Dataset Information

Recommendation algorithm based on attributed multiplex heterogeneous network.

ABSTRACT: In the field of deep learning, the processing of large network models on billions or even tens of billions of nodes and numerous edge types is still flawed, and the accuracy of recommendations is greatly compromised when large network embeddings are applied to recommendation systems. To solve the problem of inaccurate recommendations caused by processing deficiencies in large networks, this paper combines the attributed multiplex heterogeneous network with the attention mechanism that introduces the softsign and sigmoid function characteristics and derives a new framework SSN_GATNE-T (S represents the softsign function, SN represents the attention mechanism introduced by the Softsign function, and GATNE-T represents the transductive embeddings learning for attribute multiple heterogeneous networks). The attributed multiplex heterogeneous network can help obtain more user-item information with more attributes. No matter how many nodes and types are included in the model, our model can handle it well, and the improved attention mechanism can help annotations to obtain more useful information via a combination of the two. This can help to mine more potential information to improve the recommendation effect; in addition, the application of the softsign function in the fully connected layer of the model can better reduce the loss of potential user information, which can be used for accurate recommendation by the model. Using the Adam optimizer to optimize the model can not only make our model converge faster, but it is also very helpful for model tuning. The proposed framework SSN_GATNE-T was tested for two different types of datasets, Amazon and YouTube, using three evaluation indices, ROC-AUC (receiver operating characteristic-area under curve), PR-AUC (precision recall-area under curve) and F1 (F1-score), and found that SSN_GATNE-T improved on all three evaluation indices compared to the mainstream recommendation models currently in existence. This not only demonstrates that the framework can deal well with the shortcomings of obtaining accurate interaction information due to the presence of a large number of nodes and edge types of the embedding of large network models, but also demonstrates the effectiveness of addressing the shortcomings of large networks to improve recommendation performance. In addition, the model is also a good solution to the cold start problem.

SUBMITTER: Yang Z

PROVIDER: S-EPMC8725661 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BACKGROUND:Identifying protein complexes from protein-protein interaction (PPI) network is one of the most important tasks in proteomics. Existing computational methods try to incorporate a variety of biological evidences to enhance the quality of predicted complexes. However, it is still a challenge to integrate different types of biological information into the complexes discovery process under a unified framework. Recently, attributed network embedding methods have be proved to be remarkably effective in generating vector representations for nodes in the network. In the transformed vector space, both the topological proximity and node attributed affinity between different nodes are preserved. Therefore, such attributed network embedding methods provide us a unified framework to integrate various biological evidences into the protein complexes identification process. RESULTS:In this article, we propose a new method called GANE to predict protein complexes based on Gene Ontology (GO) attributed network embedding. Firstly, it learns the vector representation for each protein from a GO attributed PPI network. Based on the pair-wise vector representation similarity, a weighted adjacency matrix is constructed. Secondly, it uses the clique mining method to generate candidate cores. Consequently, seed cores are obtained by ranking candidate cores based on their densities on the weighted adjacency matrix and removing redundant cores. For each seed core, its attachments are the proteins with correlation score that is larger than a given threshold. The combination of a seed core and its attachment proteins is reported as a predicted protein complex by the GANE algorithm. For performance evaluation, we compared GANE with six protein complex identification methods on five yeast PPI networks. Experimental results showes that GANE performs better than the competing algorithms in terms of different evaluation metrics. CONCLUSIONS:GANE provides a framework that integrate many valuable and different biological information into the task of protein complex identification. The protein vector representation learned from our attributed PPI network can also be used in other tasks, such as PPI prediction and disease gene prediction.

Project description:Asthma is a complex heterogeneous respiratory disorder. In recent years nubbly regions of the role of genetic variants and transcriptome including mRNAs, microRNAs, and long non-coding RNAs in the pathogenesis of asthma have been separately excavated and reported. However, how to systematically integrate and decode this scattered information remains unclear. Further exploration would improve understanding of the internal communication of asthma. To excavate new insights into the pathogenesis of asthma, we ascertained three asthma characteristics according to reviews, airway inflammation, airway hyperresponsiveness, and airway remodeling. We manually created a contemporary catalog of corresponding risk transcriptome, including mRNAs, miRNAs, and lncRNAs. MIMP is a multiplex-heterogeneous networks-based approach, measuring the relevance of disease characteristics to the pathway by examining the similarity between the determined vectors of risk transcriptome and pathways in the same low-dimensional vector space. It was developed to enable a more concentrated and in-depth exploration of potential pathways. We integrated experimentally validated competing endogenous RNA regulatory information and the SNPs with significant pathways into the ceRNA-mediated SNP switching pathway network (CSSPN) to analyze ceRNA regulation of pathways and the role of SNP in these dysfunctions. We discovered 11 crucial ceRNA regulations concerning asthma disease feature pathway and propose a potential mechanism of ceRNA regulatory SNP → gene → pathway → disease feature effecting asthma pathogenesis, especially for MALAT1 (rs765499057/rs764699354/rs189435941) → hsa-miR-155 → IL13 (rs201185816/rs1000978586/rs202101165) → Interleukin-4 and Interleukin-13 signaling → inflammation/airway remodeling and MALAT1 (rs765499057/rs764699354/rs189435941) → hsa-miR-155 → IL17RB (rs948046241) → Interleukin-17 signaling (airway remodeling)/Cytokine-cytokine receptor interaction (inflammation). This study showed a systematic and propagable workflow for capturing the potential SNP "switch" of asthma through text and database mining and provides further information on the pathogenesis of asthma.

Project description:BackgroundDriven by the COVID-19 pandemic and the dire need to discover an antiviral drug, we explored the landscape of the SARS-CoV-2 biomedical publications to identify potential treatments.ObjectiveThe aims of this study are to identify off-label drugs that may have benefits for the coronavirus disease pandemic, present a novel ranking algorithm called CovidX to recommend existing drugs for potential repurposing, and validate the literature-based outcome with drug knowledge available in clinical trials.MethodsTo achieve such objectives, we applied natural language processing techniques to identify drugs and linked entities (eg, disease, gene, protein, chemical compounds). When such entities are linked, they form a map that can be further explored using network science tools. The CovidX algorithm was based upon a notion that we called "diversity." A diversity score for a given drug was calculated by measuring how "diverse" a drug is calculated using various biological entities (regardless of the cardinality of actual instances in each category). The algorithm validates the ranking and awards those drugs that are currently being investigated in open clinical trials. The rationale behind the open clinical trial is to provide a validating mechanism of the PubMed results. This ensures providing up to date evidence of the fast development of this disease.ResultsFrom the analyzed biomedical literature, the algorithm identified 30 possible drug candidates for repurposing, ranked them accordingly, and validated the ranking outcomes against evidence from clinical trials. The top 10 candidates according to our algorithm are hydroxychloroquine, azithromycin, chloroquine, ritonavir, losartan, remdesivir, favipiravir, methylprednisolone, rapamycin, and tilorone dihydrochloride.ConclusionsThe ranking shows both consistency and promise in identifying drugs that can be repurposed. We believe, however, the full treatment to be a multifaceted, adjuvant approach where multiple drugs may need to be taken at the same time.

Dataset Information

Recommendation algorithm based on attributed multiplex heterogeneous network.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets