Abstract
The gut microbiome plays an important role in the healthy and efficient farming of dairy cows. However, high-dimensional microbial information is difficult to interpret in a simplified manner. We collected fecal samples from 161 cows and performed 16S amplicon sequencing. We developed an interpretable machine learning framework to classify individuals based on their milk urea nitrogen (MUN) concentrations. In this framework, we address the challenge of handling high-dimensional microbial data imbalances and identify 9 microorganisms strongly correlated with MUN. We introduce the Shapley Additive Explanations (SHAP) method to provide insights into the machine learning predictions. The results of the study showed that the performance of the machine learning model improved (accuracy = 72.7%) after feature selection on high-dimensional data. Among the 9 microorganisms, g__Firmicutes_unclassified had the greatest impact in the model. This study provides a reference for precision animal husbandry.