Analyzing the molecular mechanism of xuefuzhuyu decoction in the treatment of pulmonary hypertension with network pharmacology and bioinformatics and verifying molecular docking.

BACKGROUND: XueFuZhuYu (XFZY), a typical Chinese herbal formula, has remarkable clinical effects for treating Pulmonary Hypertension (PH) with unclear mechanisms. Our research involved the utilization of network pharmacology to explore the traditional Chinese herbal monomers and their related targets within XFZY for PH treatment. Furthermore, molecular docking verification was performed. METHODS: The XFZY's primary active compounds, along with their corresponding targets, were both obtained from the TCMSP, ChEMBL, and UniProt databases. The target proteins relevant to PH were sifted through OMIM, GeneCards and TTD databases. The common "XFZY-PH" targets were evaluated with Disease Ontology (DO), Gene Ontology (GO), and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses with the assistance of R software. The Protein-Protein Interaction (PPI) network and compound-target-pathway network were constructed and a systematic analysis of network parameters was performed by the powerful software Cytoscape. Molecular docking was employed for assessing and verifying the interactions between the core targets and the top Chinese herbal monomer. RESULTS: The screening included 297 targets of active compounds in XFZY and 8400 PH-related targets. DO analysis of the above common 268 targets indicated that the treatment of the diseases by XFZY is mediated by genes related to Chronic Obstructive Pulmonary Disease (COPD), Obstructive Lung Disease (OLD), ischemia, and myocardial infarction. The findings from molecular docking indicated that the binding energies of 57 ligand-receptor pairs in PH and 20 ligand-receptor pairs in COPD-PH were lower than -7kJ•mol-1. CONCLUSIONS: This study indicates that XFZY is a promising option within traditional Chinese medicine compound preparation for combating PH, particularly in cases associated with COPD. Our demonstration of the specific molecular mechanism of XFZY anti-PH and its effective active ingredients provides a theoretical basis for better clinical application of the compound.

Developing Deep LSTMs With Later Temporal Attention for Predicting COVID-19 Severity, Clinical Outcome, and Antibody Level by Screening Serological Indicators Over Time.

OBJECTIVE: The clinical course of COVID-19, as well as the immunological reaction, is notable for its extreme variability. Identifying the main associated factors might help understand the disease progression and physiological status of COVID-19 patients. The dynamic changes of the antibody against Spike protein are crucial for understanding the immune response. This work explores a temporal attention (TA) mechanism of deep learning to predict COVID-19 disease severity, clinical outcomes, and Spike antibody levels by screening serological indicators over time. METHODS: We use feature selection techniques to filter feature subsets that are highly correlated with the target. The specific deep Long Short-Term Memory (LSTM) models are employed to capture the dynamic changes of disease severity, clinical outcome, and Spike antibody level. We also propose deep LSTMs with a TA mechanism to emphasize the later blood test records because later records often attract more attention from doctors. RESULTS: Risk factors highly correlated with COVID-19 are revealed. LSTM achieves the highest classification accuracy for disease severity prediction. Temporal Attention Long Short-Term Memory (TA-LSTM) achieves the best performance for clinical outcome prediction. For Spike antibody level prediction, LSTM achieves the best permanence. CONCLUSION: The experimental results demonstrate the effectiveness of the proposed models. The proposed models can provide a computer-aided medical diagnostics system by simply using time series of serological indicators.