Search

Crossing over is essential for chromosome segregation during meiosis. Protein modification by SUMO is implicated in crossover control, but pertinent targets have remained elusive. Here we identify Msh4 as a target of SUMO-mediated crossover regulation. Msh4 and Msh5 constitute the MutSγ complex, which stabilizes joint-molecule (JM) recombination intermediates and facilitates their resolution into crossovers. Msh4 SUMOylation enhances these processes to ensure that each chromosome pair acquires at least one crossover. Msh4 is directly targeted by E2 conjugase Ubc9, initially becoming mono-SUMOylated in response to DNA double-strand breaks, then multi/poly-SUMOylated forms arise as homologs fully engage. Mechanistically, SUMOylation fosters interaction between Msh4 and Msh5. We infer that initial SUMOylation of Msh4 enhances assembly of MutSγ in anticipation of JM formation, while secondary SUMOylation may promote downstream functions. Regulation of Msh4 by SUMO is distinct and independent of its previously described stabilization by phosphorylation, defining MutSγ as a hub for crossover control.

Graph representation learning technology aims to learn the low dimensional representation vectors for nodes while maintaining the properties of graphs and provide materials for downstream tasks. Most existing algorithms mainly focus on aggregating neighborhood features, lack the ability to capture non-linear information. To solve this issue, this paper proposes a graph convolutional network with adaptive fusion of neighborhood aggregation and interaction (AFAI-GCN). Firstly, a two-channel graph convolutional network is constructed to model the neighborhood aggregation, and the representations generated by modeling are used to calculate the neighborhood interaction items to enhance the learning capability of algorithm. Secondly, the attention mechanism is adopted in the adaptive fusion module to increase the attention on significant information and improve the task correlation of the fused information items. Finally, an information consistency constraint and a difference constraint are applied to enhancing node feature consistency and embedded representation difference. The node classification and visualization tasks are performed on three public citation datasets. Experiments results show that, compared with graph convolutional network (GCN), neighborhood aggregation and interaction graph convolutional network (AIR-GCN) and other algorithms, the classification accuracy of AFAI-GCN is increased by 1.0 to 1.6, 1.1 to 2.4, 0.3 to 0.9 percentage points on Cora, Citeseer and Pubmed datasets, respectively. In the visualization task, the degree of aggregation within clusters is higher and the boundaries of different clusters are clearer. Moreover, the convergence speed of AFAI-GCN is faster and the accuracy curve is smoother in the learning process. All these results indicate that AFAI-GCN is more advanced than the benchmark algorithms.