LRLSHMDA: Laplacian Regularized Least Squares for Human Microbe–Disease Association prediction

Abstract

An increasing number of evidences indicate microbes are implicated in human physiological mechanisms, including complicated disease pathology. Some microbes have been demonstrated to be associated with diverse important human diseases or disorders. Through investigating these disease-related microbes, we can obtain a better understanding of human disease mechanisms for advancing medical scientific progress in terms of disease diagnosis, treatment, prevention, prognosis and drug discovery. Based on the known microbe-disease association network, we developed a semi-supervised computational model of Laplacian Regularized Least Squares for Human Microbe–Disease Association (LRLSHMDA) by introducing Gaussian interaction profile kernel similarity calculation and Laplacian regularized least squares classifier. LRLSHMDA reached the reliable AUCs of 0.8909 and 0.7657 based on the global and local leave-one-out cross validations, respectively. In the framework of 5-fold cross validation, average AUC value of 0.8794 +/−0.0029 further demonstrated its promising prediction ability. In case studies, 9, 9 and 8 of top-10 predicted microbes have been manually certified to be associated with asthma, colorectal carcinoma and chronic obstructive pulmonary disease by published literature evidence. Our proposed model achieves better prediction performance relative to the previous model. We expect that LRLSHMDA could offer insights into identifying more promising human microbe-disease associations in the future.

Predicting Microbe-Disease Association by Learning Graph Representations and Rule-Based Inference on the Heterogeneous Network

“…For microbes m(i) and m(j), the similarity score is obtained according to Eq. (1) (Wang et al, 2017):…”

“…Zou et al (2017) used a bi-random walk and logistic function transformation on a heterogeneous network constructed based on the GIP kernel similarity. Through a combination of the GIP kernel similarity and LapRLS classification, Wang et al (2017) designed a computing model LRLSHMDA, which is semisupervised . Meanwhile, through integrating the GIP kernel similarity with disease symptom similarity, Qu et al (2019) implemented the matrix decomposition and label propagation algorithm on the similarity network for associations' prediction .…”

Integrative Analysis for Identifying Co-Modules of Microbe-Disease Data by Matrix Tri-Factorization With Phylogenetic Information

“…Based on the hypothesis that functionally similar microbes could be associated with more common human diseases, Gaussian kernel interaction profiles can be used to calculate the inferred microbe similarity (Wang et al, 2017;He et al, 2018). Given microbe-disease association matrix X, the ith row of X indicates the interaction profiles between microbe m i and all the diseases.…”

“…Here, n m is the number of microbes related to all diseases (here, n m =292). g′ m was set as 1 according to the previous study (Wang et al, 2017). In this way, microbe similarity matrix MS can be constructed, the element of MS indicates the similarity score between two arbitrary microbes.…”

“…Zhang et al proposed bidirection similarity integration method (BDSILP) for predicting microbe-disease associations by integrating the disease-disease semantic similarity and the microbe-microbe functional similarity. Wang et al proposed a semisupervised computational model called LRLSHMDA to predict large-scale microbe-disease association (Wang et al, 2017). Huang et al combined neighbor-based collaborative filtering and graphbased model into a unified objective function to predict microbe-disease relationship .…”