DNA methylation

Rheumatoid Arthritis DNA Methylation (GSE42861)

DNA methylation profiles from peripheral blood leukocytes of people with rheumatoid arthritis and control participants, measured with Illumina HumanMethylation450 arrays. The task is to classify rheumatoid arthritis case status from methylation levels at CpG sites.

Binary classificationLicence: NCBI GEO public data; study-specific terms require verification before re-hostingGEO-GSE42861-Methylation-RATarget: disease stategeo_matrix ↗

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
TabPFN Wide 5k (ne3)	0.7764	0.5567	0.7766	0.8597
Logistic Regression (tuned)	0.7728	0.5481	0.773	0.8457
Logistic Regression	0.7717	0.5444	0.7719	0.8485
RealTabPFN v2	0.77	0.5412	0.77	0.8398
TabDPT	0.7673	0.5383	0.7682	0.8394
LimiX2	0.7661	0.5335	0.7666	0.8399
GeneICL	0.7655	0.5327	0.7654	0.8426
Kumo Tabular (M)	0.7632	0.5313	0.7633	0.8546
TabPFN 3.5	0.7624	0.5271	0.7625	0.8533
Extra Trees (tuned)	0.7618	0.5284	0.7623	0.8339
AutoGluon	0.7612	0.5249	0.7615	0.828
RealTabPFN 2.5	0.7594	0.521	0.7595	0.8548
Extra Trees	0.7578	0.5199	0.7579	0.837
Random Forest	0.7561	0.5168	0.7563	0.8322
TabFM	0.755	0.5283	0.7569	0.856
TabM	0.753	0.5114	0.7533	0.8287
Random Forest (tuned)	0.7525	0.5066	0.7524	0.8272
MLP (tuned)	0.7495	0.5038	0.7507	0.8155
RealMLP	0.7429	0.4964	0.7444	0.8208
Causilo	0.7316	0.4778	0.7337	0.8323
XGBoost	0.7276	0.463	0.7283	0.7806
MLP	0.7206	0.4435	0.7211	0.7934
MITRA	0.7101	0.426	0.7108	0.7878
XGBoost (tuned)	0.6589	0.3437	0.6642	0.7185