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.
Highlights
Over millennia, since the mutualistic symbiotic relationship was naturally selected and developed by evolutionarily ancient symbiosis of human and their commensal microbiota, they have been mutually affected by diverse interactions in many aspects
leave-one-out cross validation (LOOCV) was implemented on the known verified microbe-disease association pairs, each of which was left out in turns to be a test sample when others were used for training model
If the test sample is ranked higher than the specific threshold, it could be considered to make a correct prediction for this test microbe-disease association pair
Summary
Since the mutualistic symbiotic relationship was naturally selected and developed by evolutionarily ancient symbiosis of human and their commensal microbiota, they have been mutually affected by diverse interactions in many aspects. A human microbe–disease association database called HMDAD41 manually integrated 483 disease-microbe association entries at the genus level based on previously published literatures These databases are regarded as the essential tools for capturing and analyzing the rapidly accumulating information for microorganisms, which provides a possibility for large-scale disease-related prediction. Increasing attention has been paid to computational biology for microbe-disease association[52,53,54,55,56] These computational methods have been developed to facilitate relevant research in different ways, such as: the package for implementing community-level metabolic network reconstruction, the computational methodology for predicting the influence of microbial proteins in human biological events, the computational framework for identification of key functional differences in microbiome-related disease, the web application for annotation and analysis of specific genes in the human gut microbiome. Promising validation results demonstrated that LRLSHMDA could be an effective tool to advance the identification of disease-related microbes and aid future research focus towards a mutualistic symbiotic relationship between microorganisms and their human host
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
