Automated ML framework

Optimum machine
learning for the
microbiome.

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.

Check real example tutorialCurrent repository

Earlier documentation and the legacy implementation remain available as secondary references: legacy docs · legacy repository.

Step 1 — MPMA discovery

Data representation meets learner: the joint search

the qualified configurations can enter the ensemble sweep

Step 2 — Multi-view ensemble construction

Ensemble sweep: combining complementary views

explainable ai methods are applied to the algorithms

Step 3a — Global XAI

Group-level explanations: four methods, results compared feature by feature

top-ranked features can be traced to individual samples

Step 3b — Local XAI

Instance-level explanations: how features contributed to each individual prediction