Browse
Submit Data
Databases
API
Help

Dataset Information

35 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Recommendation system in social networks with topical attention and probabilistic matrix factorization.

ABSTRACT: Collaborative filtering (CF) is a common recommendation mechanism that relies on user-item ratings. However, the intrinsic sparsity of user-item rating data can be problematic in many domains and settings, limiting the ability to generate accurate predictions and effective recommendations. At present, most algorithms use two-valued trust relationship of social network to improve recommendation quality but fail to take into account the difference of trust intensity of each friend and user's comment information. To this end, the recommendation system within a social network adopts topical attention and probabilistic matrix factorization (STAPMF) is proposed. We combine the trust information in social networks and the topical information from review documents by proposing a novel algorithm combining probabilistic matrix factorization and attention-based recurrent neural networks to extract item underlying feature vectors, user's personal potential feature vectors, and user's social hidden feature vectors, which represent the features extracted from the user's trusted network. Using real-world datasets, we show a significant improvement in recommendation performance comparing with the prevailing state-of-the-art algorithms for social network-based recommendation.

SUBMITTER: Zhang W

PROVIDER: S-EPMC6822766 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Bias Aware Probabilistic Boolean Matrix Factorization.

Project description:Boolean matrix factorization (BMF) is a combinatorial problem arising from a wide range of applications including recommendation system, collaborative filtering, and dimensionality reduction. Currently, the noise model of existing BMF methods is often assumed to be homoscedastic; however, in real world data scenarios, the deviations of observed data from their true values are almost surely diverse due to stochastic noises, making each data point not equally suitable for fitting a model. In this case, it is not ideal to treat all data points as equally distributed. Motivated by such observations, we introduce a probabilistic BMF model that recognizes the object- and feature-wise bias distribution respectively, called bias aware BMF (BABF). To the best of our knowledge, BABF is the first approach for Boolean decomposition with consideration of the feature-wise and object-wise bias in binary data. We conducted experiments on datasets with different levels of background noise, bias level, and sizes of the signal patterns, to test the effectiveness of our method in various scenarios. We demonstrated that our model outperforms the state-of-the-art factorization methods in both accuracy and efficiency in recovering the original datasets, and the inferred bias level is highly significantly correlated with true existing bias in both simulated and real world datasets.

| S-EPMC10421704 | biostudies-literature

Predicting drug-target interactions using probabilistic matrix factorization.

Project description:Quantitative analysis of known drug-target interactions emerged in recent years as a useful approach for drug repurposing and assessing side effects. In the present study, we present a method that uses probabilistic matrix factorization (PMF) for this purpose, which is particularly useful for analyzing large interaction networks. DrugBank drugs clustered based on PMF latent variables show phenotypic similarity even in the absence of 3D shape similarity. Benchmarking computations show that the method outperforms those recently introduced provided that the input data set of known interactions is sufficiently large--which is the case for enzymes and ion channels, but not for G-protein coupled receptors (GPCRs) and nuclear receptors. Runs performed on DrugBank after hiding 70% of known interactions show that, on average, 88 of the top 100 predictions hit the hidden interactions. De novo predictions permit us to identify new potential interactions. Drug-target pairs implicated in neurobiological disorders are overrepresented among de novo predictions.

| S-EPMC3871285 | biostudies-literature

Eliminating bias: enhancing children's book recommendation using a hybrid model of graph convolutional networks and neural matrix factorization.

Project description:Managing user bias in large-scale user review data is a significant challenge in optimizing children's book recommendation systems. To tackle this issue, this study introduces a novel hybrid model that combines graph convolutional networks (GCN) based on bipartite graphs and neural matrix factorization (NMF). This model aims to enhance the precision and efficiency of children's book recommendations by accurately capturing user biases. In this model, the complex interactions between users and books are modeled as a bipartite graph, with the users' book ratings serving as the weights of the edges. Through GCN and NMF, we can delve into the structure of the graph and the behavioral patterns of users, more accurately identify and address user biases, and predict their future behaviors. Compared to traditional recommendation systems, our hybrid model excels in handling large-scale user review data. Experimental results confirm that our model has significantly improved in terms of recommendation accuracy and scalability, positively contributing to the advancement of children's book recommendation systems.

| S-EPMC10909171 | biostudies-literature

A Probabilistic Matrix Factorization Method for Identifying lncRNA-disease Associations.

Project description:Recently, an increasing number of studies have indicated that long-non-coding RNAs (lncRNAs) can participate in various crucial biological processes and can also be used as the most promising biomarkers for the treatment of certain diseases such as coronary artery disease and various cancers. Due to costs and time complexity, the number of possible disease-related lncRNAs that can be verified by traditional biological experiments is very limited. Therefore, in recent years, it has been very popular to use computational models to predict potential disease-lncRNA associations. In this study, we constructed three kinds of association networks, namely the lncRNA-miRNA association network, the miRNA-disease association network, and the lncRNA-disease correlation network firstly. Then, through integrating these three newly constructed association networks, we constructed an lncRNA-disease weighted association network, which would be further updated by adopting the KNN algorithm based on the semantic similarity of diseases and the similarity of lncRNA functions. Thereafter, according to the updated lncRNA-disease weighted association network, a novel computational model called PMFILDA was proposed to infer potential lncRNA-disease associations based on the probability matrix decomposition. Finally, to evaluate the superiority of the new prediction model PMFILDA, we performed Leave One Out Cross-Validation (LOOCV) based on strongly validated data filtered from MNDR and the simulation results indicated that the performance of PMFILDA was better than some state-of-the-art methods. Moreover, case studies of breast cancer, lung cancer, and colorectal cancer were implemented to further estimate the performance of PMFILDA, and simulation results illustrated that PMFILDA could achieve satisfying prediction performance as well.

| S-EPMC6410097 | biostudies-literature

Joint Geographical and Temporal Modeling Based on Matrix Factorization for Point-of-Interest Recommendation

Project description:With the popularity of Location-based Social Networks, Point-of-Interest (POI) recommendation has become an important task, which learns the users’ preferences and mobility patterns to recommend POIs. Previous studies show that incorporating contextual information such as geographical and temporal influences is necessary to improve POI recommendation by addressing the data sparsity problem. However, existing methods model the geographical influence based on the physical distance between POIs and users, while ignoring the temporal characteristics of such geographical influences. In this paper, we perform a study on the user mobility patterns where we find out that users’ check-ins happen around several centers depending on their current temporal state. Next, we propose a spatio-temporal activity-centers algorithm to model users’ behavior more accurately. Finally, we demonstrate the effectiveness of our proposed contextual model by incorporating it into the matrix factorization model under two different settings: (i) static and (ii) temporal. To show the effectiveness of our proposed method, which we refer to as STACP, we conduct experiments on two well-known real-world datasets acquired from Gowalla and Foursquare LBSNs. Experimental results show that the STACP model achieves a statistically significant performance improvement, compared to the state-of-the-art techniques. Also, we demonstrate the effectiveness of capturing geographical and temporal information for modeling users’ activity centers and the importance of modeling them jointly.

| S-EPMC7148222 | biostudies-literature

Drug repositioning based on similarity constrained probabilistic matrix factorization: COVID-19 as a case study.

Project description:The novel coronavirus disease 2019 (COVID-19) pandemic has caused a massive health crisis worldwide and upended the global economy. However, vaccines and traditional drug discovery for COVID-19 cost too much in terms of time, manpower, and money. Drug repurposing becomes one of the promising treatment strategies amid the COVID-19 crisis. At present, there are no publicly existing databases for experimentally supported human drug-virus interactions, and most existing drug repurposing methods require the rich information, which is not always available, especially for a new virus. In this study, on the one hand, we put size-able efforts to collect drug-virus interaction entries from literature and build the Human Drug Virus Database (HDVD). On the other hand, we propose a new approach, called SCPMF (similarity constrained probabilistic matrix factorization), to identify new drug-virus interactions for drug repurposing. SCPMF is implemented on an adjacency matrix of a heterogeneous drug-virus network, which integrates the known drug-virus interactions, drug chemical structures, and virus genomic sequences. SCPMF projects the drug-virus interactions matrix into two latent feature matrices for the drugs and viruses, which reconstruct the drug-virus interactions matrix when multiplied together, and then introduces the weighted similarity interaction matrix as constraints for drugs and viruses. Benchmarking comparisons on two different datasets demonstrate that SCPMF has reliable prediction performance and outperforms several recent approaches. Moreover, SCPMF-predicted drug candidates of COVID-19 also confirm the accuracy and reliability of SCPMF.

| S-EPMC7825831 | biostudies-literature

Reconstruct modular phenotype-specific gene networks by knowledge-driven matrix factorization.

Project description:MotivationReconstructing gene networks from microarray data has provided mechanistic information on cellular processes. A popular structure learning method, Bayesian network inference, has been used to determine network topology despite its shortcomings, i.e. the high-computational cost when analyzing a large number of genes and the inefficiency in exploiting prior knowledge, such as the co-regulation information of the genes. To address these limitations, we are introducing an alternative method, knowledge-driven matrix factorization (KMF) framework, to reconstruct phenotype-specific modular gene networks.ResultsConsidering the reconstruction of gene network as a matrix factorization problem, we first use the gene expression data to estimate a correlation matrix, and then factorize the correlation matrix to recover the gene modules and the interactions between them. Prior knowledge from Gene Ontology is integrated into the matrix factorization. We applied this KMF algorithm to hepatocellular carcinoma (HepG2) cells treated with free fatty acids (FFAs). By comparing the module networks for the different conditions, we identified the specific modules that are involved in conferring the cytotoxic phenotype induced by palmitate. Further analysis of the gene modules of the different conditions suggested individual genes that play important roles in palmitate-induced cytotoxicity. In summary, KMF can efficiently integrate gene expression data with prior knowledge, thereby providing a powerful method of reconstructing phenotype-specific gene networks and valuable insights into the mechanisms that govern the phenotype.

| S-EPMC2800351 | biostudies-literature

Social and content aware One-Class recommendation of papers in scientific social networks.

Project description:With the rapid development of information technology, scientific social networks (SSNs) have become the fastest and most convenient way for researchers to communicate with each other. Many published papers are shared via SSNs every day, resulting in the problem of information overload. How to appropriately recommend personalized and highly valuable papers for researchers is becoming more urgent. However, when recommending papers in SSNs, only a small amount of positive instances are available, leaving a vast amount of unlabelled data, in which negative instances and potential unseen positive instances are mixed together, which naturally belongs to One-Class Collaborative Filtering (OCCF) problem. Therefore, considering the extreme data imbalance and data sparsity of this OCCF problem, a hybrid approach of Social and Content aware One-class Recommendation of Papers in SSNs, termed SCORP, is proposed in this study. Unlike previous approaches recommended to address the OCCF problem, social information, which has been proved playing a significant role in performing recommendations in many domains, is applied in both the profiling of content-based filtering and the collaborative filtering to achieve superior recommendations. To verify the effectiveness of the proposed SCORP approach, a real-life dataset from CiteULike was employed. The experimental results demonstrate that the proposed approach is superior to all of the compared approaches, thus providing a more effective method for recommending papers in SSNs.

| S-EPMC5542664 | biostudies-literature

PMF-GRN: a variational inference approach to single-cell gene regulatory network inference using probabilistic matrix factorization.

Project description:Inferring gene regulatory networks (GRNs) from single-cell data is challenging due to heuristic limitations. Existing methods also lack estimates of uncertainty. Here we present Probabilistic Matrix Factorization for Gene Regulatory Network Inference (PMF-GRN). Using single-cell expression data, PMF-GRN infers latent factors capturing transcription factor activity and regulatory relationships. Using variational inference allows hyperparameter search for principled model selection and direct comparison to other generative models. We extensively test and benchmark our method using real single-cell datasets and synthetic data. We show that PMF-GRN infers GRNs more accurately than current state-of-the-art single-cell GRN inference methods, offering well-calibrated uncertainty estimates.

| S-EPMC11003171 | biostudies-literature

A social image recommendation system based on deep reinforcement learning.

Project description:Today, due to the expansion of the Internet and social networks, people are faced with a vast amount of dynamic information. To mitigate the issue of information overload, recommender systems have become pivotal by analyzing users' activity histories to discern their interests and preferences. However, most available social image recommender systems utilize a static strategy, meaning they do not adapt to changes in user preferences. To overcome this challenge, our paper introduces a dynamic image recommender system that leverages a deep reinforcement learning (DRL) framework, enriched with a novel set of features including emotion, style, and personality. These features, uncommon in existing systems, are instrumental in crafting a user's characteristic vector, offering a personalized recommendation experience. Additionally, we overcome the challenge of state representation definition in reinforcement learning by introducing a new state representation. The experimental results show that our proposed method, compared to some related works, significantly improves Recall@k and Precision@k by approximately 7%-10% (for the top 100 images recommended) for personalized image recommendation.

| S-EPMC10994284 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data