Motivation Systemic lupus erythematosus (SLE) is an autoimmune disease and a long-term condition affecting many body parts. Autoimmune diseases are affecting more people for reasons unknown, and the causes of these diseases remain a mystery.

Method A newly introduced robust competing (risk) max-logistic regression classifier that can simultaneously perform subtype clustering and classification for disease diagnoses and predictions becomes a new hope to solve the mystery. We use this method in the study to discover critical DNA methylation CpG sites and genome genes, which lead to the highest accuracy and interpretability.

Results The DNA methylation CpG site cg05883128 (DDX60) and gene NR3C2 are essentially responsible for SLE development. They can lead to 100% prediction accuracy together with a miniature set of other CpG sites and genes, respectively. cg05883128 (DDX60) reveals the LSE mechanism affecting many body parts. NR3C2 in CD4 T cells and B cells behaves reversely, leading to the cause of LSE and explaining the mechanism of the autoimmune disease.

Conclusions This work represents a pioneering effort and intellectual discovery in applying the max-logistic competing risk factor model to identify critical genes for LSE, and the interpretability and reproducibility of the results across diverse populations suggest that the CpGs and DEGs identified can provide a comprehensive description of the transcriptomic features of SLE. The practical implications of this research include the potential for personalized risk assessment, precision diagnosis, and tailored treatment plans for patients.

The authors have declared no competing interest.

This study did not receive any funding

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE81622 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE97263 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE177029 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE50722 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE144390 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE82218 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE4588

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes