Automated ML framework
An end-to-end framework for biomedical classification on compositional microbiome data: from abundance tables to calibrated, interpretable individual or multi-view ensemble models.
The recommended package implementation is streamlined for lighter-weight configuration, reproducible sweep artefacts, out-of-fold explainability, and clone-ready examples with lightweight data.
Earlier documentation and the legacy implementation remain available as secondary references: legacy docs · legacy repository.
Step 1 — MPMA discovery
the qualified configurations can enter the ensemble sweep
Step 2 — Multi-view ensemble construction
explainable ai methods are applied to the algorithms
Step 3a — Global XAI
top-ranked features can be traced to individual samples
Step 3b — Local XAI