{"id":22709,"date":"2023-01-11T10:21:59","date_gmt":"2023-01-11T15:21:59","guid":{"rendered":"https:\/\/carleton.ca\/math\/?p=22709"},"modified":"2023-01-11T10:21:59","modified_gmt":"2023-01-11T15:21:59","slug":"colloquium-school-of-mathematics-and-statistics-carleton-university-2","status":"publish","type":"post","link":"https:\/\/carleton.ca\/math\/2023\/colloquium-school-of-mathematics-and-statistics-carleton-university-2\/","title":{"rendered":"Colloquium \u2013 School of Mathematics and Statistics, 杏吧原创 University"},"content":{"rendered":"
Date: Friday, January 20, 2023
\nTime: 3:30 – 4:30 PM (coffee starting at 3:00 p.m.)
\nRoom: Herzberg building, room 4351 (MacPhail Room)
\nTitle:\u00a0Cluster analysis of microbiome data via mixtures of Dirichlet-multinomial regression models
\nSpeaker:\u00a0 Sanjeena Dang, 杏吧原创 University<\/p>\n
Abstract:\u00a0 <\/strong>The human gut microbiome is an essential component of our physiology and exploring the relationship between biological\/environmental covariates and the resulting taxonomic composition of a given microbial community is an active area of research. Previously, a Dirichlet-multinomial regression framework has been suggested to model this relationship, but it did not account for any underlying latent group structure. An underlying group structure of guts (such as enterotypes) has been observed across gut microbiome samples in which guts in the same group share similar biota compositions. In this talk, a finite mixture of Dirichlet-multinomial regression models will be presented that accounts for this underlying group structure and to allow for a probabilistic investigation of the relationship between bacterial abundance and biological\/environmental covariates within each inferred group.<\/p>\n Furthermore, finite mixtures of regression models, which incorporate the concomitant effect of the covariates on the resulting mixing proportions are also proposed and examined within the Dirichlet-multinomial framework.<\/p>\n We utilize the proposed mixture model to gain insight on underlying subgroups in a microbiome dataset comprising of tumor and healthy samples and the relationships between covariates and microbial abundance in those subgroups. The talk will conclude with some current and future research directions involving microbiome data.<\/p>\n