With the pre-trained model on over 900 microbiome-metabolome paired samples, the ML approach yielded the most accurate predictions (i.e., highest F1 scores) of metabolite occurrences in the human gut and outperformed reference-based pipelines in predicting differential metabolites between case and control subjects. We used these datasets to evaluate two reference-based gene-to-metabolite prediction pipelines and a machine-learning (ML) based metabolic profile prediction approach. Paired microbiome sequencing (16S rRNA gene amplicons, shotgun metagenomics, and metatranscriptomics) and metabolome (mass spectrometry and nuclear magnetic resonance spectroscopy) datasets were collected from six independent studies spanning multiple diseases. To address these difficulties, we tested the feasibility of predicting the metabolites of a microbial community based solely on microbiome sequencing data. Unfortunately, as cohort sizes increase, comprehensive metabolomic profiling becomes costly and logistically difficult to perform at a large scale. As such, metabolomic information bears immense potential to improve disease diagnosis and therapeutic drug discovery. Metabolomic analyses of human gut microbiome samples can unveil the metabolic potential of host tissues and the numerous microorganisms they support, concurrently. 3Department of Medicine, University of Calgary, Calgary, AB, Canada.2Altman Analytics LLC, San Francisco, CA, United States.1Second Genome Inc., Brisbane, CA, United States.West 1 Yonggan Wu 1 Jinlyung Choi 1 Paul L. Xiaochen Yin 1 Tomer Altman 2 Erica Rutherford 1 Kiana A.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |