The research progress, hotspots, challenges and outlooks of solid-phase denitrification process.

Nitrogen pollution is one of the main reasons for water eutrophication. The difficulty of nitrogen removal in low-carbon wastewater poses a huge potential threat to the ecological environment and human health. As a clean biological nitrogen removal process, solid-phase denitrification (SPD) was proposed for long-term operation of low-carbon wastewater. In this paper, the progress, hotspots, and challenges of the SPD process based on different solid carbon sources (SCSs) are reviewed. Compared with synthetic SCS and natural SCS, blended SCSs have more application potential and have achieved pilot-scale application. Differences in SCSs will lead to changes in the enrichment of hydrolytic microorganisms and hydrolytic genes, which indirectly affect denitrification performance. Moreover, the denitrification performance of the SPD process is also affected by the physical and chemical properties of SCSs, pH of wastewater, hydraulic retention time, filling ratio, and temperature. In addition, the strengthening of the SPD process is an inevitable trend. The strengthening measures including SCSs modification and coupled electrochemical technology are regarded as the current research hotspots. It is worth noting that the outbreak of the COVID-19 epidemic has led to the increase of disinfection by-products and antibiotics in wastewater, which makes the SPD process face challenges. Finally, this review proposes prospects to provide a theoretical basis for promoting the efficient application of the SPD process and coping with the challenge of the COVID-19 epidemic.

An Interpretable Multi-Level Enhanced Graph Attention Network for Disease Diagnosis with Gene Expression Data

Clinical omics, especially gene expression data, have been widely studied and successfully applied for disease diagnosis using machine learning techniques. As genes often work interactively rather than individually, investigating co-functional gene modules can improve our understanding of disease mechanisms and facilitate disease state prediction. To this end, we in this paper propose a novel Multi-Level Enhanced Graph ATtention (MLE-GAT) network to explore the gene modules and intergene relational information contained in the omics data. In specific, we first format the omics data of each patient into co-expression graphs using weighted correlation network analysis (WGCNA) and then feed them to a well-designed multi-level graph feature fully fusion (MGFFF) module for disease diagnosis. For model interpretation, we develop a novel full-gradient graph saliency (FGS) mechanism to identify the disease-relevant genes. Comprehensive experiments show that our proposed MLE-GAT achieves state-of-the-art performance on transcriptomics data from TCGA-LGG/TCGA-GBM and proteomics data from COVID-19/non-COVID-19 patient sera. © 2021 IEEE.