We have identified a very large collection of data sets collected from Systemic Lupus Erythematosus (SLE) patients. We now want to apply rule-based machine learning to identify SLE patient subgroups, which is likely to be of significant value in diagnosing and treating such patients. Several of the SLE subtypes are morbid and early identification of these subtypes may help save lives. To this end we will use Monte Carlo Feature selection (r.mcfs) and ROSETTA — a rule-based machine learning technique implemented in R (r.rosetta). These systems have already been used on UPPMAX computers. The 16 identified sets constitute the largest known cohort of SLE patients and processing these data sets requires significant computational resources beyond laptop or desktop computers. 1. Yones SA, …, Meadows JRS, Komorowski J. Interpretable machine learning identifies paediatric Systemic Lupus Erythematosus subtypes based on gene expression data. Scientific Reports. 2022;12(1):7433. doi: 10.1038/s41598-022-10853-1.
 2. Hubbard EL, Bachali P, Kingsmore KM, He Y, Catalina MD, Grammer AC, et al. Analysis of transcriptomic features reveals molecular endotypes of SLE with clinical implications. Genome Medicine. 2023;15(1):84. doi: 10.1186/s13073-023-01237-9.