Browsing by Author "Liu K"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    CSMSA: Cross-Space Multiscale Adaptive Link Prediction for ceRNA-Mediated Multimolecular Disease Regulatory Networks
    (Association for Computing Machinery, 2025-12-10) Long J; Li J; Qu G; Liu K; Liu B
    Regulatory interactions associated with diseases are pivotal for elucidating the molecular mechanisms that drive disease progression and promoting precision medicine. Nevertheless, existing research algorithms often overlook the potential dynamic synergistic-competitive mechanisms between different ceRNA regulatory networks and lack cross-space learning capabilities across multiple heterogeneous graph structures, making it difficult to comprehensively capture the multidimensional molecular regulatory biological mechanisms in disease data with different structural densities. Therefore, we propose the cross-space multiscale adaptive learning framework (CSMSA) that integrates a heterogeneous five-layer ceRNA regulatory network and introduces an adaptive cross-space learning mechanism to dynamically capture complementary and specific interactions and effectively learn the intrinsic biological regulatory mechanisms. Moreover, the CSMSA framework employs a multi-scale feature fusion strategy that hierarchically learns node embeddings by integrating local structural information and global topological features from heterogeneous graphs to enhance predictive performance and robustness across complex datasets of varying sizes. Comprehensive evaluations on three independent datasets show that CSMSA surpasses existing methods in the multimolecular disease prediction task (Max AUC = 0.9880, Max AUPR = 0.9829), thereby providing a reliable new paradigm for probing disease regulatory links.
  • Thumbnail Image
    Item
    Optimizing irrigation and fertilization management enhances alfalfa seed yield components through improved soil nutrient availability and leaf photosynthetic efficiency
    (Frontiers Media S.A., 2025-08-29) Hui J; Sun Y; Wei K; Cartmill AD; López IF; Ma C; Zhang Q; Liu K
    Introduction: Addressing the challenges of inefficient water-fertilizer utilization and suboptimal seed yield in alfalfa (Medicago sativa L.) seed production systems, we investigated the effects of differential irrigation-fertilization regimes on soil nutrient dynamics, photosynthetic performance, and yield parameters. This study aims to optimize seed production while elucidating the response mechanisms linking soil nutrient availability, foliar photosynthetic efficiency, and seed yield outcomes. This experiment employed drip irrigation to address production constraints in alfalfa seed cultivation. Methods: Using ‘WL354HQ’ and ‘Xinmu No.4’ as the experimental materials, a two-factor randomized block design was adopted, with three fertilization levels: F0 (no fertilizer), F1 (90 kg·ha-1 N 75 kg·ha-1 P2O5, 12 kg·ha-1 K2O), and F2 (120 kg·ha-1 N, 100 kg·ha-1 P2O5, 15 kg·ha-1 K2O), and combined with three irrigation levels W1 (1650 m3·ha-1), W2 (2500 m3·ha-1), and W3 (3350 m3·ha-1). Results: Water and fertilizer management is a prerequisite for high yield of alfalfa seeds, and the impact of fertilization on seed yield is greater than that of irrigation. Compared to the non-fertilized control (F0W1), the F2W2 treatment significantly increased soil nutrients in the 0–20 cm layer: soil total nitrogen content (+52.17%), total phosphorus content (+18.72%), and organic carbon content (+16.85%), and available phosphorus content (+37.34%), and alkali-hydrolyzable nitrogen content (+17.45%). Notably, F2W2 enhanced net photosynthetic rate by 35.04% despite reduced stomatal conductance (-2.14%) and intercellular CO2 concentration (-9.50%), thereby promoting assimilate partitioning to reproductive organs. Consequently, seed dimensional parameters (width: +53.02%; thickness: +21.75%) and germination rate (+23.11%) were significantly improved (P < 0.05), increasing the seed yields of WL354HQ and Xinmu No.4 by 42.76% and 49.81% respectively. Correlation analysis revealed significant (P < 0.01) positive associations between seed yield and seed length, seed width, seed thickness, chlorophyll a, carotenoids, total chlorophyll content, and net photosynthetic rate. Principal component analysis showed that the optimal fertilization level was N 120 kg·ha-1; P2O5–100 kg·ha-1; K2O 15 kg·ha-1, with an irrigation level of 2500 m3·ha-1 (F2W2) as the optimal model. Discussion: This optimized model significantly enhanced alfalfa seed yield formation, photosynthetic characteristics, and soil nutrient availability, which provided a theoretical basis for high yield cultivation of alfalfa seed production in arid areas.