Multi-Label Fusion Collaborative Matrix Factorization for Predicting LncRNA-Disease Associations

Gao, Mingming; Cui, Zhen; Gao, Ying-Lian; Wang, Juan; Liu, Jin-Xing

doi:10.1109/jbhi.2020.2988720

Cited by 15 publications

(11 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Chen and his colleagues developed some advanced computational models that can be used effectively to identify disease-associated LncRNAs on a large scale [ 31 ]. Moreover, a a multi-label fusion collaborative matrix factorization (MLFCMF) approach was proposed for predicting lncRNA-disease associations, especially, their method finally obtains an AUC value of 0.8612 [ 32 ]. In addition to the above bioinformatics studies, the role of most lncRNAs in OC cell lines has also been explored, such as MSC-AS1 [ 33 ], TONSL-AS1 [ 34 ], and SNHG20 [ 35 ], etc.…”

Section: Discussionmentioning

confidence: 99%

Integrated clinical characteristics and omics analysis identifies a ferroptosis and iron-metabolism-related lncRNA signature for predicting prognosis and therapeutic responses in ovarian cancer

et al. 2022

View full text Add to dashboard Cite

Background Ferroptosis and iron-metabolism are regulated by Long non-coding RNAs (lncRNAs) in ovarian cancer (OC). Therefore, a comprehensive analysis of ferroptosis and iron-metabolism related lncRNAs (FIRLs) in OC is crucial for proposing therapeutic strategies and survival prediction. Methods In multi-omics data from OC patients, FIRLs were identified by calculating Pearson correlation coefficients with ferroptosis and iron-metabolism related genes (FIRGs). Cox-Lasso regression analysis was performed on the FIRLs to screen further the lncRNAs participating in FIRLs signature. In addition, all patients were divided into two robust risk subtypes using the FIRLs signature. Receiver operator characteristic (ROC) curve, Kaplan–Meier analysis, decision curve analysis (DCA), Cox regression analysis and calibration curve were used to confirm the clinical benefits of FIRLs signature. Meanwhile, two nomograms were constructed to facilitate clinical application. Moreover, the potential biological functions of the signature were investigated by genes function annotation. Finally, immune microenvironment, chemotherapeutic sensitivity, and the response of PARP inhibitors were compared in different risk groups using diversiform bioinformatics algorithms. Results The raw data were randomized into a training set (n = 264) and a testing set (n = 110). According to Pearson coefficients between FIRGs and lncRNAs, 1075 FIRLs were screened for univariate Cox regression analysis, and then LASSO regression analysis was used to construct 8-FIRLs signature. It is worth mentioning that a variety of analytical methods indicated excellent predictive performance for overall survival (OS) of FIRLs signature (p < 0.05). The multivariate Cox regression analysis showed that FIRLs signature was an independent prognostic factor for OS (p < 0.05). Moreover, significant differences in the abundance of immune cells, immune-related pathways, and drug response were excavated in different risk subtypes (p < 0.05). Conclusion The FIRLs signature can independently predict overall survival and therapeutic effect in OC patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Integrated clinical characteristics and omics analysis identifies a ferroptosis and iron-metabolism-related lncRNA signature for predicting prognosis and therapeutic responses in ovarian cancer

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In addition, the inner product of lncRNA factor vectors and disease factor vectors was used as a decoder to reconstruct the LDA matrix ( Wu et al, 2020 ). Gao et al (2021) constructed a multi-label fusion collaborative matrix decomposition approach to predict LDAs. Wang et al (2020) developed a weighted matrix factorization model on multi-relational data to predict LDAs.…”

Section: Introductionmentioning

confidence: 99%

Geometric complement heterogeneous information and random forest for predicting lncRNA-disease associations

Yao

Zhang²,

Zhan³

et al. 2022

Front. Genet.

View full text Add to dashboard Cite

More and more evidences have showed that the unnatural expression of long non-coding RNA (lncRNA) is relevant to varieties of human diseases. Therefore, accurate identification of disease-related lncRNAs can help to understand lncRNA expression at the molecular level and to explore more effective treatments for diseases. Plenty of lncRNA-disease association prediction models have been raised but it is still a challenge to recognize unknown lncRNA-disease associations. In this work, we have proposed a computational model for predicting lncRNA-disease associations based on geometric complement heterogeneous information and random forest. Firstly, geometric complement heterogeneous information was used to integrate lncRNA-miRNA interactions and miRNA-disease associations verified by experiments. Secondly, lncRNA and disease features consisted of their respective similarity coefficients were fused into input feature space. Thirdly, an autoencoder was adopted to project raw high-dimensional features into low-dimension space to learn representation for lncRNAs and diseases. Finally, the low-dimensional lncRNA and disease features were fused into input feature space to train a random forest classifier for lncRNA-disease association prediction. Under five-fold cross-validation, the AUC (area under the receiver operating characteristic curve) is 0.9897 and the AUPR (area under the precision-recall curve) is 0.7040, indicating that the performance of our model is better than several state-of-the-art lncRNA-disease association prediction models. In addition, case studies on colon and stomach cancer indicate that our model has a good ability to predict disease-related lncRNAs.

show abstract

“…For example, He et al (2018) designed a graph regularized non-negative matrix factorization (NMF) framework for prediction. In 2020, Gao et al (2021) developed multilabel fusion collaborative matrix factorization to solve lncRNA–disease association prediction task. In 2021, Xu et al (2021a) developed regularized NMF and obtained better prediction results in the lncRNA–protein interaction prediction.…”

Section: Introductionmentioning

confidence: 99%

Novel Collaborative Weighted Non-negative Matrix Factorization Improves Prediction of Disease-Associated Human Microbes

Zhang

et al. 2022

Front. Microbiol.

View full text Add to dashboard Cite

Extensive clinical and biomedical studies have shown that microbiome plays a prominent role in human health. Identifying potential microbe–disease associations (MDAs) can help reveal the pathological mechanism of human diseases and be useful for the prevention, diagnosis, and treatment of human diseases. Therefore, it is necessary to develop effective computational models and reduce the cost and time of biological experiments. Here, we developed a novel machine learning-based joint framework called CWNMF-GLapRLS for human MDA prediction using the proposed collaborative weighted non-negative matrix factorization (CWNMF) technique and graph Laplacian regularized least squares. Especially, to fuse more similarity information, we calculated the functional similarity of microbes. To deal with missing values and effectively overcome the data sparsity problem, we proposed a collaborative weighted NMF technique to reconstruct the original association matrix. In addition, we developed a graph Laplacian regularized least-squares method for prediction. The experimental results of fivefold and leave-one-out cross-validation demonstrated that our method achieved the best performance by comparing it with 5 state-of-the-art methods on the benchmark dataset. Case studies further showed that the proposed method is an effective tool to predict potential MDAs and can provide more help for biomedical researchers.

show abstract

Multi-Label Fusion Collaborative Matrix Factorization for Predicting LncRNA-Disease Associations

Cited by 15 publications

References 48 publications

Integrated clinical characteristics and omics analysis identifies a ferroptosis and iron-metabolism-related lncRNA signature for predicting prognosis and therapeutic responses in ovarian cancer

Integrated clinical characteristics and omics analysis identifies a ferroptosis and iron-metabolism-related lncRNA signature for predicting prognosis and therapeutic responses in ovarian cancer

Geometric complement heterogeneous information and random forest for predicting lncRNA-disease associations

Novel Collaborative Weighted Non-negative Matrix Factorization Improves Prediction of Disease-Associated Human Microbes

Contact Info

Product

Resources

About