To reveal the intraspecific evolution of Leptospirillum ferriphilum isolates which thrived in industrial bioleaching ecosystems and acid mine drainages,genome sequences of L.ferriphilum YSK,L.ferriphilum DX and L.ferr...To reveal the intraspecific evolution of Leptospirillum ferriphilum isolates which thrived in industrial bioleaching ecosystems and acid mine drainages,genome sequences of L.ferriphilum YSK,L.ferriphilum DX and L.ferriphilum ZJ were determined to compare with complete genome of L.ferriphilum ML-04.The genome comparisons reveal that extensive intraspecific variation occurs in their genomes,and that the loss and insertion of novel gene blocks of probable phage origin may mostly contribute to heterogeneity of gene content among L.ferriphilum genomes.Surprisingly,a nif gene cluster is identified in L.ferriphilum YSK and L.ferriphilum ZJ genomes.Intensive analysis and further experiments indicate that the nif gene cluster in L.ferriphilum YSK inherits from ancestor rather than lateral gene transfer.Overall,results suggest that the population of L.ferriphilum undergoes frequent genetic recombination,resulting in many closely related genome types in recent evolution.The combinatorial processes profoundly shape their physiologies and provide the basis for adaptation to different niches.展开更多
Retina vessel segmentation is a vital step in diagnosing ophthalmologic diseases. Traditionally, ophthalmologists segment retina vessels by hand, which is time-consuming and error-prone. Thus, more and more researcher...Retina vessel segmentation is a vital step in diagnosing ophthalmologic diseases. Traditionally, ophthalmologists segment retina vessels by hand, which is time-consuming and error-prone. Thus, more and more researchers are committed to the research of automatic segmentation algorithms. With the development of convolution neural networks(CNNs), many tasks can be solved by CNNs.In this paper, we propose an encoding-decoding network with a pyramid self-attention module(PSAM) to segment retinal vessels. The network follows a U shape structure, and it comprises stacked feature selection blocks(FSB) and a PSAM. The proposed FSB consists of two convolution blocks with the same weight and a channel-wise attention block. At the head of the network, we apply a PSAM consisting of three parallel self-attention modules to capture long-range dependence of different scales. Due to the power of PSAM and FSB, the performance of the network improves. We have evaluated our model on two public datasets: DRIVE and CHASE;B1. The results show the performance of our model is better than other methods. The F1, Accuracy, and area under curve(AUC) are 82.21%/80.57%,95.65%/97.02%, and 98.16%/98.46% on DRIVE and CHASE;B1, respectively.展开更多
基金Project(2018YFC1801804)supported by the National Key R&D Program of ChinaProjects(2016JJ3146,2017JJ3160)supported by the Natural Science Foundation of Hunan Province,China。
文摘To reveal the intraspecific evolution of Leptospirillum ferriphilum isolates which thrived in industrial bioleaching ecosystems and acid mine drainages,genome sequences of L.ferriphilum YSK,L.ferriphilum DX and L.ferriphilum ZJ were determined to compare with complete genome of L.ferriphilum ML-04.The genome comparisons reveal that extensive intraspecific variation occurs in their genomes,and that the loss and insertion of novel gene blocks of probable phage origin may mostly contribute to heterogeneity of gene content among L.ferriphilum genomes.Surprisingly,a nif gene cluster is identified in L.ferriphilum YSK and L.ferriphilum ZJ genomes.Intensive analysis and further experiments indicate that the nif gene cluster in L.ferriphilum YSK inherits from ancestor rather than lateral gene transfer.Overall,results suggest that the population of L.ferriphilum undergoes frequent genetic recombination,resulting in many closely related genome types in recent evolution.The combinatorial processes profoundly shape their physiologies and provide the basis for adaptation to different niches.
文摘Retina vessel segmentation is a vital step in diagnosing ophthalmologic diseases. Traditionally, ophthalmologists segment retina vessels by hand, which is time-consuming and error-prone. Thus, more and more researchers are committed to the research of automatic segmentation algorithms. With the development of convolution neural networks(CNNs), many tasks can be solved by CNNs.In this paper, we propose an encoding-decoding network with a pyramid self-attention module(PSAM) to segment retinal vessels. The network follows a U shape structure, and it comprises stacked feature selection blocks(FSB) and a PSAM. The proposed FSB consists of two convolution blocks with the same weight and a channel-wise attention block. At the head of the network, we apply a PSAM consisting of three parallel self-attention modules to capture long-range dependence of different scales. Due to the power of PSAM and FSB, the performance of the network improves. We have evaluated our model on two public datasets: DRIVE and CHASE;B1. The results show the performance of our model is better than other methods. The F1, Accuracy, and area under curve(AUC) are 82.21%/80.57%,95.65%/97.02%, and 98.16%/98.46% on DRIVE and CHASE;B1, respectively.