A repository of microbial marker genes related to human health and diseases for host phenotype prediction using microbiome data

Abstract

The microbiome research is going through an evolutionary transition from focusing on the characterization of reference microbiomes associated with different environments/hosts to the translational applications, including using microbiome for disease diagnosis, improving the efficacy of cancer treatments, and prevention of diseases (e.g., using probiotics). Microbial markers have been identified from microbiome data derived from cohorts of patients with different diseases, treatment responsiveness, etc, and often predictors based on these markers were built for predicting host phenotype given a microbiome dataset (e.g., to predict if a person has type 2 diabetes given his or her microbiome data). Unfortunately, these microbial markers and predictors are often not published so are not reusable by others. In this paper, we report the curation of a repository of microbial marker genes and predictors built from these markers for microbiomebased prediction of host phenotype, and a computational pipeline called Mi2P (from Microbiome to Phenotype) for using the repository. As an initial effort, we focus on microbial marker genes related to two diseases, type 2 diabetes and liver cirrhosis, and immunotherapy efficacy for two types of cancer, non-small-cell lung cancer (NSCLC) and renal cell carcinoma (RCC). We characterized the marker genes from metagenomic data using our recently developed subtractive assembly approach. We showed that predictors built from these microbial marker genes can provide fast and reasonably accurate prediction of host phenotype given microbiome data. As understanding and making use of microbiome data (our second genome) is becoming vital as we move forward in this age of precision health and precision medicine, we believe that such a repository will be useful for enabling translational applications of microbiome data.

Predicting Personalized Responses to Dietary Fiber Interventions: Opportunities for Modulation of the Gut Microbiome to Improve Health

“…Accordingly, Vangay et al (2019) compiled a microbiome learning repository consisting of curated classification and regression tasks to promote the development of machine learning methods among microbiome researchers and algorithm developers. Han & Ye (2019) have also curated a repository of microbial marker genes gathered from publicly available data sets for the purpose of creating microbiome-based predictions. Similarly, Carrieri et al (2019) and Pasolli et al (2016) described machine learning workflows specifically for predicting phenotypes from metagenomic data.…”

Use of artificial intelligence for management and identification of complications in diabetes

“…The other uses of AI could be summarized: -Population risk stratification by the healthcare recommendation system to predict the risk of diabetes. These models are based on large data analytics; -Genomics-Microbiome data has been used to build the repository of various microbial marker genes which can help in predictability of developing diabetes in future [20]; -Increasing patient's self awareness and treatment -use of mobile applications; -Remote monitoring of the diabetes status through use of automated real time monitoring devices; -Life style modification tracking devices-Wearable devices like smart bands and smart scales. Today AI has future prospects in helping physicians in decision making and to tailor make individual patient's diabetes management and also ensuring adherence to treatment for better health outcomes.…”

Locality-Sensitive Hashing-Based k-Mer Clustering for Identification of Differential Microbial Markers Related to Host Phenotype

“…The annotation of the subtractive assembly leads to the rapid identification of differential genes that can be used as features for microbiome-based phenotype prediction. We further applied CoSA to several microbiome data sets of human diseases, which were collected and disseminated for testing new methods for deriving microbial features and for developing predictive models by a broad research community (Han and Ye, 2018 ).…”