Gene expression

Breast Cancer Subtypes (GSE10893)

Microarray measurements record gene expression in human breast tissue samples from a study of breast cancer subtypes. The benchmark uses the GPL8864 subset to predict the intrinsic subtype recorded for each sample.

ClassificationLicence: Not specifiedGEO-GSE10893Target: subtypegeo ↗

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
Logistic Regression	0.4597	0.4094	0.4613	0.7897
Kumo Tabular (M)	0.454	0.4045	0.4563	0.8002
Logistic Regression (tuned)	0.4358	0.3774	0.4459	0.7775
GeneICL	0.4358	0.3919	0.4527	0.7988
LimiX2	0.4304	0.3411	0.4344	0.7454
TabM	0.4167	0.3553	0.4283	0.7265
RealMLP	0.4153	0.3646	0.4303	0.7311
MLP	0.3967	0.3422	0.4043	0.7632
TabPFN 3.5	0.3876	0.3661	0.4089	0.7668
MLP (tuned)	0.3791	0.308	0.3836	0.7422
RealTabPFN 2.5	0.3655	0.3696	0.3995	0.7906
AutoGluon	0.3449	0.353	0.3805	0.7733
TabPFN Wide 5k (ne3)	0.3399	0.3524	0.3809	0.7917
TabFM	0.3274	0.3177	0.368	0.7671
Random Forest (tuned)	0.3263	0.2896	0.3549	0.709
Causilo	0.3091	0.2574	0.3325	0.7317
TabDPT	0.3067	0.2995	0.3469	0.7729
Extra Trees	0.2961	0.2583	0.3242	0.7017
RealTabPFN v2	0.2954	0.2907	0.3288	0.701
XGBoost	0.2942	0.1742	0.3073	0.617
XGBoost (tuned)	0.2913	0.1781	0.3057	0.6802
MITRA	0.28	0.2151	0.3046	0.6334
Extra Trees (tuned)	0.2791	0.2408	0.3142	0.7052
Random Forest	0.2659	0.1887	0.2963	0.6979