Supporting data for "Random forest boosts genetic risk prediction of systemic lupus erythematosus (SLE) but does not distinguish between patients with lupus nephritis (LN) and non-LN"

Systemic lupus erythematosus (SLE) is a classic autoimmune disease that affects several vital organs throughout the body, including the heart, brain, kidneys, joints, skin and central nervous system. Conventional method of Polygenetic Risk Score (PRS) does not consider the relationships between alleles. Hence, we proposed to apply three classical supervised ML models, Random Forest (RF), Support Vector Machine (SVM) and Artificial Neural Network (ANN), whose typical characteristic is to capture correlations of genetic features, to improve the predictions for risks of developing SLE.