Gene expression

AP_Colon_Kidney

These microarray gene expression profiles come from human tumor samples collected by the Expression Project for Oncology and assembled in GEMLeR. The benchmark predicts whether each sample comes from colon or kidney tissue.

Binary classificationLicence: PublicOpenML-1137Target: Tissueopenml ↗

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

Models

All metric values at this operating point

Model	Macro-F1	MCC	Balanced accuracy	ROC-AUC
Kumo Tabular (M)	0.9816	0.9634	0.9813	0.9979
RealTabPFN 2.5	0.9779	0.9561	0.9778	0.9974
LimiX2	0.9761	0.9524	0.9759	0.9978
Logistic Regression (tuned)	0.9761	0.9524	0.9759	0.9941
TabPFN 3.5	0.9761	0.9524	0.9759	0.997
MLP (tuned)	0.9761	0.9524	0.976	0.9945
TabPFN Wide 5k (ne3)	0.9743	0.9487	0.9741	0.997
MLP	0.9743	0.9487	0.9743	0.9944
TabDPT	0.9742	0.9491	0.9736	0.9937
Logistic Regression	0.9725	0.9451	0.9724	0.994
TabFM	0.9724	0.9459	0.9725	0.9971
Random Forest (tuned)	0.9724	0.9449	0.9724	0.9965
Extra Trees	0.9724	0.945	0.9725	0.9969
RealTabPFN v2	0.9724	0.9452	0.9722	0.9972
Causilo	0.9706	0.9413	0.9706	0.9962
Random Forest	0.9706	0.9413	0.9706	0.9968
Extra Trees (tuned)	0.9706	0.9413	0.9706	0.9962
GeneICL	0.967	0.9343	0.9675	0.9936
AutoGluon	0.9668	0.9345	0.9663	0.993
MITRA	0.965	0.931	0.9647	0.9952
TabM	0.9633	0.9269	0.9638	0.9929
RealMLP	0.9614	0.923	0.9615	0.9808
XGBoost	0.932	0.8653	0.9316	0.9423
XGBoost (tuned)	0.8074	0.6835	0.8372	0.9548