Graph-DTI: A New Model for Drug-Target Interaction Prediction Based on Heterogenous Network Graph Embedding.

BACKGROUND: In this study, we aimed to develop a new end-to-end learning model called Graph-Drug-Target Interaction (DTI), which integrates various types of information in the heterogeneous network data, and to explore automatic learning of the topology-maintaining representations of drugs and targets, thereby effectively contributing to the prediction of DTI. Precise predictions of DTI can guide drug discovery and development. Most machine learning algorithms integrate multiple data sources and combine them with common embedding methods. However, the relationship between the drugs and target proteins is not well reported. Although some existing studies have used heterogeneous network graphs for DTI prediction, there are many limitations in the neighborhood information between the nodes in the heterogeneous network graphs. We studied the drug-drug interaction (DDI) and DTI from DrugBank Version 3.0, protein-protein interaction (PPI) from the human protein reference database Release 9, drug structure similarity from Morgan fingerprints of radius 2 and calculated by RDKit, and protein sequence similarity from Smith-Waterman score. METHOD: Our study consists of three major components. First, various drugs and target proteins were integrated, and a heterogeneous network was established based on a series of data sets. Second, the graph neural networks-inspired graph auto-encoding method was used to extract high-order structural information from the heterogeneous networks, thereby revealing the description of nodes (drugs and proteins) and their topological neighbors. Finally, potential DTI prediction was made, and the obtained samples were sent to the classifier for secondary classification. RESULTS: The performance of Graph-DTI and all baseline methods was evaluated using the sums of the area under the precision-recall curve (AUPR) and the area under the receiver operating characteristic curve (AUC). The results indicated that Graph-DTI outperformed the baseline methods in both performance results. CONCLUSION: Compared with other baseline DTI prediction methods, the results showed that Graph-DTI had better prediction performance. Additionally, in this study, we effectively classified drugs corresponding to different targets and vice versa. The above findings showed that Graph-DTI provided a powerful tool for drug research, development, and repositioning. Graph-DTI can serve as a drug development and repositioning tool more effectively than previous studies that did not use heterogeneous network graph embedding.

Gut microbiota and neonatal acute kidney injury biomarkers.

One of the most frequent issues in newborns is acute kidney injury (AKI), which can lengthen their hospital stay or potentially raise their chance of dying. The gut-kidney axis establishes a bidirectional interplay between gut microbiota and kidney illness, particularly AKI, and demonstrates the importance of gut microbiota to host health. Since the ability to predict neonatal AKI using blood creatinine and urine output as evaluation parameters is somewhat constrained, a number of interesting biomarkers have been developed. There are few in-depth studies on the relationships between these neonatal AKI indicators and gut microbiota. In order to gain fresh insights into the gut-kidney axis of neonatal AKI, this review is based on the gut-kidney axis and describes relationships between gut microbiota and neonatal AKI biomarkers.

Systematic evaluation of the prognostic and immunological role of PDLIM2 across 33 cancer types.

The protein PDLIM2 regulates the stability of various transcription factors and is required for polarized cell migration. However, the clinical relevance and immune infiltration of PDLIM2 in cancer are not well-understood. We utilized The Cancer Genome Atlas and Genotype-Tissue Expression database to characterize alterations in PDLIM2 in pan-cancer. TIMER was used to explore PDLIM2 expression and immune infiltration levels. We assessed the correlation between PDLIM2 expression and immune-associated gene expression, immune score, tumor mutation burden, and DNA microsatellite instability. PDLIM2 significantly affected the prognosis of various cancers. Increased expression of PDLIM2 was significantly correlated with the tumor grade in seven types of tumors. The expression level of PDLIM2 was positively correlated with immune infiltrates, including B cells, CD8+ T cells, CD4+ T cells, neutrophils, macrophages, and dendritic cells in bladder urothelial, kidney renal papillary cell, and colon adenocarcinoma. High expression levels of PDLIM2 tended to be associated with higher immune and stromal scores. PDLIM2 expression was associated with the tumor mutation burden in 12 cancer types and microsatellite instability in 5 cancer types. PDLIM2 levels were strongly correlated with diverse immune-related genes. PDLIM2 can act as a prognostic-related therapeutic target and is correlated with immune infiltrates in pan-cancer.

Prognostic and Immunological Roles of MMP-9 in Pan-Cancer.

BACKGROUND: Matrix metalloproteinase-9 (MMP-9) can degrade the extracellular matrix and participate in tumor progression. The relationship between MMP-9 and immune cells has been reported in various malignant tumors. However, there is a lack of comprehensive pan-cancer studies on the relationship between MMP-9 and cancer prognosis and immune infiltration. METHOD: We used data from TCGA and GTEx databases to comprehensively analyze the differential expression of MMP-9 in normal and cancerous tissues. Survival analysis was performed to understand the prognostic role of MMP-9 in different tumors. We then analyzed the expression of MMP-9 across different tumors and at different clinical stages. Based on the results, we assessed the correlation between MMP-9 expression and immune-associated genes and immunocytes. Finally, we calculated the tumor mutation burden (TMB) of 33 cancer types and analyzed the correlation between MMP-9 and TMB, DNA microsatellite instability, and DNA repair genes. RESULTS: MMP-9 significantly affected the prognosis and metastasis of various cancers. It was associated based on overall survival, disease-specific survival in five tumors, progression-free interval in seven tumors, and clinical stage in eight tumors, as well as with prognosis and metastasis in adrenocortical carcinoma and kidney renal clear cell carcinoma. It was also coexpressed with immune-related genes and DNA repair genes. The expression of MMP-9 was positively correlated with the markers of T cells, tumor-associated macrophages, Th1 cells, and T cell exhaustion. Furthermore, MMP-9 expression was highly correlated with macrophage M0 in 28 tumors. In addition, its expression was associated with TMB in eight cancer types and DNA microsatellite instability in six cancer types. CONCLUSION: MMP-9 is related to immune infiltration in pan-cancer and can be used as a biomarker related to cancer prognosis and metastasis. Our findings provide prognostic molecular markers and new ideas for immunotherapy.