Gene expression

Riboflavin Production

This dataset pairs gene expression measurements in the bacterium Bacillus subtilis with its production of riboflavin, also called vitamin B2. The benchmark predicts the logarithmically scaled riboflavin production rate from logarithmically scaled gene expression values.

RegressionLicence: PublicOpenML-46983Target: xopenml ↗

At this operating point

Model comparison

p=10,000, n=50 · Lower RMSE 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	RMSE	MAE	R²
MITRA	0.4892	0.3867	0.6779
RealTabPFN 2.5	0.5202	0.3872	0.6428
RealTabPFN v2	0.5535	0.4064	0.6013
Logistic Regression	0.5536	0.4373	0.5921
TabPFN 3.5	0.5553	0.4102	0.5962
Logistic Regression (tuned)	0.5611	0.4335	0.5848
LimiX2	0.5629	0.4291	0.5705
Kumo Tabular (M)	0.5641	0.4226	0.5803
Causilo	0.5788	0.4353	0.5487
TabFM	0.5896	0.4414	0.5268
GeneICL	0.5939	0.4525	0.5316
TabM	0.6245	0.4702	0.4704
Extra Trees (tuned)	0.6318	0.4716	0.4678
MLP	0.6437	0.507	0.4458
RealMLP	0.6494	0.4927	0.4378
Extra Trees	0.6546	0.4901	0.4292
TabDPT	0.6585	0.4953	0.4292
Random Forest	0.6762	0.5181	0.3863
Random Forest (tuned)	0.6763	0.5097	0.3853
XGBoost (tuned)	0.6889	0.5274	0.3417
MLP (tuned)	0.7452	0.5405	0.1628
XGBoost	0.7965	0.6492	0.1447