane potential, the down-regulation of Bcl-2 protein and the subsequent enhancement of the mitochondrial release of cytochrome c and Smac/DIABLO after denatonium treatment.ConclusionsIn this study, we demonstrated for the first time that denatonium damages mitochondria and thus induces apoptosis in airway epithelial cells.Electronic supplementary materialThe online version of this article (doi:10.1186/s12931-015-0183-9) contains supplementary material, which is available to authorized users.