A new hematological parameter model for the diagnosis and prognosis of sepsis in emergency department: A single-center retrospective study.

INTRODUCTION: Sepsis, a syndrome of organ dysfunction caused by an unregulated host response to infection. This study aimed to develop a novel sepsis diagnostic model of hematological parameters and evaluate its effectiveness in the early identification and prognosis of sepsis in emergency departments. METHODS: A retrospective study was conducted in Emergency Department. Cell population data parameters related to monocytes and neutrophils were obtained using the Mindary BC-6800 plus hematology analyzer. Receiver operating characteristic (ROC) curve analysis, logistic regression analysis was performed to assess the performance of the parameters and establish a diagnostic and prognostic model of sepsis, which was then verified with a validation cohort. RESULTS: Mon_XW exhibited the best diagnostic performance (area under the ROC curve [AUC] = 0.848, 95% confidence interval [CI]: 0.810-0.885, p < 0.001), followed by Neu_Y and Neu_YW (AUC = 0.777 95% CI: 0.730-0.824, p < 0.001). Logistic regression analysis identified Mon_XW and Neu_Y as independent predictors, which were used to establish a diagnostic model named hematological parameter for sepsis (HPS). HPS demonstrated the best diagnostic performance with an AUC of 0.862 (95% CI: 0.826-0.898, p < 0.001), sensitivity of 70.0%, and specificity of 87.1%, compared to C-reactive protein (CRP) and procalcitonin (PCT). The validation cohort also found that the positive predictive value of HPS was 70.4% and the negative predictive value was 92.2%. CONCLUSION: The developed HPS model showed promising diagnostic efficacy for sepsis in the emergency department, which outperformed CRP and PCT in terms of sensitivity and specificity. By enabling early identification and prognosis of sepsis, that contributes to reducing sepsis-related mortality.

MHAM-NPI: Predicting ncRNA-protein interactions based on multi-head attention mechanism.

Non-coding RNA (ncRNA) is a functional RNA molecule that plays a key role in various fundamental biological processes, such as gene regulation. Therefore, studying the connection between ncRNA and proteins holds significant importance in exploring the function of ncRNA. Although many efficient and accurate methods have been developed by modern biological scientists, accurate predictions still pose a major challenge for various issues. In our approach, we utilize a multi-head attention mechanism to merge residual connections, allowing for the automatic learning of ncRNA and protein sequence features. Specifically, the proposed method projects node features into multiple spaces based on multi-head attention mechanism, thereby obtaining different feature interaction patterns in these spaces. By stacking interaction layers, higher-order interaction modes can be derived, while still preserving the initial feature information through the residual connection. This strategy effectively leverages the sequence information of ncRNA and protein, enabling the capture of hidden high-order features. The final experimental results demonstrate the effectiveness of our method, with AUC values of 97.4%, 98.5%, and 94.8% achieved on the NPInter v2.0, RPI807, and RPI488 datasets, respectively. These impressive results solidify our method as a powerful tool for exploring the connection between ncRNAs and proteins. We have uploaded the implementation code on GitHub: https://github.com/ZZCrazy00/MHAM-NPI.

HeadTailTransfer: An efficient sampling method to improve the performance of graph neural network method in predicting sparse ncRNA-protein interactions.

Noncoding RNA (ncRNA) is a functional RNA derived from DNA transcription, and most transcribed genes are transcribed into ncRNA. ncRNA is not directly involved in the translation of proteins, but it can participate in gene expression in cells and affect protein synthesis, thus playing an important role in biological processes such as growth, proliferation, metabolism, and information transmission. Therefore, understanding the interaction between ncRNA and protein is the basis for studying ncRNA regulation of protein-related biological activities. However, it is very expensive and time-consuming to verify ncRNA-protein interaction through biological experiments, and prediction methods based on machine learning have been developed rapidly. Recently, the graph neural network model (GNN) stands out for its excellent performance, but lacks a general framework for predicting ncRNA-protein interactions. We propose a GNN-based framework to predict ncRNA-protein interactions, which can utilize topological structure information to complete prediction tasks faster and more accurately. Meanwhile, for some smaller datasets, many ncRNA nodes lack neighbor information, resulting in lower prediction accuracy. For some larger datasets, the long-tail distribution causes the prediction of the tail nodes (sparse nodes linking few neighbors) to be affected. Therefore, we propose a new sampling method named HeadTailTransfer to mitigate these effects. Experimental results illustrate the effectiveness of this method. Especially for task-specific prediction on the RPI369 dataset in the Graphsage-based neural network framework, the AUC and ACC values increased from 56.8% and 52.2% to 80.2% and 71.8%, respectively. Our data and codes are available: https://github.com/kkkayle/HeadTailTransfer.

DPB-NBFnet: Using neural Bellman-Ford networks to predict DNA-protein binding.

DNA is a hereditary material that plays an essential role in micro-organisms and almost all other organisms. Meanwhile, proteins are a vital composition and principal undertaker of microbe movement. Therefore, studying the bindings between DNA and proteins is of high significance from the micro-biological point of view. In addition, the binding affinity prediction is beneficial for the study of drug design. However, existing experimental methods to identifying DNA-protein bindings are extremely expensive and time consuming. To solve this problem, many deep learning methods (including graph neural networks) have been developed to predict DNA-protein interactions. Our work possesses the same motivation and we put the latest Neural Bellman-Ford neural networks (NBFnets) into use to build pair representations of DNA and protein to predict the existence of DNA-protein binding (DPB). NBFnet is a graph neural network model that uses the Bellman-Ford algorithms to get pair representations and has been proven to have a state-of-the-art performance when used to solve the link prediction problem. After building the pair representations, we designed a feed-forward neural network structure and got a 2-D vector output as a predicted value of positive or negative samples. We conducted our experiments on 100 datasets from ENCODE datasets. Our experiments indicate that the performance of DPB-NBFnet is competitive when compared with the baseline models. We have also executed parameter tuning with different architectures to explore the structure of our framework.

A new haematological model for the diagnosis and prognosis of severe community-acquired pneumonia: a single-center retrospective study.

Background: Severe community-acquired pneumonia (sCAP) is a condition where infection-induced lung tissue inflammation intensifies to a certain stage, resulting in organ dysfunction and even life-threatening disease. When sCAP occurs, neutrophils and monocytes will be activated and released into the peripheral blood to kill bacteria. There are significant morphological changes in these activated neutrophils and monocytes. Haematological parameters can reflect these morphological changes, and indicate the occurrence of sCAP and the severity of infection. This study is designed to establish a new haematological model and explore its clinical value in the diagnosis and prognosis of sCAP. Methods: Patients who fulfilled the diagnostic criteria of common pneumonia (CP) and sCAP were enrolled in this study. Healthy body check-up patients were also enrolled as a control group. Characteristic information and 28-day survival of patients were recorded. Haematological results, C-reactive protein (CRP) and procalcitonin (PCT) were calculated by BC-6800 Plus automated haematology analyser and cobas E601 automated biochemical immunoassay analyser. Results: A total of 100 check-ups patients, 100 CP patients, and 111 sCAP patients were enrolled in this study. The new haematological model WBC & Mon-XW, combining WBC (white blood cell count) and Mon-XW (monocytes complexity distribution width), was significantly elevated in the sCAP group and significantly higher than in the control group and the CP group. The new model had good diagnostic efficacy for sCAP, with an area under the receiver operating characteristic curve (ROC-AUC) of 0.842, which was higher than that of CRP (0.633) and PCT (0.750). Moreover, WBC & Mon-XW was effective for survival prognostic evaluations of sCAP, with an ROC-AUC of 0.748. The new model was the independent predictors for the death of pneumonia with an OR (odds ratio) value of 1.82. The 28-day mortality rate was approximately 40% in the WBC & Mon-XW ≥8.9 group, which was approximately 15% higher than that in the WBC & Mon-XW <8.9 group. Conclusions: The new haematological model can be used as an indicator for sCAP diagnosis and prognosis.

Predicting miRNA-lncRNA interactions on plant datasets based on bipartite network embedding method.

The research of miRNA-lncRNA interactions (MLIs) has received great attention recently due to their vital roles in microbiology and profound significance in diseases. Currently, many related studies mainly focus on animals and the link prediction problem on plants is rarely discussed comprehensively. Motivated by this, we achieve link prediction task based on the concept of bipartite graph and verify encouraging performance of our conclusions by conducting experiments on plant datasets. In this work, we firstly extract attribute information and structure information as base features and further process these information for network embedding. Intra-partition and inter-partition proximity modelling are conducted to construct the loss function, which facilitates the training of parameters. Finally, the superiority of our presented approach is shown by carrying out experiments on four plant datasets, which reflects the significance of this work to the research of microbiology and disease.

The clinical value of hematological neutrophil and monocyte parameters in the diagnosis and identification of sepsis.

BACKGROUND: Sepsis is a life-threatening condition of organ dysfunction caused by the host's disordered immune response to infection. It has a high fatality rate and seriously endangers human health. Rapid and accurate treatment plays an important role in the reduction of septic mortality. This study aimed to investigate the clinical value of hematological parameters neutrophil (NEU)-X, NEU-Y, monocyte (MON)-X, and MON-Y in sepsis, and compare their values with that of with C-reactive protein (CRP). METHODS: We collected dipotassium ethylenediaminetetraacetic acid (EDTA-K2) anticoagulant blood samples from a total of 267 patients with positive bacterial culture and 260 healthy physical check-up patients. Participants were divided into three groups: a normal control group (n=260), bacterial infection group (n=196), and a sepsis group (n=71). RESULTS: Median values of NEU-X, NEU-Y, MON-X, MON-Y, and CRP in the sepsis group were significantly higher than those in the control group and the bacterial infection group (P<0.0001). The area under the receiver operating characteristic curve (AUC) of NEU-X, NEU-Y, MON-X, MON-Y, and CRP for the diagnosis of sepsis was 0.751 (sensitivity 76.1%, specificity 58.2%), 0.877 (87.3%, 72.1%), 0.791 (77.6%, 65.9%), 0.695 (71.6%, 51.4%), and 0.790 (72.5%, 70.2%), respectively. In addition, blood smear examination results showed that NEU-X value was positively correlated with the degree of toxic granulation in neutrophils. CONCLUSIONS: The parameters NEU-X, NEU-Y, and MON-X can be used as indicators for the differential diagnosis of sepsis with comparable diagnostic efficacy to CRP. Compared to CRP, these hematological parameters are easier to obtain, more convenient, and have economic benefits.

Lymphocyte percentage and hemoglobin as a joint parameter for the prediction of severe and nonsevere COVID-19: a preliminary study.

BACKGROUND: Coronavirus disease 2019 (COVID-19) has spread rapidly around the world since December, 2019. This study aimed to identify parameters in routine blood tests that could be used to evaluate the severity of coronavirus disease 2019 (COVID-19) and, thus, assist with the clinical prediction of the extent of progression. METHODS: This retrospective study analyzed the epidemiological, clinical symptom, and laboratory examination data of 159 patients diagnosed with COVID-19. The percentage of lymphocytes (Lym%) and hemoglobin (HGB) were integrated into a joint parameter, Lym% & HGB, through binary logistic regression. RESULTS: Individually, Lym% and HGB decreased gradually with disease progression whereas the joint parameter Lym% & HGB increased gradually with disease progression. When Lym%, HGB, and Lym% & HGB were used to predict the severity of COVID-19, the area under the receiver operating characteristic (ROC) curve (AUC) was 0.89, 0.79, and 0.92, respectively. The dynamic change curves showed that Lym% and HGB continued to decline while Lym% & HGB continued to increase with disease progression in patients with severe COVID. The change in Lym% & HGB was more prominent than those in Lym% and HBG. CONCLUSIONS: The joint parameter Lym% & HGB could serve as an effective tool for differentiating severe and nonsevere COVID-19, and its sensitivity and specificity are higher than those of Lym% or HGB alone.

Clinical and hematological characteristics of 88 patients with COVID-19.

INTRODUCTION: To retrospectively analyze epidemiological, clinical and hematological characteristics of COVID-19 patients. METHODS: The demographic, symptoms, and physiological parameters of 88 patients were collected and analyzed. The performance of complete blood count (CBC) indexes for monitoring and predicting the severity of COVID-19 in patients was evaluated by analyzing and comparing CBC results among different COVID-19 patient groups. RESULTS: White blood cells (WBCs), the neutrophil percentage (Neu%), absolute neutrophil count (Neu#), and neutrophil-to-lymphocyte ratio (NLR) were significantly higher in the critical group than in the other three groups (P < .05), while the lymphocyte percentage (Lym%), monocyte percentage (Mon%), lymphocyte count (Lym#), and lymphocyte-to-monocyte ratio (LMR) were significantly lower in the critical group than in the other three groups (P < .05). WBCs, the Neu%, Neu#, NLR, and neutrophil-to-monocyte ratio (NMR) were significantly higher in the severe group than in the mild and moderate groups (P < .05), while the Lym% was significantly lower in the severe group than in the mild and moderate groups (P < .05). The Mon%, Lym#, and LMR were significantly lower in the severe group than in the moderate group (P < .05). Using receiver operating characteristic (ROC) curve analysis to differentiate severe and nonsevere patients, the areas under the curve (AUCs) for the NLR, Neu%, and Lym% were 0.733, 0.732, and 0.730, respectively. When differentiating critical patients from noncritical patients, the AUCs for the NLR, Neu%, and Lym% were 0.832, 0.831, and 0.831. CONCLUSIONS: The NLR is valuable for differentiating and predicting patients who will become critical within 4 weeks after the onset of COVID-19.