作者：Venkatraman, Vijaysree
作者：Morton, David B.
作者单位：University of Birmingham
作者：Costello, Michael S.; Neumann, Bryan; Raimondi, Mia W.; Cuthbert, Bonnie J.; Holubova, Jana; Garza-Sanchez, Fernando; Samad, Abdul; Bumba, Ladislav; Torres, Jacob A.; Holznecht, Nickolas; Mendoza, Jessica; Stanek, Ondrej; Prombhul, Sasiprapa; Weimbs, Thomas; Morrissey, Meghan A.; Acosta-Alvear, Diego; Low, David A.; Sebo, Peter; Goulding, Celia W.; Gonen, Shane; Hayes, Christopher S.
作者单位：University of California System; University of California Santa Barbara; University of California System; University of California Irvine; Czech Academy of Sciences; Institute of Microbiology of the Czech Academy of Sciences; University of California System; University of California Santa Barbara; University of California System; University of California Irvine
摘要：Pathogenic Bordetella bacteria use protein adhesins to infect the ciliated respiratory epithelia of vertebrate hosts. In this work, we show that the filamentous hemagglutinin FhaB adhesin of Bordetella carries a C-terminal microtubule-binding domain (FhaB-CT), which is translocated into host cells to promote colonization. FhaB-CT delivery is required to occupy a niche at the base of cilia in airway epithelia, and mutant bacteria lacking this domain are defective for nasal colonization. These o...
作者：Jacob-Dubuisson, Francoise
作者单位：Universite de Lille; Pasteur Network; Institut National de la Sante et de la Recherche Medicale (Inserm); Centre National de la Recherche Scientifique (CNRS); Institut Pasteur Lille
作者：Lang, Jochen; Raoux, Matthieu
作者单位：Universite de Bordeaux; Centre National de la Recherche Scientifique (CNRS); CNRS - Institute of Chemistry (INC)
作者：Beaglehole, Daniel; Radhakrishnan, Adityanarayanan; Boix-Adsera, Enric; Belkin, Mikhail
作者单位：University of California System; University of California San Diego; Massachusetts Institute of Technology (MIT); Harvard University; Massachusetts Institute of Technology (MIT); Broad Institute; University of Pennsylvania; University of California System; University of California San Diego
摘要：Artificial intelligence (AI) models contain much of human knowledge. Understanding the representation of this knowledge will lead to improvements in model capabilities and safeguards. Building on advances in feature learning, we developed an approach for extracting linear representations of semantic notions or concepts in AI models. We showed how these representations enabled model steering, through which we exposed vulnerabilities and improved model capabilities. We demonstrated that concept ...
