Identification of plant vacuole proteins by using graph neural network and contact maps.

Plant vacuoles are essential organelles in the growth and development of plants, and accurate identification of their proteins is crucial for understanding their biological properties. In this study, we developed a novel model called GraphIdn for the identification of plant vacuole proteins. The model uses SeqVec, a deep representation learning model, to initialize the amino acid sequence. We utilized the AlphaFold2 algorithm to obtain the structural information of corresponding plant vacuole proteins, and then fed the calculated contact maps into a graph convolutional neural network. GraphIdn achieved accuracy values of 88.51% and 89.93% in independent testing and fivefold cross-validation, respectively, outperforming previous state-of-the-art predictors. As far as we know, this is the first model to use predicted protein topology structure graphs to identify plant vacuole proteins. Furthermore, we assessed the effectiveness and generalization capability of our GraphIdn model by applying it to identify and locate peroxisomal proteins, which yielded promising outcomes. The source code and datasets can be accessed at https://github.com/SJNNNN/GraphIdn .

Evolution of Care and Outcomes Across Surges in Hospitalized Patients with Coronavirus Disease 2019.

BACKGROUND: The coronavirus disease 2019 (COVID-19) pandemic has unfolded in distinct surges. Understanding how surges differ may reveal important insights into the evolution of the pandemic and improve patient care. METHODS: We leveraged the Michigan Medicine COVID-19 Cohort, a prospective observational study at an academic tertiary medical center that systematically enrolled 2309 consecutive patients hospitalized for COVID-19, comprising 5 distinct surges. RESULTS: As the pandemic evolved, patients hospitalized for COVID-19 tended to have a lower burden of comorbidities and a lower inflammatory burden as measured by admission levels of C-reactive protein, ferritin, lactate dehydrogenase, and D-dimer. Use of hydroxychloroquine and azithromycin decreased substantially after Surge 1, while use of corticosteroids and remdesivir markedly increased (P < .001 for all). In-hospital mortality significantly decreased from 18.3% in Surge 1 to 5.3% in Surge 5 (P < .001). The need for mechanical ventilation significantly decreased from 42.5% in Surge 1 to 7.0% in Surge 5 (P < .001), while the need for renal replacement therapy decreased from 14.4% in Surge 1 to 2.3% in Surge 5 (P < .001). Differences in patient characteristics, treatments, and inflammatory markers accounted only partially for the differences in outcomes between surges. CONCLUSIONS: The COVID-19 pandemic has evolved significantly with respect to hospitalized patient populations and therapeutic approaches, and clinical outcomes have substantially improved. Hospitalization after the first surge was independently associated with improved outcomes, even after controlling for relevant clinical covariates.

ProSE-Pero: Peroxisomal Protein Localization Identification Model Based on Self-Supervised Multi-Task Language Pre-Training Model.

BACKGROUND: Peroxisomes are membrane-bound organelles that contain one or more types of oxidative enzymes. Aberrant localization of peroxisomal proteins can contribute to the development of various diseases. To more accurately identify and locate peroxisomal proteins, we developed the ProSE-Pero model. METHODS: We employed three methods based on deep representation learning models to extract the characteristics of peroxisomal proteins and compared their performance. Furthermore, we used the SVMSMOTE balanced dataset, SHAP interpretation model, variance analysis (ANOVA), and light gradient boosting machine (LightGBM) to select and compare the extracted features. We also constructed several traditional machine learning methods and four deep learning models to train and test our model on a dataset of 160 peroxisomal proteins using tenfold cross-validation. RESULTS: Our proposed ProSE-Pero model achieves high performance with a specificity (Sp) of 93.37%, a sensitivity (Sn) of 82.41%, an accuracy (Acc) of 95.77%, a Matthews correlation coefficient (MCC) of 0.8241, an F1 score of 0.8996, and an area under the curve (AUC) of 0.9818. Additionally, we extended our method to identify plant vacuole proteins and achieved an accuracy of 91.90% on the independent test set, which is approximately 5% higher than the latest iPVP-DRLF model. CONCLUSIONS: Our model surpasses the existing In-Pero model in terms of peroxisomal protein localization and identification. Additionally, our study showcases the proficient performance of the pre-trained multitasking language model ProSE in extracting features from protein sequences. With its established validity and broad generalization, our model holds considerable potential for expanding its application to the localization and identification of proteins in other organelles, such as mitochondria and Golgi proteins, in future investigations.

Disease-related compound identification based on deeping learning method.

Acute lung injury (ALI) is a serious respiratory disease, which can lead to acute respiratory failure or death. It is closely related to the pathogenesis of New Coronavirus pneumonia (COVID-19). Many researches showed that traditional Chinese medicine (TCM) had a good effect on its intervention, and network pharmacology could play a very important role. In order to construct "disease-gene-target-drug" interaction network more accurately, deep learning algorithm is utilized in this paper. Two ALI-related target genes (REAL and SATA3) are considered, and the active and inactive compounds of the two corresponding target genes are collected as training data, respectively. Molecular descriptors and molecular fingerprints are utilized to characterize each compound. Forest graph embedded deep feed forward network (forgeNet) is proposed to train. The experimental results show that forgeNet performs better than support vector machines (SVM), random forest (RF), logical regression (LR), Naive Bayes (NB), XGBoost, LightGBM and gcForest. forgeNet could identify 19 compounds in Erhuang decoction (EhD) and Dexamethasone (DXMS) more accurately.

Immobilized Lipase in the Synthesis of High Purity Medium Chain Diacylglycerols Using a Bubble Column Reactor: Characterization and Application.

Novozym® 435, an immobilized lipase from Candida antarctica B. (CALB), was used as a biocatalyst for the synthesis of high purity medium chain diacylglycerol (MCD) in a bubble column reactor. In this work, the properties of the MCD produced were characterized followed by determining its practical application as an emulsifier in water-in-oil (W/O) emulsion. Two types of MCDs, namely, dicaprylin (C8-DAG) and dicaprin (C10-DAG), were prepared through enzymatic esterification using the following conditions: 5% Novozym® 435, 2.5% deionized water, 60°C for 30 min followed by purification. A single-step molecular distillation (MD) (100-140°C, 0.1 Pa, 300 rpm) was performed and comparison was made to that of a double-step purification with MD followed by silica gel column chromatography technique (MD + SGCC). Crude C8-DAG and C10-DAG with DAG concentration of 41 and 44%, respectively, were obtained via the immobilized enzyme catalyzing reaction. Post-purification via MD, the concentrations of C8-DAG and C10-DAG were increased to 80 and 83%, respectively. Both MCDs had purity of 99% after the MD + SGCC purification step. Although Novozym® 435 is a non-specific lipase, higher ratios of 1,3-DAG to 1,2-DAG were acquired. Via MD, the ratios of 1,3-DAG to 1,2-DAG in C8-DAG and C10-DAG were 5.8:1 and 7.3:1, respectively. MCDs that were purified using MD + SGCC were found to contain 1,3-DAG to 1,2-DAG ratios of 8.8:1 and 9.8:1 in C8-DAG and C10-DAG, respectively. The crystallization and melting peaks were shifted to higher temperature regions as the purity of the MCD was increased. Dense needle-like crystals were observed in MCDs with high purities. Addition of 5% C8-DAG and C10-DAG as emulsifier together in the presence of 9% of hydrogenated soybean oil produced stable W/O emulsion with particle size of 18 and 10 µm, respectively.