Investigation of Adiposity Measures and Operational Taxonomic unit (OTU) Data Transformation Procedures in Stool Samples from a German Cohort Study Using Machine Learning Algorithms

Abstract

The analysis of the gut microbiome with respect to health care prevention and diagnostic purposes is increasingly the focus of current research. We analyzed around 2000 stool samples from the KORA (Cooperative Health Research in the Region of Augsburg) cohort using high-throughput 16S rRNA gene amplicon sequencing representing a total microbial diversity of 2089 operational taxonomic units (OTUs). We evaluated the combination of three different components to assess the reflection of obesity related to microbiota profiles: (i) four prediction methods (i.e., partial least squares (PLS), support vector machine regression (SVMReg), random forest (RF), and M5Rules); (ii) five OTU data transformation approaches (i.e., no transformation, relative abundance without and with log-transformation, as well as centered and isometric log-ratio transformations); and (iii) predictions from nine measurements of obesity (i.e., body mass index, three measures of body shape, and five measures of body composition). Our results showed a substantial impact of all three components. The applications of SVMReg and PLS in combination with logarithmic data transformations resulted in considerably predictive models for waist circumference-related endpoints. These combinations were at best able to explain almost 40% of the variance in obesity measurements based on stool microbiota data (i.e., OTUs) only. A reduced loss in predictive performance was seen after sex-stratification in waist–height ratio compared to other waist-related measurements. Moreover, our analysis showed that the contribution of OTUs less prevalent and abundant is minor concerning the predictive power of our models.

An approach to finding specific forms of dysbiosis that associate with different disorders

“…However, RF analyses are generally both robust and sensitive when analysing microbiome data. [20,45] Moreover in the present context, RF models generated partial plots that could help to assess the influence of heteroscedasticity in the ANHAC approach (see above).…”

“…[18] RF may be optimal for this purpose. [19][20][21][22] However, RF tends to perform badly in high-dimensional analyses with a low fraction of relevant predictors and small sample sizes. [23] Therefore, we used preliminary RF analyses to select important variables for each classification, before constructing large RFs that used the selected variables to predict each diagnostic grouping.…”

Effects of plant extracts on biogenic amine accumulation, bacterial abundance and diversity in fermented sausage

“…High throughput sequencing technologies can generate a tremendous amount of sequencing data, and detect the complex microbial communities. The sequenced reads of the amplicons were clustered into operational taxonomic units (OTUs) based on sequence similarity, and then the relative abundances and read counts were evaluated (Troll et al, 2020). Based on OTUs, the microbial diversity and species abundance were examined (Soon et al, 2013).…”