The Bi-Direction Similarity Integration Method for Predicting Microbe-Disease Associations

Zhang, Wen; Yang, Weitai; Lu, Xiaoting; Huang, Feng; Luo, Fei

doi:10.1109/access.2018.2851751

Cited by 36 publications

(25 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since spectral clustering is a widely used and accepted cluster method, we are attempting to find an improved method to discover cancer subtypes more accurately. We will consider various machine learning methods and constructing kernel methods to predict cancer subtypes (Zeng et al, 2017; Ding et al, 2018; Zhang et al, 2018a,b,c; Zou et al, 2018). We also consider the potential possibility of developing computational models for cancer subtype identification based on microRNA information (Chen and Huang, 2017; Chen et al, 2017, 2018a,b; Hu et al, 2018).…”

Section: Discussionmentioning

confidence: 99%

Discovering Cancer Subtypes via an Accurate Fusion Strategy on Multiple Profile Data

et al. 2019

View full text Add to dashboard Cite

Discovering cancer subtypes is useful for guiding clinical treatment of multiple cancers. Progressive profile technologies for tissue have accumulated diverse types of data. Based on these types of expression data, various computational methods have been proposed to predict cancer subtypes. It is crucial to study how to better integrate these multiple profiles of data. In this paper, we collect multiple profiles of data for five cancers on The Cancer Genome Atlas (TCGA). Then, we construct three similarity kernels for all patients of the same cancer by gene expression, miRNA expression and isoform expression data. We also propose a novel unsupervised multiple kernel fusion method, Similarity Kernel Fusion (SKF), in order to integrate three similarity kernels into one combined kernel. Finally, we make use of spectral clustering on the integrated kernel to predict cancer subtypes. In the experimental results, the P-values from the Cox regression model and survival curve analysis can be used to evaluate the performance of predicted subtypes on three datasets. Our kernel fusion method, SKF, has outstanding performance compared with single kernel and other multiple kernel fusion strategies. It demonstrates that our method can accurately identify more accurate subtypes on various kinds of cancers. Our cancer subtype prediction method can identify essential genes and biomarkers for disease diagnosis and prognosis, and we also discuss the possible side effects of therapies and treatment.

show abstract

Section: Discussionmentioning

confidence: 99%

Discovering Cancer Subtypes via an Accurate Fusion Strategy on Multiple Profile Data

et al. 2019

View full text Add to dashboard Cite

show abstract

“…To further evaluate the prediction performance of BWHCDA, we compare it with other five methods including KATZHCDA [ 9 ], PageRank [ 20 ], NCP [ 21 ], BDSILP [ 22 ] and HeteSim [ 23 ]. Consequently, BWHCDA method achieve the best performance among these six approaches based on AUC values of LOOCV and 10-fold CV with the same datasets (Figs.…”

Section: Resultsmentioning

confidence: 99%

Inferring Candidate CircRNA-Disease Associations by Bi-random Walk Based on CircRNA Regulatory Similarity

Fan

Lei

Tan

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Identification of associations between circular RNAs (circRNA) and diseases has become a hot topic, which is beneficial for researchers to understand the disease mechanism. However, traditional biological experiments are expensive and time-consuming. In this study, we proposed a novel method named BWHCDA, which applied bi-random walk algorithm on the heterogeneous network for predicting circRNA-disease associations. First, circRNA regulatory similarity is measured based on circRNA-miRNA interactions, and circRNA similarity is calculated by the average of circRNA regulatory similarity and Gaussian interaction profiles (GIP) kernel similarity for circRNAs. Similarly, disease similarity is the mean of disease semantic similarity and GIP kernel similarity for diseases. Then, the heterogeneous network is constructed by integrating circRNA network, disease network via circRNA-disease associations. Subsequently, the bi-random walk algorithm is implemented on the heterogeneous network to predict circRNA-disease associations. Finally, we utilize leave-one-out cross validation and 10-fold cross validation frameworks to evaluate the prediction performance of BWHCDA method and obtain AUC of 0.9334 and 0.8764 ± 0.0038, respectively. Moreover, the predicted hsa_circ_0000519-gastric cancer association is analyzed. Results show that BWHCDA could be an effective resource for clinical experimental guidance.

show abstract

“…Peng et al (2018b) exploited a adaptive boosting-based method to compute association scores for human microbe-disease pairs based on a strong classification model. Zhang et al (2018) proposed a bi-direction similarity integration label propagation method (BDSILP) for identifying MDAs. Shi et al (2018) assumed that observed incomplete microbe-non-infectious disease association matrix is composed of a parameterized matrix and a noise matrix, and then developed a Binary Matrix Completion-based model (BMCMDA) to infer possible microbe-non-infectious disease associations.…”

Section: Introductionmentioning

confidence: 99%

RNMFMDA: A Microbe-Disease Association Identification Method Based on Reliable Negative Sample Selection and Logistic Matrix Factorization With Neighborhood Regularization

et al. 2020

View full text Add to dashboard Cite

Microbes with abnormal levels have important impacts on the formation and development of various complex diseases. Identifying possible Microbe-Disease Associations (MDAs) helps to understand the mechanisms of complex diseases. However, experimental methods for MDA identification are costly and time-consuming. In this study, a new computational model, RNMFMDA, was developed to find possible MDAs. RNMFMDA contains two main processes. First, Reliable Negative MDA samples were selected based on Positive-Unlabeled (PU) learning and random walk with restart on the heterogeneous microbe-disease network. Second, Logistic Matrix Factorization with Neighborhood Regularization (LMFNR) was developed to compute the association probabilities for all microbe-disease pairs. To evaluate the performance of the proposed RNMFMDA method, we compared RNMFMDA with five state-of-the-art MDA prediction methods based on five-fold cross-validations on microbes, diseases, and MDAs. As a result, RNMFMDA obtained the best AUCs of 0.6332, 0.8669, and 0.9081, respectively for the three five-fold cross validations, significantly outperforming other models. The promising prediction performance may be attributed to the following three features: highly quality negative MDA sample selection, LMFNR-based MDA prediction model, and various biological information integration. In addition, a few predicted microbe-disease pairs with high association scores are worthy of further experimental validation.

show abstract

The Bi-Direction Similarity Integration Method for Predicting Microbe-Disease Associations

Cited by 36 publications

References 46 publications

Discovering Cancer Subtypes via an Accurate Fusion Strategy on Multiple Profile Data

Discovering Cancer Subtypes via an Accurate Fusion Strategy on Multiple Profile Data

Inferring Candidate CircRNA-Disease Associations by Bi-random Walk Based on CircRNA Regulatory Similarity

RNMFMDA: A Microbe-Disease Association Identification Method Based on Reliable Negative Sample Selection and Logistic Matrix Factorization With Neighborhood Regularization

Contact Info

Product

Resources

About