Motif-Aware miRNA-Disease Association Prediction Via Hierarchical Attention Network.

As post-transcriptional regulators of gene expression, micro-ribonucleic acids (miRNAs) are regarded as potential biomarkers for a variety of diseases. Hence, the prediction of miRNA-disease associations (MDAs) is of great significance for an in-depth understanding of disease pathogenesis and progression. Existing prediction models are mainly concentrated on incorporating different sources of biological information to perform the MDA prediction task while failing to consider the fully potential utility of MDA network information at the motif-level. To overcome this problem, we propose a novel motif-aware MDA prediction model, namely MotifMDA, by fusing a variety of high- and low-order structural information. In particular, we first design several motifs of interest considering their ability to characterize how miRNAs are associated with diseases through different network structural patterns. Then, MotifMDA adopts a two-layer hierarchical attention to identify novel MDAs. Specifically, the first attention layer learns high-order motif preferences based on their occurrences in the given MDA network, while the second one learns the final embeddings of miRNAs and diseases through coupling high- and low-order preferences. Experimental results on two benchmark datasets have demonstrated the superior performance of MotifMDA over several state-of-the-art prediction models. This strongly indicates that accurate MDA prediction can be achieved by relying solely on MDA network information. Furthermore, our case studies indicate that the incorporation of motif-level structure information allows MotifMDA to discover novel MDAs from different perspectives. The data and codes are available at https://github.com/stevejobws/MotifMDA.

Biolinguistic graph fusion model for circRNA-miRNA association prediction.

Emerging clinical evidence suggests that sophisticated associations with circular ribonucleic acids (RNAs) (circRNAs) and microRNAs (miRNAs) are a critical regulatory factor of various pathological processes and play a critical role in most intricate human diseases. Nonetheless, the above correlations via wet experiments are error-prone and labor-intensive, and the underlying novel circRNA-miRNA association (CMA) has been validated by numerous existing computational methods that rely only on single correlation data. Considering the inadequacy of existing machine learning models, we propose a new model named BGF-CMAP, which combines the gradient boosting decision tree with natural language processing and graph embedding methods to infer associations between circRNAs and miRNAs. Specifically, BGF-CMAP extracts sequence attribute features and interaction behavior features by Word2vec and two homogeneous graph embedding algorithms, large-scale information network embedding and graph factorization, respectively. Multitudinous comprehensive experimental analysis revealed that BGF-CMAP successfully predicted the complex relationship between circRNAs and miRNAs with an accuracy of 82.90% and an area under receiver operating characteristic of 0.9075. Furthermore, 23 of the top 30 miRNA-associated circRNAs of the studies on data were confirmed in relevant experiences, showing that the BGF-CMAP model is superior to others. BGF-CMAP can serve as a helpful model to provide a scientific theoretical basis for the study of CMA prediction.

Likelihood-based feature representation learning combined with neighborhood information for predicting circRNA-miRNA associations.

Connections between circular RNAs (circRNAs) and microRNAs (miRNAs) assume a pivotal position in the onset, evolution, diagnosis and treatment of diseases and tumors. Selecting the most potential circRNA-related miRNAs and taking advantage of them as the biological markers or drug targets could be conducive to dealing with complex human diseases through preventive strategies, diagnostic procedures and therapeutic approaches. Compared to traditional biological experiments, leveraging computational models to integrate diverse biological data in order to infer potential associations proves to be a more efficient and cost-effective approach. This paper developed a model of Convolutional Autoencoder for CircRNA-MiRNA Associations (CA-CMA) prediction. Initially, this model merged the natural language characteristics of the circRNA and miRNA sequence with the features of circRNA-miRNA interactions. Subsequently, it utilized all circRNA-miRNA pairs to construct a molecular association network, which was then fine-tuned by labeled samples to optimize the network parameters. Finally, the prediction outcome is obtained by utilizing the deep neural networks classifier. This model innovatively combines the likelihood objective that preserves the neighborhood through optimization, to learn the continuous feature representation of words and preserve the spatial information of two-dimensional signals. During the process of 5-fold cross-validation, CA-CMA exhibited exceptional performance compared to numerous prior computational approaches, as evidenced by its mean area under the receiver operating characteristic curve of 0.9138 and a minimal SD of 0.0024. Furthermore, recent literature has confirmed the accuracy of 25 out of the top 30 circRNA-miRNA pairs identified with the highest CA-CMA scores during case studies. The results of these experiments highlight the robustness and versatility of our model.

Discovering Consensus Regions for Interpretable Identification of RNA N6-Methyladenosine Modification Sites via Graph Contrastive Clustering.

As a pivotal post-transcriptional modification of RNA, N6-methyladenosine (m6A) has a substantial influence on gene expression modulation and cellular fate determination. Although a variety of computational models have been developed to accurately identify potential m6A modification sites, few of them are capable of interpreting the identification process with insights gained from consensus knowledge. To overcome this problem, we propose a deep learning model, namely M6A-DCR, by discovering consensus regions for interpretable identification of m6A modification sites. In particular, M6A-DCR first constructs an instance graph for each RNA sequence by integrating specific positions and types of nucleotides. The discovery of consensus regions is then formulated as a graph clustering problem in light of aggregating all instance graphs. After that, M6A-DCR adopts a motif-aware graph reconstruction optimization process to learn high-quality embeddings of input RNA sequences, thus achieving the identification of m6A modification sites in an end-to-end manner. Experimental results demonstrate the superior performance of M6A-DCR by comparing it with several state-of-the-art identification models. The consideration of consensus regions empowers our model to make interpretable predictions at the motif level. The analysis of cross validation through different species and tissues further verifies the consistency between the identification results of M6A-DCR and the evolutionary relationships among species.

Exploring the potential of a novel alternating current stimulated iron­carbon anammox process: A new horizon for nitrogen removal.

This study explored a novel alternating current (AC) stimulation approach to enhance the nitrogen removal efficiency of an iron­carbon based anammox (FeC anammox) system. In the preliminary experiment, the TN removal efficiency of the AC stimulated system was 8.06 % higher than that of a DC simulated system in same current densities of 0.25 mA/cm2. Gene expression analysis revealed that the AC-stimulated system, where, compared with the anammox system alone, the expression of HZS, HDH, NarG, NirS, NorB and NosZ increased by 1.81, 2.50, 1.64, 0.23, 1.15 and 1.27 times, respectively. In the continuous experiment, the TN removal rate increased from 60.13 % to 84.34 % after AC stimulation, and the working time of the FeC materials increased to 20 days. An analysis of the mechanism revealed that the parallel connection between the capacitive reactance and filler resistance in AC might reduce the internal resistance of the system, thereby improving the actual current density received by local microorganisms, and achieving a better strengthening effect.

Drug-disease association prediction using semantic graph and function similarity representation learning over heterogeneous information networks.

Discovering new indications for existing drugs is a promising development strategy at various stages of drug research and development. However, most of them complete their tasks by constructing a variety of heterogeneous networks without considering available higher-order connectivity patterns in heterogeneous biological information networks, which are believed to be useful for improving the accuracy of new drug discovering. To this end, we propose a computational-based model, called SFRLDDA, for drug-disease association prediction by using semantic graph and function similarity representation learning. Specifically, SFRLDDA first integrates a heterogeneous information network (HIN) by drug-disease, drug-protein, protein-disease associations, and their biological knowledge. Second, different representation learning strategies are applied to obtain the feature representations of drugs and diseases from different perspectives over semantic graph and function similarity graphs constructed, respectively. At last, a Random Forest classifier is incorporated by SFRLDDA to discover potential drug-disease associations (DDAs). Experimental results demonstrate that SFRLDDA yields a best performance when compared with other state-of-the-art models on three benchmark datasets. Moreover, case studies also indicate that the simultaneous consideration of semantic graph and function similarity of drugs and diseases in the HIN allows SFRLDDA to precisely predict DDAs in a more comprehensive manner.

Biocaiv: an integrative webserver for motif-based clustering analysis and interactive visualization of biological networks.

BACKGROUND: As an important task in bioinformatics, clustering analysis plays a critical role in understanding the functional mechanisms of many complex biological systems, which can be modeled as biological networks. The purpose of clustering analysis in biological networks is to identify functional modules of interest, but there is a lack of online clustering tools that visualize biological networks and provide in-depth biological analysis for discovered clusters. RESULTS: Here we present BioCAIV, a novel webserver dedicated to maximize its accessibility and applicability on the clustering analysis of biological networks. This, together with its user-friendly interface, assists biological researchers to perform an accurate clustering analysis for biological networks and identify functionally significant modules for further assessment. CONCLUSIONS: BioCAIV is an efficient clustering analysis webserver designed for a variety of biological networks. BioCAIV is freely available without registration requirements at http://bioinformatics.tianshanzw.cn:8888/BioCAIV/ .

iGRLDTI: an improved graph representation learning method for predicting drug-target interactions over heterogeneous biological information network.

MOTIVATION: The task of predicting drug-target interactions (DTIs) plays a significant role in facilitating the development of novel drug discovery. Compared with laboratory-based approaches, computational methods proposed for DTI prediction are preferred due to their high-efficiency and low-cost advantages. Recently, much attention has been attracted to apply different graph neural network (GNN) models to discover underlying DTIs from heterogeneous biological information network (HBIN). Although GNN-based prediction methods achieve better performance, they are prone to encounter the over-smoothing simulation when learning the latent representations of drugs and targets with their rich neighborhood information in HBIN, and thereby reduce the discriminative ability in DTI prediction. RESULTS: In this work, an improved graph representation learning method, namely iGRLDTI, is proposed to address the above issue by better capturing more discriminative representations of drugs and targets in a latent feature space. Specifically, iGRLDTI first constructs an HBIN by integrating the biological knowledge of drugs and targets with their interactions. After that, it adopts a node-dependent local smoothing strategy to adaptively decide the propagation depth of each biomolecule in HBIN, thus significantly alleviating over-smoothing by enhancing the discriminative ability of feature representations of drugs and targets. Finally, a Gradient Boosting Decision Tree classifier is used by iGRLDTI to predict novel DTIs. Experimental results demonstrate that iGRLDTI yields better performance that several state-of-the-art computational methods on the benchmark dataset. Besides, our case study indicates that iGRLDTI can successfully identify novel DTIs with more distinguishable features of drugs and targets. AVAILABILITY AND IMPLEMENTATION: Python codes and dataset are available at https://github.com/stevejobws/iGRLDTI/.

Ni-Catalyzed Protecting Group Free Diphenic Acid Analog Synthesis.

Severe side effects and drug resistance are major drawbacks of Pt-based chemotherapy in clinical practice, leading to the search for new Pt-based drugs through the tuning of coordination ligands. Therefore, seeking appropriate ligands has attracted significant interest in this area. In this study, we report a Ni-catalyzed coupling strategy for the divergent synthesis of diphenic acid derivatives and the application of these newly prepared acids in Pt(II) agent synthesis.

GraphCPIs: A novel graph-based computational model for potential compound-protein interactions.

Identifying proteins that interact with drug compounds has been recognized as an important part in the process of drug discovery. Despite extensive efforts that have been invested in predicting compound-protein interactions (CPIs), existing traditional methods still face several challenges. The computer-aided methods can identify high-quality CPI candidates instantaneously. In this research, a novel model is named GraphCPIs, proposed to improve the CPI prediction accuracy. First, we establish the adjacent matrix of entities connected to both drugs and proteins from the collected dataset. Then, the feature representation of nodes could be obtained by using the graph convolutional network and Grarep embedding model. Finally, an extreme gradient boosting (XGBoost) classifier is exploited to identify potential CPIs based on the stacked two kinds of features. The results demonstrate that GraphCPIs achieves the best performance, whose average predictive accuracy rate reaches 90.09%, average area under the receiver operating characteristic curve is 0.9572, and the average area under the precision and recall curve is 0.9621. Moreover, comparative experiments reveal that our method surpasses the state-of-the-art approaches in the field of accuracy and other indicators with the same experimental environment. We believe that the GraphCPIs model will provide valuable insight to discover novel candidate drug-related proteins.

Study on the feasibility of carbon source recovery by upflow anaerobic sludge blanket in simulated municipal wastewater.

The influence of hydraulic retention time (HRT) on the granulation process, methane-producing capacity, microbial community structure, and pollutant removal efficiency of an up-flow anaerobic sludge blanket (UASB) with simulated municipal wastewater at a mesophilic temperature was investigated. The carbon recovery capacity of the anaerobic fermentation of municipal wastewater at mesophilic temperatures is one of the problems to be investigated for the realisation of carbon neutrality in municipal wastewater treatment plants. In this study, the HRT was gradually shortened (24-6 h), and the effluent chemical oxygen demand (COD), ammonia nitrogen, pH, volatile fatty acid concentration, and specific methanogenic activity (SMA) were investigated. The sludge morphology, the particle size distribution of the different HRT, and changes in the microbial community structure were determined by scanning electron microscopy, wet screening, and high-throughput sequencing. The results indicated that even if the COD concentration was only 300-550 mg/L, with a decrease in HRT, the proportion of granular sludge in the UASB still exceeded 78 %, and the COD removal efficiency reached 82.4 %. The SMA of granular sludge increased with an increase in the size of granules and was 0.289 g CH4-COD/(g VSS d) at an HRT of 6 h, but the proportion of dissolved methane in the effluent accounted for 38-45 % of the total methane production and the proportion of Methanothrix in UASB sludge was 82.44 %. In this study, dense granular sludge was obtained by gradually shortening the HRT to start the UASB, and the lower effluent COD reduced the load of subsequent treatment processes, which could be used as a low carbon/nitrogen ratio influent for activated carbon-activated sludge, activated sludge-microalgae, and partial nitrification-anaerobic ammonia oxidation processes.

Denitrification performance and in-situ fermentation mechanism of the wastepaper-flora slow-release carbon source.

Using wastepaper as external carbon sources is an optional way to achieve total nitrogen removal faced with low carbon to nitrogen ratio municipal sewage. Most of studies have primarily focused on using cellulose-rich wastes establishing the separate denitrification units to achieve in-situ fermentation, which can cause blockages and prolong the process chain. In response, a novel in-situ fermentation wastepaper-flora slow-release carbon source (IF-WF) was proposed using in the original denitrification unit. IF-WF could be efficiently utilized in situ and the denitrification rate increased with the increase of nitrate nitrogen. The fermentation products were highly available, but internal acidification of IF-WF inhibited fermentation. Moreover, IF-WF limited the growth of polysaccharides in the extracellular polymeric substances of denitrified sludge. IF-WF finally formed the structure dominated by nitrate-reduction bacteria outside and cellulose-degrading bacteria inside. These results provide guidance for understanding the mechanism of IF-WF for in-situ fermentation to promote nitrogen removal.

Boosting capacitive performance of N, S co-doped hierarchical porous lignin-derived carbon via self-assembly assisted template-coupled activation.

Heteroatom-doped porous carbon materials show promise for use as supercapacitor electrodes, but the tradeoff between surface area and the heteroatom dopant levels limits the supercapacitive performance. Here, we modulated the pore structure and surface dopants of N, S co-doped hierarchical porous lignin-derived carbon (NS-HPLC-K) via self-assembly assisted template-coupled activation. The ingenious assembly of lignin micelles and sulfomethylated melamine into a magnesium carbonate basic template greatly promoted the KOH activation process, which endowed the NS-HPLC-K with uniform distributions of activated N/S dopants and highly accessible nanosized pores. The optimized NS-HPLC-K exhibited a three-dimensional hierarchically porous architecture composed of wrinkled nanosheets and a high specific surface area of 2538.3 ± 9.5 m2/g with a rational N content of 3.19 ± 0.01 at.%, which boosted the electrical double-layer capacitance and pseudocapacitance. Consequently, the NS-HPLC-K supercapacitor electrode delivered a superior gravimetric capacitance of 393 F/g at 0.5 A/g. Furthermore, the assembled coin-type supercapacitor showed good energy-power characteristics and cycling stability. This work provides a novel idea for designing eco-friendly porous carbons for use in advanced supercapacitors.

Efficient elimination of nonylphenol and 4-tert-octylphenol by weak electrical stimulated anaerobic microbial processes.

The investigation into the degradation of alkylphenol pollutants (APs) has become a hotspot due to their harmful effects on the environment and human health. In this study, microbial electrolysis cells (MECs) were used to degrade nonylphenol (NP) and 4-tert-octylphenol (4-tert-OP). The study found that the degradation rates of NP and 4-tert-OP for a 6-day period were 83.6% and 96.3%, respectively, which were 30.53% and 26.7% higher than those of the group without applied voltage. The double layer area in the degradation of 4-tert-OP was larger than that of NP, and the resistance exhibited by 4-tert-OP (87.47 Ω) in MEC was lower than that of NP (99.42 Ω). Meanwhile, NP had a greater effect on the bioenzyme activity than 4-tert-OP. GC-MS analysis showed that the degradation pathways of both pollutants mainly included oxidation and hydroxylation reactions. Furthermore, the microbial community analysis indicated that the main functional bacteria in NP degradation were Citrobacter, Desulfovibrio and Advenella, and those in 4-tert-OP degradation were Stenotrophomonas, Chryseobacterium, Dokdonella, and the key microbiomes underlying the cooperative relationship. The biotoxicity test indicated that the toxicity of residual substances was significantly reduced. Therefore, the MEC system is efficient and environmentally friendly and has broad application prospects in phenol refractory organics.

PDA-PRGCN: identification of Piwi-interacting RNA-disease associations through subgraph projection and residual scaling-based feature augmentation.

BACKGROUND: Emerging evidences show that Piwi-interacting RNAs (piRNAs) play a pivotal role in numerous complex human diseases. Identifying potential piRNA-disease associations (PDAs) is crucial for understanding disease pathogenesis at molecular level. Compared to the biological wet experiments, the computational methods provide a cost-effective strategy. However, few computational methods have been developed so far. RESULTS: Here, we proposed an end-to-end model, referred to as PDA-PRGCN (PDA prediction using subgraph Projection and Residual scaling-based feature augmentation through Graph Convolutional Network). Specifically, starting with the known piRNA-disease associations represented as a graph, we applied subgraph projection to construct piRNA-piRNA and disease-disease subgraphs for the first time, followed by a residual scaling-based feature augmentation algorithm for node initial representation. Then, we adopted graph convolutional network (GCN) to learn and identify potential PDAs as a link prediction task on the constructed heterogeneous graph. Comprehensive experiments, including the performance comparison of individual components in PDA-PRGCN, indicated the significant improvement of integrating subgraph projection, node feature augmentation and dual-loss mechanism into GCN for PDA prediction. Compared with state-of-the-art approaches, PDA-PRGCN gave more accurate and robust predictions. Finally, the case studies further corroborated that PDA-PRGCN can reliably detect PDAs. CONCLUSION: PDA-PRGCN provides a powerful method for PDA prediction, which can also serve as a screening tool for studies of complex diseases.

Incorporating higher order network structures to improve miRNA-disease association prediction based on functional modularity.

As microRNAs (miRNAs) are involved in many essential biological processes, their abnormal expressions can serve as biomarkers and prognostic indicators to prevent the development of complex diseases, thus providing accurate early detection and prognostic evaluation. Although a number of computational methods have been proposed to predict miRNA-disease associations (MDAs) for further experimental verification, their performance is limited primarily by the inadequacy of exploiting lower order patterns characterizing known MDAs to identify missing ones from MDA networks. Hence, in this work, we present a novel prediction model, namely HiSCMDA, by incorporating higher order network structures for improved performance of MDA prediction. To this end, HiSCMDA first integrates miRNA similarity network, disease similarity network and MDA network to preserve the advantages of all these networks. After that, it identifies overlapping functional modules from the integrated network by predefining several higher order connectivity patterns of interest. Last, a path-based scoring function is designed to infer potential MDAs based on network paths across related functional modules. HiSCMDA yields the best performance across all datasets and evaluation metrics in the cross-validation and independent validation experiments. Furthermore, in the case studies, 49 and 50 out of the top 50 miRNAs, respectively, predicted for colon neoplasms and lung neoplasms have been validated by well-established databases. Experimental results show that rich higher order organizational structures exposed in the MDA network gain new insight into the MDA prediction based on higher order connectivity patterns.

Enhancement of iron-based nitrogen removal with an electric-magnetic field in an upflow microaerobic sludge reactor (UMSR).

Traditional denitrification often produces high operating costs and excessive sludge disposal expenses due to conventional carbon sources. A novel electric-magnetic field (MF) 48 mT with Fe0 and C-Fe0 powder in an upflow microaerobic sludge reactor (UMSR) improved nitrogen removal from wastewater without organic carbon resources and gave richness to the heterotrophic bacterial community. In the current study, the reactor was operated for 78 ± 2 days, divided into five stages (without Fe0, with Fe0, coupling with MF, without coupling with MF, and coupling with MF again), at a hydraulic retention time (HRT) of 2.5 h, with an influent loading of ammonium (NH4+-N) 50 ± 2 mg/L, at 25-27 °C, and less than 1.0 mg/L dissolved oxygen (DO). The results demonstrated nitrogen removal efficiency enhanced after coupling with MF on the levels of NO3--N by 76% with an effluent concentration of 8.7 mg/L, NH4+-N by 72% with an effluent concentration of 13.6 mg/L, and total nitrogen removal (TN) by 76%, respectively. After coupling the MF with the reactor, the microbial community data analysis showed the dominant abundance of ammonia-oxidizing bacteria, heterotrophic nitrifying bacteria, and denitrifying bacteria on the level of Anaerolineaceae_uncultured 2%, which is capable of denitrification that uses Fe2+ as an electron source, Gemmatimonadaceae_uncultured 4%, Hydrogenophaga 4% which is capable of catalyzing hydrogenotrophic denitrification and correlating to nitrate removal, denitrification and desulfurization bacteria SBR1031_norank 18%, anammox-bacteria Saccharimonadales_norank 2%, and (AOM) Limnobacter 3% in the sludge.

RLFDDA: a meta-path based graph representation learning model for drug-disease association prediction.

BACKGROUND: Drug repositioning is a very important task that provides critical information for exploring the potential efficacy of drugs. Yet developing computational models that can effectively predict drug-disease associations (DDAs) is still a challenging task. Previous studies suggest that the accuracy of DDA prediction can be improved by integrating different types of biological features. But how to conduct an effective integration remains a challenging problem for accurately discovering new indications for approved drugs. METHODS: In this paper, we propose a novel meta-path based graph representation learning model, namely RLFDDA, to predict potential DDAs on heterogeneous biological networks. RLFDDA first calculates drug-drug similarities and disease-disease similarities as the intrinsic biological features of drugs and diseases. A heterogeneous network is then constructed by integrating DDAs, disease-protein associations and drug-protein associations. With such a network, RLFDDA adopts a meta-path random walk model to learn the latent representations of drugs and diseases, which are concatenated to construct joint representations of drug-disease associations. As the last step, we employ the random forest classifier to predict potential DDAs with their joint representations. RESULTS: To demonstrate the effectiveness of RLFDDA, we have conducted a series of experiments on two benchmark datasets by following a ten-fold cross-validation scheme. The results show that RLFDDA yields the best performance in terms of AUC and F1-score when compared with several state-of-the-art DDAs prediction models. We have also conducted a case study on two common diseases, i.e., paclitaxel and lung tumors, and found that 7 out of top-10 diseases and 8 out of top-10 drugs have already been validated for paclitaxel and lung tumors respectively with literature evidence. Hence, the promising performance of RLFDDA may provide a new perspective for novel DDAs discovery over heterogeneous networks.

Analysis of energy recovery and microbial community in an amalgamated CSTR-UASBs reactor for a three-stage anaerobic fermentation process of cornstalks.

In this study, a continuous stirred-tank reactor (CSTR) coupled with up-flow anaerobic sludge beds (UASBs) reactor was successfully developed for enhancing methane production and carbon recovery rate from cornstalks. Acetic acid production was higher in regions A than in B and C. The methane percentage achieved at 75.98% of total gas and methane production of cornstalks was up to 520.07 mL/g, during the stable operation period. The carbon of recovery rate, represented substrates converted to methane gas, reached 69.32% in stable stage. Microbial community structure analysis revealed that Paludibacter, Prevotella/Clostridium sensu stricto, and Caldisericum were the dominant bacteria for the degradation of cellulose, lignin, and other refractory macromolecules in regions A, B, and C, respectively. Methanobacterium and Methanolinea were the two major genera, accounting for methanogenesis generation.