1. Introduction Characterization of microbial communities with omics technologies shed to light powerful biomarkers for diagnosis and prognosis in human health [1]. In particular, shotgun metagenomics allows a highly precise microbiome profiling. Indeed, prediction of phenotypic features, such as clinical status or disease states can help to stratify patients which is the first step toward precision medicine. Many machine learning (ML) methods have been developed to tackle classification and regression problems yet statistical specificities of metagenomic data make difficult the learning task [2]. In the present work, we compare the commonly used ML methods on a quantitative metagenomics dataset. 2. Methods We developed a workflow in R to browse and compare ML methods for classification or regression implemented in the caret package [3]. A table where microbial features (species, functions, metabolites) are quantified across a set labelled samples (e.g: control/disease) is taken as input. Then, the selected models are trained and evaluated with repeated 10 fold cross validation. Each model is trained 100 times with different random splits. The Activeon Proactive workflow engine was used to efficiently distribute the computing load on multiple servers. 3. Results We applied our workflow on a dataset where the fecal microbiota of patients with cardiovascular diseases is compared to healthy controls using shotgun metagenomics. Each model was tested on regression or classification problems, expected to be easy or difficult to predict. We compared the models with several indicators including predictive performance (F-score, Rð), stability across iterations and computational resources consumption. We also explored the impact of common preprocessing steps to remove non informative variables (near zero variance features, linear combo, etc.). We observed that a wide range of common methods show similar predictive performance (svm, pls, glm, rf, etc.) although some can be very slow (spls). Finally, the choice of the best model may be guided by other criteria like the interpretability that can give insights in the underlying biological hypotheses in order to provide insightful medical decisions. References 1. Laura Judith Marcos-Zambrano et al. Applications of machine learning in human microbiome studies: a review on feature selection, biomarker identification, disease prediction and treatment. FURQWieUV iQ PicURbiRlRg\, vol. 12, p. 313, 2021. 2. Isabel Moreno-Indias et al. Statistical and machine learning techniques in human microbiome studies: contemporary challenges and solutions. FURQWieUV iQ MicURbiRlRg\, vol. 12, p. 277, 2021. 3. Max Kuhn. Caret: classification and regression training. AVWURSh\VicV SRXUce CRde LibUaU\, ascl-1505, 2015. https://topepo.github.io/caret/