Meta-Signer: Metagenomic Signature Identifier based onrank aggregation of features

The advance of metagenomic studies provides the opportunity to identify microbial taxa that are associated with human diseases. Multiple methods exist for association analysis. However, results could be inconsistent, presenting challenges in interpreting host-microbiome interactions. To address this issue, we develop Meta-Signer, a novel Metagenomic Signature Identifier tool based on rank aggregation features identified from multiple machine learning models including Random Forest, Support Vector Machines, Logistic Regression, and Multi-Layer Perceptron Neural Networks. Meta-Signer generates ranked lists by training individual over partitions aggregates into single list an optimization procedure represent most informative robust features. A User will receive speedy assessment predictive performance each ma-chine model using different numbers determine final used evaluation external datasets. is user-friendly customizable, allowing users explore their datasets quickly efficiently.