Genomic prediction

Soybean Yield Genomic Prediction

Soybean plant lines are described by SNP genotype values and paired with their measured yield trait. The regression task predicts yield from these genetic markers using the soybean panel in Azodi and colleagues' genomic-prediction study.

RegressionLicence: CC0-1.0gp-soy-YLDTarget: YLDgp ↗

At this operating point

Model comparison

p=10,000, n=100 · 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
Logistic Regression (tuned)	0.8975	0.7119	0.1935
Kumo Tabular (M)	0.8989	0.708	0.1909
Random Forest	0.9002	0.7134	0.1875
Causilo	0.9015	0.7091	0.1857
Extra Trees	0.9015	0.7141	0.1852
Random Forest (tuned)	0.9052	0.7181	0.1788
TabPFN 3.5	0.9062	0.7141	0.1773
MLP (tuned)	0.9104	0.7173	0.1697
MLP	0.9104	0.7185	0.1698
TabDPT	0.9107	0.7162	0.1691
AutoGluon	0.9112	0.7175	0.1684
TabFM	0.9132	0.7169	0.1642
RealTabPFN 2.5	0.9196	0.7257	0.1531
TabM	0.923	0.7267	0.1462
RealTabPFN v2	0.9246	0.7287	0.1437
LimiX2	0.9293	0.7295	0.1344
MITRA	0.9338	0.7379	0.1264
GeneICL	0.9365	0.7426	0.1207
XGBoost (tuned)	0.9501	0.7521	0.0943
Extra Trees (tuned)	0.9821	0.781	0.03273
Logistic Regression	0.9961	0.7916	0.005921
XGBoost	1.005	0.793	-0.01244
RealMLP	1.021	0.8	-0.04839