Inferring gene regulatory networks from single-cell transcriptomics based on graph embedding.

MOTIVATION: Gene regulatory networks (GRNs) encode gene regulation in living organisms, and have become a critical tool to understand complex biological processes. However, due to the dynamic and complex nature of gene regulation, inferring GRNs from scRNA-seq data is still a challenging task. Existing computational methods usually focus on the close connections between genes, and ignore the global structure and distal regulatory relationships. RESULTS: In this study, we develop a supervised deep learning framework, IGEGRNS, to infer GRNs from scRNA-seq data based on graph embedding. In the framework, contextual information of genes is captured by GraphSAGE, which aggregates gene features and neighborhood structures to generate low-dimensional embedding for genes. Then, the k most influential nodes in the whole graph are filtered through Top-k pooling. Finally, potential regulatory relationships between genes are predicted by stacking CNNs. Compared with nine competing supervised and unsupervised methods, our method achieves better performance on six time-series scRNA-seq datasets. AVAILABILITY AND IMPLEMENTATION: Our method IGEGRNS is implemented in Python using the Pytorch machine learning library, and it is freely available at https://github.com/DHUDBlab/IGEGRNS.

DMFDDI: deep multimodal fusion for drug-drug interaction prediction.

Drug combination therapy has gradually become a promising treatment strategy for complex or co-existing diseases. As drug-drug interactions (DDIs) may cause unexpected adverse drug reactions, DDI prediction is an important task in pharmacology and clinical applications. Recently, researchers have proposed several deep learning methods to predict DDIs. However, these methods mainly exploit the chemical or biological features of drugs, which is insufficient and limits the performances of DDI prediction. Here, we propose a new deep multimodal feature fusion framework for DDI prediction, DMFDDI, which fuses drug molecular graph, DDI network and the biochemical similarity features of drugs to predict DDIs. To fully extract drug molecular structure, we introduce an attention-gated graph neural network for capturing the global features of the molecular graph and the local features of each atom. A sparse graph convolution network is introduced to learn the topological structure information of the DDI network. In the multimodal feature fusion module, an attention mechanism is used to efficiently fuse different features. To validate the performance of DMFDDI, we compare it with 10 state-of-the-art methods. The comparison results demonstrate that DMFDDI achieves better performance in DDI prediction. Our method DMFDDI is implemented in Python using the Pytorch machine-learning library, and it is freely available at https://github.com/DHUDEBLab/DMFDDI.git.

Predicting synergistic anticancer drug combination based on low-rank global attention mechanism and bilinear predictor.

MOTIVATION: Drug combination therapy has exhibited remarkable therapeutic efficacy and has gradually become a promising clinical treatment strategy of complex diseases such as cancers. As the related databases keep expanding, computational methods based on deep learning model have become powerful tools to predict synergistic drug combinations. However, predicting effective synergistic drug combinations is still a challenge due to the high complexity of drug combinations, the lack of biological interpretability, and the large discrepancy in the response of drug combinations in vivo and in vitro biological systems. RESULTS: Here, we propose DGSSynADR, a new deep learning method based on global structured features of drugs and targets for predicting synergistic anticancer drug combinations. DGSSynADR constructs a heterogeneous graph by integrating the drug-drug, drug-target, protein-protein interactions and multi-omics data, utilizes a low-rank global attention (LRGA) model to perform global weighted aggregation of graph nodes and learn the global structured features of drugs and targets, and then feeds the embedded features into a bilinear predictor to predict the synergy scores of drug combinations in different cancer cell lines. Specifically, LRGA network brings better model generalization ability, and effectively reduces the complexity of graph computation. The bilinear predictor facilitates the dimension transformation of the features and fuses the feature representation of the two drugs to improve the prediction performance. The loss function Smooth L1 effectively avoids gradient explosion, contributing to better model convergence. To validate the performance of DGSSynADR, we compare it with seven competitive methods. The comparison results demonstrate that DGSSynADR achieves better performance. Meanwhile, the prediction of DGSSynADR is validated by previous findings in case studies. Furthermore, detailed ablation studies indicate that the one-hot coding drug feature, LRGA model and bilinear predictor play a key role in improving the prediction performance. AVAILABILITY AND IMPLEMENTATION: DGSSynADR is implemented in Python using the Pytorch machine-learning library, and it is freely available at https://github.com/DHUDBlab/DGSSynADR.

Tocilizumab attenuates acute lung injury in rats with sepsis by regulating S100A12/NLRP3.

OBJECTIVE: To investigate the mechanism of Tocilizumab (TCZ) in attenuating acute lung injury in rats with sepsis by regulating the S100A12/NLRP3 axis. METHODS: A rat model of sepsis was constructed using cecal ligation and puncture (CLP). Rats were treated with TCZ, and their lung tissue was collected. H&E staining was used to detect pathologic damage to lung tissue, and lung wet/dry (W/D) weight ratio was measured to assess pulmonary edema. Lipid oxidation assay and superoxide dismutase (SOD) activity assay kits were used to measure malondialdehyde (MDA) and SOD levels. Primary rat pulmonary microvascular endothelial cells (MPVECs) were treated with lipopolysaccharide (LPS) to construct a rat model of sepsis, which was then treated with TCZ. The mRNA and protein expressions of S100A12/NLRP3 were detected by qRT-PCR and western blot, respectively. S100A12 knockdown and overexpression plasmids, and NLRP3 knockdown plasmids were constructed and transfected into sepsis cells to intervene in the levels of S100A12/NLRP3. The apoptosis rate was detected by apoptosis assay. The levels of IL-6, TNF-α, and IL-10 in cells and tissues were analyzed by ELISA. RESULTS: Compared to the Sham group, the CLP group had increased W/D weight ratio of lung tissue, IL-6, TNF-α, and MDA levels, lowered IL-10 and SOD levels, and more severe tissue damage (all P<0.05). After TCZ treatment, the above indicators were improved. The expressions of S100A12/NLRP3 cells were increased in LPS-induced MPVECs, but decreased after TCZ treatment. LPS induced apoptosis, but TCZ reduced the apoptosis, weakened the secretion levels of IL-6 and TNF-α, and enhanced IL-10 secretion levels. Transfection to cause the overexpression of S100A12 or NLRP3 plasmid partially counteracted the effect of TCZ. Knockdown of S100A12 was transfected on the basis of overexpression of NLRP3, which weakened the countervailing effect of overexpressed NLRP3 on TCZ. CONCLUSION: TCZ has a therapeutic effect on lung injury in rats with sepsis by reducing the expressions of S100A12/NLRP3.

Inferring Gene Regulatory Networks From Single-Cell Transcriptomic Data Using Bidirectional RNN.

Accurate inference of gene regulatory rules is critical to understanding cellular processes. Existing computational methods usually decompose the inference of gene regulatory networks (GRNs) into multiple subproblems, rather than detecting potential causal relationships simultaneously, which limits the application to data with a small number of genes. Here, we propose BiRGRN, a novel computational algorithm for inferring GRNs from time-series single-cell RNA-seq (scRNA-seq) data. BiRGRN utilizes a bidirectional recurrent neural network to infer GRNs. The recurrent neural network is a complex deep neural network that can capture complex, non-linear, and dynamic relationships among variables. It maps neurons to genes, and maps the connections between neural network layers to the regulatory relationship between genes, providing an intuitive solution to model GRNs with biological closeness and mathematical flexibility. Based on the deep network, we transform the inference of GRNs into a regression problem, using the gene expression data at previous time points to predict the gene expression data at the later time point. Furthermore, we adopt two strategies to improve the accuracy and stability of the algorithm. Specifically, we utilize a bidirectional structure to integrate the forward and reverse inference results and exploit an incomplete set of prior knowledge to filter out some candidate inferences of low confidence. BiRGRN is applied to four simulated datasets and three real scRNA-seq datasets to verify the proposed method. We perform comprehensive comparisons between our proposed method with other state-of-the-art techniques. These experimental results indicate that BiRGRN is capable of inferring GRN simultaneously from time-series scRNA-seq data. Our method BiRGRN is implemented in Python using the TensorFlow machine-learning library, and it is freely available at https://gitee.com/DHUDBLab/bi-rgrn.

A 3D multiscale view convolutional neural network with attention for mental disease diagnosis on MRI images.

Computer Assisted Diagnosis (CAD) based on brain Magnetic Resonance Imaging (MRI) is a popular research field for the computer science and medical engineering. Traditional machine learning and deep learning methods were employed in the classification of brain MRI images in the previous studies. However, the current algorithms rarely take into consideration the influence of multi-scale brain connectivity disorders on some mental diseases. To improve this defect, a deep learning structure was proposed based on MRI images, which was designed to consider the brain's connections at different sizes and the attention of connections. In this work, a Multiscale View (MV) module was proposed, which was designed to detect multi-scale brain network disorders. On the basis of the MV module, the path attention module was also proposed to simulate the attention selection of the parallel paths in the MV module. Based on the two modules, we proposed a 3D Multiscale View Convolutional Neural Network with Attention (3D MVA-CNN) for classification of MRI images for mental disease. The proposed method outperformed the previous 3D CNN structures in the structural MRI data of ADHD-200 and the functional MRI data of schizophrenia. Finally, we also proposed a preliminary framework for clinical application using 3D CNN, and discussed its limitations on data accessing and reliability. This work promoted the assisted diagnosis of mental diseases based on deep learning and provided a novel 3D CNN method based on MRI data.

Effects of emergency treatment mode of damage-control orthopedics in pelvic fracture complicated with multiple fractures.

OBJECTIVE: This study aimed to observe the application effect of emergency treatment mode of damage-control orthopedics (DCO) in pelvic fracture complicated with multiple fractures. METHODS: Ninety-four patients with pelvic fracture complicated with multiple fractures in our hospital were recruited and divided into two groups according to the random number table method, with 47 cases in each group. Patients in the control group received traditional methods for emergency treatment (early complete treatment), and patients in the research group received DCO for emergency treatment (treatment performed in stages according to patient's physiological tolerance, with simplified initial surgery, followed by ICU resuscitation, and finally definitive surgery). The two groups were compared in terms of mortality, the incidence of acidosis and hypothermia three days after the first surgery, surgery-related indexes (time of the first surgery, blood transfusion volume, intraoperative blood loss, recovery time of temperature, and length of hospital stay), coagulation function indexes (activated partial thromboplastin time (APTT), thrombin time (TT), prothrombin time (PT) and fibrinogen (FIB)), postoperative reduction of fracture, complication rate, and quality of life. RESULTS: The incidences of acidosis, hypothermia, and mortality three days after the first surgery in the research group were lower than those in the control group (P<0.05). Compared with the control group, the research group experienced shorter time of the first surgery, less intraoperative blood transfusion volume, less intraoperative blood loss, shorter recovery time of body temperature, and shorter length of hospital stay (P<0.05). Seven days after surgery, PT, TT and APTT decreased and FIB increased in both groups (P<0.05), PT, TT and APTT in the research group were lower than those in the control group (P<0.05), while FIB was higher (P<0.05). The good rate of reduction in the research group was higher than that in the control group (P=0.025). The incidence of complications in the research group was lower than that in the control group (P=0.049). Six months after surgery, the scores of physiological function (PF), body pain (BP), role physical (RP), emotional function (EF), social function (SF), vitality, and general health (GH) of the research group were higher than those of the control group (P<0.05), but there was no significant difference in mental health (MH) between the two groups (P>0.05). CONCLUSION: The emergency treatment mode of DCO is effective in pelvic fracture complicated with multiple fractures, which can effectively improve postoperative reduction of patients, improve the coagulation function, reduce complications, and improve the quality of life.

microRNA-98 protects sepsis mice from cardiac dysfunction, liver and lung injury by negatively regulating HMGA2 through inhibiting NF-κB signaling pathway.

Recently, MicroRNA-98 (miR-98) works as a biomarker in some diseases, such as lung cancer, Schizophrenia, and breast cancer, but there still lack of studies on the function of miR-98 during sepsis. Thus, our study is conducted to figure out the function of miR-98 for the regulation of cardiac dysfunction, liver and lung injury in sepsis mice. Cecum ligation and puncture was used to establish the sepsis mice model. Next, miR-Con and agomiR-98 were injected into the tail vein of mice 48 h after modeling. Then, expression of miR-98, HMGA2, NF-κB, inflammatory factors, apoptosis-related proteins in myocardial, liver and lung tissues of septic mice were determined. Moreover, other indices that were associated with cardiac dysfunction, liver and lung injury in septic mice were detected. Finally, bioinformatics analysis and luciferase activity assay were utilized to validate the binding site between miR-98 and HMGA2. miR-98 was poorly expressed, while HMGA2, NF-κB pathway-related proteins were highly expressed in myocardial, liver, and lung tissues of mice with sepsis. Upregulated miR-98 inhibited HMGA2, NF-κB, TNF-α, IL-6, Bcl-2 and increased IL-10, Cleaved caspase-3 and Bax expression in myocardial, liver, and lung tissues of septic mice. Upregulation of miR-98 decreased LVEDP, CTn-I, BNP, ALT, AST, TBIL, LDH, and PaCO2 while increased +dp/dt max, -dp/dt max, pH and PaO2 in sepsis mice. miR-98 was a direct target gene of HMGA2. Our study provides evidence that miR-98 protects sepsis mice from cardiac dysfunction, liver and lung injury by negatively mediating HMGA2 via the inhibition of the NF-κB signaling pathway.

Efficient string similarity join in multi-core and distributed systems.

In big data area a significant challenge about string similarity join is to find all similar pairs more efficiently. In this paper, we propose a parallel processing framework for efficient string similarity join. First, the input is split into some disjoint small subsets according to the joint frequency distribution and the interval distribution of strings. Then the filter-verification strategy is adopted in the computation of string similarity for each subset so that the number of candidate pairs is reduced before an effective pruning strategy is used to improve the performance. Finally, the operation of string join is executed in parallel. Para-Join algorithm based on the multi-threading technique is proposed to implement the framework in a multi-core system while Pada-Join algorithm based on Spark platform is proposed to implement the framework in a cluster system. We prove that Para-Join and Pada-Join cannot only avoid reduplicate computation but also ensure the completeness of the result. Experimental results show that Para-Join can achieve high efficiency and significantly outperform than state-of-the-art approaches, meanwhile, Pada-Join can work on large datasets.

Dynamic epigenetic mode analysis using spatial temporal clustering.

BACKGROUND: Differentiation of human embryonic stem cells requires precise control of gene expression that depends on specific spatial and temporal epigenetic regulation. Recently available temporal epigenomic data derived from cellular differentiation processes provides an unprecedented opportunity for characterizing fundamental properties of epigenomic dynamics and revealing regulatory roles of epigenetic modifications. RESULTS: This paper presents a spatial temporal clustering approach, named STCluster, which exploits the temporal variation information of epigenomes to characterize dynamic epigenetic mode during cellular differentiation. This approach identifies significant spatial temporal patterns of epigenetic modifications along human embryonic stem cell differentiation and cluster regulatory sequences by their spatial temporal epigenetic patterns. CONCLUSIONS: The results show that this approach is effective in capturing epigenetic modification patterns associated with specific cell types. In addition, STCluster allows straightforward identification of coherent epigenetic modes in multiple cell types, indicating the ability in the establishment of the most conserved epigenetic signatures during cellular differentiation process.