MRGCN: cancer subtyping with multi-reconstruction graph convolutional network using full and partial multi-omics dataset.

MOTIVATION: Cancer is a molecular complex and heterogeneous disease. Each type of cancer is usually composed of several subtypes with different treatment responses and clinical outcomes. Therefore, subtyping is a crucial step in cancer diagnosis and therapy. The rapid advances in high-throughput sequencing technologies provide an increasing amount of multi-omics data, which benefits our understanding of cancer genetic architecture, and yet poses new challenges in multi-omics data integration. RESULTS: We propose a graph convolutional network model, called MRGCN for multi-omics data integrative representation. MRGCN simultaneously encodes and reconstructs multiple omics expression and similarity relationships into a shared latent embedding space. In addition, MRGCN adopts an indicator matrix to denote the situation of missing values in partial omics, so that the full and partial multi-omics processing procedures are combined in a unified framework. Experimental results on 11 multi-omics datasets show that cancer subtypes obtained by MRGCN with superior enriched clinical parameters and log-rank test P-values in survival analysis over many typical integrative methods. AVAILABILITY AND IMPLEMENTATION: https://github.com/Polytech-bioinf/MRGCN.git https://figshare.com/articles/software/MRGCN/23058503.

Deep structure integrative representation of multi-omics data for cancer subtyping.

MOTIVATION: Cancer is a heterogeneous group of diseases. Cancer subtyping is a crucial and critical step to diagnosis, prognosis and treatment. Since high-throughput sequencing technologies provide an unprecedented opportunity to rapidly collect multi-omics data for the same individuals, an urgent need in current is how to effectively represent and integrate these multi-omics data to achieve clinically meaningful cancer subtyping. RESULTS: We propose a novel deep learning model, called Deep Structure Integrative Representation (DSIR), for cancer subtypes dentification by integrating representation and clustering multi-omics data. DSIR simultaneously captures the global structures in sparse subspace and local structures in manifold subspace from multi-omics data and constructs a consensus similarity matrix by utilizing deep neural networks. Extensive tests are performed in 12 different cancers on three levels of omics data from The Cancer Genome Atlas. The results demonstrate that DSIR obtains more significant performances than the state-of-the-art integrative methods. AVAILABILITY AND IMPLEMENTATION: https://github.com/Polytech-bioinf/Deep-structure-integrative-representation.git. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Characterization of the complete chloroplast genome of Lonicera tangutica (Caprifoliaceae), an ornamental and medicinal plant in China.

In the present study, the complete chloroplast genome of Lonicera tangutica is presented and characterized for the first time. The complete chloroplast genome was 156,121 bp in length, including 23,899 bp inverted repeat (IR) regions, an 89,466 bp large single-copy (LSC) region, and an 18,851 bp small single-copy (SSC) region. A total of 129 genes, including 37 tRNA genes, eight rRNA genes, and 84 protein-coding genes, were annotated, and the overall GC content of the chloroplast genome was 38.35%. Two introns in the ycf3 gene and a single intron in another gene were detected. Maximum-likelihood phylogenetic analysis indicated that L. tangutica has a very close evolutionary relationship with Lonicera praeflorens, Lonicera hispida, Lonicera fragrantissima, and Lonicera stephanocarpa. These results are valuable for studying the evolution and genetic diversity of L. tangutica.

Face mask detection and classification via deep transfer learning.

Wearing a mask is an important way of preventing COVID-19 transmission and infection. German researchers found that wearing masks can effectively reduce the infection rate of COVID-19 by 40%. However, the detection of face mask-wearing in the real world is affected by factors such as light, occlusion, and multi-object. The detection effect is poor, and the wearing of cotton masks, sponge masks, scarves and other items greatly reduces the personal protection effect. Therefore, this paper proposes a new algorithm for mask detection and classification that fuses transfer learning and deep learning. Firstly, this paper proposes a new algorithm for face mask detection that integrates transfer learning and Efficient-Yolov3, using EfficientNet as the backbone feature extraction network, and choosing CIoU as the loss function to reduce the number of network parameters and improve the accuracy of mask detection. Secondly, this paper divides the mask into two categories of qualified masks (N95 masks, disposable medical masks) and unqualified masks (cotton masks, sponge masks, scarves, etc.), creates a mask classification data set, and proposes a new mask classification algorithm that the combines transfer learning and MobileNet, enhances the generalization of the model and solves the problem of small data size and easy overfitting. Experiments on the public face mask detection data set show that the proposed algorithm has a better performance than existing algorithms. In addition, experiments are performed on the created mask classification data set. The mask classification accuracy of the proposed algorithm is 97.84%, which is better than other algorithms.

The Link between Landscape Characteristics and Soil Losses Rates over a Range of Spatiotemporal Scales: Hubei Province, China.

Controlling soil erosion is beneficial to the conservation of soil resources and ecological restoration. Understanding the spatial distribution characteristics of soil erosion helps find the key areas for soil control projects and optimal scale for investing in a soil and water conservation project at the lowest cost. This study aims to answer the question of how the spatial distribution of soil erosion in Hubei Province changed between 2000 and 2020. Moreover, how do the effects of natural factors and human activities on soil erosion vary over the years? What are the differences in landscape pattern characteristics and the spatial cluster of soil erosion at multiple administrative scales? We simulated the spatial distribution of soil erosion in Hubei province from 2000 to 2020 by the Chinese Soil Loss Equation model at three administrative scales. We investigated the relationship between soil erosion and driving factors by Geodector. We explored the landscape pattern and hotspots of land at different levels of soil erosion by Fragstat and hotspot analysis. The results show that: (1) The average soil erosion rate decreased from 2000 to 2020. Soil erosion is severe in the mountainous areas of western Hubei province, while it is less severe in the central plains. (2) Land-cover type, precipitation, and normalized difference vegetation index are the most influencing factors of soil erosion in 2000-2010, 2015, and 2020, respectively. (3) The aggregation index values at the town scale are higher than those at the city and county scales, while the fractal dimension index values at the town scale are lower, which indicates that soil erosion projects are most efficient when the project unit is 'town'. (4) At the town scale, if the hotspot area (6.84% of the total area) is treated as the protection target, it can reduce 50.42% of the total soil erosion of Hubei province. Hotspots of soil erosion overlap with high erosion zones, mainly in the northwestern, northeastern, and southwestern parts of Hubei province in 2000, while the hotspots in northwestern Hubei disappear in 2020. In conclusion, land managers in Hubei should optimize the land-use structure, soil and water conservation in slope land, and eco-engineering controls at the town scale.

Designing Ecological Security Patterns Based on the Framework of Ecological Quality and Ecological Sensitivity: A Case Study of Jianghan Plain, China.

Researchers and managers of natural resource conservation have increasingly emphasized the importance of maintaining a connected network of important ecological patches to mitigate landscape fragmentation, reduce the decline of biodiversity, and sustain ecological services. This research aimed to guide landscape management and decision-making by developing an evaluation framework to construct ecological security patterns. Taking the Jianghan Plain as the study area, we identified key ecological sources by overlaying the spatial patterns of ecological quality (biodiversity, carbon storage, and water yield) and ecological sensitivity (habitat sensitivity, soil erosion sensitivity, and water sensitivity) using the Integrated Valuation of Environmental Services and Tradeoffs (InVEST) model and the Chinese Soil Loss Equation Function. Ecological corridors were obtained by the least-cost path analysis method and circuit theory. A total of 48 ecological sources (3812.95 km2), primarily consisting of water area, forestland, and cropland, were identified. Ninety-one ecological corridors were derived, with a total length of 2036.28 km. Forty barriers and 40 pinch points with the highest improvement coefficient scores or priority scores were selected. There were 11 priority corridors with very high levels of connectivity improvement potential and conservation priority, occupying 16.15% of the total length of corridors. The overall potential for ecological connectivity is high on the Jianghan Plain. Our framework offers a valuable reference for constructing ecological security patterns and identifying sites for ecological restoration at the regional scale.