Natural rubber is an indispensable material of strategic importance that has critical applications in industry and the military.However,the development of the natural rubber industry is impeded by the red root rot dis...Natural rubber is an indispensable material of strategic importance that has critical applications in industry and the military.However,the development of the natural rubber industry is impeded by the red root rot disease of rubber trees caused by Ganoderma pseudoferreum,which is one of the most devastating diseases in the rubber tree growing regions in China.To combat this disease,we screened the antifungal activity of 223 candidate bacterial strains against G.pseudoferreum,and found that Bacillus velezensis strain SF305 exhibited significant antifungal activity against G.pseudoferreum.Bacillus velezensis SF305 had a nearly 70%efficacy against the red root rot disease of rubber trees with the therapeutic treatment(Tre),while it exhibited over 90%protection effectiveness with the preventive treatment(Pre).The underlying biocontrol mechanism revealed that B.velezensis SF305 could reduce the disease severity of red root rot by degrading the mycelia of G.pseudoferreum.An antiSMASH analysis revealed that B.velezensis SF305 contains 15 gene clusters related to secondary metabolite synthesis,13 of which are conserved in species of B.velezensis,but surprisingly,B.velezensis SF305 possesses 2 unique secondary metabolite gene clusters.One is predicted to synthesize locillomycin,and the other is a novel nonribosomal peptides synthetase(NRPS)gene cluster.Genomic analysis showed that B.velezensis SF305 harbors genes involved in motility,chemotaxis,biofilm formation,stress resistance,volatile organic compounds(VOCs)and synthesis of the auxin indole-3-acetic acid(IAA),suggesting its plant growth-promoting rhizobacteria(PGPR)properties.Bacillus velezensis SF305 can promote plant growth and efficiently antagonize some important phytopathogenic fungi and bacteria.This study indicates that B.velezensis SF305 is a versatile plant probiotic bacterium.To the best of our knowledge,this is the first time a B.velezensis strain has been reported as a promising biocontrol agent against the red root rot disease of rubber trees.展开更多
Interactive medical image segmentation based on human-in-the-loop machine learning is a novel paradigm that draws on human expert knowledge to assist medical image segmentation.However,existing methods often fall into...Interactive medical image segmentation based on human-in-the-loop machine learning is a novel paradigm that draws on human expert knowledge to assist medical image segmentation.However,existing methods often fall into what we call interactive misunderstanding,the essence of which is the dilemma in trading off short-and long-term interaction information.To better use the interaction information at various timescales,we propose an interactive segmentation framework,called interactive MEdical image segmentation with self-adaptive Confidence CAlibration(MECCA),which combines action-based confidence learning and multi-agent reinforcement learning.A novel confidence network is learned by predicting the alignment level of the action with short-term interaction information.A confidence-based reward-shaping mechanism is then proposed to explicitly incorporate confidence in the policy gradient calculation,thus directly correcting the model’s interactive misunderstanding.MECCA also enables user-friendly interactions by reducing the interaction intensity and difficulty via label generation and interaction guidance,respectively.Numerical experiments on different segmentation tasks show that MECCA can significantly improve short-and long-term interaction information utilization efficiency with remarkably fewer labeled samples.The demo video is available at https://bit.ly/mecca-demo-video.展开更多
基金financially supported by the National Key Research and Development Program of China(2023YFD1200204)the Special Fund for Hainan Excellent Team“Rubber Genetics and Breeding”,China(20210203)。
文摘Natural rubber is an indispensable material of strategic importance that has critical applications in industry and the military.However,the development of the natural rubber industry is impeded by the red root rot disease of rubber trees caused by Ganoderma pseudoferreum,which is one of the most devastating diseases in the rubber tree growing regions in China.To combat this disease,we screened the antifungal activity of 223 candidate bacterial strains against G.pseudoferreum,and found that Bacillus velezensis strain SF305 exhibited significant antifungal activity against G.pseudoferreum.Bacillus velezensis SF305 had a nearly 70%efficacy against the red root rot disease of rubber trees with the therapeutic treatment(Tre),while it exhibited over 90%protection effectiveness with the preventive treatment(Pre).The underlying biocontrol mechanism revealed that B.velezensis SF305 could reduce the disease severity of red root rot by degrading the mycelia of G.pseudoferreum.An antiSMASH analysis revealed that B.velezensis SF305 contains 15 gene clusters related to secondary metabolite synthesis,13 of which are conserved in species of B.velezensis,but surprisingly,B.velezensis SF305 possesses 2 unique secondary metabolite gene clusters.One is predicted to synthesize locillomycin,and the other is a novel nonribosomal peptides synthetase(NRPS)gene cluster.Genomic analysis showed that B.velezensis SF305 harbors genes involved in motility,chemotaxis,biofilm formation,stress resistance,volatile organic compounds(VOCs)and synthesis of the auxin indole-3-acetic acid(IAA),suggesting its plant growth-promoting rhizobacteria(PGPR)properties.Bacillus velezensis SF305 can promote plant growth and efficiently antagonize some important phytopathogenic fungi and bacteria.This study indicates that B.velezensis SF305 is a versatile plant probiotic bacterium.To the best of our knowledge,this is the first time a B.velezensis strain has been reported as a promising biocontrol agent against the red root rot disease of rubber trees.
基金Project supported by the Science and Technology Commission of Shanghai Municipality,China(No.22511106004)the Postdoctoral Science Foundation of China(No.2022M723039)+1 种基金the National Natural Science Foundation of China(No.12071145)the Shanghai Trusted Industry Internet Software Collaborative Innovation Center,China。
文摘Interactive medical image segmentation based on human-in-the-loop machine learning is a novel paradigm that draws on human expert knowledge to assist medical image segmentation.However,existing methods often fall into what we call interactive misunderstanding,the essence of which is the dilemma in trading off short-and long-term interaction information.To better use the interaction information at various timescales,we propose an interactive segmentation framework,called interactive MEdical image segmentation with self-adaptive Confidence CAlibration(MECCA),which combines action-based confidence learning and multi-agent reinforcement learning.A novel confidence network is learned by predicting the alignment level of the action with short-term interaction information.A confidence-based reward-shaping mechanism is then proposed to explicitly incorporate confidence in the policy gradient calculation,thus directly correcting the model’s interactive misunderstanding.MECCA also enables user-friendly interactions by reducing the interaction intensity and difficulty via label generation and interaction guidance,respectively.Numerical experiments on different segmentation tasks show that MECCA can significantly improve short-and long-term interaction information utilization efficiency with remarkably fewer labeled samples.The demo video is available at https://bit.ly/mecca-demo-video.
