← All datasets

Metagenomics

EMG produced TPA metagenomics assembly of the PRJNA275349 data set (Human Microbiome Environment Metagenome).

Assembled Human Microbiome Project sequences from samples collected across several body sites in healthy adults. The benchmark uses MGnify InterPro functional-abundance profiles to predict each sample's recorded isolation source.

Binary classificationLicence: PublicMGYS00005380Target: isolation sourcemgnify ↗

Mean cross-validation scores for this dataset. Each score comes from the requested feature- and sample-cap cell, and failed fits use the constant predictor.

At this operating point

Model comparison

p=10,000, n=100 · Higher Macro-F1 is better

Random Forest is marked with a diamond. Models are ordered by the selected metric.

Across sample budgets

Learning curves

All metric values at this operating point
ModelMacro-F1MCCBalanced accuracyROC-AUC
AutoGluon1111
Causilo1111
GeneICL1111
Kumo Tabular (M)1111
LimiX21111
Logistic Regression1111
MLP1111
MLP (tuned)1111
RealMLP1111
RealTabPFN v21111
RealTabPFN 2.51111
TabDPT1111
TabFM1111
TabPFN 3.51111
Logistic Regression (tuned)0.99570.99160.99441
MITRA0.99570.99160.99441
TabPFN Wide 5k (ne3)0.99570.99160.99441
TabM0.99170.98380.98941
Extra Trees (tuned)0.99170.98380.98941
Random Forest0.99130.98320.98891
Extra Trees0.99130.98320.98891
Random Forest (tuned)0.98730.97550.98391
XGBoost0.97750.95820.97190.9719
XGBoost (tuned)0.97370.94990.96660.9783