Fig 5 - uploaded by Gianvito Pio
Content may be subject to copyright.
Context in source publication
Context 1
... particular, we evaluated the results with the following configurations: α = 0.1 and β = 0.3; α = 0.1 and β = 0.4; α = 0.2 and β = 0.3; α = 0.2 and β = 0.4. By observing the results reported in Figure 5, obtained with the EC strategy on the first three hierarchical levels, we can conclude that the results do not appear to be significantly affected by these parameters. A similar behavior was observed for the other combination strategies and for HOCCLUS2. ...
Similar publications
Citations
... LION model applied the characteristics of lncRNAs, genes, and diseases to predict the relationships between lncRNAs and diseases through network diffusion (Sumathipala et al., 2019). At the same time, there are also related study based on heterogeneous clustering methods to predict the unknown relationships between lncRNAs and diseases based on the relationship network constructed by diseases, lncRNAs, microRNAs, and genes (Barracchia et al., 2018). LP-HCLUS uses multi-type hierarchical clustering methods to predict potentially lncRNA-disease relationships (Barracchia et al., 2020). ...
Motivation: Long non-coding RNAs (lncRNAs) play important roles in cancer development. Prediction of lncRNA–cancer association is necessary for efficiently discovering biomarkers and designing treatment for cancers. Currently, several methods have been developed to predict lncRNA–cancer associations. However, most of them do not consider the relationships between lncRNA with other molecules and with cancer prognosis, which has limited the accuracy of the prediction.
Method: Here, we constructed relationship matrices between 1,679 lncRNAs, 2,759 miRNAs, and 16,410 genes and cancer prognosis on three types of cancers (breast, lung, and colorectal cancers) to predict lncRNA–cancer associations. The matrices were iteratively reconstructed by matrix factorization to optimize low-rank size. This method is called detecting lncRNA cancer association (DRACA).
Results: Application of this method in the prediction of lncRNAs–breast cancer, lncRNA–lung cancer, and lncRNA–colorectal cancer associations achieved an area under curve (AUC) of 0.810, 0.796, and 0.795, respectively, by 10-fold cross-validations. The performances of DRACA in predicting associations between lncRNAs with three kinds of cancers were at least 6.6, 7.2, and 6.9% better than other methods, respectively. To our knowledge, this is the first method employing cancer prognosis in the prediction of lncRNA–cancer associations. When removing the relationships between cancer prognosis and genes, the AUCs were decreased 7.2, 0.6, and 5% for breast, lung, and colorectal cancers, respectively. Moreover, the predicted lncRNAs were found with greater numbers of somatic mutations than the lncRNAs not predicted as cancer-associated for three types of cancers. DRACA predicted many novel lncRNAs, whose expressions were found to be related to survival rates of patients. The method is available at https://github.com/Yanh35/DRACA.
... Therefore, lncRNAs could be used as biomarkers for the early diagnosis and prognosis of corresponding cancers, which motivates the identification and confirmation of the associations between lncRNAs and diseases to become a research focus. The lncRNA related databases (such as LncRNAdb [14], LncRNADisease [15], NRED [16], and NONCODE [17]) provide strong data support on which the computational prediction models can be built to provide more accurate experimental targets as well as an effective supplement to biological experiments [18][19][20][21][22]: Have a profound implication on drug development and medical improvement. ...
Long non-coding RNAs (long ncRNAs, lncRNAs) of all kinds have been implicated in a range of cell developmental processes and diseases, while they are not translated into proteins. Inferring diseases associated lncRNAs by computational methods can be helpful to understand the pathogenesis of diseases, but those current computational methods still have not achieved remarkable predictive performance: such as the inaccurate construction of similarity networks and inadequate numbers of known lncRNA–disease associations. In this research, we proposed a lncRNA–disease associations inference based on integrated space projection scores (LDAI-ISPS) composed of the following key steps: changing the Boolean network of known lncRNA–disease associations into the weighted networks via combining all the global information (e.g., disease semantic similarities, lncRNA functional similarities, and known lncRNA–disease associations); obtaining the space projection scores via vector projections of the weighted networks to form the final prediction scores without biases. The leave-one-out cross validation (LOOCV) results showed that, compared with other methods, LDAI-ISPS had a higher accuracy with area-under-the-curve (AUC) value of 0.9154 for inferring diseases, with AUC value of 0.8865 for inferring new lncRNAs (whose associations related to diseases are unknown), with AUC value of 0.7518 for inferring isolated diseases (whose associations related to lncRNAs are unknown). A case study also confirmed the predictive performance of LDAI-ISPS as a helper for traditional biological experiments in inferring the potential LncRNA–disease associations and isolated diseases.
... Several computation methods like LncRNADisease (Wang et al., 2016), GrwLDA (Gu et al., 2017), TPGLDA (Ding et al., 2018), and KATZLDA (Chen, 2015) uncover potential lncRNA-disease associations by integrating lncRNA functional similarities, lncRNA expression profiles, known lncRNA-disease associations, disease semantic similarities, and gene-disease associations. Studies seeking to predict non-coding RNAs in disease by constructing heterogenous networks with multiple types of biological interactions include ncPred, which uses resource transfer on a tripartite network (Alaimo et al., 2014); ComiRNet, which applies clustering to miRNA-gene regulatory networks (Pio et al., 2015); and LP-HCLUS, which integrates across interactions between lncRNAs, miRNAs, diseases, and genes (Barracchia et al., 2018). Most of these approaches use experimentally known lncRNA-disease associations as part of their input data and infer new lncRNA-disease associations. ...
Recently, long-non-coding RNAs (lncRNAs) have attracted attention because of their emerging role in many important biological mechanisms. The accumulating evidence indicates that the dysregulation of lncRNAs is associated with complex diseases. However, only a few lncRNA-disease associations have been experimentally validated and therefore, predicting potential lncRNAs that are associated with diseases become an important task. Current computational approaches often use known lncRNA-disease associations to predict potential lncRNA-disease links. In this work, we exploited the topology of multi-level networks to propose the LncRNA rankIng by NetwOrk DiffusioN (LION) approach to identify lncRNA-disease associations. The multi-level complex network consisted of lncRNA-protein, protein–protein interactions, and protein-disease associations. We applied the network diffusion algorithm of LION to predict the lncRNA-disease associations within the multi-level network. LION achieved an AUC value of 96.8% for cardiovascular diseases, 91.9% for cancer, and 90.2% for neurological diseases by using experimentally verified lncRNAs associated with diseases. Furthermore, compared to a similar approach (TPGLDA), LION performed better for cardiovascular diseases and cancer. Given the versatile role played by lncRNAs in different biological mechanisms that are perturbed in diseases, LION’s accurate prediction of lncRNA-disease associations helps in ranking lncRNAs that could function as potential biomarkers and potential drug targets.
Heterogeneous information network (HIN) is a kind of large-scale network which contains different types of objects and complex links. It is distinguished from a homogenous network for its heterogeneity of objects represented as nodes and complexity of links, which also makes the object classification more difficult. A meta-path can denote the relationship between nodes in HINs, and the path information can be enriched by extracting jump-paths. Based on this idea, the problem of data sparseness can be alleviated effectively. As multiple meta-paths represent different semantics, we propose an active weight learning method for each type, which aims to maximize the weight of meta-path with strong correlation and lower the weight if the correlation is weak. The feature matrix based on the meta-path is constructed and the Random Forest classifier is trained to implement the node classification in HINs. The experimental results show that our method achieves better performance in the complex network by using the fewer labeled data. The active learning strategy is effective for identifying objects to label for training.
