|
Title A Machine Learning Model Basing On Initial Gut Microbiome Data for Predicting Changes Of Bifidobacterium after Prebiotics Consumption |
|
Type Poster Presentation |
|
Theme Probiotics and Prebiotics: Excellence in Science and Clinical Translation |
|
Topic Probiotic and Prebiotic Clinical Research, From Newborns to Elderly |
|
Main Author Yuemei Luo1 2 |
|
Presenting Author Yuemei Luo1 2 Feitong Liu1 2 Muxuan Chen2 Hongwei Zhou2 |
|
Co-Author Feitong Liu1 2 Muxuan Chen2 Hongwei Zhou2 |
|
Department / Institution / Country Department of Environmental Health / School of Public Health, Southern Medical University / China (中国)1 Division of Laboratory Medicine / Zhujiang Hospital, Southern Medical University / China (中国)2 |
|
Background and Rationale Short-term prebiotics intervention effect in Intestinal flora base on high-throughput sequencing has not been set forth. Personal effect linking to initial gut microbiome after prebiotics consumption still uncleared. |
|
Objectives: Indicates the purpose of the study The aim of the study was to investigate the effects of 9 days prebiotics supplementation on gut microbiota structure and function, and then to establish a machine learning model based on initial gut microbiota for predicting the variation of Bifidobacterium after prebiotic intake, which might provide a guidance to personalized diet. |
|
Methodology: Describe pertinent experimental procedures 35 healthy subjects consumed FOS or GOS for 9 days (16g per day) in a randomized double-blind self-controlled study. 16S rRNA gene high-throughput sequencing was performed to investigate the change of gut microbiota after prebiotics intake. PICRUSt was used to infer differences between the functional modules of the bacterial communities. Random forest model based on initial gut microbiota was used to identify the change of Bifidobacterium after 5 days prebiotic intake and then built a continuous index to predict the change of Bifidobacterium. |
|
Results: Summarize the results of the research Feces samples analysis with QIIME revealed that both FOS and GOS supplement decrease α-diversity. The continuous index could successful predict the change of Bifidobacterium (R=0.45, p=0.01). Prediction was accurate in a validation model (R=0.62, p=0.01). |
|
Conclusions: State the main conclusions Short-term prebiotics intervention could significantly decrease α diversity of intestinal flora. A machine learning model based on initial gut microbiota could accurately predict the change of Bifidobacterium. This method might provide reference for personalized nutrition intervention and precisely modulating intestinal flora. |