Search

Exploring drought stress-responsive genes in rice is essential for breeding drought-resistant varieties. Rice drought resistance is controlled by multiple genes, and mining drought stress-responsive genes solely based on single omics data lacks stability and accuracy. Multi-omics correlation analysis and biological molecular network analysis provide robust solutions. This study proposed a random walk with a multi-restart probability (RWMRP) algorithm, based on the Restarted Random Walk (RWR) algorithm, to operate on rice MultiPlex biological networks. It explores the interactions between biological molecules across various levels and ranks potential genes. RWMRP uses eigenvector centrality to evaluate node importance in the network and adjusts the restart probabilities accordingly, diverging from the uniform restart probability employed in RWR. In the random walk process, it can be better to consider the global relationships in the network. Firstly, we constructed a MultiPlex biological network by integrating the rice protein–protein interaction, gene pathway, and gene co-expression network. Then, we employed RWMRP to predict the potential genes associated with rice tolerance to drought stress. Enrichment and correlation analyses resulted in the identification of 12 drought-related genes. We further conducted quantitative real-time polymerase chain reaction (qRT-PCR) analysis on these 12 genes, ultimately identifying 10 genes responsive to drought stress. [ABSTRACT FROM AUTHOR]

Information technology and statistical modeling have made significant contributions to smart agriculture. Machine vision and hyperspectral technologies, with their non-destructive and real-time capabilities, have been extensively utilized in the non-destructive diagnosis and quality monitoring of crops and seeds, becoming essential tools in traditional agriculture. This work applies these techniques to address the color classification of rapeseed, which is of great significance in the field of rapeseed growth diagnosis research. To bridge the gap between machine vision and hyperspectral technology, a framework is developed that includes seed color calibration, spectral feature extraction and fusion, and the recognition modeling of three seed colors using four machine learning methods. Three categories of rapeseed coat colors are calibrated based on visual perception and vector-square distance methods. A fast-weighted visibility graph method is employed to map the spectral reflectance sequences to complex networks, and five global network attributes are extracted to fuse the full-band reflectance as model input. The experimental results demonstrate that the classification recognition rate of the fused feature reaches 0.943 under the XGBoost model, confirming the effectiveness of the network features as a complement to the spectral reflectance. The high recognition accuracy and simple operation process of the framework support the further application of hyperspectral technology to analyze the quality of rapeseed. [ABSTRACT FROM AUTHOR]

Due to the low storage cost and high computation efficiency of hashing, cross-modal hashing has been attracting widespread attention in recent years. In this paper, we investigate how supervised cross-modal hashing (CMH) benefits from multi-label and contrastive learning (CL) by overcoming the following two challenges: (i) how to combine multi-label and supervised contrastive learning to consider diverse relationships among cross-modal instances, and (ii) how to reduce the sparsity of multi-label representation so as to improve the similarity measurement accuracy. To this end, we propose a novel cross-modal hashing framework, dubbed Multi-Label Weighted Contrastive Hashing (MLWCH). This framework involves compact consistent similarity representation, a new designed multi-label similarity calculation method that efficiently reduces the sparsity of multi-label by reducing redundant zero elements. Furthermore, a novel multi-label weighted contrastive learning strategy is developed to significantly improve hashing learning by assigning similarity weight to positive samples under both linear and non-linear similarities. Extensive experiments and ablation analysis over three benchmark datasets validate the superiority of our MLWCH method, especially over several outstanding baselines. [ABSTRACT FROM AUTHOR]

To enhance the microhardness and wear resistance of low-carbon steel, laser cladding was employed to create A100-Y2O3 cladding coatings that remained free of cracks. The phase composition, microstructure, and element distribution of these coatings were examined using XRD and SEM analyses, respectively. The microhardness and wear resistance of the A100-Y2O3 cladding coatings were tested by an HXS-1000 A type digital liquid crystal intelligent microhardness tester and an ML-10 friction and wear tester, respectively. The XRD results show that the addition of Y2O3 did not change the phase composition of the A100-Y2O3 cladding coatings. With the addition of Y2O3, the grains of the A100-Y2O3 cladding coatings are finer compared with those of the A100-0%Y2O3 cladding coating. The upper part of the A100-Y2O3 cladding coatings were composed of fine equiaxed grains. The average microhardness of the A100-0%Y2O3 cladding coatings was 532.489 HV. With the addition of Y2O3, the microhardness of the A100-Y2O3 cladding coatings was obviously improved, and the average microhardness of A100-1.5%Y2O3 coating reached 617.290 HV. The A100-Y2O3 cladding coatings were reduced, and the worn surface became relatively smooth owing to the addition of Y2O3. The addition of Y2O3 significantly improved the wear resistance of the A100-Y2O3 cladding coatings. [ABSTRACT FROM AUTHOR]