Human microbiota is an important determinant for health and disease, and accumulating recent studies emphasize the associations between microbiota and a wide range of human noninfectious diseases. For example, microbes inhabiting the human intestine mediate key metabolic, physiological and immune functions, and perturbations of this ecosystem can profoundly influence health and disease. As disease states can also impose secondary changes to the microbiota, a fundamental understanding of the forces determining micro¬bial composition in healthy individuals is essential for deciphering the nature of disease states and developing therapeutic strategies. The human microbiota is highly variable from one person to another, but many studies have been conducted to examine as to what extent the microbiota composition influence the host diseases.
Understanding how the microbiota is assembled and associated to the host disease can be relevant in the treatment of chronic complex diseases, such as inflammatory bowel disease (IBD), diabetes and so on. Predicting microbe–disease associations could not only boost human disease diagnostic and prognostic, but also improve the new drug development. However, little efforts have been attempted to understand and predict human microbe–disease associations on a large scale until now. And the traditional methods are both expansive and time-consuming. In contrast to the traditional experimental approach, the aim of us is to assess these microbe-disease associations on a large-scale in human with the computational methods based on the big data accumulated by the previous experimental methods. To find associations between the microbes and their corresponding diseases of the host, various statistical and computational techniques could be employed.
Meanwhile, benefitting from the rapid development of artificial intelligence, accumulating computational methods of analyses and prediction on large scale data have been developed to work for various fields related to data science. As the previous traditional experimental results revealed, the human microbe-disease pairs appeared some laws to be associated with each other. Therefore, it is feasible and necessary to build advanced intelligent algorithm or computational models to reveal the microbe-disease associations. Furthermore, with the help of the computational methods, the experimental analyses of associations between microbes and disease or other instances could be more convenient and accurate. Therefore, we can look forward that more and more computational models on microbe-disease association prediction will be developed to promote the further experimental studies with our best efforts.
Human microbiota is an important determinant for health and disease, and accumulating recent studies emphasize the associations between microbiota and a wide range of human noninfectious diseases. For example, microbes inhabiting the human intestine mediate key metabolic, physiological and immune functions, and perturbations of this ecosystem can profoundly influence health and disease. As disease states can also impose secondary changes to the microbiota, a fundamental understanding of the forces determining micro¬bial composition in healthy individuals is essential for deciphering the nature of disease states and developing therapeutic strategies. The human microbiota is highly variable from one person to another, but many studies have been conducted to examine as to what extent the microbiota composition influence the host diseases.
Understanding how the microbiota is assembled and associated to the host disease can be relevant in the treatment of chronic complex diseases, such as inflammatory bowel disease (IBD), diabetes and so on. Predicting microbe–disease associations could not only boost human disease diagnostic and prognostic, but also improve the new drug development. However, little efforts have been attempted to understand and predict human microbe–disease associations on a large scale until now. And the traditional methods are both expansive and time-consuming. In contrast to the traditional experimental approach, the aim of us is to assess these microbe-disease associations on a large-scale in human with the computational methods based on the big data accumulated by the previous experimental methods. To find associations between the microbes and their corresponding diseases of the host, various statistical and computational techniques could be employed.
Meanwhile, benefitting from the rapid development of artificial intelligence, accumulating computational methods of analyses and prediction on large scale data have been developed to work for various fields related to data science. As the previous traditional experimental results revealed, the human microbe-disease pairs appeared some laws to be associated with each other. Therefore, it is feasible and necessary to build advanced intelligent algorithm or computational models to reveal the microbe-disease associations. Furthermore, with the help of the computational methods, the experimental analyses of associations between microbes and disease or other instances could be more convenient and accurate. Therefore, we can look forward that more and more computational models on microbe-disease association prediction will be developed to promote the further experimental studies with our best efforts.
