Identifying diseases-related metabolites using random walk

Abstract

BackgroundMetabolites disrupted by abnormal state of human body are deemed as the effect of diseases. In comparison with the cause of diseases like genes, these markers are easier to be captured for the prevention and diagnosis of metabolic diseases. Currently, a large number of metabolic markers of diseases need to be explored, which drive us to do this work.MethodsThe existing metabolite-disease associations were extracted from Human Metabolome Database (HMDB) using a text mining tool NCBO annotator as priori knowledge. Next we calculated the similarity of a pair-wise metabolites based on the similarity of disease sets of them. Then, all the similarities of metabolite pairs were utilized for constructing a weighted metabolite association network (WMAN). Subsequently, the network was utilized for predicting novel metabolic markers of diseases using random walk.ResultsTotally, 604 metabolites and 228 diseases were extracted from HMDB. From 604 metabolites, 453 metabolites are selected to construct the WMAN, where each metabolite is deemed as a node, and the similarity of two metabolites as the weight of the edge linking them. The performance of the network is validated using the leave one out method. As a result, the high area under the receiver operating characteristic curve (AUC) (0.7048) is achieved. The further case studies for identifying novel metabolites of diabetes mellitus were validated in the recent studies.ConclusionIn this paper, we presented a novel method for prioritizing metabolite-disease pairs. The superior performance validates its reliability for exploring novel metabolic markers of diseases.

Multi‐network logistic matrix factorization for metabolite–disease interaction prediction

“…In the previous studies [10,11], many methods took advantage of the known metabolite–disease interaction network to build the metabolite similarity network, which would lead to the model relying too much on the current known interaction information. Therefore, this way of constructing metabolite similarity network is not conducive for the model to predict novel metabolites (or diseases) without any interactive information .…”

“…Based on the disease similarity network and the metabolite–disease interaction network, Hu et al . [10] utilized ‘MISIM’ to obtain the metabolite network and then used random walk to predict the metabolite–disease interactions. Recently, Wang et al .…”

“…[11] proposed a metabolite–disease interaction prediction model, which, unlike Hu et al . [10], utilized modified collaborative filtering to construct a metabolite network.…”

6mA-RicePred: A Method for Identifying DNA N6-Methyladenine Sites in the Rice Genome Based on Feature Fusion

“…It is important to evaluate the results of a new model, and several evaluation metrics are available. Sensitivity (Sn), specificity (Sp), accuracy (Acc), and Mathew's correlation coefficient (MCC) are often used to evaluate the quality of a model in machine learning (Liu B. et al, 2019;Cheng et al, 2012;Cheng et al, 2016;Ding et al, 2016b;Mariani et al, 2017;Ding et al, 2017;Wei et al, 2017a;Wei et al, 2017b;Hu et al, 2018;Zhang et al, 2018c;Ding et al, 2019;Shan et al, 2019;Tan et al, 2019b;Cheng et al, 2019b). These metrics are formulated as follows: These metrics are commonly used in machine learning.…”

PSBP-SVM: A Machine Learning-Based Computational Identifier for Predicting Polystyrene Binding Peptides

“…In addition, the SVM is also one of the common kernel learning methods for non-linear classification (Yang et al, 2019a). In recent years, SVMs have been successfully applied in bioinformatics fields (Xiong et al, 2012(Xiong et al, , 2019Zhang et al, 2015;Zhang J. et al, 2019;Ding et al, 2016a,b;Wei et al, 2016;Zeng et al, 2017;Zhao et al, 2017;Bu et al, 2018;Xu et al, 2018c;Hu et al, 2019;Liu and Li, 2019;Liu et al, 2019b;Wang et al, 2019;Dou et al, 2020). The LIBSVM is a widely used SVM tool.…”