Research indicates that microbe activity within the human body significantly influences health by being closely linked to various diseases. Accurately predicting microbe-disease interactions (MDIs) offers critical insights for disease intervention and pharmaceutical research. Current advanced AI-based technologies automatically generate robust representations of microbes and diseases, enabling effective MDI predictions. However, these models continue to face significant challenges. A major issue is their reliance on complex feature extractors and classifiers, which substantially diminishes the models' generalizability. To address this, we introduce a novel graph autoencoder framework that utilizes decoupled representation learning and multi-scale information fusion strategies to efficiently infer potential MDIs. Initially, we randomly mask portions of the input microbe-disease graph based on Bernoulli distribution to boost self-supervised training and minimize noise-related performance degradation. Secondly, we employ decoupled representation learning technology, compelling the graph neural network (GNN) to independently learn the weights for each feature subspace, thus enhancing its expressive power. Finally, we implement multi-scale information fusion technology to amalgamate the multi-layer outputs of GNN, reducing information loss due to occlusion. Extensive experiments on public datasets demonstrate that our model significantly surpasses existing top MDI prediction models. This indicates that our model can accurately predict unknown MDIs and is likely to aid in disease discovery and precision pharmaceutical research. Code and data are accessible at: https://github.com/shmildsj/MDI-IFDRL.

Objective To explore the association between the tag single nucleotide polymorphism (tag SNP) of the adenylyl cyclase 3 (ADCY3) and the essential hypertension (EH).Methods From April to July 2013,a total of 1 061 subjects diagnosed with EH and 1 218 control subjects were recruited from Ningbo,Zhejiang Province.Information was collected by face-to-face interview.Twelve tag SNPs were detected by ligase detection reaction technique.Results After adjusted for age,gender,body mass index and other related factors,logistic regression analysis showed that 3 loci (rs11689546,rs7593130,rs2241759) were associated with EH.AG genotype of rs11689546 was associated with 0.494 times lower risk of EH (OR =0.494,95％ CI0.246-0.993;compared with AA genotype).CT genotype of rs7593130 was associated with 1.596 times higher risk of EH (OR =1.596,95％ CI 1.009-2.524;compared with TT genotype),and CT/CC genotype of rs7593130 was associated with 1.627 times higher risk of EH (OR =1.627,95％ CI 1.034-2.559;compared with TT genotype).AG genotype of rs2241759 was associated with 0.669 times lower risk of EH (OR =0.669,95％ CI 0.503-0.891;compared with AA genotype),and CT/CC genotype of rs2241759 was associated with 0.687 times lower risk of EH (OR =0.687,95％ CI 0.518-0.911;compared with TT genotype).Conclusion The polymorphisms of ADCY3 are associated with lower (G allele of the rs11689546 locus and G allele of the rs2241759 locus) or higher (C allele of the rs7593130 locus) risk of essential hypertension.