1Department of Chemistry;
2Department of Bioengineering;
3School of Environmental and Forest Sciences;
4Department of Rehabilitation Medicine;
5Department of Applied Mathematics, University of Washington, Seattle, WA, 98105
Once thought only to be pathogenic, the microorganisms living on and within an animal host
are now recognized as playing critical roles in host health. Factors that shape gut microbial communities
are multifaceted and include the host’s diet and life-stage.
While microbial shifts have been implicated in numerous human ailments (e.g., obesity, anxiety,
inflammatory bowel disease), research has thus far been limited to differentiating microbial communities
between groups and less for predictive uses. As a result of an ever expanding
microbiome data availability, microbiome research lends itself to advancement with machine learning and data science.
However, the implementation of machine learning in microbiome research might feel daunting and time consuming to
those outside of the realm of data science.
Our team strive to build a software prroduct that can deploy an automated machine learning model with minimum of knowledge in data science and machine learning. The model is developed based on the open source dataset from Qiita.
Our product is developed based on 7 different algorithms, each of it have different characteistics so that our product can handle different dataset.
Click the dropdown list to see algorithms option we provide
